Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: original
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# original
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the Sky-T1 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 96
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0a0+f70bd71a48.nv24.06
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9952038369304557,
+    "total_flos": 213263567486976.0,
+    "train_loss": 0.5326878637648546,
+    "train_runtime": 19065.5756,
+    "train_samples_per_second": 1.049,
+    "train_steps_per_second": 0.011
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8ce82a451babd6c9d8d718ae5a8e501d93bf1f42bef52dc8bff8e443313767
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e94b80c6c64fb2735fd96cc0362e8a3f43bf380ea26f1965a2bbd6c44273d2
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00fbcda5a374d4dd86e8900a6298de4299de5a74f7a321bfc5dad224ab4f0c7f
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dbbf763471a3b48f0a44a625ec0329ba8d28a82ca5c3365c37a27bc69ead02d
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) 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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9952038369304557,
+    "total_flos": 213263567486976.0,
+    "train_loss": 0.5326878637648546,
+    "train_runtime": 19065.5756,
+    "train_samples_per_second": 1.049,
+    "train_steps_per_second": 0.011
+}

trainer_log.jsonl

@@ -0,0 +1,209 @@
+{"current_steps": 1, "total_steps": 208, "loss": 0.8413, "lr": 9.523809523809525e-07, "epoch": 0.009592326139088728, "percentage": 0.48, "elapsed_time": "0:01:26", "remaining_time": "4:58:38"}
+{"current_steps": 2, "total_steps": 208, "loss": 0.8899, "lr": 1.904761904761905e-06, "epoch": 0.019184652278177457, "percentage": 0.96, "elapsed_time": "0:02:52", "remaining_time": "4:56:01"}
+{"current_steps": 3, "total_steps": 208, "loss": 0.8986, "lr": 2.8571428571428573e-06, "epoch": 0.02877697841726619, "percentage": 1.44, "elapsed_time": "0:04:22", "remaining_time": "4:58:37"}
+{"current_steps": 4, "total_steps": 208, "loss": 0.8766, "lr": 3.80952380952381e-06, "epoch": 0.03836930455635491, "percentage": 1.92, "elapsed_time": "0:06:01", "remaining_time": "5:06:59"}
+{"current_steps": 5, "total_steps": 208, "loss": 0.8245, "lr": 4.761904761904762e-06, "epoch": 0.047961630695443645, "percentage": 2.4, "elapsed_time": "0:07:21", "remaining_time": "4:58:45"}
+{"current_steps": 6, "total_steps": 208, "loss": 0.839, "lr": 5.7142857142857145e-06, "epoch": 0.05755395683453238, "percentage": 2.88, "elapsed_time": "0:09:09", "remaining_time": "5:08:14"}
+{"current_steps": 7, "total_steps": 208, "loss": 0.7857, "lr": 6.666666666666667e-06, "epoch": 0.0671462829736211, "percentage": 3.37, "elapsed_time": "0:10:32", "remaining_time": "5:02:32"}
+{"current_steps": 8, "total_steps": 208, "loss": 0.7935, "lr": 7.61904761904762e-06, "epoch": 0.07673860911270983, "percentage": 3.85, "elapsed_time": "0:11:48", "remaining_time": "4:55:13"}
+{"current_steps": 9, "total_steps": 208, "loss": 0.8195, "lr": 8.571428571428571e-06, "epoch": 0.08633093525179857, "percentage": 4.33, "elapsed_time": "0:13:25", "remaining_time": "4:56:43"}
+{"current_steps": 10, "total_steps": 208, "loss": 0.7268, "lr": 9.523809523809525e-06, "epoch": 0.09592326139088729, "percentage": 4.81, "elapsed_time": "0:14:55", "remaining_time": "4:55:37"}
+{"current_steps": 11, "total_steps": 208, "loss": 0.7487, "lr": 1.0476190476190477e-05, "epoch": 0.10551558752997602, "percentage": 5.29, "elapsed_time": "0:16:25", "remaining_time": "4:54:06"}
+{"current_steps": 12, "total_steps": 208, "loss": 0.7149, "lr": 1.1428571428571429e-05, "epoch": 0.11510791366906475, "percentage": 5.77, "elapsed_time": "0:17:52", "remaining_time": "4:51:56"}
+{"current_steps": 13, "total_steps": 208, "loss": 0.7312, "lr": 1.2380952380952383e-05, "epoch": 0.12470023980815348, "percentage": 6.25, "elapsed_time": "0:19:37", "remaining_time": "4:54:19"}
+{"current_steps": 14, "total_steps": 208, "loss": 0.709, "lr": 1.3333333333333333e-05, "epoch": 0.1342925659472422, "percentage": 6.73, "elapsed_time": "0:21:10", "remaining_time": "4:53:21"}
+{"current_steps": 15, "total_steps": 208, "loss": 0.6828, "lr": 1.4285714285714287e-05, "epoch": 0.14388489208633093, "percentage": 7.21, "elapsed_time": "0:22:36", "remaining_time": "4:50:57"}
+{"current_steps": 16, "total_steps": 208, "loss": 0.6861, "lr": 1.523809523809524e-05, "epoch": 0.15347721822541965, "percentage": 7.69, "elapsed_time": "0:24:15", "remaining_time": "4:51:02"}
+{"current_steps": 17, "total_steps": 208, "loss": 0.6665, "lr": 1.6190476190476193e-05, "epoch": 0.1630695443645084, "percentage": 8.17, "elapsed_time": "0:25:36", "remaining_time": "4:47:42"}
+{"current_steps": 18, "total_steps": 208, "loss": 0.6522, "lr": 1.7142857142857142e-05, "epoch": 0.17266187050359713, "percentage": 8.65, "elapsed_time": "0:26:49", "remaining_time": "4:43:10"}
+{"current_steps": 19, "total_steps": 208, "loss": 0.6865, "lr": 1.8095238095238097e-05, "epoch": 0.18225419664268586, "percentage": 9.13, "elapsed_time": "0:28:17", "remaining_time": "4:41:25"}
+{"current_steps": 20, "total_steps": 208, "loss": 0.6201, "lr": 1.904761904761905e-05, "epoch": 0.19184652278177458, "percentage": 9.62, "elapsed_time": "0:29:51", "remaining_time": "4:40:41"}
+{"current_steps": 21, "total_steps": 208, "loss": 0.6356, "lr": 2e-05, "epoch": 0.2014388489208633, "percentage": 10.1, "elapsed_time": "0:31:28", "remaining_time": "4:40:12"}
+{"current_steps": 22, "total_steps": 208, "loss": 0.6532, "lr": 1.9998588839790777e-05, "epoch": 0.21103117505995203, "percentage": 10.58, "elapsed_time": "0:33:12", "remaining_time": "4:40:49"}
+{"current_steps": 23, "total_steps": 208, "loss": 0.6073, "lr": 1.999435575743774e-05, "epoch": 0.22062350119904076, "percentage": 11.06, "elapsed_time": "0:34:47", "remaining_time": "4:39:49"}
+{"current_steps": 24, "total_steps": 208, "loss": 0.6342, "lr": 1.9987301947652354e-05, "epoch": 0.2302158273381295, "percentage": 11.54, "elapsed_time": "0:36:32", "remaining_time": "4:40:05"}
+{"current_steps": 25, "total_steps": 208, "loss": 0.6402, "lr": 1.9977429401245764e-05, "epoch": 0.23980815347721823, "percentage": 12.02, "elapsed_time": "0:38:11", "remaining_time": "4:39:31"}
+{"current_steps": 26, "total_steps": 208, "loss": 0.6104, "lr": 1.9964740904566903e-05, "epoch": 0.24940047961630696, "percentage": 12.5, "elapsed_time": "0:39:44", "remaining_time": "4:38:14"}
+{"current_steps": 27, "total_steps": 208, "loss": 0.5895, "lr": 1.9949240038716092e-05, "epoch": 0.2589928057553957, "percentage": 12.98, "elapsed_time": "0:41:04", "remaining_time": "4:35:21"}
+{"current_steps": 28, "total_steps": 208, "loss": 0.5959, "lr": 1.9930931178534353e-05, "epoch": 0.2685851318944844, "percentage": 13.46, "elapsed_time": "0:42:23", "remaining_time": "4:32:33"}
+{"current_steps": 29, "total_steps": 208, "loss": 0.5908, "lr": 1.9909819491368677e-05, "epoch": 0.27817745803357313, "percentage": 13.94, "elapsed_time": "0:43:42", "remaining_time": "4:29:44"}
+{"current_steps": 30, "total_steps": 208, "loss": 0.607, "lr": 1.988591093561364e-05, "epoch": 0.28776978417266186, "percentage": 14.42, "elapsed_time": "0:45:05", "remaining_time": "4:27:29"}
+{"current_steps": 31, "total_steps": 208, "loss": 0.6049, "lr": 1.985921225902975e-05, "epoch": 0.2973621103117506, "percentage": 14.9, "elapsed_time": "0:46:37", "remaining_time": "4:26:15"}
+{"current_steps": 32, "total_steps": 208, "loss": 0.5783, "lr": 1.982973099683902e-05, "epoch": 0.3069544364508393, "percentage": 15.38, "elapsed_time": "0:48:00", "remaining_time": "4:24:04"}
+{"current_steps": 33, "total_steps": 208, "loss": 0.5838, "lr": 1.9797475469598267e-05, "epoch": 0.31654676258992803, "percentage": 15.87, "elapsed_time": "0:49:45", "remaining_time": "4:23:52"}
+{"current_steps": 34, "total_steps": 208, "loss": 0.5764, "lr": 1.9762454780850807e-05, "epoch": 0.3261390887290168, "percentage": 16.35, "elapsed_time": "0:51:03", "remaining_time": "4:21:16"}
+{"current_steps": 35, "total_steps": 208, "loss": 0.5966, "lr": 1.972467881455713e-05, "epoch": 0.33573141486810554, "percentage": 16.83, "elapsed_time": "0:52:45", "remaining_time": "4:20:46"}
+{"current_steps": 36, "total_steps": 208, "loss": 0.5835, "lr": 1.968415823230534e-05, "epoch": 0.34532374100719426, "percentage": 17.31, "elapsed_time": "0:54:06", "remaining_time": "4:18:31"}
+{"current_steps": 37, "total_steps": 208, "loss": 0.5588, "lr": 1.96409044703021e-05, "epoch": 0.354916067146283, "percentage": 17.79, "elapsed_time": "0:55:41", "remaining_time": "4:17:24"}
+{"current_steps": 38, "total_steps": 208, "loss": 0.6096, "lr": 1.9594929736144978e-05, "epoch": 0.3645083932853717, "percentage": 18.27, "elapsed_time": "0:57:00", "remaining_time": "4:15:02"}
+{"current_steps": 39, "total_steps": 208, "loss": 0.5659, "lr": 1.9546247005377065e-05, "epoch": 0.37410071942446044, "percentage": 18.75, "elapsed_time": "0:58:30", "remaining_time": "4:13:34"}
