Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/config-checkpoint.json +30 -0
- .ipynb_checkpoints/vocab-checkpoint.json +0 -0
- added_tokens.json +28 -0
- checkpoint-16000/config.json +30 -0
- checkpoint-16000/generation_config.json +6 -0
- checkpoint-16000/model.safetensors +3 -0
- checkpoint-16000/optimizer.pt +3 -0
- checkpoint-16000/rng_state.pth +3 -0
- checkpoint-16000/scaler.pt +3 -0
- checkpoint-16000/scheduler.pt +3 -0
- checkpoint-16000/trainer_state.json +514 -0
- checkpoint-16000/training_args.bin +3 -0
- checkpoint-16446/config.json +30 -0
- checkpoint-16446/generation_config.json +6 -0
- checkpoint-16446/model.safetensors +3 -0
- checkpoint-16446/optimizer.pt +3 -0
- checkpoint-16446/rng_state.pth +3 -0
- checkpoint-16446/scaler.pt +3 -0
- checkpoint-16446/scheduler.pt +3 -0
- checkpoint-16446/trainer_state.json +514 -0
- checkpoint-16446/training_args.bin +3 -0
- config.json +30 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- pytorch_model.bin +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
.ipynb_checkpoints/vocab-checkpoint.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
checkpoint-16000/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
checkpoint-16000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
checkpoint-16000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f9a747d25bc46b98589f8b086c2a4a073afcabe15af837f12b22384551bfab6
|
| 3 |
+
size 2384234968
|
checkpoint-16000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c3dc88a51aa901e207301a78392958cea8d3e500d7280300bf3d0d7b47e09f7
|
| 3 |
+
size 4768662910
|
checkpoint-16000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51a85118c1d3983de4500b7efa8b6b31ec254d90541c1771bf541cfe64d8984f
|
| 3 |
+
size 14244
|
checkpoint-16000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:924287e4da9237d8d29c116c557ced8b141da9b9d0d99f20cb0e3fcb7f9d438e
|
| 3 |
+
size 988
|
checkpoint-16000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93f2306239c0e0dfb9fd526afcc69625686a8ba2d76e0e259d39a0e62cc04a11
|
| 3 |
+
size 1064
|
checkpoint-16000/trainer_state.json
ADDED
|
@@ -0,0 +1,514 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.918642831083546,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 16000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.09120758847136082,
|
| 14 |
+
"grad_norm": 2.8996551036834717,
|
| 15 |
+
"learning_rate": 4.849507479022255e-05,
|
| 16 |
+
"loss": 0.8414,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09120758847136082,
|
| 21 |
+
"eval_loss": 0.8034613132476807,
|
| 22 |
+
"eval_runtime": 67.9143,
|
| 23 |
+
"eval_samples_per_second": 35.883,
|
| 24 |
+
"eval_steps_per_second": 4.491,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.18241517694272164,
|
| 29 |
+
"grad_norm": 3.896031141281128,
|
| 30 |
+
"learning_rate": 4.697494831569987e-05,
|
| 31 |
+
"loss": 0.8357,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18241517694272164,
|
| 36 |
+
"eval_loss": 0.7636010050773621,
|
| 37 |
+
"eval_runtime": 66.4597,
|
| 38 |
+
"eval_samples_per_second": 36.669,
|
| 39 |
+
"eval_steps_per_second": 4.589,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.2736227654140824,
|
| 44 |
+
"grad_norm": 3.0594074726104736,
|
| 45 |
+
"learning_rate": 4.5454821841177186e-05,
|
| 46 |
+
"loss": 0.784,
|
| 47 |
+
"step": 1500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.2736227654140824,
|
| 51 |
+
"eval_loss": 0.7404520511627197,
|
| 52 |
+
"eval_runtime": 66.4753,
|
| 53 |
+
"eval_samples_per_second": 36.66,
|
| 54 |
+
"eval_steps_per_second": 4.588,
|
| 55 |
+
"step": 1500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.36483035388544327,
|
| 59 |
+
"grad_norm": 2.4666194915771484,
|
| 60 |
+
"learning_rate": 4.393469536665451e-05,
|
| 61 |
+
"loss": 0.7527,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.36483035388544327,
|
| 66 |
+
"eval_loss": 0.720551073551178,
|
| 67 |
+
"eval_runtime": 66.4761,
|
| 68 |
+
"eval_samples_per_second": 36.66,
|
| 69 |
+
"eval_steps_per_second": 4.588,
|
| 70 |
+
"step": 2000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.45603794235680406,
|
| 74 |
+
"grad_norm": 3.1520893573760986,
|
| 75 |
+
"learning_rate": 4.2414568892131825e-05,
|
| 76 |
+
"loss": 0.7588,
|
| 77 |
+
"step": 2500
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.45603794235680406,
|
| 81 |
+
"eval_loss": 0.7047598958015442,
|
| 82 |
+
"eval_runtime": 66.6712,
|
| 83 |
+
"eval_samples_per_second": 36.552,
|
| 84 |
+
"eval_steps_per_second": 4.575,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.5472455308281649,
