first version
Browse files- ego4d_diffusion_with_vllm_feature.ckpt +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/config.json +39 -0
- llava-llama-2-13b-chat-forecasting-finetune/generation_config.json +7 -0
- llava-llama-2-13b-chat-forecasting-finetune/latest +1 -0
- llava-llama-2-13b-chat-forecasting-finetune/pytorch_model-00001-of-00003.bin +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/pytorch_model-00002-of-00003.bin +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/pytorch_model-00003-of-00003.bin +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/pytorch_model.bin.index.json +803 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_0.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_1.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_2.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_3.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_4.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_5.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_6.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/rng_state_7.pth +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/special_tokens_map.json +24 -0
- llava-llama-2-13b-chat-forecasting-finetune/tokenizer.model +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/tokenizer_config.json +35 -0
- llava-llama-2-13b-chat-forecasting-finetune/trainer_state.json +2716 -0
- llava-llama-2-13b-chat-forecasting-finetune/training_args.bin +3 -0
- llava-llama-2-13b-chat-forecasting-finetune/zero_to_fp32.py +578 -0
- scaleup_training_ego4d_eval.ckpt +3 -0
ego4d_diffusion_with_vllm_feature.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b84b56ffbb5363bd720e590398ded8b5cbb5ff85b9432bca569b01a86f300978
|
| 3 |
+
size 7779511314
|
llava-llama-2-13b-chat-forecasting-finetune/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/checkpoints/bolinlai/llava/released/models--liuhaotian--llava-llama-2-13b-chat-lightning-preview/snapshots/bcda0227a7f371117a195ef0af88c1616a830520",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlavaLlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"freeze_mm_mlp_adapter": false,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
+
"image_aspect_ratio": "square",
|
| 12 |
+
"image_grid_pinpoints": null,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 13824,
|
| 15 |
+
"max_position_embeddings": 4096,
|
| 16 |
+
"mm_hidden_size": 1024,
|
| 17 |
+
"mm_resampler_type": null,
|
| 18 |
+
"mm_use_im_patch_token": false,
|
| 19 |
+
"mm_use_im_start_end": false,
|
| 20 |
+
"mm_vision_select_feature": "patch",
|
| 21 |
+
"mm_vision_select_layer": -2,
|
| 22 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14",
|
| 23 |
+
"model_type": "llava",
|
| 24 |
+
"num_attention_heads": 40,
|
| 25 |
+
"num_hidden_layers": 40,
|
| 26 |
+
"num_key_value_heads": 40,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"pretraining_tp": 1,
|
| 29 |
+
"rms_norm_eps": 1e-05,
|
| 30 |
+
"rope_scaling": null,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.31.0",
|
| 34 |
+
"tune_mm_mlp_adapter": false,
|
| 35 |
+
"tune_mm_vision_resampler": false,
|
| 36 |
+
"use_cache": false,
|
| 37 |
+
"use_mm_proj": true,
|
| 38 |
+
"vocab_size": 32000
|
| 39 |
+
}
|
llava-llama-2-13b-chat-forecasting-finetune/generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.31.0"
|
| 7 |
+
}
|
llava-llama-2-13b-chat-forecasting-finetune/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step450
|
llava-llama-2-13b-chat-forecasting-finetune/pytorch_model-00001-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f35c573bc8e9dd0b0881f63e09cf960c5046dd113f343fb0088e969594538d15
|
| 3 |
+
size 9948726510
|
llava-llama-2-13b-chat-forecasting-finetune/pytorch_model-00002-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda7e1ef460d292c1ef88fa0e2686323dd69ca5531da62c491a6a1c51e4756d0
|
| 3 |
+
size 9904162976
|
llava-llama-2-13b-chat-forecasting-finetune/pytorch_model-00003-of-00003.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:279fb8b5a34da2ba5b3bb6d666240a3b7412d67199cbb459aadca5c8fec57e85
|
| 3 |
+
size 6795987143
|
llava-llama-2-13b-chat-forecasting-finetune/pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,803 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 26648589312
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 358 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 359 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 360 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 361 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 362 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 363 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 364 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 365 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 366 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 367 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 368 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 369 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 370 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 371 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 372 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 373 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 374 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 375 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 376 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 377 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 378 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 379 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 380 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 381 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 382 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 383 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 384 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 385 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 386 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 387 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 388 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 389 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 390 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 391 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 392 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 393 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 394 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 395 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 396 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 397 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 398 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 399 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 400 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 401 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 402 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
|
| 403 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 404 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 405 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 406 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
|
| 407 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
| 408 |
+
"model.mm_projector.bias": "pytorch_model-00003-of-00003.bin",
|
| 409 |
+
"model.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
|
| 410 |
+
"model.norm.weight": "pytorch_model-00003-of-00003.bin",
|
| 411 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00003-of-00003.bin",
|
| 412 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00003-of-00003.bin",
|
| 413 |
+
"model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00003-of-00003.bin",
|
| 414 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 415 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 416 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 417 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 418 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 419 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 420 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 421 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 422 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 423 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 424 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 425 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 426 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 427 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 428 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 429 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 430 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 431 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 432 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 433 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 434 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 435 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 436 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 437 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 438 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 439 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 440 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 441 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 442 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 443 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 444 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 445 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 446 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 447 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 448 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 449 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 450 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 451 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 452 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 453 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 454 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 455 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 456 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 457 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 458 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 459 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 460 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 461 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 462 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 463 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 464 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 465 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 466 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 467 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 468 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 469 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 470 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 471 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 472 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 473 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 474 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 475 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 476 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 477 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 478 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 479 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 480 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 481 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 482 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 483 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 484 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 485 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 486 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 487 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 488 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 489 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 490 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 491 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 492 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 493 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 494 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 495 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 496 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 497 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 498 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 499 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 500 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 501 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 502 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 503 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 504 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 505 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 506 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 507 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 508 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 509 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 510 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 511 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 512 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 513 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 514 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 515 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 516 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 517 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 518 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 519 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 520 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 521 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 522 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 523 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 524 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 525 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 526 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 527 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 528 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 529 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 530 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 531 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 532 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 533 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 534 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 535 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 