+{"current_steps": 40, "total_steps": 208, "loss": 0.5525, "lr": 1.9494870017824877e-05, "epoch": 0.38369304556354916, "percentage": 19.23, "elapsed_time": "0:59:56", "remaining_time": "4:11:44"}
+{"current_steps": 41, "total_steps": 208, "loss": 0.552, "lr": 1.9440813273720504e-05, "epoch": 0.3932853717026379, "percentage": 19.71, "elapsed_time": "1:01:17", "remaining_time": "4:09:39"}
+{"current_steps": 42, "total_steps": 208, "loss": 0.5368, "lr": 1.938409202960922e-05, "epoch": 0.4028776978417266, "percentage": 20.19, "elapsed_time": "1:02:44", "remaining_time": "4:07:57"}
+{"current_steps": 43, "total_steps": 208, "loss": 0.5808, "lr": 1.932472229404356e-05, "epoch": 0.41247002398081534, "percentage": 20.67, "elapsed_time": "1:04:11", "remaining_time": "4:06:19"}
+{"current_steps": 44, "total_steps": 208, "loss": 0.5886, "lr": 1.9262720823065217e-05, "epoch": 0.42206235011990406, "percentage": 21.15, "elapsed_time": "1:05:50", "remaining_time": "4:05:23"}
+{"current_steps": 45, "total_steps": 208, "loss": 0.5622, "lr": 1.9198105115475946e-05, "epoch": 0.4316546762589928, "percentage": 21.63, "elapsed_time": "1:07:13", "remaining_time": "4:03:31"}
+{"current_steps": 46, "total_steps": 208, "loss": 0.5744, "lr": 1.9130893407898834e-05, "epoch": 0.4412470023980815, "percentage": 22.12, "elapsed_time": "1:08:42", "remaining_time": "4:02:00"}
+{"current_steps": 47, "total_steps": 208, "loss": 0.5542, "lr": 1.9061104669631343e-05, "epoch": 0.45083932853717024, "percentage": 22.6, "elapsed_time": "1:10:17", "remaining_time": "4:00:47"}
+{"current_steps": 48, "total_steps": 208, "loss": 0.5806, "lr": 1.8988758597291577e-05, "epoch": 0.460431654676259, "percentage": 23.08, "elapsed_time": "1:11:47", "remaining_time": "3:59:17"}
+{"current_steps": 49, "total_steps": 208, "loss": 0.5425, "lr": 1.8913875609259246e-05, "epoch": 0.47002398081534774, "percentage": 23.56, "elapsed_time": "1:13:21", "remaining_time": "3:58:04"}
+{"current_steps": 50, "total_steps": 208, "loss": 0.5607, "lr": 1.8836476839912967e-05, "epoch": 0.47961630695443647, "percentage": 24.04, "elapsed_time": "1:14:46", "remaining_time": "3:56:17"}
+{"current_steps": 51, "total_steps": 208, "loss": 0.5745, "lr": 1.8756584133665447e-05, "epoch": 0.4892086330935252, "percentage": 24.52, "elapsed_time": "1:16:11", "remaining_time": "3:54:34"}
+{"current_steps": 52, "total_steps": 208, "loss": 0.5752, "lr": 1.86742200387983e-05, "epoch": 0.4988009592326139, "percentage": 25.0, "elapsed_time": "1:17:43", "remaining_time": "3:53:11"}
+{"current_steps": 53, "total_steps": 208, "loss": 0.5151, "lr": 1.8589407801098192e-05, "epoch": 0.5083932853717026, "percentage": 25.48, "elapsed_time": "1:19:11", "remaining_time": "3:51:36"}
+{"current_steps": 54, "total_steps": 208, "loss": 0.5622, "lr": 1.8502171357296144e-05, "epoch": 0.5179856115107914, "percentage": 25.96, "elapsed_time": "1:20:43", "remaining_time": "3:50:13"}
+{"current_steps": 55, "total_steps": 208, "loss": 0.5735, "lr": 1.8412535328311813e-05, "epoch": 0.5275779376498801, "percentage": 26.44, "elapsed_time": "1:22:11", "remaining_time": "3:48:38"}
+{"current_steps": 56, "total_steps": 208, "loss": 0.5369, "lr": 1.8320525012304685e-05, "epoch": 0.5371702637889688, "percentage": 26.92, "elapsed_time": "1:23:41", "remaining_time": "3:47:10"}
+{"current_steps": 57, "total_steps": 208, "loss": 0.5405, "lr": 1.8226166377534113e-05, "epoch": 0.5467625899280576, "percentage": 27.4, "elapsed_time": "1:25:14", "remaining_time": "3:45:48"}
+{"current_steps": 58, "total_steps": 208, "loss": 0.5775, "lr": 1.8129486055030255e-05, "epoch": 0.5563549160671463, "percentage": 27.88, "elapsed_time": "1:26:52", "remaining_time": "3:44:40"}
+{"current_steps": 59, "total_steps": 208, "loss": 0.509, "lr": 1.8030511331077945e-05, "epoch": 0.565947242206235, "percentage": 28.37, "elapsed_time": "1:28:17", "remaining_time": "3:42:58"}
+{"current_steps": 60, "total_steps": 208, "loss": 0.5459, "lr": 1.7929270139515606e-05, "epoch": 0.5755395683453237, "percentage": 28.85, "elapsed_time": "1:29:53", "remaining_time": "3:41:43"}
+{"current_steps": 61, "total_steps": 208, "loss": 0.5221, "lr": 1.782579105385145e-05, "epoch": 0.5851318944844125, "percentage": 29.33, "elapsed_time": "1:30:54", "remaining_time": "3:39:04"}
+{"current_steps": 62, "total_steps": 208, "loss": 0.5693, "lr": 1.772010327919912e-05, "epoch": 0.5947242206235012, "percentage": 29.81, "elapsed_time": "1:32:45", "remaining_time": "3:38:26"}
+{"current_steps": 63, "total_steps": 208, "loss": 0.5564, "lr": 1.761223664403505e-05, "epoch": 0.60431654676259, "percentage": 30.29, "elapsed_time": "1:34:29", "remaining_time": "3:37:28"}
+{"current_steps": 64, "total_steps": 208, "loss": 0.546, "lr": 1.7502221591779932e-05, "epoch": 0.6139088729016786, "percentage": 30.77, "elapsed_time": "1:36:02", "remaining_time": "3:36:04"}
+{"current_steps": 65, "total_steps": 208, "loss": 0.5632, "lr": 1.7390089172206594e-05, "epoch": 0.6235011990407674, "percentage": 31.25, "elapsed_time": "1:37:41", "remaining_time": "3:34:56"}
+{"current_steps": 66, "total_steps": 208, "loss": 0.5555, "lr": 1.727587103267677e-05, "epoch": 0.6330935251798561, "percentage": 31.73, "elapsed_time": "1:39:07", "remaining_time": "3:33:16"}
+{"current_steps": 67, "total_steps": 208, "loss": 0.5945, "lr": 1.7159599409209194e-05, "epoch": 0.6426858513189448, "percentage": 32.21, "elapsed_time": "1:40:44", "remaining_time": "3:32:00"}
+{"current_steps": 68, "total_steps": 208, "loss": 0.4992, "lr": 1.704130711738157e-05, "epoch": 0.6522781774580336, "percentage": 32.69, "elapsed_time": "1:41:49", "remaining_time": "3:29:39"}
+{"current_steps": 69, "total_steps": 208, "loss": 0.5502, "lr": 1.692102754306895e-05, "epoch": 0.6618705035971223, "percentage": 33.17, "elapsed_time": "1:43:30", "remaining_time": "3:28:30"}
+{"current_steps": 70, "total_steps": 208, "loss": 0.5459, "lr": 1.6798794633021192e-05, "epoch": 0.6714628297362111, "percentage": 33.65, "elapsed_time": "1:45:14", "remaining_time": "3:27:29"}
+{"current_steps": 71, "total_steps": 208, "loss": 0.5545, "lr": 1.667464288528207e-05, "epoch": 0.6810551558752997, "percentage": 34.13, "elapsed_time": "1:46:44", "remaining_time": "3:25:58"}
+{"current_steps": 72, "total_steps": 208, "loss": 0.5409, "lr": 1.6548607339452853e-05, "epoch": 0.6906474820143885, "percentage": 34.62, "elapsed_time": "1:48:19", "remaining_time": "3:24:37"}
+{"current_steps": 73, "total_steps": 208, "loss": 0.5388, "lr": 1.6420723566802982e-05, "epoch": 0.7002398081534772, "percentage": 35.1, "elapsed_time": "1:49:47", "remaining_time": "3:23:01"}
+{"current_steps": 74, "total_steps": 208, "loss": 0.549, "lr": 1.6291027660230735e-05, "epoch": 0.709832134292566, "percentage": 35.58, "elapsed_time": "1:51:08", "remaining_time": "3:21:14"}
+{"current_steps": 75, "total_steps": 208, "loss": 0.5277, "lr": 1.6159556224076637e-05, "epoch": 0.7194244604316546, "percentage": 36.06, "elapsed_time": "1:52:36", "remaining_time": "3:19:40"}
+{"current_steps": 76, "total_steps": 208, "loss": 0.5637, "lr": 1.6026346363792565e-05, "epoch": 0.7290167865707434, "percentage": 36.54, "elapsed_time": "1:54:20", "remaining_time": "3:18:36"}
+{"current_steps": 77, "total_steps": 208, "loss": 0.562, "lr": 1.5891435675469376e-05, "epoch": 0.7386091127098321, "percentage": 37.02, "elapsed_time": "1:55:53", "remaining_time": "3:17:10"}
+{"current_steps": 78, "total_steps": 208, "loss": 0.5617, "lr": 1.57548622352261e-05, "epoch": 0.7482014388489209, "percentage": 37.5, "elapsed_time": "1:57:19", "remaining_time": "3:15:32"}
+{"current_steps": 79, "total_steps": 208, "loss": 0.5431, "lr": 1.561666458846365e-05, "epoch": 0.7577937649880095, "percentage": 37.98, "elapsed_time": "1:59:10", "remaining_time": "3:14:36"}
+{"current_steps": 80, "total_steps": 208, "loss": 0.5598, "lr": 1.5476881738986037e-05, "epoch": 0.7673860911270983, "percentage": 38.46, "elapsed_time": "2:00:43", "remaining_time": "3:13:09"}
+{"current_steps": 81, "total_steps": 208, "loss": 0.5075, "lr": 1.5335553137992286e-05, "epoch": 0.7769784172661871, "percentage": 38.94, "elapsed_time": "2:02:03", "remaining_time": "3:11:22"}
+{"current_steps": 82, "total_steps": 208, "loss": 0.531, "lr": 1.519271867294203e-05, "epoch": 0.7865707434052758, "percentage": 39.42, "elapsed_time": "2:03:45", "remaining_time": "3:10:09"}
+{"current_steps": 83, "total_steps": 208, "loss": 0.5838, "lr": 1.504841865629799e-05, "epoch": 0.7961630695443646, "percentage": 39.9, "elapsed_time": "2:05:23", "remaining_time": "3:08:50"}
+{"current_steps": 84, "total_steps": 208, "loss": 0.5844, "lr": 1.490269381414849e-05, "epoch": 0.8057553956834532, "percentage": 40.38, "elapsed_time": "2:06:53", "remaining_time": "3:07:18"}
+{"current_steps": 85, "total_steps": 208, "loss": 0.5258, "lr": 1.4755585274713289e-05, "epoch": 0.815347721822542, "percentage": 40.87, "elapsed_time": "2:08:29", "remaining_time": "3:05:56"}
+{"current_steps": 86, "total_steps": 208, "loss": 0.5028, "lr": 1.4607134556735836e-05, "epoch": 0.8249400479616307, "percentage": 41.35, "elapsed_time": "2:09:47", "remaining_time": "3:04:07"}