|
| 89 |
+
"grad_norm": 2.88120174407959,
|
| 90 |
+
"learning_rate": 4.0894442417609145e-05,
|
| 91 |
+
"loss": 0.7203,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.5472455308281649,
|
| 96 |
+
"eval_loss": 0.6884846091270447,
|
| 97 |
+
"eval_runtime": 66.5954,
|
| 98 |
+
"eval_samples_per_second": 36.594,
|
| 99 |
+
"eval_steps_per_second": 4.58,
|
| 100 |
+
"step": 3000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6384531192995258,
|
| 104 |
+
"grad_norm": 2.235811710357666,
|
| 105 |
+
"learning_rate": 3.9374315943086464e-05,
|
| 106 |
+
"loss": 0.7098,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6384531192995258,
|
| 111 |
+
"eval_loss": 0.6729713082313538,
|
| 112 |
+
"eval_runtime": 66.5208,
|
| 113 |
+
"eval_samples_per_second": 36.635,
|
| 114 |
+
"eval_steps_per_second": 4.585,
|
| 115 |
+
"step": 3500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.7296607077708865,
|
| 119 |
+
"grad_norm": 4.2170891761779785,
|
| 120 |
+
"learning_rate": 3.785418946856379e-05,
|
| 121 |
+
"loss": 0.6946,
|
| 122 |
+
"step": 4000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7296607077708865,
|
| 126 |
+
"eval_loss": 0.6604794263839722,
|
| 127 |
+
"eval_runtime": 66.5342,
|
| 128 |
+
"eval_samples_per_second": 36.628,
|
| 129 |
+
"eval_steps_per_second": 4.584,
|
| 130 |
+
"step": 4000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.8208682962422473,
|
| 134 |
+
"grad_norm": 3.053722381591797,
|
| 135 |
+
"learning_rate": 3.633406299404111e-05,
|
| 136 |
+
"loss": 0.684,
|
| 137 |
+
"step": 4500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.8208682962422473,
|
| 141 |
+
"eval_loss": 0.646191418170929,
|
| 142 |
+
"eval_runtime": 66.6938,
|
| 143 |
+
"eval_samples_per_second": 36.54,
|
| 144 |
+
"eval_steps_per_second": 4.573,
|
| 145 |
+
"step": 4500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.9120758847136081,
|
| 149 |
+
"grad_norm": 2.7756240367889404,
|
| 150 |
+
"learning_rate": 3.481393651951842e-05,
|
| 151 |
+
"loss": 0.6772,
|
| 152 |
+
"step": 5000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.9120758847136081,
|
| 156 |
+
"eval_loss": 0.6353339552879333,
|
| 157 |
+
"eval_runtime": 66.5122,
|
| 158 |
+
"eval_samples_per_second": 36.64,
|
| 159 |
+
"eval_steps_per_second": 4.586,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.003283473184969,
|
| 164 |
+
"grad_norm": 1.9400490522384644,
|
| 165 |
+
"learning_rate": 3.329381004499574e-05,
|
| 166 |
+
"loss": 0.6393,
|
| 167 |
+
"step": 5500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.003283473184969,
|
| 171 |
+
"eval_loss": 0.643139123916626,
|
| 172 |
+
"eval_runtime": 66.5024,
|
| 173 |
+
"eval_samples_per_second": 36.645,
|
| 174 |
+
"eval_steps_per_second": 4.586,
|
| 175 |
+
"step": 5500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.09449106165633,
|
| 179 |
+
"grad_norm": 2.2215569019317627,
|
| 180 |
+
"learning_rate": 3.177368357047307e-05,
|
| 181 |
+
"loss": 0.4513,
|
| 182 |
+
"step": 6000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.09449106165633,
|
| 186 |
+
"eval_loss": 0.6397776007652283,
|
| 187 |
+
"eval_runtime": 66.4386,
|
| 188 |
+
"eval_samples_per_second": 36.68,
|
| 189 |
+
"eval_steps_per_second": 4.591,
|
| 190 |
+
"step": 6000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.1856986501276907,
|
| 194 |
+
"grad_norm": 2.093801736831665,
|
| 195 |
+
"learning_rate": 3.0253557095950385e-05,
|
| 196 |
+
"loss": 0.4427,
|
| 197 |
+
"step": 6500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.1856986501276907,
|
| 201 |
+
"eval_loss": 0.636920154094696,
|
| 202 |
+
"eval_runtime": 66.5515,
|
| 203 |
+
"eval_samples_per_second": 36.618,
|
| 204 |
+
"eval_steps_per_second": 4.583,
|
| 205 |
+
"step": 6500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.2769062385990515,
|
| 209 |
+
"grad_norm": 4.663333892822266,
|
| 210 |
+
"learning_rate": 2.8733430621427704e-05,
|
| 211 |
+
"loss": 0.4468,
|
| 212 |
+
"step": 7000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2769062385990515,
|
| 216 |
+
"eval_loss": 0.6325265169143677,
|
| 217 |
+
"eval_runtime": 66.5785,
|
| 218 |
+
"eval_samples_per_second": 36.603,
|
| 219 |
+
"eval_steps_per_second": 4.581,
|
| 220 |
+
"step": 7000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.3681138270704123,
|
| 224 |
+
"grad_norm": 3.2814857959747314,
|
| 225 |
+
"learning_rate": 2.721330414690502e-05,
|
| 226 |
+
"loss": 0.4555,
|
| 227 |
+
"step": 7500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.3681138270704123,
|
| 231 |
+