536 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 537 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 538 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 539 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 540 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 541 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 542 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 543 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 544 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 545 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 546 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 547 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 548 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 549 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 550 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 551 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 552 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 553 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 554 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 555 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 556 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 557 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 558 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 559 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 560 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 561 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 562 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 563 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 564 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 565 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 566 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 567 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 568 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 569 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 570 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 571 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 572 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 573 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 574 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 575 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 576 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 577 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 578 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 579 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 580 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 581 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 582 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 583 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 584 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 585 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 586 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 587 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 588 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 589 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 590 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 591 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 592 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 593 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 594 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 595 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 596 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 597 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 598 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 599 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 600 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 601 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 602 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 603 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 604 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 605 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 606 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 607 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 608 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 609 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 610 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 611 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 612 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 613 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 614 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 615 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 616 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 617 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 618 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 619 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 620 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 621 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 622 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 623 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 624 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 625 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 626 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 627 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 628 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 629 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 630 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 631 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 632 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 633 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 634 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 635 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 636 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 637 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 638 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 639 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 640 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 641 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 642 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 643 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 644 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 645 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 646 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 647 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 648 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 649 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 650 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 651 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 652 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 653 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 654 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 655 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 656 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 657 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 658 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 659 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 660 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 661 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 662 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 663 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 664 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 665 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 666 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 667 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 668 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 669 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 670 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 671 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 672 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 673 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 674 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 675 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 676 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 677 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 678 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 679 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 680 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 681 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 682 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 683 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 684 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 685 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 686 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 687 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 688 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 689 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 690 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 691 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 692 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 693 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 694 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 695 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 696 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 697 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 698 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 699 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 700 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 701 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 702 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 703 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 704 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 705 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 706 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 707 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 708 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 709 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 710 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 711 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 712 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 713 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 714 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 715 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 716 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 717 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 718 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 719 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 720 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 721 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 722 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 723 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 724 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 725 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 726 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 727 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 728 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 729 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 730 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 731 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 732 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 733 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 734 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 735 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 736 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 737 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 738 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 739 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 740 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 741 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 742 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 743 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 744 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 745 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 746 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 747 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 748 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 749 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 750 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 751 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 752 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 753 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 754 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 755 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 756 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 757 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 758 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 759 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 760 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 761 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 762 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 763 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 764 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 765 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 766 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 767 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 768 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 769 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 770 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 771 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 772 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 773 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 774 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 775 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 776 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 777 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 778 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 779 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 780 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 781 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 782 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00003-of-00003.bin",
|
| 783 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00003-of-00003.bin",
|
| 784 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00003-of-00003.bin",
|
| 785 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00003-of-00003.bin",
|
| 786 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00003-of-00003.bin",
|
| 787 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00003-of-00003.bin",
|