+{"current_steps": 87, "total_steps": 208, "loss": 0.5728, "lr": 1.4457383557765385e-05, "epoch": 0.8345323741007195, "percentage": 41.83, "elapsed_time": "2:11:20", "remaining_time": "3:02:39"}
+{"current_steps": 88, "total_steps": 208, "loss": 0.5434, "lr": 1.4306374542332141e-05, "epoch": 0.8441247002398081, "percentage": 42.31, "elapsed_time": "2:12:45", "remaining_time": "3:01:01"}
+{"current_steps": 89, "total_steps": 208, "loss": 0.5308, "lr": 1.4154150130018867e-05, "epoch": 0.8537170263788969, "percentage": 42.79, "elapsed_time": "2:14:09", "remaining_time": "2:59:23"}
+{"current_steps": 90, "total_steps": 208, "loss": 0.5664, "lr": 1.4000753283432267e-05, "epoch": 0.8633093525179856, "percentage": 43.27, "elapsed_time": "2:15:46", "remaining_time": "2:58:00"}
+{"current_steps": 91, "total_steps": 208, "loss": 0.5509, "lr": 1.3846227296077568e-05, "epoch": 0.8729016786570744, "percentage": 43.75, "elapsed_time": "2:17:17", "remaining_time": "2:56:31"}
+{"current_steps": 92, "total_steps": 208, "loss": 0.5217, "lr": 1.3690615780139703e-05, "epoch": 0.882494004796163, "percentage": 44.23, "elapsed_time": "2:18:42", "remaining_time": "2:54:52"}
+{"current_steps": 93, "total_steps": 208, "loss": 0.5502, "lr": 1.3533962654174542e-05, "epoch": 0.8920863309352518, "percentage": 44.71, "elapsed_time": "2:20:18", "remaining_time": "2:53:29"}
+{"current_steps": 94, "total_steps": 208, "loss": 0.5284, "lr": 1.337631213071369e-05, "epoch": 0.9016786570743405, "percentage": 45.19, "elapsed_time": "2:21:48", "remaining_time": "2:51:58"}
+{"current_steps": 95, "total_steps": 208, "loss": 0.5374, "lr": 1.321770870378628e-05, "epoch": 0.9112709832134293, "percentage": 45.67, "elapsed_time": "2:23:19", "remaining_time": "2:50:28"}
+{"current_steps": 96, "total_steps": 208, "loss": 0.5362, "lr": 1.3058197136361344e-05, "epoch": 0.920863309352518, "percentage": 46.15, "elapsed_time": "2:24:57", "remaining_time": "2:49:07"}
+{"current_steps": 97, "total_steps": 208, "loss": 0.5427, "lr": 1.2897822447714247e-05, "epoch": 0.9304556354916067, "percentage": 46.63, "elapsed_time": "2:26:19", "remaining_time": "2:47:26"}
+{"current_steps": 98, "total_steps": 208, "loss": 0.5195, "lr": 1.2736629900720832e-05, "epoch": 0.9400479616306955, "percentage": 47.12, "elapsed_time": "2:27:53", "remaining_time": "2:46:00"}
+{"current_steps": 99, "total_steps": 208, "loss": 0.5356, "lr": 1.257466498908276e-05, "epoch": 0.9496402877697842, "percentage": 47.6, "elapsed_time": "2:29:24", "remaining_time": "2:44:29"}
+{"current_steps": 100, "total_steps": 208, "loss": 0.5594, "lr": 1.2411973424487751e-05, "epoch": 0.9592326139088729, "percentage": 48.08, "elapsed_time": "2:30:44", "remaining_time": "2:42:47"}
+{"current_steps": 101, "total_steps": 208, "loss": 0.542, "lr": 1.2248601123708279e-05, "epoch": 0.9688249400479616, "percentage": 48.56, "elapsed_time": "2:33:08", "remaining_time": "2:42:14"}
+{"current_steps": 102, "total_steps": 208, "loss": 0.5407, "lr": 1.2084594195642367e-05, "epoch": 0.9784172661870504, "percentage": 49.04, "elapsed_time": "2:34:50", "remaining_time": "2:40:55"}
+{"current_steps": 103, "total_steps": 208, "loss": 0.5394, "lr": 1.1919998928300203e-05, "epoch": 0.988009592326139, "percentage": 49.52, "elapsed_time": "2:36:30", "remaining_time": "2:39:32"}
+{"current_steps": 104, "total_steps": 208, "loss": 0.5681, "lr": 1.1754861775740163e-05, "epoch": 0.9976019184652278, "percentage": 50.0, "elapsed_time": "2:38:05", "remaining_time": "2:38:05"}
+{"current_steps": 105, "total_steps": 208, "loss": 0.8402, "lr": 1.1589229344958e-05, "epoch": 1.0071942446043165, "percentage": 50.48, "elapsed_time": "2:39:34", "remaining_time": "2:36:32"}
+{"current_steps": 106, "total_steps": 208, "loss": 0.4084, "lr": 1.1423148382732854e-05, "epoch": 1.0167865707434052, "percentage": 50.96, "elapsed_time": "2:40:52", "remaining_time": "2:34:48"}
+{"current_steps": 107, "total_steps": 208, "loss": 0.4635, "lr": 1.1256665762433798e-05, "epoch": 1.026378896882494, "percentage": 51.44, "elapsed_time": "2:42:15", "remaining_time": "2:33:09"}
+{"current_steps": 108, "total_steps": 208, "loss": 0.4702, "lr": 1.1089828470790694e-05, "epoch": 1.0359712230215827, "percentage": 51.92, "elapsed_time": "2:43:38", "remaining_time": "2:31:31"}
+{"current_steps": 109, "total_steps": 208, "loss": 0.5416, "lr": 1.092268359463302e-05, "epoch": 1.0455635491606714, "percentage": 52.4, "elapsed_time": "2:45:10", "remaining_time": "2:30:00"}
+{"current_steps": 110, "total_steps": 208, "loss": 0.4767, "lr": 1.0755278307600459e-05, "epoch": 1.0551558752997603, "percentage": 52.88, "elapsed_time": "2:46:39", "remaining_time": "2:28:29"}
+{"current_steps": 111, "total_steps": 208, "loss": 0.4414, "lr": 1.058765985682898e-05, "epoch": 1.064748201438849, "percentage": 53.37, "elapsed_time": "2:48:07", "remaining_time": "2:26:55"}
+{"current_steps": 112, "total_steps": 208, "loss": 0.4378, "lr": 1.0419875549616196e-05, "epoch": 1.0743405275779376, "percentage": 53.85, "elapsed_time": "2:49:39", "remaining_time": "2:25:25"}
+{"current_steps": 113, "total_steps": 208, "loss": 0.5092, "lr": 1.0251972740069724e-05, "epoch": 1.0839328537170263, "percentage": 54.33, "elapsed_time": "2:51:21", "remaining_time": "2:24:03"}
+{"current_steps": 114, "total_steps": 208, "loss": 0.4518, "lr": 1.0083998815742335e-05, "epoch": 1.0935251798561152, "percentage": 54.81, "elapsed_time": "2:52:53", "remaining_time": "2:22:33"}
+{"current_steps": 115, "total_steps": 208, "loss": 0.4128, "lr": 9.916001184257668e-06, "epoch": 1.1031175059952039, "percentage": 55.29, "elapsed_time": "2:54:01", "remaining_time": "2:20:43"}
+{"current_steps": 116, "total_steps": 208, "loss": 0.4915, "lr": 9.748027259930276e-06, "epoch": 1.1127098321342925, "percentage": 55.77, "elapsed_time": "2:55:39", "remaining_time": "2:19:18"}
+{"current_steps": 117, "total_steps": 208, "loss": 0.5308, "lr": 9.580124450383804e-06, "epoch": 1.1223021582733812, "percentage": 56.25, "elapsed_time": "2:57:23", "remaining_time": "2:17:58"}
+{"current_steps": 118, "total_steps": 208, "loss": 0.4496, "lr": 9.412340143171025e-06, "epoch": 1.13189448441247, "percentage": 56.73, "elapsed_time": "2:58:45", "remaining_time": "2:16:20"}
+{"current_steps": 119, "total_steps": 208, "loss": 0.4636, "lr": 9.244721692399545e-06, "epoch": 1.1414868105515588, "percentage": 57.21, "elapsed_time": "3:00:19", "remaining_time": "2:14:52"}
+{"current_steps": 120, "total_steps": 208, "loss": 0.4587, "lr": 9.07731640536698e-06, "epoch": 1.1510791366906474, "percentage": 57.69, "elapsed_time": "3:01:42", "remaining_time": "2:13:15"}
+{"current_steps": 121, "total_steps": 208, "loss": 0.452, "lr": 8.910171529209306e-06, "epoch": 1.160671462829736, "percentage": 58.17, "elapsed_time": "3:03:12", "remaining_time": "2:11:43"}
+{"current_steps": 122, "total_steps": 208, "loss": 0.5034, "lr": 8.743334237566202e-06, "epoch": 1.170263788968825, "percentage": 58.65, "elapsed_time": "3:04:35", "remaining_time": "2:10:07"}
+{"current_steps": 123, "total_steps": 208, "loss": 0.4566, "lr": 8.576851617267151e-06, "epoch": 1.1798561151079137, "percentage": 59.13, "elapsed_time": "3:06:08", "remaining_time": "2:08:38"}
+{"current_steps": 124, "total_steps": 208, "loss": 0.4569, "lr": 8.410770655042003e-06, "epoch": 1.1894484412470023, "percentage": 59.62, "elapsed_time": "3:07:31", "remaining_time": "2:07:01"}
+{"current_steps": 125, "total_steps": 208, "loss": 0.509, "lr": 8.24513822425984e-06, "epoch": 1.1990407673860912, "percentage": 60.1, "elapsed_time": "3:09:07", "remaining_time": "2:05:34"}
+{"current_steps": 126, "total_steps": 208, "loss": 0.4554, "lr": 8.0800010716998e-06, "epoch": 1.20863309352518, "percentage": 60.58, "elapsed_time": "3:10:43", "remaining_time": "2:04:07"}
+{"current_steps": 127, "total_steps": 208, "loss": 0.4381, "lr": 7.915405804357632e-06, "epoch": 1.2182254196642686, "percentage": 61.06, "elapsed_time": "3:12:09", "remaining_time": "2:02:33"}
+{"current_steps": 128, "total_steps": 208, "loss": 0.4517, "lr": 7.751398876291725e-06, "epoch": 1.2278177458033572, "percentage": 61.54, "elapsed_time": "3:13:28", "remaining_time": "2:00:55"}
+{"current_steps": 129, "total_steps": 208, "loss": 0.5156, "lr": 7.58802657551225e-06, "epoch": 1.2374100719424461, "percentage": 62.02, "elapsed_time": "3:15:05", "remaining_time": "1:59:28"}
+{"current_steps": 130, "total_steps": 208, "loss": 0.4501, "lr": 7.425335010917244e-06, "epoch": 1.2470023980815348, "percentage": 62.5, "elapsed_time": "3:16:40", "remaining_time": "1:58:00"}
+{"current_steps": 131, "total_steps": 208, "loss": 0.5551, "lr": 7.263370099279173e-06, "epoch": 1.2565947242206235, "percentage": 62.98, "elapsed_time": "3:18:29", "remaining_time": "1:56:40"}
+{"current_steps": 132, "total_steps": 208, "loss": 0.4076, "lr": 7.102177552285753e-06, "epoch": 1.2661870503597124, "percentage": 63.46, "elapsed_time": "3:19:41", "remaining_time": "1:54:58"}
+{"current_steps": 133, "total_steps": 208, "loss": 0.4547, "lr": 6.9418028636386595e-06, "epoch": 1.275779376498801, "percentage": 63.94, "elapsed_time": "3:21:00", "remaining_time": "1:53:20"}