"eval_loss": 0.6226893067359924,
|
| 232 |
+
"eval_runtime": 66.6251,
|
| 233 |
+
"eval_samples_per_second": 36.578,
|
| 234 |
+
"eval_steps_per_second": 4.578,
|
| 235 |
+
"step": 7500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.459321415541773,
|
| 239 |
+
"grad_norm": 1.9859124422073364,
|
| 240 |
+
"learning_rate": 2.5693177672382347e-05,
|
| 241 |
+
"loss": 0.4306,
|
| 242 |
+
"step": 8000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.459321415541773,
|
| 246 |
+
"eval_loss": 0.6232908368110657,
|
| 247 |
+
"eval_runtime": 66.5211,
|
| 248 |
+
"eval_samples_per_second": 36.635,
|
| 249 |
+
"eval_steps_per_second": 4.585,
|
| 250 |
+
"step": 8000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.5505290040131339,
|
| 254 |
+
"grad_norm": 2.86844539642334,
|
| 255 |
+
"learning_rate": 2.4173051197859663e-05,
|
| 256 |
+
"loss": 0.4399,
|
| 257 |
+
"step": 8500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.5505290040131339,
|
| 261 |
+
"eval_loss": 0.6131536960601807,
|
| 262 |
+
"eval_runtime": 66.4759,
|
| 263 |
+
"eval_samples_per_second": 36.66,
|
| 264 |
+
"eval_steps_per_second": 4.588,
|
| 265 |
+
"step": 8500
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.6417365924844947,
|
| 269 |
+
"grad_norm": 2.0596117973327637,
|
| 270 |
+
"learning_rate": 2.2652924723336982e-05,
|
| 271 |
+
"loss": 0.4357,
|
| 272 |
+
"step": 9000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.6417365924844947,
|
| 276 |
+
"eval_loss": 0.6083381175994873,
|
| 277 |
+
"eval_runtime": 66.5319,
|
| 278 |
+
"eval_samples_per_second": 36.629,
|
| 279 |
+
"eval_steps_per_second": 4.584,
|
| 280 |
+
"step": 9000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.7329441809558555,
|
| 284 |
+
"grad_norm": 2.2367780208587646,
|
| 285 |
+
"learning_rate": 2.1132798248814302e-05,
|
| 286 |
+
"loss": 0.4387,
|
| 287 |
+
"step": 9500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.7329441809558555,
|
| 291 |
+
"eval_loss": 0.6063674688339233,
|
| 292 |
+
"eval_runtime": 66.5477,
|
| 293 |
+
"eval_samples_per_second": 36.62,
|
| 294 |
+
"eval_steps_per_second": 4.583,
|
| 295 |
+
"step": 9500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.8241517694272162,
|
| 299 |
+
"grad_norm": 2.397143602371216,
|
| 300 |
+
"learning_rate": 1.961267177429162e-05,
|
| 301 |
+
"loss": 0.4353,
|
| 302 |
+
"step": 10000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.8241517694272162,
|
| 306 |
+
"eval_loss": 0.5975276231765747,
|
| 307 |
+
"eval_runtime": 66.5784,
|
| 308 |
+
"eval_samples_per_second": 36.603,
|
| 309 |
+
"eval_steps_per_second": 4.581,
|
| 310 |
+
"step": 10000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.915359357898577,
|
| 314 |
+
"grad_norm": 3.369065284729004,
|
| 315 |
+
"learning_rate": 1.8092545299768944e-05,
|
| 316 |
+
"loss": 0.4334,
|
| 317 |
+
"step": 10500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.915359357898577,
|
| 321 |
+
"eval_loss": 0.5899476408958435,
|
| 322 |
+
"eval_runtime": 66.4613,
|
| 323 |
+
"eval_samples_per_second": 36.668,
|
| 324 |
+
"eval_steps_per_second": 4.589,
|
| 325 |
+
"step": 10500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.006566946369938,
|
| 329 |
+
"grad_norm": 2.555560827255249,
|
| 330 |
+
"learning_rate": 1.657241882524626e-05,
|
| 331 |
+
"loss": 0.4188,
|
| 332 |
+
"step": 11000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.006566946369938,
|
| 336 |
+
"eval_loss": 0.670684278011322,
|
| 337 |
+
"eval_runtime": 66.4465,
|
| 338 |
+
"eval_samples_per_second": 36.676,
|
| 339 |
+
"eval_steps_per_second": 4.59,
|
| 340 |
+
"step": 11000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.0977745348412986,
|
| 344 |
+
"grad_norm": 3.1445837020874023,
|
| 345 |
+
"learning_rate": 1.5052292350723582e-05,
|
| 346 |
+
"loss": 0.2206,
|
| 347 |
+
"step": 11500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.0977745348412986,
|
| 351 |
+
"eval_loss": 0.7085195183753967,
|
| 352 |
+
"eval_runtime": 66.4599,
|
| 353 |
+
"eval_samples_per_second": 36.669,
|
| 354 |
+
"eval_steps_per_second": 4.589,
|
| 355 |
+
"step": 11500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.18898212331266,
|
| 359 |
+
"grad_norm": 1.821514368057251,
|
| 360 |
+
"learning_rate": 1.35321658762009e-05,
|
| 361 |
+
"loss": 0.2125,
|
| 362 |
+
"step": 12000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.18898212331266,
|
| 366 |
+
"eval_loss": 0.7055649161338806,
|
| 367 |
+
"eval_runtime": 66.4182,
|
| 368 |
+
"eval_samples_per_second": 36.692,
|
| 369 |
+
"eval_steps_per_second": 4.592,
|
| 370 |
+