| 788 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00003-of-00003.bin",
|
| 789 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00003-of-00003.bin",
|
| 790 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 791 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 792 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 793 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 794 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 795 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 796 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
|
| 797 |
+
"model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
| 798 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00003-of-00003.bin",
|
| 799 |
+
"model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00003-of-00003.bin",
|
| 800 |
+
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00003-of-00003.bin",
|
| 801 |
+
"model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00003-of-00003.bin"
|
| 802 |
+
}
|
| 803 |
+
}
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c1d4aab692d41c18c919a673e506a5264ad9de9ff132b0de5dab52510157c75
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72575f2b4522908157bba855533d15354ced6598ecdc09ca8ce5417fa99c9b92
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eabb43b1fac99cd8e34e58482a942b31a1855cd53120560e1428e8a2aae185e9
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfd9568c2d39f428f86eb5a99beb6f19ac57f3f024ec4494b8cadd107d148298
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ab6cb42d703108752ec781af0a5227b721321c411bb7f7bca00b6ec4e15324
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9fe828193c13a4a1adccaf24735d85428cb925bfa6204603f3a0a4a34c8cec9
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36e15c4dcb706b97a74d0f8259d6466dd2e46e60fd71dcb2c6d99e1e9ff2f204
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a467ddda52bc75625e56adc924121f89adb1e65a5733eec05f6284586a9a926
|
| 3 |
+
size 21687
|
llava-llama-2-13b-chat-forecasting-finetune/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
llava-llama-2-13b-chat-forecasting-finetune/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
llava-llama-2-13b-chat-forecasting-finetune/tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": true,
|
| 22 |
+
"model_max_length": 2048,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|
llava-llama-2-13b-chat-forecasting-finetune/trainer_state.json
ADDED
|
@@ -0,0 +1,2716 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.7439024390243905,
|
| 5 |
+
"global_step": 450,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 0.0,
|
| 13 |
+
"loss": 1.7617,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"learning_rate": 4.6275642631951835e-06,
|
| 19 |
+
"loss": 0.9497,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"learning_rate": 7.3345158268416935e-06,
|
| 25 |
+
"loss": 0.9375,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.02,
|
| 30 |
+
"learning_rate": 9.255128526390367e-06,
|
| 31 |
+
"loss": 0.6309,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.03,
|
| 36 |
+
"learning_rate": 1.0744871473609633e-05,
|
| 37 |
+
"loss": 0.478,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.04,
|
| 42 |
+
"learning_rate": 1.1962080090036879e-05,
|
| 43 |
+
"loss": 0.5774,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04,
|
| 48 |
+
"learning_rate": 1.299121531141887e-05,
|
| 49 |
+
"loss": 0.4492,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.05,
|
| 54 |
+
"learning_rate": 1.388269278958555e-05,
|
| 55 |
+
"loss": 0.4519,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.05,
|
| 60 |
+
"learning_rate": 1.4669031653683387e-05,
|
| 61 |
+
"loss": 0.4429,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.06,
|
| 66 |
+
"learning_rate": 1.537243573680482e-05,
|
| 67 |
+
"loss": 0.437,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.07,
|
| 72 |
+
"learning_rate": 1.600874212937343e-05,
|
| 73 |
+
"loss": 0.4043,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.07,
|
| 78 |
+
"learning_rate": 1.6589644353232063e-05,
|
| 79 |
+
"loss": 0.3865,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.08,
|
| 84 |
+
"learning_rate": 1.712402259777778e-05,
|
| 85 |
+
"loss": 0.3904,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.09,
|
| 90 |
+
"learning_rate": 1.7618779574614054e-05,
|
| 91 |
+
"loss": 0.3884,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.09,
|
| 96 |
+
"learning_rate": 1.8079387300451327e-05,
|
| 97 |
+
"loss": 0.3555,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.1,
|
| 102 |
+
"learning_rate": 1.8510257052780734e-05,
|
| 103 |
+
"loss": 0.3621,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.1,
|
| 108 |
+
"learning_rate": 1.891499697130832e-05,
|
| 109 |
+
"loss": 0.3779,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11,
|
| 114 |
+
"learning_rate": 1.929659591687857e-05,
|
| 115 |
+
"loss": 0.3604,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.12,
|
| 120 |
+
"learning_rate": 1.9657557553855117e-05,
|
| 121 |
+
"loss": 0.3112,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.12,
|
| 126 |
+
"learning_rate": 2e-05,
|
| 127 |
+
"loss": 0.3611,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.13,
|
| 132 |
+
"learning_rate": 2e-05,
|
| 133 |
+
"loss": 0.3394,
|
| 134 |
+
"step": 21
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.13,
|
| 138 |
+
"learning_rate": 2e-05,
|
| 139 |
+
"loss": 0.3376,
|
| 140 |
+
"step": 22
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.14,
|
| 144 |
+
"learning_rate": 2e-05,
|
| 145 |
+
"loss": 0.3569,
|
| 146 |
+
"step": 23
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.15,
|
| 150 |
+
"learning_rate": 2e-05,
|
| 151 |
+
"loss": 0.3665,
|
| 152 |
+
"step": 24
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.15,
|
| 156 |
+
"learning_rate": 2e-05,
|
| 157 |
+
"loss": 0.3387,
|
| 158 |
+
"step": 25
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.16,
|
| 162 |
+
"learning_rate": 2e-05,
|
| 163 |
+
"loss": 0.3163,
|
| 164 |
+
"step": 26
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.16,
|
| 168 |
+
"learning_rate": 2e-05,
|
| 169 |
+
"loss": 0.3247,
|
| 170 |
+
"step": 27
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.17,
|
| 174 |
+
"learning_rate": 2e-05,
|
| 175 |
+
"loss": 0.2898,
|
| 176 |
+
"step": 28
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.18,
|
| 180 |
+
"learning_rate": 2e-05,
|
| 181 |
+
"loss": 0.3478,
|
| 182 |
+
"step": 29
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.18,
|
| 186 |
+
"learning_rate": 2e-05,
|
| 187 |
+
"loss": 0.3394,
|
| 188 |
+
"step": 30
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.19,
|
| 192 |
+
"learning_rate": 2e-05,
|
| 193 |
+
"loss": 0.3236,
|
| 194 |
+
"step": 31
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.2,
|
| 198 |
+
"learning_rate": 2e-05,
|
| 199 |
+
"loss": 0.328,
|
| 200 |
+
"step": 32
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.2,
|
| 204 |
+
"learning_rate": 2e-05,
|
| 205 |
+
"loss": 0.3147,
|
| 206 |
+
"step": 33
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.21,
|
| 210 |
+
"learning_rate": 2e-05,
|
| 211 |
+
"loss": 0.3195,
|
| 212 |
+
"step": 34
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.21,
|
| 216 |
+
"learning_rate": 2e-05,
|
| 217 |
+
"loss": 0.309,
|
| 218 |
+
"step": 35
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.22,
|
| 222 |
+
"learning_rate": 2e-05,
|
| 223 |
+
"loss": 0.3364,
|
| 224 |
+
"step": 36
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.23,
|
| 228 |
+
"learning_rate": 2e-05,
|
| 229 |
+
"loss": 0.3057,
|
| 230 |
+
"step": 37
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.23,
|
| 234 |
+
"learning_rate": 2e-05,
|
| 235 |
+
"loss": 0.3101,
|
| 236 |
+
"step": 38
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.24,
|
| 240 |
+
"learning_rate": 2e-05,
|
| 241 |
+
"loss": 0.356,
|
| 242 |
+
"step": 39
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.24,
|
| 246 |
+
"learning_rate": 2e-05,
|
| 247 |
+
"loss": 0.3015,
|
| 248 |
+
"step": 40
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.25,
|
| 252 |
+
"learning_rate": 2e-05,
|
| 253 |
+
"loss": 0.3142,
|
| 254 |
+
"step": 41
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.26,
|
| 258 |
+
"learning_rate": 2e-05,
|
| 259 |
+
"loss": 0.3322,
|
| 260 |
+
"step": 42
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.26,
|
| 264 |
+
"learning_rate": 2e-05,
|
| 265 |
+
"loss": 0.3276,
|
| 266 |
+
"step": 43
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.27,
|
| 270 |
+
"learning_rate": 2e-05,
|
| 271 |
+
"loss": 0.363,
|
| 272 |
+
"step": 44
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.27,
|
| 276 |
+
"learning_rate": 2e-05,
|
| 277 |
+
"loss": 0.3447,
|
| 278 |
+
"step": 45
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.28,
|
| 282 |
+
"learning_rate": 2e-05,
|
| 283 |
+
"loss": 0.3438,
|
| 284 |
+
"step": 46
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.29,
|
| 288 |
+
"learning_rate": 2e-05,
|
| 289 |
+
"loss": 0.3313,
|
| 290 |
+
"step": 47
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.29,
|
| 294 |
+
"learning_rate": 2e-05,
|
| 295 |
+
"loss": 0.2706,
|
| 296 |
+
"step": 48
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3,
|
| 300 |
+
"learning_rate": 2e-05,
|
| 301 |
+
"loss": 0.3207,
|
| 302 |
+
"step": 49
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3,
|
| 306 |
+
"learning_rate": 2e-05,
|
| 307 |
+
"loss": 0.2988,
|
| 308 |
+
"step": 50
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.31,
|
| 312 |
+
"learning_rate": 2e-05,
|
| 313 |
+
"loss": 0.324,
|
| 314 |
+
"step": 51
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.32,
|
| 318 |
+
"learning_rate": 2e-05,
|
| 319 |
+
"loss": 0.343,
|
| 320 |
+
"step": 52
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.32,
|
| 324 |
+
"learning_rate": 2e-05,
|
| 325 |
+
"loss": 0.2748,
|
| 326 |
+
"step": 53
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.33,
|
| 330 |
+
"learning_rate": 2e-05,
|
| 331 |
+
"loss": 0.2943,
|
| 332 |
+
"step": 54
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.34,
|
| 336 |
+
"learning_rate": 2e-05,
|
| 337 |
+
"loss": 0.3333,
|
| 338 |
+
"step": 55
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.34,
|
| 342 |
+
"learning_rate": 2e-05,
|
| 343 |
+
"loss": 0.3104,
|
| 344 |
+
"step": 56
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.35,
|
| 348 |
+
"learning_rate": 2e-05,
|
| 349 |
+
"loss": 0.3447,
|
| 350 |
+
"step": 57
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.35,
|
| 354 |
+
"learning_rate": 2e-05,
|
| 355 |
+
"loss": 0.3418,
|
| 356 |
+
"step": 58
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.36,
|
| 360 |
+
"learning_rate": 2e-05,
|
| 361 |
+
"loss": 0.3175,
|
| 362 |
+
"step": 59
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.37,
|
| 366 |
+
"learning_rate": 2e-05,
|
| 367 |
+
"loss": 0.3259,
|
| 368 |
+
"step": 60
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.37,
|
| 372 |
+
"learning_rate": 2e-05,
|
| 373 |
+
"loss": 0.2996,
|
| 374 |
+
"step": 61
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.38,
|
| 378 |
+
"learning_rate": 2e-05,
|
| 379 |
+
"loss": 0.3335,
|
| 380 |
+
"step": 62
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.38,
|
| 384 |
+
"learning_rate": 2e-05,
|
| 385 |
+
"loss": 0.314,
|
| 386 |
+
"step": 63
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.39,
|
| 390 |
+
"learning_rate": 2e-05,
|
| 391 |
+
"loss": 0.3087,
|
| 392 |
+
"step": 64
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.4,
|
| 396 |
+
"learning_rate": 2e-05,
|
| 397 |
+
"loss": 0.3124,
|
| 398 |
+
"step": 65
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.4,
|
| 402 |
+
"learning_rate": 2e-05,
|
| 403 |
+
"loss": 0.321,
|
| 404 |
+
"step": 66
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.41,
|
| 408 |
+
"learning_rate": 2e-05,
|
| 409 |
+
"loss": 0.3059,
|
| 410 |
+
"step": 67
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.41,
|
| 414 |
+
"learning_rate": 2e-05,
|
| 415 |
+
"loss": 0.2977,
|
| 416 |
+
"step": 68
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.42,
|
| 420 |
+
"learning_rate": 2e-05,
|
| 421 |
+
"loss": 0.2971,
|
| 422 |
+
"step": 69
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.43,
|
| 426 |
+
"learning_rate": 2e-05,
|
| 427 |
+
"loss": 0.3499,
|
| 428 |
+
"step": 70
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.43,
|
| 432 |
+
"learning_rate": 2e-05,
|
| 433 |
+
"loss": 0.2977,
|
| 434 |
+
"step": 71
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.44,
|
| 438 |
+
"learning_rate": 2e-05,
|
| 439 |
+
"loss": 0.3418,
|
| 440 |
+
"step": 72
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.45,
|
| 444 |
+
"learning_rate": 2e-05,
|
| 445 |
+
"loss": 0.3479,
|
| 446 |
+
"step": 73
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.45,
|
| 450 |
+
"learning_rate": 2e-05,
|
| 451 |
+
"loss": 0.2861,
|
| 452 |
+
"step": 74
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.46,
|
| 456 |
+
"learning_rate": 2e-05,
|
| 457 |
+
"loss": 0.3472,
|
| 458 |
+
"step": 75
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.46,
|
| 462 |
+
"learning_rate": 2e-05,
|
| 463 |
+
"loss": 0.3213,
|
| 464 |
+
"step": 76
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.47,
|
| 468 |
+
"learning_rate": 2e-05,
|
| 469 |
+
"loss": 0.3031,
|
| 470 |
+
"step": 77
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 0.48,
|
| 474 |
+
"learning_rate": 2e-05,
|
| 475 |
+
"loss": 0.3098,
|
| 476 |
+
"step": 78
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 0.48,
|
| 480 |
+
"learning_rate": 2e-05,
|
| 481 |
+
"loss": 0.3196,
|
| 482 |
+
"step": 79
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.49,
|
| 486 |
+
"learning_rate": 2e-05,
|
| 487 |
+
"loss": 0.2961,
|
| 488 |
+
"step": 80
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.49,
|
| 492 |
+
"learning_rate": 2e-05,
|
| 493 |
+
"loss": 0.2742,
|
| 494 |
+
"step": 81
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5,
|
| 498 |
+
"learning_rate": 2e-05,
|
| 499 |
+
"loss": 0.2969,
|
| 500 |
+
"step": 82
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.51,
|
| 504 |
+
"learning_rate": 2e-05,
|
| 505 |
+
"loss": 0.3085,
|
| 506 |
+
"step": 83
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.51,
|
| 510 |
+
"learning_rate": 2e-05,
|
| 511 |
+
"loss": 0.2861,
|
| 512 |
+
"step": 84
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.52,
|
| 516 |
+
"learning_rate": 2e-05,
|
| 517 |
+
"loss": 0.3313,
|
| 518 |
+
"step": 85
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.52,
|
| 522 |
+
"learning_rate": 2e-05,
|
| 523 |
+
"loss": 0.3047,
|
| 524 |
+
"step": 86
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.53,