+{"current_steps": 134, "total_steps": 208, "loss": 0.4673, "lr": 6.7822912962137225e-06, "epoch": 1.2853717026378897, "percentage": 64.42, "elapsed_time": "3:22:32", "remaining_time": "1:51:50"}
+{"current_steps": 135, "total_steps": 208, "loss": 0.4789, "lr": 6.623687869286314e-06, "epoch": 1.2949640287769784, "percentage": 64.9, "elapsed_time": "3:24:05", "remaining_time": "1:50:21"}
+{"current_steps": 136, "total_steps": 208, "loss": 0.4581, "lr": 6.466037345825462e-06, "epoch": 1.304556354916067, "percentage": 65.38, "elapsed_time": "3:25:41", "remaining_time": "1:48:53"}
+{"current_steps": 137, "total_steps": 208, "loss": 0.4581, "lr": 6.3093842198603014e-06, "epoch": 1.314148681055156, "percentage": 65.87, "elapsed_time": "3:27:13", "remaining_time": "1:47:23"}
+{"current_steps": 138, "total_steps": 208, "loss": 0.4402, "lr": 6.153772703922434e-06, "epoch": 1.3237410071942446, "percentage": 66.35, "elapsed_time": "3:28:29", "remaining_time": "1:45:45"}
+{"current_steps": 139, "total_steps": 208, "loss": 0.4542, "lr": 5.999246716567737e-06, "epoch": 1.3333333333333333, "percentage": 66.83, "elapsed_time": "3:30:04", "remaining_time": "1:44:17"}
+{"current_steps": 140, "total_steps": 208, "loss": 0.4522, "lr": 5.845849869981137e-06, "epoch": 1.3429256594724222, "percentage": 67.31, "elapsed_time": "3:31:30", "remaining_time": "1:42:43"}
+{"current_steps": 141, "total_steps": 208, "loss": 0.42, "lr": 5.693625457667862e-06, "epoch": 1.3525179856115108, "percentage": 67.79, "elapsed_time": "3:32:52", "remaining_time": "1:41:09"}
+{"current_steps": 142, "total_steps": 208, "loss": 0.4896, "lr": 5.542616442234618e-06, "epoch": 1.3621103117505995, "percentage": 68.27, "elapsed_time": "3:34:31", "remaining_time": "1:39:42"}
+{"current_steps": 143, "total_steps": 208, "loss": 0.4754, "lr": 5.392865443264164e-06, "epoch": 1.3717026378896882, "percentage": 68.75, "elapsed_time": "3:36:04", "remaining_time": "1:38:12"}
+{"current_steps": 144, "total_steps": 208, "loss": 0.4778, "lr": 5.244414725286717e-06, "epoch": 1.381294964028777, "percentage": 69.23, "elapsed_time": "3:37:41", "remaining_time": "1:36:45"}
+{"current_steps": 145, "total_steps": 208, "loss": 0.4799, "lr": 5.097306185851515e-06, "epoch": 1.3908872901678657, "percentage": 69.71, "elapsed_time": "3:39:15", "remaining_time": "1:35:15"}
+{"current_steps": 146, "total_steps": 208, "loss": 0.4485, "lr": 4.951581343702014e-06, "epoch": 1.4004796163069544, "percentage": 70.19, "elapsed_time": "3:40:51", "remaining_time": "1:33:47"}
+{"current_steps": 147, "total_steps": 208, "loss": 0.4715, "lr": 4.807281327057972e-06, "epoch": 1.4100719424460433, "percentage": 70.67, "elapsed_time": "3:42:22", "remaining_time": "1:32:16"}
+{"current_steps": 148, "total_steps": 208, "loss": 0.4358, "lr": 4.664446862007718e-06, "epoch": 1.419664268585132, "percentage": 71.15, "elapsed_time": "3:43:57", "remaining_time": "1:30:47"}
+{"current_steps": 149, "total_steps": 208, "loss": 0.5265, "lr": 4.523118261013969e-06, "epoch": 1.4292565947242206, "percentage": 71.63, "elapsed_time": "3:45:23", "remaining_time": "1:29:15"}
+{"current_steps": 150, "total_steps": 208, "loss": 0.4388, "lr": 4.383335411536357e-06, "epoch": 1.4388489208633093, "percentage": 72.12, "elapsed_time": "3:46:44", "remaining_time": "1:27:40"}
+{"current_steps": 151, "total_steps": 208, "loss": 0.4611, "lr": 4.245137764773899e-06, "epoch": 1.448441247002398, "percentage": 72.6, "elapsed_time": "3:48:15", "remaining_time": "1:26:09"}
+{"current_steps": 152, "total_steps": 208, "loss": 0.4364, "lr": 4.108564324530626e-06, "epoch": 1.4580335731414868, "percentage": 73.08, "elapsed_time": "3:49:40", "remaining_time": "1:24:36"}
+{"current_steps": 153, "total_steps": 208, "loss": 0.5079, "lr": 3.973653636207437e-06, "epoch": 1.4676258992805755, "percentage": 73.56, "elapsed_time": "3:51:15", "remaining_time": "1:23:07"}
+{"current_steps": 154, "total_steps": 208, "loss": 0.4235, "lr": 3.840443775923365e-06, "epoch": 1.4772182254196642, "percentage": 74.04, "elapsed_time": "3:52:44", "remaining_time": "1:21:36"}
+{"current_steps": 155, "total_steps": 208, "loss": 0.4592, "lr": 3.70897233976927e-06, "epoch": 1.486810551558753, "percentage": 74.52, "elapsed_time": "3:54:07", "remaining_time": "1:20:03"}
+{"current_steps": 156, "total_steps": 208, "loss": 0.4623, "lr": 3.5792764331970187e-06, "epoch": 1.4964028776978417, "percentage": 75.0, "elapsed_time": "3:55:46", "remaining_time": "1:18:35"}
+{"current_steps": 157, "total_steps": 208, "loss": 0.4361, "lr": 3.4513926605471504e-06, "epoch": 1.5059952038369304, "percentage": 75.48, "elapsed_time": "3:56:59", "remaining_time": "1:16:59"}
+{"current_steps": 158, "total_steps": 208, "loss": 0.4034, "lr": 3.3253571147179333e-06, "epoch": 1.515587529976019, "percentage": 75.96, "elapsed_time": "3:58:40", "remaining_time": "1:15:31"}
+{"current_steps": 159, "total_steps": 208, "loss": 0.5412, "lr": 3.2012053669788136e-06, "epoch": 1.5251798561151078, "percentage": 76.44, "elapsed_time": "4:00:21", "remaining_time": "1:14:04"}
+{"current_steps": 160, "total_steps": 208, "loss": 0.5193, "lr": 3.0789724569310532e-06, "epoch": 1.5347721822541966, "percentage": 76.92, "elapsed_time": "4:02:11", "remaining_time": "1:12:39"}
+{"current_steps": 161, "total_steps": 208, "loss": 0.3989, "lr": 2.9586928826184323e-06, "epoch": 1.5443645083932853, "percentage": 77.4, "elapsed_time": "4:03:45", "remaining_time": "1:11:09"}
+{"current_steps": 162, "total_steps": 208, "loss": 0.495, "lr": 2.8404005907908083e-06, "epoch": 1.5539568345323742, "percentage": 77.88, "elapsed_time": "4:05:31", "remaining_time": "1:09:43"}
+{"current_steps": 163, "total_steps": 208, "loss": 0.4592, "lr": 2.724128967323234e-06, "epoch": 1.5635491606714629, "percentage": 78.37, "elapsed_time": "4:07:00", "remaining_time": "1:08:11"}
+{"current_steps": 164, "total_steps": 208, "loss": 0.5052, "lr": 2.6099108277934105e-06, "epoch": 1.5731414868105515, "percentage": 78.85, "elapsed_time": "4:08:50", "remaining_time": "1:06:45"}
+{"current_steps": 165, "total_steps": 208, "loss": 0.4581, "lr": 2.4977784082200728e-06, "epoch": 1.5827338129496402, "percentage": 79.33, "elapsed_time": "4:10:19", "remaining_time": "1:05:14"}
+{"current_steps": 166, "total_steps": 208, "loss": 0.4616, "lr": 2.3877633559649505e-06, "epoch": 1.5923261390887289, "percentage": 79.81, "elapsed_time": "4:11:47", "remaining_time": "1:03:42"}
+{"current_steps": 167, "total_steps": 208, "loss": 0.4446, "lr": 2.2798967208008806e-06, "epoch": 1.6019184652278178, "percentage": 80.29, "elapsed_time": "4:13:05", "remaining_time": "1:02:08"}
+{"current_steps": 168, "total_steps": 208, "loss": 0.4786, "lr": 2.1742089461485504e-06, "epoch": 1.6115107913669064, "percentage": 80.77, "elapsed_time": "4:14:27", "remaining_time": "1:00:35"}
+{"current_steps": 169, "total_steps": 208, "loss": 0.4576, "lr": 2.0707298604843964e-06, "epoch": 1.6211031175059953, "percentage": 81.25, "elapsed_time": "4:16:06", "remaining_time": "0:59:06"}
+{"current_steps": 170, "total_steps": 208, "loss": 0.4435, "lr": 1.9694886689220592e-06, "epoch": 1.630695443645084, "percentage": 81.73, "elapsed_time": "4:17:29", "remaining_time": "0:57:33"}
+{"current_steps": 171, "total_steps": 208, "loss": 0.504, "lr": 1.870513944969743e-06, "epoch": 1.6402877697841727, "percentage": 82.21, "elapsed_time": "4:19:12", "remaining_time": "0:56:05"}
+{"current_steps": 172, "total_steps": 208, "loss": 0.4355, "lr": 1.773833622465888e-06, "epoch": 1.6498800959232613, "percentage": 82.69, "elapsed_time": "4:20:30", "remaining_time": "0:54:31"}
+{"current_steps": 173, "total_steps": 208, "loss": 0.4532, "lr": 1.6794749876953187e-06, "epoch": 1.65947242206235, "percentage": 83.17, "elapsed_time": "4:21:59", "remaining_time": "0:53:00"}
+{"current_steps": 174, "total_steps": 208, "loss": 0.5107, "lr": 1.587464671688187e-06, "epoch": 1.6690647482014387, "percentage": 83.65, "elapsed_time": "4:23:32", "remaining_time": "0:51:29"}
+{"current_steps": 175, "total_steps": 208, "loss": 0.456, "lr": 1.4978286427038602e-06, "epoch": 1.6786570743405276, "percentage": 84.13, "elapsed_time": "4:24:52", "remaining_time": "0:49:56"}
+{"current_steps": 176, "total_steps": 208, "loss": 0.4294, "lr": 1.4105921989018112e-06, "epoch": 1.6882494004796165, "percentage": 84.62, "elapsed_time": "4:26:23", "remaining_time": "0:48:26"}
+{"current_steps": 177, "total_steps": 208, "loss": 0.4907, "lr": 1.325779961201703e-06, "epoch": 1.6978417266187051, "percentage": 85.1, "elapsed_time": "4:27:56", "remaining_time": "0:46:55"}
+{"current_steps": 178, "total_steps": 208, "loss": 0.3882, "lr": 1.2434158663345553e-06, "epoch": 1.7074340527577938, "percentage": 85.58, "elapsed_time": "4:29:33", "remaining_time": "0:45:25"}
+{"current_steps": 179, "total_steps": 208, "loss": 0.4902, "lr": 1.1635231600870334e-06, "epoch": 1.7170263788968825, "percentage": 86.06, "elapsed_time": "4:30:53", "remaining_time": "0:43:53"}
+{"current_steps": 180, "total_steps": 208, "loss": 0.4223, "lr": 1.086124390740757e-06, "epoch": 1.7266187050359711, "percentage": 86.54, "elapsed_time": "4:32:23", "remaining_time": "0:42:22"}