"step": 12000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.28018971178402,
|
| 374 |
+
"grad_norm": 2.517010450363159,
|
| 375 |
+
"learning_rate": 1.2015079654627266e-05,
|
| 376 |
+
"loss": 0.2136,
|
| 377 |
+
"step": 12500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.28018971178402,
|
| 381 |
+
"eval_loss": 0.7125562429428101,
|
| 382 |
+
"eval_runtime": 66.4822,
|
| 383 |
+
"eval_samples_per_second": 36.656,
|
| 384 |
+
"eval_steps_per_second": 4.588,
|
| 385 |
+
"step": 12500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.3713973002553814,
|
| 389 |
+
"grad_norm": 2.654905319213867,
|
| 390 |
+
"learning_rate": 1.049799343305363e-05,
|
| 391 |
+
"loss": 0.2186,
|
| 392 |
+
"step": 13000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.3713973002553814,
|
| 396 |
+
"eval_loss": 0.711520254611969,
|
| 397 |
+
"eval_runtime": 66.4793,
|
| 398 |
+
"eval_samples_per_second": 36.658,
|
| 399 |
+
"eval_steps_per_second": 4.588,
|
| 400 |
+
"step": 13000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.462604888726742,
|
| 404 |
+
"grad_norm": 1.6538429260253906,
|
| 405 |
+
"learning_rate": 8.97786695853095e-06,
|
| 406 |
+
"loss": 0.2119,
|
| 407 |
+
"step": 13500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.462604888726742,
|
| 411 |
+
"eval_loss": 0.7095320820808411,
|
| 412 |
+
"eval_runtime": 66.4626,
|
| 413 |
+
"eval_samples_per_second": 36.667,
|
| 414 |
+
"eval_steps_per_second": 4.589,
|
| 415 |
+
"step": 13500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.553812477198103,
|
| 419 |
+
"grad_norm": 2.4926905632019043,
|
| 420 |
+
"learning_rate": 7.45774048400827e-06,
|
| 421 |
+
"loss": 0.2093,
|
| 422 |
+
"step": 14000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.553812477198103,
|
| 426 |
+
"eval_loss": 0.7063737511634827,
|
| 427 |
+
"eval_runtime": 66.4346,
|
| 428 |
+
"eval_samples_per_second": 36.683,
|
| 429 |
+
"eval_steps_per_second": 4.591,
|
| 430 |
+
"step": 14000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.645020065669464,
|
| 434 |
+
"grad_norm": 2.814349412918091,
|
| 435 |
+
"learning_rate": 5.93761400948559e-06,
|
| 436 |
+
"loss": 0.203,
|
| 437 |
+
"step": 14500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.645020065669464,
|
| 441 |
+
"eval_loss": 0.7055577635765076,
|
| 442 |
+
"eval_runtime": 66.5157,
|
| 443 |
+
"eval_samples_per_second": 36.638,
|
| 444 |
+
"eval_steps_per_second": 4.585,
|
| 445 |
+
"step": 14500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.7362276541408246,
|
| 449 |
+
"grad_norm": 2.242487907409668,
|
| 450 |
+
"learning_rate": 4.417487534962909e-06,
|
| 451 |
+
"loss": 0.2019,
|
| 452 |
+
"step": 15000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.7362276541408246,
|
| 456 |
+
"eval_loss": 0.7038553357124329,
|
| 457 |
+
"eval_runtime": 66.6171,
|
| 458 |
+
"eval_samples_per_second": 36.582,
|
| 459 |
+
"eval_steps_per_second": 4.578,
|
| 460 |
+
"step": 15000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.8274352426121854,
|
| 464 |
+
"grad_norm": 3.0727193355560303,
|
| 465 |
+
"learning_rate": 2.8973610604402286e-06,
|
| 466 |
+
"loss": 0.2,
|
| 467 |
+
"step": 15500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.8274352426121854,
|
| 471 |
+
"eval_loss": 0.7052037119865417,
|
| 472 |
+
"eval_runtime": 66.5239,
|
| 473 |
+
"eval_samples_per_second": 36.633,
|
| 474 |
+
"eval_steps_per_second": 4.585,
|
| 475 |
+
"step": 15500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.918642831083546,
|
| 479 |
+
"grad_norm": 2.016516923904419,
|
| 480 |
+
"learning_rate": 1.3772345859175483e-06,
|
| 481 |
+
"loss": 0.2011,
|
| 482 |
+
"step": 16000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.918642831083546,
|
| 486 |
+
"eval_loss": 0.7026786804199219,
|
| 487 |
+
"eval_runtime": 66.488,
|
| 488 |
+
"eval_samples_per_second": 36.653,
|
| 489 |
+
"eval_steps_per_second": 4.587,
|
| 490 |
+
"step": 16000
|
| 491 |
+
}
|
| 492 |
+
],
|
| 493 |
+
"logging_steps": 500,
|
| 494 |
+
"max_steps": 16446,
|
| 495 |
+
"num_input_tokens_seen": 0,
|
| 496 |
+
"num_train_epochs": 3,
|
| 497 |
+
"save_steps": 500,
|
| 498 |
+
"stateful_callbacks": {
|
| 499 |
+
"TrainerControl": {
|
| 500 |
+
"args": {
|
| 501 |
+
"should_epoch_stop": false,
|
| 502 |
+
"should_evaluate": false,
|
| 503 |
+
"should_log": false,
|
| 504 |
+
"should_save": true,
|
| 505 |
+
"should_training_stop": false
|
| 506 |
+
},
|
| 507 |
+
"attributes": {}
|
| 508 |
+
}
|
| 509 |
+
},
|
| 510 |
+
"total_flos": 8.6599425589248e+16,
|
| 511 |
+
"train_batch_size": 1,
|
| 512 |
+