|
| 528 |
+
"learning_rate": 2e-05,
|
| 529 |
+
"loss": 0.2556,
|
| 530 |
+
"step": 87
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.54,
|
| 534 |
+
"learning_rate": 2e-05,
|
| 535 |
+
"loss": 0.3018,
|
| 536 |
+
"step": 88
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.54,
|
| 540 |
+
"learning_rate": 2e-05,
|
| 541 |
+
"loss": 0.2803,
|
| 542 |
+
"step": 89
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.55,
|
| 546 |
+
"learning_rate": 2e-05,
|
| 547 |
+
"loss": 0.3021,
|
| 548 |
+
"step": 90
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.55,
|
| 552 |
+
"learning_rate": 2e-05,
|
| 553 |
+
"loss": 0.2819,
|
| 554 |
+
"step": 91
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.56,
|
| 558 |
+
"learning_rate": 2e-05,
|
| 559 |
+
"loss": 0.3086,
|
| 560 |
+
"step": 92
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.57,
|
| 564 |
+
"learning_rate": 2e-05,
|
| 565 |
+
"loss": 0.3086,
|
| 566 |
+
"step": 93
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.57,
|
| 570 |
+
"learning_rate": 2e-05,
|
| 571 |
+
"loss": 0.2765,
|
| 572 |
+
"step": 94
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.58,
|
| 576 |
+
"learning_rate": 2e-05,
|
| 577 |
+
"loss": 0.3156,
|
| 578 |
+
"step": 95
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.59,
|
| 582 |
+
"learning_rate": 2e-05,
|
| 583 |
+
"loss": 0.287,
|
| 584 |
+
"step": 96
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.59,
|
| 588 |
+
"learning_rate": 2e-05,
|
| 589 |
+
"loss": 0.3473,
|
| 590 |
+
"step": 97
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.6,
|
| 594 |
+
"learning_rate": 2e-05,
|
| 595 |
+
"loss": 0.293,
|
| 596 |
+
"step": 98
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.6,
|
| 600 |
+
"learning_rate": 2e-05,
|
| 601 |
+
"loss": 0.3049,
|
| 602 |
+
"step": 99
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.61,
|
| 606 |
+
"learning_rate": 2e-05,
|
| 607 |
+
"loss": 0.2904,
|
| 608 |
+
"step": 100
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.62,
|
| 612 |
+
"learning_rate": 2e-05,
|
| 613 |
+
"loss": 0.3564,
|
| 614 |
+
"step": 101
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.62,
|
| 618 |
+
"learning_rate": 2e-05,
|
| 619 |
+
"loss": 0.2704,
|
| 620 |
+
"step": 102
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.63,
|
| 624 |
+
"learning_rate": 2e-05,
|
| 625 |
+
"loss": 0.3119,
|
| 626 |
+
"step": 103
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.63,
|
| 630 |
+
"learning_rate": 2e-05,
|
| 631 |
+
"loss": 0.2975,
|
| 632 |
+
"step": 104
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.64,
|
| 636 |
+
"learning_rate": 2e-05,
|
| 637 |
+
"loss": 0.2811,
|
| 638 |
+
"step": 105
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.65,
|
| 642 |
+
"learning_rate": 2e-05,
|
| 643 |
+
"loss": 0.3073,
|
| 644 |
+
"step": 106
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.65,
|
| 648 |
+
"learning_rate": 2e-05,
|
| 649 |
+
"loss": 0.2983,
|
| 650 |
+
"step": 107
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.66,
|
| 654 |
+
"learning_rate": 2e-05,
|
| 655 |
+
"loss": 0.2913,
|
| 656 |
+
"step": 108
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 0.66,
|
| 660 |
+
"learning_rate": 2e-05,
|
| 661 |
+
"loss": 0.2657,
|
| 662 |
+
"step": 109
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.67,
|
| 666 |
+
"learning_rate": 2e-05,
|
| 667 |
+
"loss": 0.2823,
|
| 668 |
+
"step": 110
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.68,
|
| 672 |
+
"learning_rate": 2e-05,
|
| 673 |
+
"loss": 0.2972,
|
| 674 |
+
"step": 111
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.68,
|
| 678 |
+
"learning_rate": 2e-05,
|
| 679 |
+
"loss": 0.3135,
|
| 680 |
+
"step": 112
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.69,
|
| 684 |
+
"learning_rate": 2e-05,
|
| 685 |
+
"loss": 0.2676,
|
| 686 |
+
"step": 113
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.7,
|
| 690 |
+
"learning_rate": 2e-05,
|
| 691 |
+
"loss": 0.2899,
|
| 692 |
+
"step": 114
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.7,
|
| 696 |
+
"learning_rate": 2e-05,
|
| 697 |
+
"loss": 0.272,
|
| 698 |
+
"step": 115
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.71,
|
| 702 |
+
"learning_rate": 2e-05,
|
| 703 |
+
"loss": 0.3032,
|
| 704 |
+
"step": 116
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.71,
|
| 708 |
+
"learning_rate": 2e-05,
|
| 709 |
+
"loss": 0.3073,
|
| 710 |
+
"step": 117
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.72,
|
| 714 |
+
"learning_rate": 2e-05,
|
| 715 |
+
"loss": 0.3027,
|
| 716 |
+
"step": 118
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.73,
|
| 720 |
+
"learning_rate": 2e-05,
|
| 721 |
+
"loss": 0.2893,
|
| 722 |
+
"step": 119
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.73,
|
| 726 |
+
"learning_rate": 2e-05,
|
| 727 |
+
"loss": 0.3013,
|
| 728 |
+
"step": 120
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.74,
|
| 732 |
+
"learning_rate": 2e-05,
|
| 733 |
+
"loss": 0.2638,
|
| 734 |
+
"step": 121
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.74,
|
| 738 |
+
"learning_rate": 2e-05,
|
| 739 |
+
"loss": 0.2773,
|
| 740 |
+
"step": 122
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.75,
|
| 744 |
+
"learning_rate": 2e-05,
|
| 745 |
+
"loss": 0.2708,
|
| 746 |
+
"step": 123
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.76,
|
| 750 |
+
"learning_rate": 2e-05,
|
| 751 |
+
"loss": 0.2303,
|
| 752 |
+
"step": 124
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.76,
|
| 756 |
+
"learning_rate": 2e-05,
|
| 757 |
+
"loss": 0.2764,
|
| 758 |
+
"step": 125
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.77,
|
| 762 |
+
"learning_rate": 2e-05,
|
| 763 |
+
"loss": 0.2909,
|
| 764 |
+
"step": 126
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.77,
|
| 768 |
+
"learning_rate": 2e-05,
|
| 769 |
+
"loss": 0.2799,
|
| 770 |
+
"step": 127
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.78,
|
| 774 |
+
"learning_rate": 2e-05,
|
| 775 |
+
"loss": 0.2573,
|
| 776 |
+
"step": 128
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.79,
|
| 780 |
+
"learning_rate": 2e-05,
|
| 781 |
+
"loss": 0.2845,
|
| 782 |
+
"step": 129
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.79,
|
| 786 |
+
"learning_rate": 2e-05,
|
| 787 |
+
"loss": 0.2667,
|
| 788 |
+
"step": 130
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.8,
|
| 792 |
+
"learning_rate": 2e-05,
|
| 793 |
+
"loss": 0.2623,
|
| 794 |
+
"step": 131
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8,
|
| 798 |
+
"learning_rate": 2e-05,
|
| 799 |
+
"loss": 0.2728,
|
| 800 |
+
"step": 132
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.81,
|
| 804 |
+
"learning_rate": 2e-05,
|
| 805 |
+
"loss": 0.3169,
|
| 806 |
+
"step": 133
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 0.82,
|
| 810 |
+
"learning_rate": 2e-05,
|
| 811 |
+
"loss": 0.2861,
|
| 812 |
+
"step": 134
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.82,
|
| 816 |
+
"learning_rate": 2e-05,
|
| 817 |
+
"loss": 0.2921,
|
| 818 |
+
"step": 135
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.83,
|
| 822 |
+
"learning_rate": 2e-05,
|
| 823 |
+
"loss": 0.304,
|
| 824 |
+
"step": 136
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.84,
|
| 828 |
+
"learning_rate": 2e-05,
|
| 829 |
+
"loss": 0.2804,
|
| 830 |
+
"step": 137
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.84,
|
| 834 |
+
"learning_rate": 2e-05,
|
| 835 |
+
"loss": 0.2739,
|
| 836 |
+
"step": 138
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.85,
|
| 840 |
+
"learning_rate": 2e-05,
|
| 841 |
+
"loss": 0.2738,
|
| 842 |
+
"step": 139
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.85,
|
| 846 |
+
"learning_rate": 2e-05,
|
| 847 |
+
"loss": 0.2675,
|
| 848 |
+
"step": 140
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.86,
|
| 852 |
+
"learning_rate": 2e-05,
|
| 853 |
+
"loss": 0.2942,
|
| 854 |
+
"step": 141
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.87,
|
| 858 |
+
"learning_rate": 2e-05,
|
| 859 |
+
"loss": 0.3074,
|
| 860 |
+
"step": 142
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 0.87,
|
| 864 |
+
"learning_rate": 2e-05,
|
| 865 |
+
"loss": 0.265,
|
| 866 |
+
"step": 143
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.88,
|
| 870 |
+
"learning_rate": 2e-05,
|
| 871 |
+
"loss": 0.2885,
|
| 872 |
+
"step": 144
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.88,
|
| 876 |
+
"learning_rate": 2e-05,
|
| 877 |
+
"loss": 0.3245,
|
| 878 |
+
"step": 145
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.89,
|
| 882 |
+
"learning_rate": 2e-05,
|
| 883 |
+
"loss": 0.2657,
|
| 884 |
+
"step": 146
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.9,
|
| 888 |
+
"learning_rate": 2e-05,
|
| 889 |
+
"loss": 0.2815,
|
| 890 |
+
"step": 147
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.9,
|
| 894 |
+
"learning_rate": 2e-05,
|
| 895 |
+
"loss": 0.2615,
|
| 896 |
+
"step": 148
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.91,
|
| 900 |
+
"learning_rate": 2e-05,
|
| 901 |
+
"loss": 0.3202,
|
| 902 |
+
"step": 149
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 0.91,
|
| 906 |
+
"learning_rate": 2e-05,
|
| 907 |
+
"loss": 0.3335,
|
| 908 |
+
"step": 150
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.92,
|
| 912 |
+
"learning_rate": 2e-05,
|
| 913 |
+
"loss": 0.3079,
|
| 914 |
+
"step": 151
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.93,
|
| 918 |
+
"learning_rate": 2e-05,
|
| 919 |
+
"loss": 0.3115,
|
| 920 |
+
"step": 152
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.93,
|
| 924 |
+
"learning_rate": 2e-05,
|
| 925 |
+
"loss": 0.2924,
|
| 926 |
+
"step": 153
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.94,
|
| 930 |
+
"learning_rate": 2e-05,
|
| 931 |
+
"loss": 0.2808,
|
| 932 |
+
"step": 154
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 0.95,
|
| 936 |
+
"learning_rate": 2e-05,
|
| 937 |
+
"loss": 0.2941,
|
| 938 |
+
"step": 155
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.95,
|
| 942 |
+
"learning_rate": 2e-05,
|
| 943 |
+
"loss": 0.2778,
|
| 944 |
+
"step": 156
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.96,
|
| 948 |
+
"learning_rate": 2e-05,
|
| 949 |
+
"loss": 0.2935,
|
| 950 |
+
"step": 157
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.96,
|
| 954 |
+
"learning_rate": 2e-05,
|
| 955 |
+
"loss": 0.3024,
|
| 956 |
+
"step": 158
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.97,
|
| 960 |
+
"learning_rate": 2e-05,
|
| 961 |
+
"loss": 0.2821,
|
| 962 |
+
"step": 159
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.98,
|
| 966 |
+
"learning_rate": 2e-05,
|
| 967 |
+
"loss": 0.3009,
|
| 968 |
+
"step": 160
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.98,
|
| 972 |
+
"learning_rate": 2e-05,
|
| 973 |
+
"loss": 0.3063,
|
| 974 |
+
"step": 161
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.99,
|
| 978 |
+
"learning_rate": 2e-05,
|
| 979 |
+
"loss": 0.2719,
|
| 980 |
+
"step": 162
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.99,
|
| 984 |
+
"learning_rate": 2e-05,
|
| 985 |
+
"loss": 0.2865,
|
| 986 |
+
"step": 163
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 1.0,
|
| 990 |
+
"learning_rate": 2e-05,
|
| 991 |
+
"loss": 0.2507,
|
| 992 |
+
"step": 164
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 1.01,
|
| 996 |
+
"learning_rate": 2e-05,
|
| 997 |
+
"loss": 0.2312,
|
| 998 |
+
"step": 165
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 1.01,
|
| 1002 |
+
"learning_rate": 2e-05,
|
| 1003 |
+
"loss": 0.2336,
|
| 1004 |
+
"step": 166
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.02,
|
| 1008 |
+
"learning_rate": 2e-05,
|
| 1009 |
+
"loss": 0.2188,
|
| 1010 |
+
"step": 167
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 1.02,
|
| 1014 |
+
"learning_rate": 2e-05,
|
| 1015 |
+
"loss": 0.1769,
|
| 1016 |
+
"step": 168
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 1.03,
|
| 1020 |
+
"learning_rate": 2e-05,
|
| 1021 |
+
"loss": 0.1957,
|
| 1022 |
+
"step": 169
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 1.04,
|
| 1026 |
+
"learning_rate": 2e-05,
|
| 1027 |
+
"loss": 0.1978,
|
| 1028 |
+
"step": 170
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 1.04,
|
| 1032 |
+
"learning_rate": 2e-05,
|
| 1033 |
+
"loss": 0.2185,
|
| 1034 |
+
"step": 171
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 1.05,
|
| 1038 |
+
"learning_rate": 2e-05,
|
| 1039 |
+
"loss": 0.1927,
|
| 1040 |
+
"step": 172
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.05,
|
| 1044 |
+
"learning_rate": 2e-05,
|
| 1045 |
+
"loss": 0.2238,
|
| 1046 |
+
"step": 173
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.06,
|
| 1050 |
+
"learning_rate": 2e-05,
|
| 1051 |
+
"loss": 0.2159,
|
| 1052 |
+
"step": 174
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.07,
|
| 1056 |
+
"learning_rate": 2e-05,
|
| 1057 |
+
"loss": 0.1945,
|
| 1058 |
+
"step": 175
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.07,
|
| 1062 |
+
"learning_rate": 2e-05,
|
| 1063 |
+
"loss": 0.2045,
|
| 1064 |
+
"step": 176
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.08,
|
| 1068 |
+
"learning_rate": 2e-05,
|
| 1069 |
+
"loss": 0.198,
|
| 1070 |
+
"step": 177
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 1.09,
|
| 1074 |
+
"learning_rate": 2e-05,
|
| 1075 |
+
"loss": 0.2074,
|
| 1076 |
+
"step": 178
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 1.09,
|
| 1080 |
+
"learning_rate": 2e-05,
|
| 1081 |
+
"loss": 0.2106,
|
| 1082 |
+
"step": 179
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 1.1,
|
| 1086 |
+
"learning_rate": 2e-05,
|
| 1087 |
+
"loss": 0.1984,
|
| 1088 |
+
"step": 180
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.1,
|
| 1092 |
+
"learning_rate": 2e-05,
|
| 1093 |
+
"loss": 0.2229,
|
| 1094 |
+
"step": 181
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 1.11,
|
| 1098 |
+
"learning_rate": 2e-05,
|
| 1099 |
+
"loss": 0.1941,
|
| 1100 |
+
"step": 182
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 1.12,
|
| 1104 |
+
"learning_rate": 2e-05,
|
| 1105 |
+
"loss": 0.1978,
|
| 1106 |
+
"step": 183
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 1.12,
|
| 1110 |
+
"learning_rate": 2e-05,
|
| 1111 |
+
"loss": 0.1808,
|
| 1112 |
+
"step": 184
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.13,
|
| 1116 |
+
"learning_rate": 2e-05,
|
| 1117 |
+
"loss": 0.1936,
|
| 1118 |
+
"step": 185
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 1.13,
|
| 1122 |
+
"learning_rate": 2e-05,
|
| 1123 |
+
"loss": 0.2327,
|
| 1124 |
+
"step": 186
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 1.14,
|
| 1128 |
+
"learning_rate": 2e-05,
|
| 1129 |
+
"loss": 0.1876,
|
| 1130 |
+
"step": 187