+{"current_steps": 181, "total_steps": 208, "loss": 0.4593, "lr": 1.0112414027084262e-06, "epoch": 1.7362110311750598, "percentage": 87.02, "elapsed_time": "4:33:40", "remaining_time": "0:40:49"}
+{"current_steps": 182, "total_steps": 208, "loss": 0.507, "lr": 9.388953303686587e-07, "epoch": 1.7458033573141487, "percentage": 87.5, "elapsed_time": "4:35:17", "remaining_time": "0:39:19"}
+{"current_steps": 183, "total_steps": 208, "loss": 0.4046, "lr": 8.691065921011687e-07, "epoch": 1.7553956834532374, "percentage": 87.98, "elapsed_time": "4:36:45", "remaining_time": "0:37:48"}
+{"current_steps": 184, "total_steps": 208, "loss": 0.4293, "lr": 8.018948845240538e-07, "epoch": 1.7649880095923263, "percentage": 88.46, "elapsed_time": "4:38:15", "remaining_time": "0:36:17"}
+{"current_steps": 185, "total_steps": 208, "loss": 0.4817, "lr": 7.372791769347843e-07, "epoch": 1.774580335731415, "percentage": 88.94, "elapsed_time": "4:39:40", "remaining_time": "0:34:46"}
+{"current_steps": 186, "total_steps": 208, "loss": 0.467, "lr": 6.752777059564431e-07, "epoch": 1.7841726618705036, "percentage": 89.42, "elapsed_time": "4:41:14", "remaining_time": "0:33:15"}
+{"current_steps": 187, "total_steps": 208, "loss": 0.4007, "lr": 6.159079703907823e-07, "epoch": 1.7937649880095923, "percentage": 89.9, "elapsed_time": "4:42:54", "remaining_time": "0:31:46"}
+{"current_steps": 188, "total_steps": 208, "loss": 0.4383, "lr": 5.591867262794969e-07, "epoch": 1.803357314148681, "percentage": 90.38, "elapsed_time": "4:44:13", "remaining_time": "0:30:14"}
+{"current_steps": 189, "total_steps": 208, "loss": 0.4637, "lr": 5.051299821751254e-07, "epoch": 1.8129496402877698, "percentage": 90.87, "elapsed_time": "4:45:51", "remaining_time": "0:28:44"}
+{"current_steps": 190, "total_steps": 208, "loss": 0.455, "lr": 4.537529946229369e-07, "epoch": 1.8225419664268585, "percentage": 91.35, "elapsed_time": "4:47:19", "remaining_time": "0:27:13"}
+{"current_steps": 191, "total_steps": 208, "loss": 0.404, "lr": 4.0507026385502747e-07, "epoch": 1.8321342925659474, "percentage": 91.83, "elapsed_time": "4:48:42", "remaining_time": "0:25:41"}
+{"current_steps": 192, "total_steps": 208, "loss": 0.5082, "lr": 3.5909552969790376e-07, "epoch": 1.841726618705036, "percentage": 92.31, "elapsed_time": "4:50:15", "remaining_time": "0:24:11"}
+{"current_steps": 193, "total_steps": 208, "loss": 0.4359, "lr": 3.158417676946635e-07, "epoch": 1.8513189448441247, "percentage": 92.79, "elapsed_time": "4:51:49", "remaining_time": "0:22:40"}
+{"current_steps": 194, "total_steps": 208, "loss": 0.4456, "lr": 2.753211854428728e-07, "epoch": 1.8609112709832134, "percentage": 93.27, "elapsed_time": "4:53:17", "remaining_time": "0:21:09"}
+{"current_steps": 195, "total_steps": 208, "loss": 0.5353, "lr": 2.375452191491967e-07, "epoch": 1.870503597122302, "percentage": 93.75, "elapsed_time": "4:55:08", "remaining_time": "0:19:40"}
+{"current_steps": 196, "total_steps": 208, "loss": 0.4546, "lr": 2.0252453040173646e-07, "epoch": 1.8800959232613907, "percentage": 94.23, "elapsed_time": "4:56:49", "remaining_time": "0:18:10"}
+{"current_steps": 197, "total_steps": 208, "loss": 0.4125, "lr": 1.7026900316098217e-07, "epoch": 1.8896882494004796, "percentage": 94.71, "elapsed_time": "4:58:06", "remaining_time": "0:16:38"}
+{"current_steps": 198, "total_steps": 208, "loss": 0.4024, "lr": 1.407877409702496e-07, "epoch": 1.8992805755395683, "percentage": 95.19, "elapsed_time": "4:59:21", "remaining_time": "0:15:07"}
+{"current_steps": 199, "total_steps": 208, "loss": 0.548, "lr": 1.1408906438636236e-07, "epoch": 1.9088729016786572, "percentage": 95.67, "elapsed_time": "5:00:58", "remaining_time": "0:13:36"}
+{"current_steps": 200, "total_steps": 208, "loss": 0.4678, "lr": 9.018050863132566e-08, "epoch": 1.9184652278177459, "percentage": 96.15, "elapsed_time": "5:02:28", "remaining_time": "0:12:05"}
+{"current_steps": 201, "total_steps": 208, "loss": 0.4359, "lr": 6.906882146565097e-08, "epoch": 1.9280575539568345, "percentage": 96.63, "elapsed_time": "5:05:07", "remaining_time": "0:10:37"}
+{"current_steps": 202, "total_steps": 208, "loss": 0.4864, "lr": 5.0759961283911584e-08, "epoch": 1.9376498800959232, "percentage": 97.12, "elapsed_time": "5:06:42", "remaining_time": "0:09:06"}
+{"current_steps": 203, "total_steps": 208, "loss": 0.4142, "lr": 3.525909543310002e-08, "epoch": 1.9472422062350119, "percentage": 97.6, "elapsed_time": "5:08:00", "remaining_time": "0:07:35"}
+{"current_steps": 204, "total_steps": 208, "loss": 0.4492, "lr": 2.257059875423795e-08, "epoch": 1.9568345323741008, "percentage": 98.08, "elapsed_time": "5:09:48", "remaining_time": "0:06:04"}
+{"current_steps": 205, "total_steps": 208, "loss": 0.4688, "lr": 1.2698052347649426e-08, "epoch": 1.9664268585131894, "percentage": 98.56, "elapsed_time": "5:11:26", "remaining_time": "0:04:33"}
+{"current_steps": 206, "total_steps": 208, "loss": 0.467, "lr": 5.644242562264923e-09, "epoch": 1.9760191846522783, "percentage": 99.04, "elapsed_time": "5:13:05", "remaining_time": "0:03:02"}
+{"current_steps": 207, "total_steps": 208, "loss": 0.4595, "lr": 1.4111602092226062e-09, "epoch": 1.985611510791367, "percentage": 99.52, "elapsed_time": "5:14:59", "remaining_time": "0:01:31"}
+{"current_steps": 208, "total_steps": 208, "loss": 0.5022, "lr": 0.0, "epoch": 1.9952038369304557, "percentage": 100.0, "elapsed_time": "5:16:39", "remaining_time": "0:00:00"}
+{"current_steps": 208, "total_steps": 208, "epoch": 1.9952038369304557, "percentage": 100.0, "elapsed_time": "5:17:44", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1498 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9952038369304557,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009592326139088728,
+      "grad_norm": 5.463140487670898,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 0.8413,
+      "step": 1
+    },
+    {
+      "epoch": 0.019184652278177457,
+      "grad_norm": 5.583210468292236,
+      "learning_rate": 1.904761904761905e-06,
+      "loss": 0.8899,
+      "step": 2
+    },
+    {
+      "epoch": 0.02877697841726619,
+      "grad_norm": 5.741968154907227,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.8986,
+      "step": 3
+    },
+    {
+      "epoch": 0.03836930455635491,
+      "grad_norm": 5.1438140869140625,
+      "learning_rate": 3.80952380952381e-06,
+      "loss": 0.8766,
+      "step": 4
+    },
+    {
+      "epoch": 0.047961630695443645,
+      "grad_norm": 4.009731292724609,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.8245,
+      "step": 5
+    },
+    {
+      "epoch": 0.05755395683453238,
+      "grad_norm": 2.5350778102874756,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.839,
+      "step": 6
+    },
+    {
+      "epoch": 0.0671462829736211,
+      "grad_norm": 2.255117416381836,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.7857,
+      "step": 7
+    },
+    {
+      "epoch": 0.07673860911270983,
+      "grad_norm": 4.770721435546875,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 0.7935,
+      "step": 8
+    },
+    {
+      "epoch": 0.08633093525179857,
+      "grad_norm": 5.30348539352417,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.8195,
+      "step": 9
+    },
+    {
+      "epoch": 0.09592326139088729,
+      "grad_norm": 4.574321746826172,
+      "learning_rate": 9.523809523809525e-06,
+      "loss": 0.7268,
+      "step": 10
+    },
+    {
+      "epoch": 0.10551558752997602,
+      "grad_norm": 5.198180675506592,
+      "learning_rate": 1.0476190476190477e-05,
+      "loss": 0.7487,
+      "step": 11
+    },
+    {
+      "epoch": 0.11510791366906475,
+      "grad_norm": 3.5458109378814697,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 0.7149,
+      "step": 12
+    },
+    {
+      "epoch": 0.12470023980815348,
+      "grad_norm": 2.4721553325653076,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 0.7312,
+      "step": 13
+    },
+    {
+      "epoch": 0.1342925659472422,
+      "grad_norm": 2.6414973735809326,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.709,
+      "step": 14
+    },
+    {
+      "epoch": 0.14388489208633093,
+      "grad_norm": 2.932861328125,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.6828,
+      "step": 15
+    },
+    {
+      "epoch": 0.15347721822541965,
+      "grad_norm": 2.295720100402832,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 0.6861,
+      "step": 16
+    },
+    {
+      "epoch": 0.1630695443645084,
+      "grad_norm": 1.6587889194488525,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.6665,
+      "step": 17
+    },
+    {
+      "epoch": 0.17266187050359713,
+      "grad_norm": 1.7021684646606445,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.6522,
+      "step": 18
+    },
+    {
+      "epoch": 0.18225419664268586,
+      "grad_norm": 1.632843255996704,
+      "learning_rate": 1.8095238095238097e-05,
+      "loss": 0.6865,
+      "step": 19
+    },
+    {
+      "epoch": 0.19184652278177458,