"trial_name": null,
|
| 513 |
+
"trial_params": null
|
| 514 |
+
}
|
checkpoint-16000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:234fbe87ef57dfef64eac7ccede9d1a856cd7c6d37bee47c3ebf9de75a3405b3
|
| 3 |
+
size 5240
|
checkpoint-16446/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
checkpoint-16446/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
checkpoint-16446/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfddc9c15cfb892fb069db6c0d028bfbaa30a0c3dc3aeff9452beb1fc23884c2
|
| 3 |
+
size 2384234968
|
checkpoint-16446/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:488c92a32b19598e9b28fe603fd4d8096f2d825a2fcd735585cd50965b26c2e9
|
| 3 |
+
size 4768662910
|
checkpoint-16446/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:51a85118c1d3983de4500b7efa8b6b31ec254d90541c1771bf541cfe64d8984f
|
| 3 |
+
size 14244
|
checkpoint-16446/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91662014d5935c1368dd5a053f00aaa834bb8e9816bcd25c24b5c61d9a3e1066
|
| 3 |
+
size 988
|
checkpoint-16446/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:907ef8e2b3f5f5a376f161eac21e78740b56bbe11007f24834c30d7345453c18
|
| 3 |
+
size 1064
|
checkpoint-16446/trainer_state.json
ADDED
|
@@ -0,0 +1,514 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 16446,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.09120758847136082,
|
| 14 |
+
"grad_norm": 2.8996551036834717,
|
| 15 |
+
"learning_rate": 4.849507479022255e-05,
|
| 16 |
+
"loss": 0.8414,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.09120758847136082,
|
| 21 |
+
"eval_loss": 0.8034613132476807,
|
| 22 |
+
"eval_runtime": 67.9143,
|
| 23 |
+
"eval_samples_per_second": 35.883,
|
| 24 |
+
"eval_steps_per_second": 4.491,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.18241517694272164,
|
| 29 |
+
"grad_norm": 3.896031141281128,
|
| 30 |
+
"learning_rate": 4.697494831569987e-05,
|
| 31 |
+
"loss": 0.8357,
|
| 32 |
+
"step": 1000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.18241517694272164,
|
| 36 |
+
"eval_loss": 0.7636010050773621,
|
| 37 |
+
"eval_runtime": 66.4597,
|
| 38 |
+
"eval_samples_per_second": 36.669,
|
| 39 |
+
"eval_steps_per_second": 4.589,
|
| 40 |
+
"step": 1000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.2736227654140824,
|
| 44 |
+
"grad_norm": 3.0594074726104736,
|
| 45 |
+
"learning_rate": 4.5454821841177186e-05,
|
| 46 |
+
"loss": 0.784,
|
| 47 |
+
"step": 1500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.2736227654140824,
|
| 51 |
+
"eval_loss": 0.7404520511627197,
|
| 52 |
+
"eval_runtime": 66.4753,
|
| 53 |
+
"eval_samples_per_second": 36.66,
|
| 54 |
+
"eval_steps_per_second": 4.588,
|
| 55 |
+
"step": 1500
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.36483035388544327,
|
| 59 |
+
"grad_norm": 2.4666194915771484,
|
| 60 |
+
"learning_rate": 4.393469536665451e-05,
|
| 61 |
+
"loss": 0.7527,
|
| 62 |
+
"step": 2000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.36483035388544327,
|
| 66 |
+
"eval_loss": 0.720551073551178,
|
| 67 |
+
"eval_runtime": 66.4761,
|
| 68 |
+
"eval_samples_per_second": 36.66,
|
| 69 |
+
"eval_steps_per_second": 4.588,
|
| 70 |
+
"step": 2000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.45603794235680406,
|
| 74 |
+
"grad_norm": 3.1520893573760986,
|
| 75 |
+
"learning_rate": 4.2414568892131825e-05,
|
| 76 |
+
"loss": 0.7588,
|
| 77 |
+
"step": 2500
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.45603794235680406,
|
| 81 |
+
"eval_loss": 0.7047598958015442,
|
| 82 |
+
"eval_runtime": 66.6712,
|
| 83 |
+
"eval_samples_per_second": 36.552,
|
| 84 |
+
"eval_steps_per_second": 4.575,
|
| 85 |
+
"step": 2500
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.5472455308281649,
|
| 89 |
+
"grad_norm": 2.88120174407959,
|
| 90 |
+
"learning_rate": 4.0894442417609145e-05,
|
| 91 |
+
"loss": 0.7203,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.5472455308281649,
|
| 96 |
+
"eval_loss": 0.6884846091270447,
|
| 97 |
+
"eval_runtime": 66.5954,
|
| 98 |
+
"eval_samples_per_second": 36.594,
|
| 99 |
+
"eval_steps_per_second": 4.58,
|
| 100 |
+
"step": 3000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.6384531192995258,
|
| 104 |
+
"grad_norm": 2.235811710357666,
|
| 105 |
+
"learning_rate": 3.9374315943086464e-05,
|
| 106 |
+
"loss": 0.7098,
|
| 107 |
+
"step": 3500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.6384531192995258,
|
| 111 |
+
"eval_loss": 0.6729713082313538,
|
| 112 |
+
"eval_runtime": 66.5208,
|
| 113 |
+
"eval_samples_per_second": 36.635,
|
| 114 |
+
"eval_steps_per_second": 4.585,