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.15,
|
| 1134 |
+
"learning_rate": 2e-05,
|
| 1135 |
+
"loss": 0.2247,
|
| 1136 |
+
"step": 188
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.15,
|
| 1140 |
+
"learning_rate": 2e-05,
|
| 1141 |
+
"loss": 0.2155,
|
| 1142 |
+
"step": 189
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 1.16,
|
| 1146 |
+
"learning_rate": 2e-05,
|
| 1147 |
+
"loss": 0.1917,
|
| 1148 |
+
"step": 190
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 1.16,
|
| 1152 |
+
"learning_rate": 2e-05,
|
| 1153 |
+
"loss": 0.193,
|
| 1154 |
+
"step": 191
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.17,
|
| 1158 |
+
"learning_rate": 2e-05,
|
| 1159 |
+
"loss": 0.2141,
|
| 1160 |
+
"step": 192
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 1.18,
|
| 1164 |
+
"learning_rate": 2e-05,
|
| 1165 |
+
"loss": 0.2195,
|
| 1166 |
+
"step": 193
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 1.18,
|
| 1170 |
+
"learning_rate": 2e-05,
|
| 1171 |
+
"loss": 0.1937,
|
| 1172 |
+
"step": 194
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.19,
|
| 1176 |
+
"learning_rate": 2e-05,
|
| 1177 |
+
"loss": 0.2067,
|
| 1178 |
+
"step": 195
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.2,
|
| 1182 |
+
"learning_rate": 2e-05,
|
| 1183 |
+
"loss": 0.2426,
|
| 1184 |
+
"step": 196
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 1.2,
|
| 1188 |
+
"learning_rate": 2e-05,
|
| 1189 |
+
"loss": 0.2234,
|
| 1190 |
+
"step": 197
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.21,
|
| 1194 |
+
"learning_rate": 2e-05,
|
| 1195 |
+
"loss": 0.2133,
|
| 1196 |
+
"step": 198
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.21,
|
| 1200 |
+
"learning_rate": 2e-05,
|
| 1201 |
+
"loss": 0.2021,
|
| 1202 |
+
"step": 199
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 1.22,
|
| 1206 |
+
"learning_rate": 2e-05,
|
| 1207 |
+
"loss": 0.2015,
|
| 1208 |
+
"step": 200
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 1.23,
|
| 1212 |
+
"learning_rate": 2e-05,
|
| 1213 |
+
"loss": 0.2271,
|
| 1214 |
+
"step": 201
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.23,
|
| 1218 |
+
"learning_rate": 2e-05,
|
| 1219 |
+
"loss": 0.2024,
|
| 1220 |
+
"step": 202
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.24,
|
| 1224 |
+
"learning_rate": 2e-05,
|
| 1225 |
+
"loss": 0.2025,
|
| 1226 |
+
"step": 203
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.24,
|
| 1230 |
+
"learning_rate": 2e-05,
|
| 1231 |
+
"loss": 0.2179,
|
| 1232 |
+
"step": 204
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.25,
|
| 1236 |
+
"learning_rate": 2e-05,
|
| 1237 |
+
"loss": 0.2128,
|
| 1238 |
+
"step": 205
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.26,
|
| 1242 |
+
"learning_rate": 2e-05,
|
| 1243 |
+
"loss": 0.1875,
|
| 1244 |
+
"step": 206
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.26,
|
| 1248 |
+
"learning_rate": 2e-05,
|
| 1249 |
+
"loss": 0.2263,
|
| 1250 |
+
"step": 207
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.27,
|
| 1254 |
+
"learning_rate": 2e-05,
|
| 1255 |
+
"loss": 0.2032,
|
| 1256 |
+
"step": 208
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.27,
|
| 1260 |
+
"learning_rate": 2e-05,
|
| 1261 |
+
"loss": 0.203,
|
| 1262 |
+
"step": 209
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.28,
|
| 1266 |
+
"learning_rate": 2e-05,
|
| 1267 |
+
"loss": 0.2262,
|
| 1268 |
+
"step": 210
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 1.29,
|
| 1272 |
+
"learning_rate": 2e-05,
|
| 1273 |
+
"loss": 0.2151,
|
| 1274 |
+
"step": 211
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.29,
|
| 1278 |
+
"learning_rate": 2e-05,
|
| 1279 |
+
"loss": 0.2174,
|
| 1280 |
+
"step": 212
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.3,
|
| 1284 |
+
"learning_rate": 2e-05,
|
| 1285 |
+
"loss": 0.1843,
|
| 1286 |
+
"step": 213
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 1.3,
|
| 1290 |
+
"learning_rate": 2e-05,
|
| 1291 |
+
"loss": 0.1965,
|
| 1292 |
+
"step": 214
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 1.31,
|
| 1296 |
+
"learning_rate": 2e-05,
|
| 1297 |
+
"loss": 0.2238,
|
| 1298 |
+
"step": 215
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.32,
|
| 1302 |
+
"learning_rate": 2e-05,
|
| 1303 |
+
"loss": 0.1907,
|
| 1304 |
+
"step": 216
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 1.32,
|
| 1308 |
+
"learning_rate": 2e-05,
|
| 1309 |
+
"loss": 0.2238,
|
| 1310 |
+
"step": 217
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 1.33,
|
| 1314 |
+
"learning_rate": 2e-05,
|
| 1315 |
+
"loss": 0.1917,
|
| 1316 |
+
"step": 218
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 1.34,
|
| 1320 |
+
"learning_rate": 2e-05,
|
| 1321 |
+
"loss": 0.2024,
|
| 1322 |
+
"step": 219
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.34,
|
| 1326 |
+
"learning_rate": 2e-05,
|
| 1327 |
+
"loss": 0.2097,
|
| 1328 |
+
"step": 220
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 1.35,
|
| 1332 |
+
"learning_rate": 2e-05,
|
| 1333 |
+
"loss": 0.2217,
|
| 1334 |
+
"step": 221
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 1.35,
|
| 1338 |
+
"learning_rate": 2e-05,
|
| 1339 |
+
"loss": 0.2335,
|
| 1340 |
+
"step": 222
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.36,
|
| 1344 |
+
"learning_rate": 2e-05,
|
| 1345 |
+
"loss": 0.2006,
|
| 1346 |
+
"step": 223
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 1.37,
|
| 1350 |
+
"learning_rate": 2e-05,
|
| 1351 |
+
"loss": 0.215,
|
| 1352 |
+
"step": 224
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 1.37,
|
| 1356 |
+
"learning_rate": 2e-05,
|
| 1357 |
+
"loss": 0.2419,
|
| 1358 |
+
"step": 225
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.38,
|
| 1362 |
+
"learning_rate": 2e-05,
|
| 1363 |
+
"loss": 0.2238,
|
| 1364 |
+
"step": 226
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.38,
|
| 1368 |
+
"learning_rate": 2e-05,
|
| 1369 |
+
"loss": 0.2188,
|
| 1370 |
+
"step": 227
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 1.39,
|
| 1374 |
+
"learning_rate": 2e-05,
|
| 1375 |
+
"loss": 0.1932,
|
| 1376 |
+
"step": 228
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 1.4,
|
| 1380 |
+
"learning_rate": 2e-05,
|
| 1381 |
+
"loss": 0.2273,
|
| 1382 |
+
"step": 229
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.4,
|
| 1386 |
+
"learning_rate": 2e-05,
|
| 1387 |
+
"loss": 0.2068,
|
| 1388 |
+
"step": 230
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 1.41,
|
| 1392 |
+
"learning_rate": 2e-05,
|
| 1393 |
+
"loss": 0.1949,
|
| 1394 |
+
"step": 231
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 1.41,
|
| 1398 |
+
"learning_rate": 2e-05,
|
| 1399 |
+
"loss": 0.2098,
|
| 1400 |
+
"step": 232
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.42,
|
| 1404 |
+
"learning_rate": 2e-05,
|
| 1405 |
+
"loss": 0.2012,
|
| 1406 |
+
"step": 233
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.43,
|
| 1410 |
+
"learning_rate": 2e-05,
|
| 1411 |
+
"loss": 0.2117,
|
| 1412 |
+
"step": 234
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.43,
|
| 1416 |
+
"learning_rate": 2e-05,
|
| 1417 |
+
"loss": 0.2446,
|
| 1418 |
+
"step": 235
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.44,
|
| 1422 |
+
"learning_rate": 2e-05,
|
| 1423 |
+
"loss": 0.2042,
|
| 1424 |
+
"step": 236
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.45,
|
| 1428 |
+
"learning_rate": 2e-05,
|
| 1429 |
+
"loss": 0.1885,
|
| 1430 |
+
"step": 237
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.45,
|
| 1434 |
+
"learning_rate": 2e-05,
|
| 1435 |
+
"loss": 0.2098,
|
| 1436 |
+
"step": 238
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.46,
|
| 1440 |
+
"learning_rate": 2e-05,
|
| 1441 |
+
"loss": 0.2004,
|
| 1442 |
+
"step": 239
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.46,
|
| 1446 |
+
"learning_rate": 2e-05,
|
| 1447 |
+
"loss": 0.2108,
|
| 1448 |
+
"step": 240
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 1.47,
|
| 1452 |
+
"learning_rate": 2e-05,
|
| 1453 |
+
"loss": 0.1917,
|
| 1454 |
+
"step": 241
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 1.48,
|
| 1458 |
+
"learning_rate": 2e-05,
|
| 1459 |
+
"loss": 0.2324,
|
| 1460 |
+
"step": 242
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 1.48,
|
| 1464 |
+
"learning_rate": 2e-05,
|
| 1465 |
+
"loss": 0.2211,
|
| 1466 |
+
"step": 243
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.49,
|
| 1470 |
+
"learning_rate": 2e-05,
|
| 1471 |
+
"loss": 0.2102,
|
| 1472 |
+
"step": 244
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 1.49,
|
| 1476 |
+
"learning_rate": 2e-05,
|
| 1477 |
+
"loss": 0.2356,
|
| 1478 |
+
"step": 245
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 1.5,
|
| 1482 |
+
"learning_rate": 2e-05,
|
| 1483 |
+
"loss": 0.2201,
|
| 1484 |
+
"step": 246
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.51,
|
| 1488 |
+
"learning_rate": 2e-05,
|
| 1489 |
+
"loss": 0.2198,
|
| 1490 |
+
"step": 247
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.51,
|
| 1494 |
+
"learning_rate": 2e-05,
|
| 1495 |
+
"loss": 0.2089,
|
| 1496 |
+
"step": 248
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 1.52,
|
| 1500 |
+
"learning_rate": 2e-05,
|
| 1501 |
+
"loss": 0.2169,
|
| 1502 |
+
"step": 249
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 1.52,
|
| 1506 |
+
"learning_rate": 2e-05,
|
| 1507 |
+
"loss": 0.2181,
|
| 1508 |
+
"step": 250
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.53,
|
| 1512 |
+
"learning_rate": 2e-05,
|
| 1513 |
+
"loss": 0.2356,
|
| 1514 |
+
"step": 251
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.54,
|
| 1518 |
+
"learning_rate": 2e-05,
|
| 1519 |
+
"loss": 0.1996,
|
| 1520 |
+
"step": 252
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 1.54,
|
| 1524 |
+
"learning_rate": 2e-05,
|
| 1525 |
+
"loss": 0.2262,
|
| 1526 |
+
"step": 253
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.55,
|
| 1530 |
+
"learning_rate": 2e-05,
|
| 1531 |
+
"loss": 0.2146,
|
| 1532 |
+
"step": 254
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 1.55,
|
| 1536 |
+
"learning_rate": 2e-05,
|
| 1537 |
+
"loss": 0.2051,
|
| 1538 |
+
"step": 255
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.56,
|
| 1542 |
+
"learning_rate": 2e-05,
|
| 1543 |
+
"loss": 0.2008,
|
| 1544 |
+
"step": 256
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 1.57,
|
| 1548 |
+
"learning_rate": 2e-05,
|
| 1549 |
+
"loss": 0.222,
|
| 1550 |
+
"step": 257
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.57,
|
| 1554 |
+
"learning_rate": 2e-05,
|
| 1555 |
+
"loss": 0.2349,
|
| 1556 |
+
"step": 258
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 1.58,
|
| 1560 |
+
"learning_rate": 2e-05,
|
| 1561 |
+
"loss": 0.217,
|
| 1562 |
+
"step": 259
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.59,
|
| 1566 |
+
"learning_rate": 2e-05,
|
| 1567 |
+
"loss": 0.223,
|
| 1568 |
+
"step": 260
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.59,
|
| 1572 |
+
"learning_rate": 2e-05,
|
| 1573 |
+
"loss": 0.2213,
|
| 1574 |
+
"step": 261
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 1.6,
|
| 1578 |
+
"learning_rate": 2e-05,
|
| 1579 |
+
"loss": 0.2327,
|
| 1580 |
+
"step": 262
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 1.6,
|
| 1584 |
+
"learning_rate": 2e-05,
|
| 1585 |
+
"loss": 0.2203,
|
| 1586 |
+
"step": 263
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.61,
|
| 1590 |
+
"learning_rate": 2e-05,
|
| 1591 |
+
"loss": 0.2134,
|
| 1592 |
+
"step": 264
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.62,
|
| 1596 |
+
"learning_rate": 2e-05,
|
| 1597 |
+
"loss": 0.2103,
|
| 1598 |
+
"step": 265
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 1.62,
|
| 1602 |
+
"learning_rate": 2e-05,
|
| 1603 |
+
"loss": 0.2181,
|
| 1604 |
+
"step": 266
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 1.63,
|
| 1608 |
+
"learning_rate": 2e-05,
|
| 1609 |
+
"loss": 0.2207,
|
| 1610 |
+
"step": 267
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.63,
|
| 1614 |
+
"learning_rate": 2e-05,
|
| 1615 |
+
"loss": 0.2064,
|
| 1616 |
+
"step": 268
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 1.64,
|
| 1620 |
+
"learning_rate": 2e-05,
|
| 1621 |
+
"loss": 0.2107,
|
| 1622 |
+
"step": 269
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 1.65,
|
| 1626 |
+
"learning_rate": 2e-05,
|
| 1627 |
+
"loss": 0.2234,
|
| 1628 |
+
"step": 270
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 1.65,
|
| 1632 |
+
"learning_rate": 2e-05,
|
| 1633 |
+
"loss": 0.2382,
|
| 1634 |
+
"step": 271
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.66,
|
| 1638 |
+
"learning_rate": 2e-05,
|
| 1639 |
+
"loss": 0.1884,
|
| 1640 |
+
"step": 272
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 1.66,
|
| 1644 |
+
"learning_rate": 2e-05,
|
| 1645 |
+
"loss": 0.2007,
|
| 1646 |
+
"step": 273
|
| 1647 |
+
},
|
| 1648 |
+
{
|
| 1649 |
+
"epoch": 1.67,
|
| 1650 |
+
"learning_rate": 2e-05,
|
| 1651 |
+
"loss": 0.2222,
|
| 1652 |
+
"step": 274
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 1.68,
|
| 1656 |
+
"learning_rate": 2e-05,
|
| 1657 |
+
"loss": 0.2294,
|
| 1658 |
+
"step": 275
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.68,
|
| 1662 |
+
"learning_rate": 2e-05,
|
| 1663 |
+
"loss": 0.2177,
|
| 1664 |
+
"step": 276
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 1.69,
|
| 1668 |
+
"learning_rate": 2e-05,
|
| 1669 |
+
"loss": 0.2065,
|
| 1670 |
+
"step": 277
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 1.7,
|
| 1674 |
+
"learning_rate": 2e-05,
|
| 1675 |
+
"loss": 0.2003,
|
| 1676 |
+
"step": 278
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 1.7,
|
| 1680 |
+
"learning_rate": 2e-05,
|
| 1681 |
+
"loss": 0.1974,
|
| 1682 |
+
"step": 279
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.71,
|
| 1686 |
+
"learning_rate": 2e-05,
|
| 1687 |
+
"loss": 0.2146,
|
| 1688 |
+
"step": 280
|
| 1689 |
+
},
|
| 1690 |
+
{
|
| 1691 |
+
"epoch": 1.71,
|
| 1692 |
+
"learning_rate": 2e-05,
|
| 1693 |
+
"loss": 0.2466,
|
| 1694 |
+
"step": 281
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 1.72,
|
| 1698 |
+
"learning_rate": 2e-05,
|
| 1699 |
+
"loss": 0.2023,
|
| 1700 |
+
"step": 282
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 1.73,
|
| 1704 |
+
"learning_rate": 2e-05,
|
| 1705 |
+
"loss": 0.1937,
|
| 1706 |
+
"step": 283
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.73,
|
| 1710 |
+
"learning_rate": 2e-05,
|
| 1711 |
+
"loss": 0.2134,
|
| 1712 |
+
"step": 284
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 1.74,
|
| 1716 |
+
"learning_rate": 2e-05,
|
| 1717 |
+
"loss": 0.2152,
|
| 1718 |
+
"step": 285
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 1.74,
|
| 1722 |
+
"learning_rate": 2e-05,