+      "grad_norm": 1.1444873809814453,
+      "learning_rate": 1.904761904761905e-05,
+      "loss": 0.6201,
+      "step": 20
+    },
+    {
+      "epoch": 0.2014388489208633,
+      "grad_norm": 1.109742522239685,
+      "learning_rate": 2e-05,
+      "loss": 0.6356,
+      "step": 21
+    },
+    {
+      "epoch": 0.21103117505995203,
+      "grad_norm": 1.2274072170257568,
+      "learning_rate": 1.9998588839790777e-05,
+      "loss": 0.6532,
+      "step": 22
+    },
+    {
+      "epoch": 0.22062350119904076,
+      "grad_norm": 0.9234100580215454,
+      "learning_rate": 1.999435575743774e-05,
+      "loss": 0.6073,
+      "step": 23
+    },
+    {
+      "epoch": 0.2302158273381295,
+      "grad_norm": 0.8935877084732056,
+      "learning_rate": 1.9987301947652354e-05,
+      "loss": 0.6342,
+      "step": 24
+    },
+    {
+      "epoch": 0.23980815347721823,
+      "grad_norm": 0.9229422211647034,
+      "learning_rate": 1.9977429401245764e-05,
+      "loss": 0.6402,
+      "step": 25
+    },
+    {
+      "epoch": 0.24940047961630696,
+      "grad_norm": 0.9000350832939148,
+      "learning_rate": 1.9964740904566903e-05,
+      "loss": 0.6104,
+      "step": 26
+    },
+    {
+      "epoch": 0.2589928057553957,
+      "grad_norm": 0.7615777850151062,
+      "learning_rate": 1.9949240038716092e-05,
+      "loss": 0.5895,
+      "step": 27
+    },
+    {
+      "epoch": 0.2685851318944844,
+      "grad_norm": 0.7478572726249695,
+      "learning_rate": 1.9930931178534353e-05,
+      "loss": 0.5959,
+      "step": 28
+    },
+    {
+      "epoch": 0.27817745803357313,
+      "grad_norm": 0.8021923303604126,
+      "learning_rate": 1.9909819491368677e-05,
+      "loss": 0.5908,
+      "step": 29
+    },
+    {
+      "epoch": 0.28776978417266186,
+      "grad_norm": 0.9070956110954285,
+      "learning_rate": 1.988591093561364e-05,
+      "loss": 0.607,
+      "step": 30
+    },
+    {
+      "epoch": 0.2973621103117506,
+      "grad_norm": 0.7348839044570923,
+      "learning_rate": 1.985921225902975e-05,
+      "loss": 0.6049,
+      "step": 31
+    },
+    {
+      "epoch": 0.3069544364508393,
+      "grad_norm": 0.8037014603614807,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 0.5783,
+      "step": 32
+    },
+    {
+      "epoch": 0.31654676258992803,
+      "grad_norm": 0.9512137174606323,
+      "learning_rate": 1.9797475469598267e-05,
+      "loss": 0.5838,
+      "step": 33
+    },
+    {
+      "epoch": 0.3261390887290168,
+      "grad_norm": 0.8966214060783386,
+      "learning_rate": 1.9762454780850807e-05,
+      "loss": 0.5764,
+      "step": 34
+    },
+    {
+      "epoch": 0.33573141486810554,
+      "grad_norm": 1.0402454137802124,
+      "learning_rate": 1.972467881455713e-05,
+      "loss": 0.5966,
+      "step": 35
+    },
+    {
+      "epoch": 0.34532374100719426,
+      "grad_norm": 0.934277355670929,
+      "learning_rate": 1.968415823230534e-05,
+      "loss": 0.5835,
+      "step": 36
+    },
+    {
+      "epoch": 0.354916067146283,
+      "grad_norm": 0.8191694617271423,
+      "learning_rate": 1.96409044703021e-05,
+      "loss": 0.5588,
+      "step": 37
+    },
+    {
+      "epoch": 0.3645083932853717,
+      "grad_norm": 1.1408041715621948,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 0.6096,
+      "step": 38
+    },
+    {
+      "epoch": 0.37410071942446044,
+      "grad_norm": 0.816935122013092,
+      "learning_rate": 1.9546247005377065e-05,
+      "loss": 0.5659,
+      "step": 39
+    },
+    {
+      "epoch": 0.38369304556354916,
+      "grad_norm": 2.111696481704712,
+      "learning_rate": 1.9494870017824877e-05,
+      "loss": 0.5525,
+      "step": 40
+    },
+    {
+      "epoch": 0.3932853717026379,
+      "grad_norm": 1.060172200202942,
+      "learning_rate": 1.9440813273720504e-05,
+      "loss": 0.552,
+      "step": 41
+    },
+    {
+      "epoch": 0.4028776978417266,
+      "grad_norm": 0.9724858999252319,
+      "learning_rate": 1.938409202960922e-05,
+      "loss": 0.5368,
+      "step": 42
+    },
+    {
+      "epoch": 0.41247002398081534,
+      "grad_norm": 1.1475540399551392,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 0.5808,
+      "step": 43
+    },
+    {
+      "epoch": 0.42206235011990406,
+      "grad_norm": 1.071284532546997,
+      "learning_rate": 1.9262720823065217e-05,
+      "loss": 0.5886,
+      "step": 44
+    },
+    {
+      "epoch": 0.4316546762589928,
+      "grad_norm": 1.001071572303772,
+      "learning_rate": 1.9198105115475946e-05,
+      "loss": 0.5622,
+      "step": 45
+    },
+    {
+      "epoch": 0.4412470023980815,
+      "grad_norm": 0.9534435272216797,
+      "learning_rate": 1.9130893407898834e-05,
+      "loss": 0.5744,
+      "step": 46
+    },
+    {
+      "epoch": 0.45083932853717024,
+      "grad_norm": 0.8966878652572632,
+      "learning_rate": 1.9061104669631343e-05,
+      "loss": 0.5542,
+      "step": 47
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 1.213246464729309,
+      "learning_rate": 1.8988758597291577e-05,
+      "loss": 0.5806,
+      "step": 48
+    },
+    {
+      "epoch": 0.47002398081534774,
+      "grad_norm": 0.7803760766983032,
+      "learning_rate": 1.8913875609259246e-05,
+      "loss": 0.5425,
+      "step": 49
+    },
+    {
+      "epoch": 0.47961630695443647,
+      "grad_norm": 0.7918503284454346,
+      "learning_rate": 1.8836476839912967e-05,
+      "loss": 0.5607,
+      "step": 50
+    },
+    {
+      "epoch": 0.4892086330935252,
+      "grad_norm": 1.1437450647354126,
+      "learning_rate": 1.8756584133665447e-05,
+      "loss": 0.5745,
+      "step": 51
+    },
+    {
+      "epoch": 0.4988009592326139,
+      "grad_norm": 0.8342698216438293,
+      "learning_rate": 1.86742200387983e-05,
+      "loss": 0.5752,
+      "step": 52
+    },
+    {
+      "epoch": 0.5083932853717026,
+      "grad_norm": 0.7877181172370911,
+      "learning_rate": 1.8589407801098192e-05,
+      "loss": 0.5151,
+      "step": 53
+    },
+    {
+      "epoch": 0.5179856115107914,
+      "grad_norm": 0.8752153515815735,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 0.5622,
+      "step": 54
+    },
+    {
+      "epoch": 0.5275779376498801,
+      "grad_norm": 0.8533386588096619,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 0.5735,
+      "step": 55
+    },
+    {
+      "epoch": 0.5371702637889688,
+      "grad_norm": 0.7831606864929199,
+      "learning_rate": 1.8320525012304685e-05,
+      "loss": 0.5369,
+      "step": 56
+    },
+    {
+      "epoch": 0.5467625899280576,
+      "grad_norm": 0.5700156092643738,
+      "learning_rate": 1.8226166377534113e-05,
+      "loss": 0.5405,
+      "step": 57
+    },
+    {
+      "epoch": 0.5563549160671463,
+      "grad_norm": 0.8519093990325928,
+      "learning_rate": 1.8129486055030255e-05,
+      "loss": 0.5775,
+      "step": 58
+    },
+    {
+      "epoch": 0.565947242206235,
+      "grad_norm": 0.6054497957229614,
+      "learning_rate": 1.8030511331077945e-05,
+      "loss": 0.509,
+      "step": 59
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.8640238642692566,
+      "learning_rate": 1.7929270139515606e-05,
+      "loss": 0.5459,
+      "step": 60
+    },
+    {
+      "epoch": 0.5851318944844125,
+      "grad_norm": 0.6853044629096985,
+      "learning_rate": 1.782579105385145e-05,
+      "loss": 0.5221,
+      "step": 61
+    },
+    {
+      "epoch": 0.5947242206235012,
+      "grad_norm": 0.7154713273048401,
+      "learning_rate": 1.772010327919912e-05,
+      "loss": 0.5693,
+      "step": 62
+    },
+    {
+      "epoch": 0.60431654676259,
+      "grad_norm": 0.7710362672805786,
+      "learning_rate": 1.761223664403505e-05,
+      "loss": 0.5564,
+      "step": 63
+    },
+    {
+      "epoch": 0.6139088729016786,
+      "grad_norm": 0.7269302010536194,
+      "learning_rate": 1.7502221591779932e-05,
+      "loss": 0.546,
+      "step": 64
+    },
+    {
+      "epoch": 0.6235011990407674,
+      "grad_norm": 0.8431626558303833,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 0.5632,
+      "step": 65
+    },
+    {
+      "epoch": 0.6330935251798561,
+      "grad_norm": 0.6030045747756958,
+      "learning_rate": 1.727587103267677e-05,
+      "loss": 0.5555,
+      "step": 66
+    },
+    {
+      "epoch": 0.6426858513189448,
+      "grad_norm": 0.8990049958229065,
+      "learning_rate": 1.7159599409209194e-05,
+      "loss": 0.5945,
+      "step": 67
+    },
+    {
+      "epoch": 0.6522781774580336,
+      "grad_norm": 0.6241750717163086,
+      "learning_rate": 1.704130711738157e-05,
+      "loss": 0.4992,
+      "step": 68
+    },
+    {
+      "epoch": 0.6618705035971223,
+      "grad_norm": 0.8116146326065063,
+      "learning_rate": 1.692102754306895e-05,
+      "loss": 0.5502,
+      "step": 69
+    },
+    {
+      "epoch": 0.6714628297362111,
+      "grad_norm": 0.6331062316894531,
+      "learning_rate": 1.6798794633021192e-05,
+      "loss": 0.5459,
+      "step": 70
+    },
+    {
+      "epoch": 0.6810551558752997,
+      "grad_norm": 0.8457932472229004,