|
| 115 |
+
"step": 3500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.7296607077708865,
|
| 119 |
+
"grad_norm": 4.2170891761779785,
|
| 120 |
+
"learning_rate": 3.785418946856379e-05,
|
| 121 |
+
"loss": 0.6946,
|
| 122 |
+
"step": 4000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.7296607077708865,
|
| 126 |
+
"eval_loss": 0.6604794263839722,
|
| 127 |
+
"eval_runtime": 66.5342,
|
| 128 |
+
"eval_samples_per_second": 36.628,
|
| 129 |
+
"eval_steps_per_second": 4.584,
|
| 130 |
+
"step": 4000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.8208682962422473,
|
| 134 |
+
"grad_norm": 3.053722381591797,
|
| 135 |
+
"learning_rate": 3.633406299404111e-05,
|
| 136 |
+
"loss": 0.684,
|
| 137 |
+
"step": 4500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.8208682962422473,
|
| 141 |
+
"eval_loss": 0.646191418170929,
|
| 142 |
+
"eval_runtime": 66.6938,
|
| 143 |
+
"eval_samples_per_second": 36.54,
|
| 144 |
+
"eval_steps_per_second": 4.573,
|
| 145 |
+
"step": 4500
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.9120758847136081,
|
| 149 |
+
"grad_norm": 2.7756240367889404,
|
| 150 |
+
"learning_rate": 3.481393651951842e-05,
|
| 151 |
+
"loss": 0.6772,
|
| 152 |
+
"step": 5000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.9120758847136081,
|
| 156 |
+
"eval_loss": 0.6353339552879333,
|
| 157 |
+
"eval_runtime": 66.5122,
|
| 158 |
+
"eval_samples_per_second": 36.64,
|
| 159 |
+
"eval_steps_per_second": 4.586,
|
| 160 |
+
"step": 5000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.003283473184969,
|
| 164 |
+
"grad_norm": 1.9400490522384644,
|
| 165 |
+
"learning_rate": 3.329381004499574e-05,
|
| 166 |
+
"loss": 0.6393,
|
| 167 |
+
"step": 5500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.003283473184969,
|
| 171 |
+
"eval_loss": 0.643139123916626,
|
| 172 |
+
"eval_runtime": 66.5024,
|
| 173 |
+
"eval_samples_per_second": 36.645,
|
| 174 |
+
"eval_steps_per_second": 4.586,
|
| 175 |
+
"step": 5500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.09449106165633,
|
| 179 |
+
"grad_norm": 2.2215569019317627,
|
| 180 |
+
"learning_rate": 3.177368357047307e-05,
|
| 181 |
+
"loss": 0.4513,
|
| 182 |
+
"step": 6000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.09449106165633,
|
| 186 |
+
"eval_loss": 0.6397776007652283,
|
| 187 |
+
"eval_runtime": 66.4386,
|
| 188 |
+
"eval_samples_per_second": 36.68,
|
| 189 |
+
"eval_steps_per_second": 4.591,
|
| 190 |
+
"step": 6000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.1856986501276907,
|
| 194 |
+
"grad_norm": 2.093801736831665,
|
| 195 |
+
"learning_rate": 3.0253557095950385e-05,
|
| 196 |
+
"loss": 0.4427,
|
| 197 |
+
"step": 6500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.1856986501276907,
|
| 201 |
+
"eval_loss": 0.636920154094696,
|
| 202 |
+
"eval_runtime": 66.5515,
|
| 203 |
+
"eval_samples_per_second": 36.618,
|
| 204 |
+
"eval_steps_per_second": 4.583,
|
| 205 |
+
"step": 6500
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.2769062385990515,
|
| 209 |
+
"grad_norm": 4.663333892822266,
|
| 210 |
+
"learning_rate": 2.8733430621427704e-05,
|
| 211 |
+
"loss": 0.4468,
|
| 212 |
+
"step": 7000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.2769062385990515,
|
| 216 |
+
"eval_loss": 0.6325265169143677,
|
| 217 |
+
"eval_runtime": 66.5785,
|
| 218 |
+
"eval_samples_per_second": 36.603,
|
| 219 |
+
"eval_steps_per_second": 4.581,
|
| 220 |
+
"step": 7000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.3681138270704123,
|
| 224 |
+
"grad_norm": 3.2814857959747314,
|
| 225 |
+
"learning_rate": 2.721330414690502e-05,
|
| 226 |
+
"loss": 0.4555,
|
| 227 |
+
"step": 7500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.3681138270704123,
|
| 231 |
+
"eval_loss": 0.6226893067359924,
|
| 232 |
+
"eval_runtime": 66.6251,
|
| 233 |
+
"eval_samples_per_second": 36.578,
|
| 234 |
+
"eval_steps_per_second": 4.578,
|
| 235 |
+
"step": 7500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.459321415541773,
|
| 239 |
+
"grad_norm": 1.9859124422073364,
|
| 240 |
+
"learning_rate": 2.5693177672382347e-05,
|
| 241 |
+
"loss": 0.4306,
|
| 242 |
+
"step": 8000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.459321415541773,
|
| 246 |
+
"eval_loss": 0.6232908368110657,
|
| 247 |
+
"eval_runtime": 66.5211,
|
| 248 |
+
"eval_samples_per_second": 36.635,
|
| 249 |
+
"eval_steps_per_second": 4.585,
|
| 250 |
+
"step": 8000
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.5505290040131339,
|
| 254 |
+
"grad_norm": 2.86844539642334,
|
| 255 |
+
"learning_rate": 2.4173051197859663e-05,