|
| 1723 |
+
"loss": 0.2357,
|
| 1724 |
+
"step": 286
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 1.75,
|
| 1728 |
+
"learning_rate": 2e-05,
|
| 1729 |
+
"loss": 0.2061,
|
| 1730 |
+
"step": 287
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.76,
|
| 1734 |
+
"learning_rate": 2e-05,
|
| 1735 |
+
"loss": 0.2004,
|
| 1736 |
+
"step": 288
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.76,
|
| 1740 |
+
"learning_rate": 2e-05,
|
| 1741 |
+
"loss": 0.1984,
|
| 1742 |
+
"step": 289
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 1.77,
|
| 1746 |
+
"learning_rate": 2e-05,
|
| 1747 |
+
"loss": 0.2134,
|
| 1748 |
+
"step": 290
|
| 1749 |
+
},
|
| 1750 |
+
{
|
| 1751 |
+
"epoch": 1.77,
|
| 1752 |
+
"learning_rate": 2e-05,
|
| 1753 |
+
"loss": 0.2006,
|
| 1754 |
+
"step": 291
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.78,
|
| 1758 |
+
"learning_rate": 2e-05,
|
| 1759 |
+
"loss": 0.2203,
|
| 1760 |
+
"step": 292
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 1.79,
|
| 1764 |
+
"learning_rate": 2e-05,
|
| 1765 |
+
"loss": 0.2067,
|
| 1766 |
+
"step": 293
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 1.79,
|
| 1770 |
+
"learning_rate": 2e-05,
|
| 1771 |
+
"loss": 0.2218,
|
| 1772 |
+
"step": 294
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 1.8,
|
| 1776 |
+
"learning_rate": 2e-05,
|
| 1777 |
+
"loss": 0.2255,
|
| 1778 |
+
"step": 295
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.8,
|
| 1782 |
+
"learning_rate": 2e-05,
|
| 1783 |
+
"loss": 0.2156,
|
| 1784 |
+
"step": 296
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 1.81,
|
| 1788 |
+
"learning_rate": 2e-05,
|
| 1789 |
+
"loss": 0.2092,
|
| 1790 |
+
"step": 297
|
| 1791 |
+
},
|
| 1792 |
+
{
|
| 1793 |
+
"epoch": 1.82,
|
| 1794 |
+
"learning_rate": 2e-05,
|
| 1795 |
+
"loss": 0.2135,
|
| 1796 |
+
"step": 298
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 1.82,
|
| 1800 |
+
"learning_rate": 2e-05,
|
| 1801 |
+
"loss": 0.2123,
|
| 1802 |
+
"step": 299
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.83,
|
| 1806 |
+
"learning_rate": 2e-05,
|
| 1807 |
+
"loss": 0.2131,
|
| 1808 |
+
"step": 300
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 1.84,
|
| 1812 |
+
"learning_rate": 2e-05,
|
| 1813 |
+
"loss": 0.1343,
|
| 1814 |
+
"step": 301
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 1.84,
|
| 1818 |
+
"learning_rate": 2e-05,
|
| 1819 |
+
"loss": 0.1756,
|
| 1820 |
+
"step": 302
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 1.85,
|
| 1824 |
+
"learning_rate": 2e-05,
|
| 1825 |
+
"loss": 0.1584,
|
| 1826 |
+
"step": 303
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 1.85,
|
| 1830 |
+
"learning_rate": 2e-05,
|
| 1831 |
+
"loss": 0.17,
|
| 1832 |
+
"step": 304
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 1.86,
|
| 1836 |
+
"learning_rate": 2e-05,
|
| 1837 |
+
"loss": 0.1644,
|
| 1838 |
+
"step": 305
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 1.87,
|
| 1842 |
+
"learning_rate": 2e-05,
|
| 1843 |
+
"loss": 0.1394,
|
| 1844 |
+
"step": 306
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 1.87,
|
| 1848 |
+
"learning_rate": 2e-05,
|
| 1849 |
+
"loss": 0.1244,
|
| 1850 |
+
"step": 307
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.88,
|
| 1854 |
+
"learning_rate": 2e-05,
|
| 1855 |
+
"loss": 0.1575,
|
| 1856 |
+
"step": 308
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 1.88,
|
| 1860 |
+
"learning_rate": 2e-05,
|
| 1861 |
+
"loss": 0.139,
|
| 1862 |
+
"step": 309
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 1.89,
|
| 1866 |
+
"learning_rate": 2e-05,
|
| 1867 |
+
"loss": 0.1434,
|
| 1868 |
+
"step": 310
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 1.9,
|
| 1872 |
+
"learning_rate": 2e-05,
|
| 1873 |
+
"loss": 0.1583,
|
| 1874 |
+
"step": 311
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.9,
|
| 1878 |
+
"learning_rate": 2e-05,
|
| 1879 |
+
"loss": 0.1606,
|
| 1880 |
+
"step": 312
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 1.91,
|
| 1884 |
+
"learning_rate": 2e-05,
|
| 1885 |
+
"loss": 0.1411,
|
| 1886 |
+
"step": 313
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 1.91,
|
| 1890 |
+
"learning_rate": 2e-05,
|
| 1891 |
+
"loss": 0.1259,
|
| 1892 |
+
"step": 314
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 1.92,
|
| 1896 |
+
"learning_rate": 2e-05,
|
| 1897 |
+
"loss": 0.1534,
|
| 1898 |
+
"step": 315
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.93,
|
| 1902 |
+
"learning_rate": 2e-05,
|
| 1903 |
+
"loss": 0.129,
|
| 1904 |
+
"step": 316
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 1.93,
|
| 1908 |
+
"learning_rate": 2e-05,
|
| 1909 |
+
"loss": 0.152,
|
| 1910 |
+
"step": 317
|
| 1911 |
+
},
|
| 1912 |
+
{
|
| 1913 |
+
"epoch": 1.94,
|
| 1914 |
+
"learning_rate": 2e-05,
|
| 1915 |
+
"loss": 0.1489,
|
| 1916 |
+
"step": 318
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 1.95,
|
| 1920 |
+
"learning_rate": 2e-05,
|
| 1921 |
+
"loss": 0.1431,
|
| 1922 |
+
"step": 319
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.95,
|
| 1926 |
+
"learning_rate": 2e-05,
|
| 1927 |
+
"loss": 0.1387,
|
| 1928 |
+
"step": 320
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 1.96,
|
| 1932 |
+
"learning_rate": 2e-05,
|
| 1933 |
+
"loss": 0.1499,
|
| 1934 |
+
"step": 321
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 1.96,
|
| 1938 |
+
"learning_rate": 2e-05,
|
| 1939 |
+
"loss": 0.1519,
|
| 1940 |
+
"step": 322
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 1.97,
|
| 1944 |
+
"learning_rate": 2e-05,
|
| 1945 |
+
"loss": 0.1506,
|
| 1946 |
+
"step": 323
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.98,
|
| 1950 |
+
"learning_rate": 2e-05,
|
| 1951 |
+
"loss": 0.1567,
|
| 1952 |
+
"step": 324
|
| 1953 |
+
},
|
| 1954 |
+
{
|
| 1955 |
+
"epoch": 1.98,
|
| 1956 |
+
"learning_rate": 2e-05,
|
| 1957 |
+
"loss": 0.141,
|
| 1958 |
+
"step": 325
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 1.99,
|
| 1962 |
+
"learning_rate": 2e-05,
|
| 1963 |
+
"loss": 0.1713,
|
| 1964 |
+
"step": 326
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 1.99,
|
| 1968 |
+
"learning_rate": 2e-05,
|
| 1969 |
+
"loss": 0.1493,
|
| 1970 |
+
"step": 327
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.0,
|
| 1974 |
+
"learning_rate": 2e-05,
|
| 1975 |
+
"loss": 0.1281,
|
| 1976 |
+
"step": 328
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 2.01,
|
| 1980 |
+
"learning_rate": 2e-05,
|
| 1981 |
+
"loss": 0.1395,
|
| 1982 |
+
"step": 329
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 2.01,
|
| 1986 |
+
"learning_rate": 2e-05,
|
| 1987 |
+
"loss": 0.1452,
|
| 1988 |
+
"step": 330
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 2.02,
|
| 1992 |
+
"learning_rate": 2e-05,
|
| 1993 |
+
"loss": 0.1342,
|
| 1994 |
+
"step": 331
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 2.02,
|
| 1998 |
+
"learning_rate": 2e-05,
|
| 1999 |
+
"loss": 0.1445,
|
| 2000 |
+
"step": 332
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 2.03,
|
| 2004 |
+
"learning_rate": 2e-05,
|
| 2005 |
+
"loss": 0.1173,
|
| 2006 |
+
"step": 333
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 2.04,
|
| 2010 |
+
"learning_rate": 2e-05,
|
| 2011 |
+
"loss": 0.1302,
|
| 2012 |
+
"step": 334
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.04,
|
| 2016 |
+
"learning_rate": 2e-05,
|
| 2017 |
+
"loss": 0.125,
|
| 2018 |
+
"step": 335
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 2.05,
|
| 2022 |
+
"learning_rate": 2e-05,
|
| 2023 |
+
"loss": 0.1432,
|
| 2024 |
+
"step": 336
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 2.05,
|
| 2028 |
+
"learning_rate": 2e-05,
|
| 2029 |
+
"loss": 0.1283,
|
| 2030 |
+
"step": 337
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 2.06,
|
| 2034 |
+
"learning_rate": 2e-05,
|
| 2035 |
+
"loss": 0.1395,
|
| 2036 |
+
"step": 338
|
| 2037 |
+
},
|
| 2038 |
+
{
|
| 2039 |
+
"epoch": 2.07,
|
| 2040 |
+
"learning_rate": 2e-05,
|
| 2041 |
+
"loss": 0.1331,
|
| 2042 |
+
"step": 339
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 2.07,
|
| 2046 |
+
"learning_rate": 2e-05,
|
| 2047 |
+
"loss": 0.1505,
|
| 2048 |
+
"step": 340
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 2.08,
|
| 2052 |
+
"learning_rate": 2e-05,
|
| 2053 |
+
"loss": 0.1298,
|
| 2054 |
+
"step": 341
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.09,
|
| 2058 |
+
"learning_rate": 2e-05,
|
| 2059 |
+
"loss": 0.1499,
|
| 2060 |
+
"step": 342
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 2.09,
|
| 2064 |
+
"learning_rate": 2e-05,
|
| 2065 |
+
"loss": 0.151,
|
| 2066 |
+
"step": 343
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 2.1,
|
| 2070 |
+
"learning_rate": 2e-05,
|
| 2071 |
+
"loss": 0.1628,
|
| 2072 |
+
"step": 344
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 2.1,
|
| 2076 |
+
"learning_rate": 2e-05,
|
| 2077 |
+
"loss": 0.1378,
|
| 2078 |
+
"step": 345
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 2.11,
|
| 2082 |
+
"learning_rate": 2e-05,
|
| 2083 |
+
"loss": 0.1484,
|
| 2084 |
+
"step": 346
|
| 2085 |
+
},
|
| 2086 |
+
{
|
| 2087 |
+
"epoch": 2.12,
|
| 2088 |
+
"learning_rate": 2e-05,
|
| 2089 |
+
"loss": 0.1513,
|
| 2090 |
+
"step": 347
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 2.12,
|
| 2094 |
+
"learning_rate": 2e-05,
|
| 2095 |
+
"loss": 0.1323,
|
| 2096 |
+
"step": 348
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.13,
|
| 2100 |
+
"learning_rate": 2e-05,
|
| 2101 |
+
"loss": 0.1422,
|
| 2102 |
+
"step": 349
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 2.13,
|
| 2106 |
+
"learning_rate": 2e-05,
|
| 2107 |
+
"loss": 0.1706,
|
| 2108 |
+
"step": 350
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 2.14,
|
| 2112 |
+
"learning_rate": 2e-05,
|
| 2113 |
+
"loss": 0.1591,
|
| 2114 |
+
"step": 351
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 2.15,
|
| 2118 |
+
"learning_rate": 2e-05,
|
| 2119 |
+
"loss": 0.1483,
|
| 2120 |
+
"step": 352
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 2.15,
|
| 2124 |
+
"learning_rate": 2e-05,
|
| 2125 |
+
"loss": 0.1484,
|
| 2126 |
+
"step": 353
|
| 2127 |
+
},
|
| 2128 |
+
{
|
| 2129 |
+
"epoch": 2.16,
|
| 2130 |
+
"learning_rate": 2e-05,
|
| 2131 |
+
"loss": 0.1393,
|
| 2132 |
+
"step": 354
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 2.16,
|
| 2136 |
+
"learning_rate": 2e-05,
|
| 2137 |
+
"loss": 0.1543,
|
| 2138 |
+
"step": 355
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.17,
|
| 2142 |
+
"learning_rate": 2e-05,
|
| 2143 |
+
"loss": 0.142,
|
| 2144 |
+
"step": 356
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 2.18,
|
| 2148 |
+
"learning_rate": 2e-05,
|
| 2149 |
+
"loss": 0.1474,
|
| 2150 |
+
"step": 357
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 2.18,
|
| 2154 |
+
"learning_rate": 2e-05,
|
| 2155 |
+
"loss": 0.1469,
|
| 2156 |
+
"step": 358
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 2.19,
|
| 2160 |
+
"learning_rate": 2e-05,
|
| 2161 |
+
"loss": 0.1516,
|
| 2162 |
+
"step": 359
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 2.2,
|
| 2166 |
+
"learning_rate": 2e-05,
|
| 2167 |
+
"loss": 0.1666,
|
| 2168 |
+
"step": 360
|
| 2169 |
+
},
|
| 2170 |
+
{
|
| 2171 |
+
"epoch": 2.2,
|
| 2172 |
+
"learning_rate": 2e-05,
|
| 2173 |
+
"loss": 0.1473,
|
| 2174 |
+
"step": 361
|
| 2175 |
+
},
|
| 2176 |
+
{
|
| 2177 |
+
"epoch": 2.21,
|
| 2178 |
+
"learning_rate": 2e-05,
|
| 2179 |
+
"loss": 0.1707,
|
| 2180 |
+
"step": 362
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.21,
|
| 2184 |
+
"learning_rate": 2e-05,
|
| 2185 |
+
"loss": 0.1487,
|
| 2186 |
+
"step": 363
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 2.22,
|
| 2190 |
+
"learning_rate": 2e-05,
|
| 2191 |
+
"loss": 0.1558,
|
| 2192 |
+
"step": 364
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 2.23,
|
| 2196 |
+
"learning_rate": 2e-05,
|
| 2197 |
+
"loss": 0.1622,
|
| 2198 |
+
"step": 365
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 2.23,
|
| 2202 |
+
"learning_rate": 2e-05,
|
| 2203 |
+
"loss": 0.1339,
|
| 2204 |
+
"step": 366
|
| 2205 |
+
},
|
| 2206 |
+
{
|
| 2207 |
+
"epoch": 2.24,
|
| 2208 |
+
"learning_rate": 2e-05,
|
| 2209 |
+
"loss": 0.1516,
|
| 2210 |
+
"step": 367
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 2.24,
|
| 2214 |
+
"learning_rate": 2e-05,
|
| 2215 |
+
"loss": 0.1515,
|
| 2216 |
+
"step": 368
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 2.25,
|
| 2220 |
+
"learning_rate": 2e-05,
|
| 2221 |
+
"loss": 0.1341,
|
| 2222 |
+
"step": 369
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.26,
|
| 2226 |
+
"learning_rate": 2e-05,
|
| 2227 |
+
"loss": 0.1589,
|
| 2228 |
+
"step": 370
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 2.26,
|
| 2232 |
+
"learning_rate": 2e-05,
|
| 2233 |
+
"loss": 0.1413,
|
| 2234 |
+
"step": 371
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 2.27,
|
| 2238 |
+
"learning_rate": 2e-05,
|
| 2239 |
+
"loss": 0.1544,
|
| 2240 |
+
"step": 372
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 2.27,
|
| 2244 |
+
"learning_rate": 2e-05,
|
| 2245 |
+
"loss": 0.1476,
|
| 2246 |
+
"step": 373
|
| 2247 |
+
},
|
| 2248 |
+
{
|
| 2249 |
+
"epoch": 2.28,
|
| 2250 |
+
"learning_rate": 2e-05,
|
| 2251 |
+
"loss": 0.1409,
|
| 2252 |
+
"step": 374
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 2.29,
|
| 2256 |
+
"learning_rate": 2e-05,
|
| 2257 |
+
"loss": 0.1395,
|
| 2258 |
+
"step": 375
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 2.29,
|
| 2262 |
+
"learning_rate": 2e-05,
|
| 2263 |
+
"loss": 0.1431,
|
| 2264 |
+
"step": 376
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.3,
|
| 2268 |
+
"learning_rate": 2e-05,
|
| 2269 |
+
"loss": 0.1431,
|
| 2270 |
+
"step": 377
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 2.3,
|
| 2274 |
+
"learning_rate": 2e-05,
|
| 2275 |
+
"loss": 0.1384,
|
| 2276 |
+
"step": 378
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 2.31,
|
| 2280 |
+
"learning_rate": 2e-05,
|
| 2281 |
+
"loss": 0.166,
|
| 2282 |
+
"step": 379
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 2.32,
|
| 2286 |
+
"learning_rate": 2e-05,
|
| 2287 |
+
"loss": 0.1419,
|
| 2288 |
+
"step": 380
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 2.32,
|
| 2292 |
+
"learning_rate": 2e-05,
|
| 2293 |
+
"loss": 0.166,
|
| 2294 |
+
"step": 381
|
| 2295 |
+
},
|
| 2296 |
+
{
|
| 2297 |
+
"epoch": 2.33,
|
| 2298 |
+
"learning_rate": 2e-05,
|
| 2299 |
+
"loss": 0.1641,
|
| 2300 |
+
"step": 382
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"epoch": 2.34,
|
| 2304 |
+
"learning_rate": 2e-05,
|
| 2305 |
+
"loss": 0.1548,
|
| 2306 |
+
"step": 383
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.34,
|
| 2310 |
+
"learning_rate": 2e-05,
|
| 2311 |
+
"loss": 0.1518,
|