+      "learning_rate": 1.667464288528207e-05,
+      "loss": 0.5545,
+      "step": 71
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.7906983494758606,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 0.5409,
+      "step": 72
+    },
+    {
+      "epoch": 0.7002398081534772,
+      "grad_norm": 0.6743340492248535,
+      "learning_rate": 1.6420723566802982e-05,
+      "loss": 0.5388,
+      "step": 73
+    },
+    {
+      "epoch": 0.709832134292566,
+      "grad_norm": 0.6750152111053467,
+      "learning_rate": 1.6291027660230735e-05,
+      "loss": 0.549,
+      "step": 74
+    },
+    {
+      "epoch": 0.7194244604316546,
+      "grad_norm": 0.6285757422447205,
+      "learning_rate": 1.6159556224076637e-05,
+      "loss": 0.5277,
+      "step": 75
+    },
+    {
+      "epoch": 0.7290167865707434,
+      "grad_norm": 0.857350766658783,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 0.5637,
+      "step": 76
+    },
+    {
+      "epoch": 0.7386091127098321,
+      "grad_norm": 0.5904400944709778,
+      "learning_rate": 1.5891435675469376e-05,
+      "loss": 0.562,
+      "step": 77
+    },
+    {
+      "epoch": 0.7482014388489209,
+      "grad_norm": 0.6850619316101074,
+      "learning_rate": 1.57548622352261e-05,
+      "loss": 0.5617,
+      "step": 78
+    },
+    {
+      "epoch": 0.7577937649880095,
+      "grad_norm": 0.723716676235199,
+      "learning_rate": 1.561666458846365e-05,
+      "loss": 0.5431,
+      "step": 79
+    },
+    {
+      "epoch": 0.7673860911270983,
+      "grad_norm": 0.8396223783493042,
+      "learning_rate": 1.5476881738986037e-05,
+      "loss": 0.5598,
+      "step": 80
+    },
+    {
+      "epoch": 0.7769784172661871,
+      "grad_norm": 0.5982377529144287,
+      "learning_rate": 1.5335553137992286e-05,
+      "loss": 0.5075,
+      "step": 81
+    },
+    {
+      "epoch": 0.7865707434052758,
+      "grad_norm": 0.6610307693481445,
+      "learning_rate": 1.519271867294203e-05,
+      "loss": 0.531,
+      "step": 82
+    },
+    {
+      "epoch": 0.7961630695443646,
+      "grad_norm": 0.7004625201225281,
+      "learning_rate": 1.504841865629799e-05,
+      "loss": 0.5838,
+      "step": 83
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.6314057111740112,
+      "learning_rate": 1.490269381414849e-05,
+      "loss": 0.5844,
+      "step": 84
+    },
+    {
+      "epoch": 0.815347721822542,
+      "grad_norm": 0.6121094822883606,
+      "learning_rate": 1.4755585274713289e-05,
+      "loss": 0.5258,
+      "step": 85
+    },
+    {
+      "epoch": 0.8249400479616307,
+      "grad_norm": 0.5207806825637817,
+      "learning_rate": 1.4607134556735836e-05,
+      "loss": 0.5028,
+      "step": 86
+    },
+    {
+      "epoch": 0.8345323741007195,
+      "grad_norm": 0.7948092818260193,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 0.5728,
+      "step": 87
+    },
+    {
+      "epoch": 0.8441247002398081,
+      "grad_norm": 0.5630785822868347,
+      "learning_rate": 1.4306374542332141e-05,
+      "loss": 0.5434,
+      "step": 88
+    },
+    {
+      "epoch": 0.8537170263788969,
+      "grad_norm": 0.7460189461708069,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 0.5308,
+      "step": 89
+    },
+    {
+      "epoch": 0.8633093525179856,
+      "grad_norm": 0.5590621829032898,
+      "learning_rate": 1.4000753283432267e-05,
+      "loss": 0.5664,
+      "step": 90
+    },
+    {
+      "epoch": 0.8729016786570744,
+      "grad_norm": 0.6667270660400391,
+      "learning_rate": 1.3846227296077568e-05,
+      "loss": 0.5509,
+      "step": 91
+    },
+    {
+      "epoch": 0.882494004796163,
+      "grad_norm": 0.6306936740875244,
+      "learning_rate": 1.3690615780139703e-05,
+      "loss": 0.5217,
+      "step": 92
+    },
+    {
+      "epoch": 0.8920863309352518,
+      "grad_norm": 0.5348330736160278,
+      "learning_rate": 1.3533962654174542e-05,
+      "loss": 0.5502,
+      "step": 93
+    },
+    {
+      "epoch": 0.9016786570743405,
+      "grad_norm": 0.6074246764183044,
+      "learning_rate": 1.337631213071369e-05,
+      "loss": 0.5284,
+      "step": 94
+    },
+    {
+      "epoch": 0.9112709832134293,
+      "grad_norm": 0.5508787631988525,
+      "learning_rate": 1.321770870378628e-05,
+      "loss": 0.5374,
+      "step": 95
+    },
+    {
+      "epoch": 0.920863309352518,
+      "grad_norm": 0.5803295373916626,
+      "learning_rate": 1.3058197136361344e-05,
+      "loss": 0.5362,
+      "step": 96
+    },
+    {
+      "epoch": 0.9304556354916067,
+      "grad_norm": 0.6018428206443787,
+      "learning_rate": 1.2897822447714247e-05,
+      "loss": 0.5427,
+      "step": 97
+    },
+    {
+      "epoch": 0.9400479616306955,
+      "grad_norm": 0.6748164892196655,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 0.5195,
+      "step": 98
+    },
+    {
+      "epoch": 0.9496402877697842,
+      "grad_norm": 0.5500775575637817,
+      "learning_rate": 1.257466498908276e-05,
+      "loss": 0.5356,
+      "step": 99
+    },
+    {
+      "epoch": 0.9592326139088729,
+      "grad_norm": 0.6489828824996948,
+      "learning_rate": 1.2411973424487751e-05,
+      "loss": 0.5594,
+      "step": 100
+    },
+    {
+      "epoch": 0.9688249400479616,
+      "grad_norm": 0.6224409937858582,
+      "learning_rate": 1.2248601123708279e-05,
+      "loss": 0.542,
+      "step": 101
+    },
+    {
+      "epoch": 0.9784172661870504,
+      "grad_norm": 0.5973473787307739,
+      "learning_rate": 1.2084594195642367e-05,
+      "loss": 0.5407,
+      "step": 102
+    },
+    {
+      "epoch": 0.988009592326139,
+      "grad_norm": 0.6067144274711609,
+      "learning_rate": 1.1919998928300203e-05,
+      "loss": 0.5394,
+      "step": 103
+    },
+    {
+      "epoch": 0.9976019184652278,
+      "grad_norm": 0.6564667820930481,
+      "learning_rate": 1.1754861775740163e-05,
+      "loss": 0.5681,
+      "step": 104
+    },
+    {
+      "epoch": 1.0071942446043165,
+      "grad_norm": 1.2927284240722656,
+      "learning_rate": 1.1589229344958e-05,
+      "loss": 0.8402,
+      "step": 105
+    },
+    {
+      "epoch": 1.0167865707434052,
+      "grad_norm": 0.5975750684738159,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 0.4084,
+      "step": 106
+    },
+    {
+      "epoch": 1.026378896882494,
+      "grad_norm": 0.8134109973907471,
+      "learning_rate": 1.1256665762433798e-05,
+      "loss": 0.4635,
+      "step": 107
+    },
+    {
+      "epoch": 1.0359712230215827,
+      "grad_norm": 0.6802660226821899,
+      "learning_rate": 1.1089828470790694e-05,
+      "loss": 0.4702,
+      "step": 108
+    },
+    {
+      "epoch": 1.0455635491606714,
+      "grad_norm": 0.776054859161377,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 0.5416,
+      "step": 109
+    },
+    {
+      "epoch": 1.0551558752997603,
+      "grad_norm": 0.8164082765579224,
+      "learning_rate": 1.0755278307600459e-05,
+      "loss": 0.4767,
+      "step": 110
+    },
+    {
+      "epoch": 1.064748201438849,
+      "grad_norm": 0.5975356698036194,
+      "learning_rate": 1.058765985682898e-05,
+      "loss": 0.4414,
+      "step": 111
+    },
+    {
+      "epoch": 1.0743405275779376,
+      "grad_norm": 0.6108450293540955,
+      "learning_rate": 1.0419875549616196e-05,
+      "loss": 0.4378,
+      "step": 112
+    },
+    {
+      "epoch": 1.0839328537170263,
+      "grad_norm": 0.6446887850761414,
+      "learning_rate": 1.0251972740069724e-05,
+      "loss": 0.5092,
+      "step": 113
+    },
+    {
+      "epoch": 1.0935251798561152,
+      "grad_norm": 0.6943943500518799,
+      "learning_rate": 1.0083998815742335e-05,
+      "loss": 0.4518,
+      "step": 114
+    },
+    {
+      "epoch": 1.1031175059952039,
+      "grad_norm": 0.6275978088378906,
+      "learning_rate": 9.916001184257668e-06,
+      "loss": 0.4128,
+      "step": 115
+    },
+    {
+      "epoch": 1.1127098321342925,
+      "grad_norm": 0.6340152621269226,
+      "learning_rate": 9.748027259930276e-06,
+      "loss": 0.4915,
+      "step": 116
+    },
+    {
+      "epoch": 1.1223021582733812,
+      "grad_norm": 0.8123753070831299,
+      "learning_rate": 9.580124450383804e-06,
+      "loss": 0.5308,
+      "step": 117
+    },
+    {
+      "epoch": 1.13189448441247,
+      "grad_norm": 0.8013598322868347,
+      "learning_rate": 9.412340143171025e-06,
+      "loss": 0.4496,
+      "step": 118
+    },
+    {
+      "epoch": 1.1414868105515588,
+      "grad_norm": 0.7643545866012573,
+      "learning_rate": 9.244721692399545e-06,
+      "loss": 0.4636,
+      "step": 119
+    },
+    {
+      "epoch": 1.1510791366906474,
+      "grad_norm": 0.6572363972663879,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 0.4587,
+      "step": 120
+    },
+    {
+      "epoch": 1.160671462829736,
+      "grad_norm": 0.624904453754425,
+      "learning_rate": 8.910171529209306e-06,
+      "loss": 0.452,
+      "step": 121
+    },
+    {
+      "epoch": 1.170263788968825,
+      "grad_norm": 0.7192939519882202,
+      "learning_rate": 8.743334237566202e-06,
+      "loss": 0.5034,