|
| 256 |
+
"loss": 0.4399,
|
| 257 |
+
"step": 8500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.5505290040131339,
|
| 261 |
+
"eval_loss": 0.6131536960601807,
|
| 262 |
+
"eval_runtime": 66.4759,
|
| 263 |
+
"eval_samples_per_second": 36.66,
|
| 264 |
+
"eval_steps_per_second": 4.588,
|
| 265 |
+
"step": 8500
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.6417365924844947,
|
| 269 |
+
"grad_norm": 2.0596117973327637,
|
| 270 |
+
"learning_rate": 2.2652924723336982e-05,
|
| 271 |
+
"loss": 0.4357,
|
| 272 |
+
"step": 9000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.6417365924844947,
|
| 276 |
+
"eval_loss": 0.6083381175994873,
|
| 277 |
+
"eval_runtime": 66.5319,
|
| 278 |
+
"eval_samples_per_second": 36.629,
|
| 279 |
+
"eval_steps_per_second": 4.584,
|
| 280 |
+
"step": 9000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.7329441809558555,
|
| 284 |
+
"grad_norm": 2.2367780208587646,
|
| 285 |
+
"learning_rate": 2.1132798248814302e-05,
|
| 286 |
+
"loss": 0.4387,
|
| 287 |
+
"step": 9500
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.7329441809558555,
|
| 291 |
+
"eval_loss": 0.6063674688339233,
|
| 292 |
+
"eval_runtime": 66.5477,
|
| 293 |
+
"eval_samples_per_second": 36.62,
|
| 294 |
+
"eval_steps_per_second": 4.583,
|
| 295 |
+
"step": 9500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.8241517694272162,
|
| 299 |
+
"grad_norm": 2.397143602371216,
|
| 300 |
+
"learning_rate": 1.961267177429162e-05,
|
| 301 |
+
"loss": 0.4353,
|
| 302 |
+
"step": 10000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.8241517694272162,
|
| 306 |
+
"eval_loss": 0.5975276231765747,
|
| 307 |
+
"eval_runtime": 66.5784,
|
| 308 |
+
"eval_samples_per_second": 36.603,
|
| 309 |
+
"eval_steps_per_second": 4.581,
|
| 310 |
+
"step": 10000
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.915359357898577,
|
| 314 |
+
"grad_norm": 3.369065284729004,
|
| 315 |
+
"learning_rate": 1.8092545299768944e-05,
|
| 316 |
+
"loss": 0.4334,
|
| 317 |
+
"step": 10500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.915359357898577,
|
| 321 |
+
"eval_loss": 0.5899476408958435,
|
| 322 |
+
"eval_runtime": 66.4613,
|
| 323 |
+
"eval_samples_per_second": 36.668,
|
| 324 |
+
"eval_steps_per_second": 4.589,
|
| 325 |
+
"step": 10500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.006566946369938,
|
| 329 |
+
"grad_norm": 2.555560827255249,
|
| 330 |
+
"learning_rate": 1.657241882524626e-05,
|
| 331 |
+
"loss": 0.4188,
|
| 332 |
+
"step": 11000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.006566946369938,
|
| 336 |
+
"eval_loss": 0.670684278011322,
|
| 337 |
+
"eval_runtime": 66.4465,
|
| 338 |
+
"eval_samples_per_second": 36.676,
|
| 339 |
+
"eval_steps_per_second": 4.59,
|
| 340 |
+
"step": 11000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.0977745348412986,
|
| 344 |
+
"grad_norm": 3.1445837020874023,
|
| 345 |
+
"learning_rate": 1.5052292350723582e-05,
|
| 346 |
+
"loss": 0.2206,
|
| 347 |
+
"step": 11500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.0977745348412986,
|
| 351 |
+
"eval_loss": 0.7085195183753967,
|
| 352 |
+
"eval_runtime": 66.4599,
|
| 353 |
+
"eval_samples_per_second": 36.669,
|
| 354 |
+
"eval_steps_per_second": 4.589,
|
| 355 |
+
"step": 11500
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.18898212331266,
|
| 359 |
+
"grad_norm": 1.821514368057251,
|
| 360 |
+
"learning_rate": 1.35321658762009e-05,
|
| 361 |
+
"loss": 0.2125,
|
| 362 |
+
"step": 12000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.18898212331266,
|
| 366 |
+
"eval_loss": 0.7055649161338806,
|
| 367 |
+
"eval_runtime": 66.4182,
|
| 368 |
+
"eval_samples_per_second": 36.692,
|
| 369 |
+
"eval_steps_per_second": 4.592,
|
| 370 |
+
"step": 12000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.28018971178402,
|
| 374 |
+
"grad_norm": 2.517010450363159,
|
| 375 |
+
"learning_rate": 1.2015079654627266e-05,
|
| 376 |
+
"loss": 0.2136,
|
| 377 |
+
"step": 12500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.28018971178402,
|
| 381 |
+
"eval_loss": 0.7125562429428101,
|
| 382 |
+
"eval_runtime": 66.4822,
|
| 383 |
+
"eval_samples_per_second": 36.656,
|
| 384 |
+
"eval_steps_per_second": 4.588,
|
| 385 |
+
"step": 12500
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.3713973002553814,
|
| 389 |
+
"grad_norm": 2.654905319213867,
|
| 390 |
+
"learning_rate": 1.049799343305363e-05,
|
| 391 |
+
"loss": 0.2186,
|
| 392 |
+
"step": 13000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.3713973002553814,
|
| 396 |
+