| 2312 |
+
"step": 384
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 2.35,
|
| 2316 |
+
"learning_rate": 2e-05,
|
| 2317 |
+
"loss": 0.1584,
|
| 2318 |
+
"step": 385
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 2.35,
|
| 2322 |
+
"learning_rate": 2e-05,
|
| 2323 |
+
"loss": 0.1664,
|
| 2324 |
+
"step": 386
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 2.36,
|
| 2328 |
+
"learning_rate": 2e-05,
|
| 2329 |
+
"loss": 0.1805,
|
| 2330 |
+
"step": 387
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 2.37,
|
| 2334 |
+
"learning_rate": 2e-05,
|
| 2335 |
+
"loss": 0.1447,
|
| 2336 |
+
"step": 388
|
| 2337 |
+
},
|
| 2338 |
+
{
|
| 2339 |
+
"epoch": 2.37,
|
| 2340 |
+
"learning_rate": 2e-05,
|
| 2341 |
+
"loss": 0.1539,
|
| 2342 |
+
"step": 389
|
| 2343 |
+
},
|
| 2344 |
+
{
|
| 2345 |
+
"epoch": 2.38,
|
| 2346 |
+
"learning_rate": 2e-05,
|
| 2347 |
+
"loss": 0.1656,
|
| 2348 |
+
"step": 390
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.38,
|
| 2352 |
+
"learning_rate": 2e-05,
|
| 2353 |
+
"loss": 0.1654,
|
| 2354 |
+
"step": 391
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 2.39,
|
| 2358 |
+
"learning_rate": 2e-05,
|
| 2359 |
+
"loss": 0.16,
|
| 2360 |
+
"step": 392
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 2.4,
|
| 2364 |
+
"learning_rate": 2e-05,
|
| 2365 |
+
"loss": 0.1528,
|
| 2366 |
+
"step": 393
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 2.4,
|
| 2370 |
+
"learning_rate": 2e-05,
|
| 2371 |
+
"loss": 0.1653,
|
| 2372 |
+
"step": 394
|
| 2373 |
+
},
|
| 2374 |
+
{
|
| 2375 |
+
"epoch": 2.41,
|
| 2376 |
+
"learning_rate": 2e-05,
|
| 2377 |
+
"loss": 0.1619,
|
| 2378 |
+
"step": 395
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 2.41,
|
| 2382 |
+
"learning_rate": 2e-05,
|
| 2383 |
+
"loss": 0.1544,
|
| 2384 |
+
"step": 396
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 2.42,
|
| 2388 |
+
"learning_rate": 2e-05,
|
| 2389 |
+
"loss": 0.1675,
|
| 2390 |
+
"step": 397
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.43,
|
| 2394 |
+
"learning_rate": 2e-05,
|
| 2395 |
+
"loss": 0.1733,
|
| 2396 |
+
"step": 398
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 2.43,
|
| 2400 |
+
"learning_rate": 2e-05,
|
| 2401 |
+
"loss": 0.1523,
|
| 2402 |
+
"step": 399
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 2.44,
|
| 2406 |
+
"learning_rate": 2e-05,
|
| 2407 |
+
"loss": 0.1631,
|
| 2408 |
+
"step": 400
|
| 2409 |
+
},
|
| 2410 |
+
{
|
| 2411 |
+
"epoch": 2.45,
|
| 2412 |
+
"learning_rate": 2e-05,
|
| 2413 |
+
"loss": 0.168,
|
| 2414 |
+
"step": 401
|
| 2415 |
+
},
|
| 2416 |
+
{
|
| 2417 |
+
"epoch": 2.45,
|
| 2418 |
+
"learning_rate": 2e-05,
|
| 2419 |
+
"loss": 0.1574,
|
| 2420 |
+
"step": 402
|
| 2421 |
+
},
|
| 2422 |
+
{
|
| 2423 |
+
"epoch": 2.46,
|
| 2424 |
+
"learning_rate": 2e-05,
|
| 2425 |
+
"loss": 0.1512,
|
| 2426 |
+
"step": 403
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 2.46,
|
| 2430 |
+
"learning_rate": 2e-05,
|
| 2431 |
+
"loss": 0.1578,
|
| 2432 |
+
"step": 404
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.47,
|
| 2436 |
+
"learning_rate": 2e-05,
|
| 2437 |
+
"loss": 0.1411,
|
| 2438 |
+
"step": 405
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 2.48,
|
| 2442 |
+
"learning_rate": 2e-05,
|
| 2443 |
+
"loss": 0.1568,
|
| 2444 |
+
"step": 406
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 2.48,
|
| 2448 |
+
"learning_rate": 2e-05,
|
| 2449 |
+
"loss": 0.1852,
|
| 2450 |
+
"step": 407
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 2.49,
|
| 2454 |
+
"learning_rate": 2e-05,
|
| 2455 |
+
"loss": 0.124,
|
| 2456 |
+
"step": 408
|
| 2457 |
+
},
|
| 2458 |
+
{
|
| 2459 |
+
"epoch": 2.49,
|
| 2460 |
+
"learning_rate": 2e-05,
|
| 2461 |
+
"loss": 0.1692,
|
| 2462 |
+
"step": 409
|
| 2463 |
+
},
|
| 2464 |
+
{
|
| 2465 |
+
"epoch": 2.5,
|
| 2466 |
+
"learning_rate": 2e-05,
|
| 2467 |
+
"loss": 0.1602,
|
| 2468 |
+
"step": 410
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 2.51,
|
| 2472 |
+
"learning_rate": 2e-05,
|
| 2473 |
+
"loss": 0.1721,
|
| 2474 |
+
"step": 411
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 2.51,
|
| 2478 |
+
"learning_rate": 2e-05,
|
| 2479 |
+
"loss": 0.1541,
|
| 2480 |
+
"step": 412
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 2.52,
|
| 2484 |
+
"learning_rate": 2e-05,
|
| 2485 |
+
"loss": 0.1462,
|
| 2486 |
+
"step": 413
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 2.52,
|
| 2490 |
+
"learning_rate": 2e-05,
|
| 2491 |
+
"loss": 0.1569,
|
| 2492 |
+
"step": 414
|
| 2493 |
+
},
|
| 2494 |
+
{
|
| 2495 |
+
"epoch": 2.53,
|
| 2496 |
+
"learning_rate": 2e-05,
|
| 2497 |
+
"loss": 0.1622,
|
| 2498 |
+
"step": 415
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 2.54,
|
| 2502 |
+
"learning_rate": 2e-05,
|
| 2503 |
+
"loss": 0.1652,
|
| 2504 |
+
"step": 416
|
| 2505 |
+
},
|
| 2506 |
+
{
|
| 2507 |
+
"epoch": 2.54,
|
| 2508 |
+
"learning_rate": 2e-05,
|
| 2509 |
+
"loss": 0.167,
|
| 2510 |
+
"step": 417
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 2.55,
|
| 2514 |
+
"learning_rate": 2e-05,
|
| 2515 |
+
"loss": 0.1511,
|
| 2516 |
+
"step": 418
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 2.55,
|
| 2520 |
+
"learning_rate": 2e-05,
|
| 2521 |
+
"loss": 0.1372,
|
| 2522 |
+
"step": 419
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 2.56,
|
| 2526 |
+
"learning_rate": 2e-05,
|
| 2527 |
+
"loss": 0.15,
|
| 2528 |
+
"step": 420
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 2.57,
|
| 2532 |
+
"learning_rate": 2e-05,
|
| 2533 |
+
"loss": 0.1584,
|
| 2534 |
+
"step": 421
|
| 2535 |
+
},
|
| 2536 |
+
{
|
| 2537 |
+
"epoch": 2.57,
|
| 2538 |
+
"learning_rate": 2e-05,
|
| 2539 |
+
"loss": 0.1606,
|
| 2540 |
+
"step": 422
|
| 2541 |
+
},
|
| 2542 |
+
{
|
| 2543 |
+
"epoch": 2.58,
|
| 2544 |
+
"learning_rate": 2e-05,
|
| 2545 |
+
"loss": 0.1569,
|
| 2546 |
+
"step": 423
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 2.59,
|
| 2550 |
+
"learning_rate": 2e-05,
|
| 2551 |
+
"loss": 0.1763,
|
| 2552 |
+
"step": 424
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 2.59,
|
| 2556 |
+
"learning_rate": 2e-05,
|
| 2557 |
+
"loss": 0.1517,
|
| 2558 |
+
"step": 425
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 2.6,
|
| 2562 |
+
"learning_rate": 2e-05,
|
| 2563 |
+
"loss": 0.1569,
|
| 2564 |
+
"step": 426
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 2.6,
|
| 2568 |
+
"learning_rate": 2e-05,
|
| 2569 |
+
"loss": 0.1896,
|
| 2570 |
+
"step": 427
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 2.61,
|
| 2574 |
+
"learning_rate": 2e-05,
|
| 2575 |
+
"loss": 0.1402,
|
| 2576 |
+
"step": 428
|
| 2577 |
+
},
|
| 2578 |
+
{
|
| 2579 |
+
"epoch": 2.62,
|
| 2580 |
+
"learning_rate": 2e-05,
|
| 2581 |
+
"loss": 0.1613,
|
| 2582 |
+
"step": 429
|
| 2583 |
+
},
|
| 2584 |
+
{
|
| 2585 |
+
"epoch": 2.62,
|
| 2586 |
+
"learning_rate": 2e-05,
|
| 2587 |
+
"loss": 0.1566,
|
| 2588 |
+
"step": 430
|
| 2589 |
+
},
|
| 2590 |
+
{
|
| 2591 |
+
"epoch": 2.63,
|
| 2592 |
+
"learning_rate": 2e-05,
|
| 2593 |
+
"loss": 0.1556,
|
| 2594 |
+
"step": 431
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 2.63,
|
| 2598 |
+
"learning_rate": 2e-05,
|
| 2599 |
+
"loss": 0.1581,
|
| 2600 |
+
"step": 432
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 2.64,
|
| 2604 |
+
"learning_rate": 2e-05,
|
| 2605 |
+
"loss": 0.1572,
|
| 2606 |
+
"step": 433
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 2.65,
|
| 2610 |
+
"learning_rate": 2e-05,
|
| 2611 |
+
"loss": 0.1613,
|
| 2612 |
+
"step": 434
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 2.65,
|
| 2616 |
+
"learning_rate": 2e-05,
|
| 2617 |
+
"loss": 0.1454,
|
| 2618 |
+
"step": 435
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 2.66,
|
| 2622 |
+
"learning_rate": 2e-05,
|
| 2623 |
+
"loss": 0.176,
|
| 2624 |
+
"step": 436
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 2.66,
|
| 2628 |
+
"learning_rate": 2e-05,
|
| 2629 |
+
"loss": 0.1788,
|
| 2630 |
+
"step": 437
|
| 2631 |
+
},
|
| 2632 |
+
{
|
| 2633 |
+
"epoch": 2.67,
|
| 2634 |
+
"learning_rate": 2e-05,
|
| 2635 |
+
"loss": 0.1685,
|
| 2636 |
+
"step": 438
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 2.68,
|
| 2640 |
+
"learning_rate": 2e-05,
|
| 2641 |
+
"loss": 0.1452,
|
| 2642 |
+
"step": 439
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 2.68,
|
| 2646 |
+
"learning_rate": 2e-05,
|
| 2647 |
+
"loss": 0.1402,
|
| 2648 |
+
"step": 440
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 2.69,
|
| 2652 |
+
"learning_rate": 2e-05,
|
| 2653 |
+
"loss": 0.158,
|
| 2654 |
+
"step": 441
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 2.7,
|
| 2658 |
+
"learning_rate": 2e-05,
|
| 2659 |
+
"loss": 0.1637,
|
| 2660 |
+
"step": 442
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 2.7,
|
| 2664 |
+
"learning_rate": 2e-05,
|
| 2665 |
+
"loss": 0.1667,
|
| 2666 |
+
"step": 443
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 2.71,
|
| 2670 |
+
"learning_rate": 2e-05,
|
| 2671 |
+
"loss": 0.1841,
|
| 2672 |
+
"step": 444
|
| 2673 |
+
},
|
| 2674 |
+
{
|
| 2675 |
+
"epoch": 2.71,
|
| 2676 |
+
"learning_rate": 2e-05,
|
| 2677 |
+
"loss": 0.1604,
|
| 2678 |
+
"step": 445
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 2.72,
|
| 2682 |
+
"learning_rate": 2e-05,
|
| 2683 |
+
"loss": 0.1517,
|
| 2684 |
+
"step": 446
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 2.73,
|
| 2688 |
+
"learning_rate": 2e-05,
|
| 2689 |
+
"loss": 0.1727,
|
| 2690 |
+
"step": 447
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 2.73,
|
| 2694 |
+
"learning_rate": 2e-05,
|
| 2695 |
+
"loss": 0.1555,
|
| 2696 |
+
"step": 448
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 2.74,
|
| 2700 |
+
"learning_rate": 2e-05,
|
| 2701 |
+
"loss": 0.1465,
|
| 2702 |
+
"step": 449
|
| 2703 |
+
},
|
| 2704 |
+
{
|
| 2705 |
+
"epoch": 2.74,
|
| 2706 |
+
"learning_rate": 2e-05,
|
| 2707 |
+
"loss": 0.1685,
|
| 2708 |
+
"step": 450
|
| 2709 |
+
}
|
| 2710 |
+
],
|
| 2711 |
+
"max_steps": 656,
|
| 2712 |
+
"num_train_epochs": 4,
|
| 2713 |
+
"total_flos": 30697938616320.0,
|
| 2714 |
+
"trial_name": null,
|
| 2715 |
+
"trial_params": null
|
| 2716 |
+
}
|
llava-llama-2-13b-chat-forecasting-finetune/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d5ac233a90f6199ef502f1c1721ec8a2ed4585cb99941d004bde111d8a88279
|
| 3 |
+
size 6651
|
llava-llama-2-13b-chat-forecasting-finetune/zero_to_fp32.py
ADDED
|
@@ -0,0 +1,578 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
| 14 |
+
|
| 15 |
+
import argparse
|
| 16 |
+
import torch
|
| 17 |
+
import glob
|
| 18 |
+
import math
|
| 19 |
+
import os
|
| 20 |
+
import re
|
| 21 |
+
from collections import OrderedDict
|
| 22 |
+
from dataclasses import dataclass
|
| 23 |
+
|
| 24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 26 |
+
from deepspeed.utils import logger
|
| 27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
@dataclass
|
| 33 |
+
class zero_model_state:
|
| 34 |
+
buffers: dict()
|
| 35 |
+
param_shapes: dict()
|
| 36 |
+
shared_params: list
|
| 37 |
+
ds_version: int
|
| 38 |
+
frozen_param_shapes: dict()
|
| 39 |
+
frozen_param_fragments: dict()
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
debug = 0
|
| 43 |
+
|
| 44 |
+
# load to cpu
|
| 45 |
+
device = torch.device('cpu')
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
def atoi(text):
|
| 49 |
+
return int(text) if text.isdigit() else text
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
def natural_keys(text):
|
| 53 |
+
'''
|
| 54 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 56 |
+
(See Toothy's implementation in the comments)
|
| 57 |
+
'''
|
| 58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 62 |
+
if not os.path.isdir(checkpoint_dir):
|
| 63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 64 |
+
|
| 65 |
+
# there should be only one file
|
| 66 |
+
if zero_stage == 2:
|
| 67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 68 |
+
elif zero_stage == 3:
|
| 69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 70 |
+
|
| 71 |
+
if not os.path.exists(file):
|
| 72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 73 |
+
|
| 74 |
+
return file
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 80 |
+
|
| 81 |
+
if len(ckpt_files) == 0:
|
| 82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 83 |
+
|
| 84 |
+
return ckpt_files
|
| 85 |
+
|
| 86 |
+
|
| 87 |
+
def get_optim_files(checkpoint_dir):
|
| 88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
def get_model_state_files(checkpoint_dir):
|
| 92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
def parse_model_states(files):
|
| 96 |
+
zero_model_states = []
|
| 97 |
+
for file in files:
|
| 98 |
+
state_dict = torch.load(file, map_location=device)
|
| 99 |
+
|
| 100 |
+
if BUFFER_NAMES not in state_dict:
|
| 101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 103 |
+
if debug:
|
| 104 |
+
print("Found buffers:", buffer_names)
|
| 105 |
+
|
| 106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 109 |
+
|
| 110 |
+
# collect parameters that are included in param_shapes
|
| 111 |
+
param_names = []
|
| 112 |
+
for s in param_shapes:
|
| 113 |
+
for name in s.keys():
|
| 114 |
+
param_names.append(name)
|
| 115 |
+
|
| 116 |
+
# update with frozen parameters
|
| 117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 118 |
+
if frozen_param_shapes is not None:
|
| 119 |
+
if debug:
|
| 120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 121 |
+
param_names += list(frozen_param_shapes.keys())
|
| 122 |
+
|
| 123 |
+
# handle shared params
|
| 124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 125 |
+
|
| 126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 127 |
+
|
| 128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 129 |
+
|
| 130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 131 |
+
param_shapes=param_shapes,
|
| 132 |
+
shared_params=shared_params,
|
| 133 |
+
ds_version=ds_version,
|
| 134 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 135 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 136 |
+
zero_model_states.append(z_model_state)
|
| 137 |
+
|
| 138 |
+
return zero_model_states
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 142 |
+
|
| 143 |
+
total_files = len(files)
|
| 144 |
+
state_dicts = []
|
| 145 |
+
for f in files:
|
| 146 |
+
state_dicts.append(torch.load(f, map_location=device))
|
| 147 |
+
|
| 148 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 149 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 150 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 151 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 152 |
+
|
| 153 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 154 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 155 |