"eval_loss": 0.711520254611969,
|
| 397 |
+
"eval_runtime": 66.4793,
|
| 398 |
+
"eval_samples_per_second": 36.658,
|
| 399 |
+
"eval_steps_per_second": 4.588,
|
| 400 |
+
"step": 13000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.462604888726742,
|
| 404 |
+
"grad_norm": 1.6538429260253906,
|
| 405 |
+
"learning_rate": 8.97786695853095e-06,
|
| 406 |
+
"loss": 0.2119,
|
| 407 |
+
"step": 13500
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.462604888726742,
|
| 411 |
+
"eval_loss": 0.7095320820808411,
|
| 412 |
+
"eval_runtime": 66.4626,
|
| 413 |
+
"eval_samples_per_second": 36.667,
|
| 414 |
+
"eval_steps_per_second": 4.589,
|
| 415 |
+
"step": 13500
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.553812477198103,
|
| 419 |
+
"grad_norm": 2.4926905632019043,
|
| 420 |
+
"learning_rate": 7.45774048400827e-06,
|
| 421 |
+
"loss": 0.2093,
|
| 422 |
+
"step": 14000
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.553812477198103,
|
| 426 |
+
"eval_loss": 0.7063737511634827,
|
| 427 |
+
"eval_runtime": 66.4346,
|
| 428 |
+
"eval_samples_per_second": 36.683,
|
| 429 |
+
"eval_steps_per_second": 4.591,
|
| 430 |
+
"step": 14000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 2.645020065669464,
|
| 434 |
+
"grad_norm": 2.814349412918091,
|
| 435 |
+
"learning_rate": 5.93761400948559e-06,
|
| 436 |
+
"loss": 0.203,
|
| 437 |
+
"step": 14500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.645020065669464,
|
| 441 |
+
"eval_loss": 0.7055577635765076,
|
| 442 |
+
"eval_runtime": 66.5157,
|
| 443 |
+
"eval_samples_per_second": 36.638,
|
| 444 |
+
"eval_steps_per_second": 4.585,
|
| 445 |
+
"step": 14500
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.7362276541408246,
|
| 449 |
+
"grad_norm": 2.242487907409668,
|
| 450 |
+
"learning_rate": 4.417487534962909e-06,
|
| 451 |
+
"loss": 0.2019,
|
| 452 |
+
"step": 15000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.7362276541408246,
|
| 456 |
+
"eval_loss": 0.7038553357124329,
|
| 457 |
+
"eval_runtime": 66.6171,
|
| 458 |
+
"eval_samples_per_second": 36.582,
|
| 459 |
+
"eval_steps_per_second": 4.578,
|
| 460 |
+
"step": 15000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.8274352426121854,
|
| 464 |
+
"grad_norm": 3.0727193355560303,
|
| 465 |
+
"learning_rate": 2.8973610604402286e-06,
|
| 466 |
+
"loss": 0.2,
|
| 467 |
+
"step": 15500
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.8274352426121854,
|
| 471 |
+
"eval_loss": 0.7052037119865417,
|
| 472 |
+
"eval_runtime": 66.5239,
|
| 473 |
+
"eval_samples_per_second": 36.633,
|
| 474 |
+
"eval_steps_per_second": 4.585,
|
| 475 |
+
"step": 15500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.918642831083546,
|
| 479 |
+
"grad_norm": 2.016516923904419,
|
| 480 |
+
"learning_rate": 1.3772345859175483e-06,
|
| 481 |
+
"loss": 0.2011,
|
| 482 |
+
"step": 16000
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.918642831083546,
|
| 486 |
+
"eval_loss": 0.7026786804199219,
|
| 487 |
+
"eval_runtime": 66.488,
|
| 488 |
+
"eval_samples_per_second": 36.653,
|
| 489 |
+
"eval_steps_per_second": 4.587,
|
| 490 |
+
"step": 16000
|
| 491 |
+
}
|
| 492 |
+
],
|
| 493 |
+
"logging_steps": 500,
|
| 494 |
+
"max_steps": 16446,
|
| 495 |
+
"num_input_tokens_seen": 0,
|
| 496 |
+
"num_train_epochs": 3,
|
| 497 |
+
"save_steps": 500,
|
| 498 |
+
"stateful_callbacks": {
|
| 499 |
+
"TrainerControl": {
|
| 500 |
+
"args": {
|
| 501 |
+
"should_epoch_stop": false,
|
| 502 |
+
"should_evaluate": false,
|
| 503 |
+
"should_log": false,
|
| 504 |
+
"should_save": true,
|
| 505 |
+
"should_training_stop": true
|
| 506 |
+
},
|
| 507 |
+
"attributes": {}
|
| 508 |
+
}
|
| 509 |
+
},
|
| 510 |
+
"total_flos": 8.901338457754829e+16,
|
| 511 |
+
"train_batch_size": 1,
|
| 512 |
+
"trial_name": null,
|
| 513 |
+
"trial_params": null
|
| 514 |
+
}
|
checkpoint-16446/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:234fbe87ef57dfef64eac7ccede9d1a856cd7c6d37bee47c3ebf9de75a3405b3
|
| 3 |
+
size 5240
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 32768,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "float32",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfddc9c15cfb892fb069db6c0d028bfbaa30a0c3dc3aeff9452beb1fc23884c2
|
| 3 |
+
size 2384234968
|
pytorch_model.bin
ADDED
|
File without changes
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:352a863cd2761388ccc58f1432467ba6a1037bf12df9069889b142fa246471f6
|
| 3 |
+
size 11422752
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|endoftext|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|