+
# use the max of the partition_count to get the dp world_size.
|
| 156 |
+
|
| 157 |
+
if type(world_size) is list:
|
| 158 |
+
world_size = max(world_size)
|
| 159 |
+
|
| 160 |
+
if world_size != total_files:
|
| 161 |
+
raise ValueError(
|
| 162 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 163 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 164 |
+
)
|
| 165 |
+
|
| 166 |
+
# the groups are named differently in each stage
|
| 167 |
+
if zero_stage == 2:
|
| 168 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 169 |
+
elif zero_stage == 3:
|
| 170 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 171 |
+
else:
|
| 172 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 173 |
+
|
| 174 |
+
if zero_stage == 2:
|
| 175 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 176 |
+
elif zero_stage == 3:
|
| 177 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
| 178 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
| 179 |
+
#
|
| 180 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
| 181 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
| 182 |
+
|
| 183 |
+
fp32_flat_groups = [
|
| 184 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
| 185 |
+
]
|
| 186 |
+
|
| 187 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
| 191 |
+
"""
|
| 192 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 193 |
+
|
| 194 |
+
Args:
|
| 195 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 196 |
+
|
| 197 |
+
"""
|
| 198 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 199 |
+
|
| 200 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 201 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 202 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 203 |
+
|
| 204 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 205 |
+
|
| 206 |
+
zero_model_states = parse_model_states(model_files)
|
| 207 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 208 |
+
|
| 209 |
+
if zero_stage == 2:
|
| 210 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
| 211 |
+
elif zero_stage == 3:
|
| 212 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 248 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 249 |
+
|
| 250 |
+
# Reconstruction protocol:
|
| 251 |
+
#
|
| 252 |
+
# XXX: document this
|
| 253 |
+
|
| 254 |
+
if debug:
|
| 255 |
+
for i in range(world_size):
|
| 256 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 257 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 258 |
+
|
| 259 |
+
# XXX: memory usage doubles here (zero2)
|
| 260 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 261 |
+
merged_single_partition_of_fp32_groups = []
|
| 262 |
+
for i in range(num_param_groups):
|
| 263 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 264 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 265 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 266 |
+
avail_numel = sum(
|
| 267 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 268 |
+
|
| 269 |
+
if debug:
|
| 270 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 271 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 272 |
+
# not asserting if there is a mismatch due to possible padding
|
| 273 |
+
print(f"Have {avail_numel} numels to process.")
|
| 274 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 275 |
+
|
| 276 |
+
# params
|
| 277 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 278 |
+
# out-of-core computing solution
|
| 279 |
+
total_numel = 0
|
| 280 |
+
total_params = 0
|
| 281 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 282 |
+
offset = 0
|
| 283 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 284 |
+
for name, shape in shapes.items():
|
| 285 |
+
|
| 286 |
+
unpartitioned_numel = shape.numel()
|
| 287 |
+
total_numel += unpartitioned_numel
|
| 288 |
+
total_params += 1
|
| 289 |
+
|
| 290 |
+
if debug:
|
| 291 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 292 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 293 |
+
offset += unpartitioned_numel
|
| 294 |
+
|
| 295 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 296 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 297 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 298 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 299 |
+
align_to = 2 * world_size
|
| 300 |
+
|
| 301 |
+
def zero2_align(x):
|
| 302 |
+
return align_to * math.ceil(x / align_to)
|
| 303 |
+
|
| 304 |
+
if debug:
|
| 305 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 306 |
+
|
| 307 |
+
offset = zero2_align(offset)
|
| 308 |
+
avail_numel = zero2_align(avail_numel)
|
| 309 |
+
|
| 310 |
+
if debug:
|
| 311 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 312 |
+
|
| 313 |
+
# Sanity check
|
| 314 |
+
if offset != avail_numel:
|
| 315 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 316 |
+
|
| 317 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 318 |
+
|
| 319 |
+
|
| 320 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
| 321 |
+
state_dict = OrderedDict()
|
| 322 |
+
|
| 323 |
+
# buffers
|
| 324 |
+
buffers = zero_model_states[0].buffers
|
| 325 |
+
state_dict.update(buffers)
|
| 326 |
+
if debug:
|
| 327 |
+
print(f"added {len(buffers)} buffers")
|
| 328 |
+
|
| 329 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 330 |
+
|
| 331 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 332 |
+
|
| 333 |
+
# recover shared parameters
|
| 334 |
+
for pair in zero_model_states[0].shared_params:
|
| 335 |
+
if pair[1] in state_dict:
|
| 336 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 337 |
+
|
| 338 |
+
return state_dict
|
| 339 |
+
|
| 340 |
+
|
| 341 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 342 |
+
remainder = unpartitioned_numel % world_size
|
| 343 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 344 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 345 |
+
return partitioned_numel, padding_numel
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 349 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 350 |
+
return
|
| 351 |
+
|
| 352 |
+
if debug:
|
| 353 |
+
for i in range(world_size):
|
| 354 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 355 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 356 |
+
|
| 357 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 358 |
+
wanted_params = len(frozen_param_shapes)
|
| 359 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 360 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 361 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 362 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 363 |
+
|
| 364 |
+
total_params = 0
|
| 365 |
+
total_numel = 0
|
| 366 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 367 |
+
total_params += 1
|
| 368 |
+
unpartitioned_numel = shape.numel()
|
| 369 |
+
total_numel += unpartitioned_numel
|
| 370 |
+
|
| 371 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 372 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 373 |
+
|
| 374 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 375 |
+
|
| 376 |
+
if debug:
|
| 377 |
+
print(
|
| 378 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 379 |
+
)
|
| 380 |
+
|
| 381 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 382 |
+
|
| 383 |
+
|
| 384 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 385 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 386 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 387 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 388 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 389 |
+
|
| 390 |
+
# merge list of dicts, preserving order
|
| 391 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 392 |
+
|
| 393 |
+
if debug:
|
| 394 |
+
for i in range(world_size):
|
| 395 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 396 |
+
|
| 397 |
+
wanted_params = len(param_shapes)
|
| 398 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 399 |
+
# not asserting if there is a mismatch due to possible padding
|
| 400 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 401 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 402 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 403 |
+
|
| 404 |
+
# params
|
| 405 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 406 |
+
# out-of-core computing solution
|
| 407 |
+
offset = 0
|
| 408 |
+
total_numel = 0
|
| 409 |
+
total_params = 0
|
| 410 |
+
for name, shape in param_shapes.items():
|
| 411 |
+
|
| 412 |
+
unpartitioned_numel = shape.numel()
|
| 413 |
+
total_numel += unpartitioned_numel
|
| 414 |
+
total_params += 1
|
| 415 |
+
|
| 416 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 417 |
+
|
| 418 |
+
if debug:
|
| 419 |
+
print(
|
| 420 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 421 |
+
)
|
| 422 |
+
|
| 423 |
+
# XXX: memory usage doubles here
|
| 424 |
+
state_dict[name] = torch.cat(
|
| 425 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
| 426 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 427 |
+
offset += partitioned_numel
|
| 428 |
+
|
| 429 |
+
offset *= world_size
|
| 430 |
+
|
| 431 |
+
# Sanity check
|
| 432 |
+
if offset != avail_numel:
|
| 433 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 434 |
+
|
| 435 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 436 |
+
|
| 437 |
+
|
| 438 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
| 439 |
+
state_dict = OrderedDict()
|
| 440 |
+
|
| 441 |
+
# buffers
|
| 442 |
+
buffers = zero_model_states[0].buffers
|
| 443 |
+
state_dict.update(buffers)
|
| 444 |
+
if debug:
|
| 445 |
+
print(f"added {len(buffers)} buffers")
|
| 446 |
+
|
| 447 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 448 |
+
|
| 449 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 450 |
+
|
| 451 |
+
# recover shared parameters
|
| 452 |
+
for pair in zero_model_states[0].shared_params:
|
| 453 |
+
if pair[1] in state_dict:
|
| 454 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 455 |
+
|
| 456 |
+
return state_dict
|
| 457 |
+
|
| 458 |
+
|
| 459 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
| 460 |
+
"""
|
| 461 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 462 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 463 |
+
via a model hub.
|
| 464 |
+
|
| 465 |
+
Args:
|
| 466 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 467 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 468 |
+
|
| 469 |
+
Returns:
|
| 470 |
+
- pytorch ``state_dict``
|
| 471 |
+
|
| 472 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
| 473 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 474 |
+
the checkpoint.
|
| 475 |
+
|
| 476 |
+
A typical usage might be ::
|
| 477 |
+
|
| 478 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 479 |
+
# do the training and checkpoint saving
|
| 480 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 481 |
+
model = model.cpu() # move to cpu
|
| 482 |
+
model.load_state_dict(state_dict)
|
| 483 |
+
# submit to model hub or save the model to share with others
|
| 484 |
+
|
| 485 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 486 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 487 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 488 |
+
|
| 489 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 490 |
+
|
| 491 |
+
"""
|
| 492 |
+
if tag is None:
|
| 493 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 494 |
+
if os.path.isfile(latest_path):
|
| 495 |
+
with open(latest_path, 'r') as fd:
|
| 496 |
+
tag = fd.read().strip()
|
| 497 |
+
else:
|
| 498 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 499 |
+
|
| 500 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 501 |
+
|
| 502 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 503 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 504 |
+
|
| 505 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
| 506 |
+
|
| 507 |
+
|
| 508 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
| 509 |
+
"""
|
| 510 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 511 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 512 |
+
|
| 513 |
+
Args:
|
| 514 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 515 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
| 516 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 517 |
+
"""
|
| 518 |
+
|
| 519 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 520 |
+
print(f"Saving fp32 state dict to {output_file}")
|
| 521 |
+
torch.save(state_dict, output_file)
|
| 522 |
+
|
| 523 |
+
|
| 524 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 525 |
+
"""
|
| 526 |
+
1. Put the provided model to cpu
|
| 527 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 528 |
+
3. Load it into the provided model
|
| 529 |
+
|
| 530 |
+
Args:
|
| 531 |
+
- ``model``: the model object to update
|
| 532 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 533 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 534 |
+
|
| 535 |
+
Returns:
|
| 536 |
+
- ``model`: modified model
|
| 537 |
+
|
| 538 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 539 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 540 |
+
conveniently placed for you in the checkpoint folder.
|
| 541 |
+
|
| 542 |
+
A typical usage might be ::
|
| 543 |
+
|
| 544 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 545 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 546 |
+
# submit to model hub or save the model to share with others
|
| 547 |
+
|
| 548 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 549 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 550 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 551 |
+
|
| 552 |
+
"""
|
| 553 |
+
logger.info(f"Extracting fp32 weights")
|
| 554 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 555 |
+
|
| 556 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 557 |
+
model = model.cpu()
|
| 558 |
+
model.load_state_dict(state_dict, strict=False)
|
| 559 |
+
|
| 560 |
+
return model
|
| 561 |
+
|
| 562 |
+
|
| 563 |
+
if __name__ == "__main__":
|
| 564 |
+
|
| 565 |
+
parser = argparse.ArgumentParser()
|
| 566 |
+
parser.add_argument("checkpoint_dir",
|
| 567 |
+
type=str,
|
| 568 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 569 |
+
parser.add_argument(
|
| 570 |
+
"output_file",
|
| 571 |
+
type=str,
|
| 572 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
| 573 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 574 |
+
args = parser.parse_args()
|
| 575 |
+
|
| 576 |
+
debug = args.debug
|
| 577 |
+
|
| 578 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file)
|
scaleup_training_ego4d_eval.ckpt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7be3d661a26ae03d4621bc9e0231a0b2be7cef9bf4693743265eb2cac4578c7
|
| 3 |
+
size 7779511314
|