+      "step": 122
+    },
+    {
+      "epoch": 1.1798561151079137,
+      "grad_norm": 0.7390738129615784,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 0.4566,
+      "step": 123
+    },
+    {
+      "epoch": 1.1894484412470023,
+      "grad_norm": 0.5554519295692444,
+      "learning_rate": 8.410770655042003e-06,
+      "loss": 0.4569,
+      "step": 124
+    },
+    {
+      "epoch": 1.1990407673860912,
+      "grad_norm": 0.71725994348526,
+      "learning_rate": 8.24513822425984e-06,
+      "loss": 0.509,
+      "step": 125
+    },
+    {
+      "epoch": 1.20863309352518,
+      "grad_norm": 0.5959192514419556,
+      "learning_rate": 8.0800010716998e-06,
+      "loss": 0.4554,
+      "step": 126
+    },
+    {
+      "epoch": 1.2182254196642686,
+      "grad_norm": 0.593908965587616,
+      "learning_rate": 7.915405804357632e-06,
+      "loss": 0.4381,
+      "step": 127
+    },
+    {
+      "epoch": 1.2278177458033572,
+      "grad_norm": 0.5293657779693604,
+      "learning_rate": 7.751398876291725e-06,
+      "loss": 0.4517,
+      "step": 128
+    },
+    {
+      "epoch": 1.2374100719424461,
+      "grad_norm": 0.6665202379226685,
+      "learning_rate": 7.58802657551225e-06,
+      "loss": 0.5156,
+      "step": 129
+    },
+    {
+      "epoch": 1.2470023980815348,
+      "grad_norm": 0.6169362664222717,
+      "learning_rate": 7.425335010917244e-06,
+      "loss": 0.4501,
+      "step": 130
+    },
+    {
+      "epoch": 1.2565947242206235,
+      "grad_norm": 0.6470293402671814,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 0.5551,
+      "step": 131
+    },
+    {
+      "epoch": 1.2661870503597124,
+      "grad_norm": 0.4676002562046051,
+      "learning_rate": 7.102177552285753e-06,
+      "loss": 0.4076,
+      "step": 132
+    },
+    {
+      "epoch": 1.275779376498801,
+      "grad_norm": 0.5901790261268616,
+      "learning_rate": 6.9418028636386595e-06,
+      "loss": 0.4547,
+      "step": 133
+    },
+    {
+      "epoch": 1.2853717026378897,
+      "grad_norm": 0.5097313523292542,
+      "learning_rate": 6.7822912962137225e-06,
+      "loss": 0.4673,
+      "step": 134
+    },
+    {
+      "epoch": 1.2949640287769784,
+      "grad_norm": 0.5144338011741638,
+      "learning_rate": 6.623687869286314e-06,
+      "loss": 0.4789,
+      "step": 135
+    },
+    {
+      "epoch": 1.304556354916067,
+      "grad_norm": 0.4996054768562317,
+      "learning_rate": 6.466037345825462e-06,
+      "loss": 0.4581,
+      "step": 136
+    },
+    {
+      "epoch": 1.314148681055156,
+      "grad_norm": 0.42683184146881104,
+      "learning_rate": 6.3093842198603014e-06,
+      "loss": 0.4581,
+      "step": 137
+    },
+    {
+      "epoch": 1.3237410071942446,
+      "grad_norm": 0.5013344883918762,
+      "learning_rate": 6.153772703922434e-06,
+      "loss": 0.4402,
+      "step": 138
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.55416339635849,
+      "learning_rate": 5.999246716567737e-06,
+      "loss": 0.4542,
+      "step": 139
+    },
+    {
+      "epoch": 1.3429256594724222,
+      "grad_norm": 0.5039543509483337,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 0.4522,
+      "step": 140
+    },
+    {
+      "epoch": 1.3525179856115108,
+      "grad_norm": 0.4409497380256653,
+      "learning_rate": 5.693625457667862e-06,
+      "loss": 0.42,
+      "step": 141
+    },
+    {
+      "epoch": 1.3621103117505995,
+      "grad_norm": 0.5174093842506409,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 0.4896,
+      "step": 142
+    },
+    {
+      "epoch": 1.3717026378896882,
+      "grad_norm": 0.46308115124702454,
+      "learning_rate": 5.392865443264164e-06,
+      "loss": 0.4754,
+      "step": 143
+    },
+    {
+      "epoch": 1.381294964028777,
+      "grad_norm": 0.47446274757385254,
+      "learning_rate": 5.244414725286717e-06,
+      "loss": 0.4778,
+      "step": 144
+    },
+    {
+      "epoch": 1.3908872901678657,
+      "grad_norm": 0.49401265382766724,
+      "learning_rate": 5.097306185851515e-06,
+      "loss": 0.4799,
+      "step": 145
+    },
+    {
+      "epoch": 1.4004796163069544,
+      "grad_norm": 0.4623788297176361,
+      "learning_rate": 4.951581343702014e-06,
+      "loss": 0.4485,
+      "step": 146
+    },
+    {
+      "epoch": 1.4100719424460433,
+      "grad_norm": 0.570754885673523,
+      "learning_rate": 4.807281327057972e-06,
+      "loss": 0.4715,
+      "step": 147
+    },
+    {
+      "epoch": 1.419664268585132,
+      "grad_norm": 0.41729313135147095,
+      "learning_rate": 4.664446862007718e-06,
+      "loss": 0.4358,
+      "step": 148
+    },
+    {
+      "epoch": 1.4292565947242206,
+      "grad_norm": 0.47093185782432556,
+      "learning_rate": 4.523118261013969e-06,
+      "loss": 0.5265,
+      "step": 149
+    },
+    {
+      "epoch": 1.4388489208633093,
+      "grad_norm": 0.5182215571403503,
+      "learning_rate": 4.383335411536357e-06,
+      "loss": 0.4388,
+      "step": 150
+    },
+    {
+      "epoch": 1.448441247002398,
+      "grad_norm": 0.4269079267978668,
+      "learning_rate": 4.245137764773899e-06,
+      "loss": 0.4611,
+      "step": 151
+    },
+    {
+      "epoch": 1.4580335731414868,
+      "grad_norm": 0.37275925278663635,
+      "learning_rate": 4.108564324530626e-06,
+      "loss": 0.4364,
+      "step": 152
+    },
+    {
+      "epoch": 1.4676258992805755,
+      "grad_norm": 0.4746614098548889,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 0.5079,
+      "step": 153
+    },
+    {
+      "epoch": 1.4772182254196642,
+      "grad_norm": 0.4228520393371582,
+      "learning_rate": 3.840443775923365e-06,
+      "loss": 0.4235,
+      "step": 154
+    },
+    {
+      "epoch": 1.486810551558753,
+      "grad_norm": 0.4543722867965698,
+      "learning_rate": 3.70897233976927e-06,
+      "loss": 0.4592,
+      "step": 155
+    },
+    {
+      "epoch": 1.4964028776978417,
+      "grad_norm": 0.4404360353946686,
+      "learning_rate": 3.5792764331970187e-06,
+      "loss": 0.4623,
+      "step": 156
+    },
+    {
+      "epoch": 1.5059952038369304,
+      "grad_norm": 0.4294821619987488,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 0.4361,
+      "step": 157
+    },
+    {
+      "epoch": 1.515587529976019,
+      "grad_norm": 0.4436289966106415,
+      "learning_rate": 3.3253571147179333e-06,
+      "loss": 0.4034,
+      "step": 158
+    },
+    {
+      "epoch": 1.5251798561151078,
+      "grad_norm": 0.5218536853790283,
+      "learning_rate": 3.2012053669788136e-06,
+      "loss": 0.5412,
+      "step": 159
+    },
+    {
+      "epoch": 1.5347721822541966,
+      "grad_norm": 0.44115403294563293,
+      "learning_rate": 3.0789724569310532e-06,
+      "loss": 0.5193,
+      "step": 160
+    },
+    {
+      "epoch": 1.5443645083932853,
+      "grad_norm": 0.34902071952819824,
+      "learning_rate": 2.9586928826184323e-06,
+      "loss": 0.3989,
+      "step": 161
+    },
+    {
+      "epoch": 1.5539568345323742,
+      "grad_norm": 0.41857436299324036,
+      "learning_rate": 2.8404005907908083e-06,
+      "loss": 0.495,
+      "step": 162
+    },
+    {
+      "epoch": 1.5635491606714629,
+      "grad_norm": 0.47862207889556885,
+      "learning_rate": 2.724128967323234e-06,
+      "loss": 0.4592,
+      "step": 163
+    },
+    {
+      "epoch": 1.5731414868105515,
+      "grad_norm": 0.4449855089187622,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 0.5052,
+      "step": 164
+    },
+    {
+      "epoch": 1.5827338129496402,
+      "grad_norm": 0.41668611764907837,
+      "learning_rate": 2.4977784082200728e-06,
+      "loss": 0.4581,
+      "step": 165
+    },
+    {
+      "epoch": 1.5923261390887289,
+      "grad_norm": 0.40094488859176636,
+      "learning_rate": 2.3877633559649505e-06,
+      "loss": 0.4616,
+      "step": 166
+    },
+    {
+      "epoch": 1.6019184652278178,
+      "grad_norm": 0.3881120979785919,
+      "learning_rate": 2.2798967208008806e-06,
+      "loss": 0.4446,
+      "step": 167
+    },
+    {
+      "epoch": 1.6115107913669064,
+      "grad_norm": 0.4159110188484192,
+      "learning_rate": 2.1742089461485504e-06,
+      "loss": 0.4786,
+      "step": 168
+    },
+    {
+      "epoch": 1.6211031175059953,
+      "grad_norm": 0.4027980864048004,
+      "learning_rate": 2.0707298604843964e-06,
+      "loss": 0.4576,
+      "step": 169
+    },
+    {
+      "epoch": 1.630695443645084,
+      "grad_norm": 0.384933739900589,
+      "learning_rate": 1.9694886689220592e-06,
+      "loss": 0.4435,
+      "step": 170
+    },
+    {
+      "epoch": 1.6402877697841727,
+      "grad_norm": 0.40097036957740784,
+      "learning_rate": 1.870513944969743e-06,
+      "loss": 0.504,
+      "step": 171
+    },
+    {
+      "epoch": 1.6498800959232613,
+      "grad_norm": 0.36205577850341797,
+      "learning_rate": 1.773833622465888e-06,
+      "loss": 0.4355,
+      "step": 172
+    },
+    {
+      "epoch": 1.65947242206235,
+      "grad_norm": 0.41958150267601013,
+      "learning_rate": 1.6794749876953187e-06,
+      "loss": 0.4532,
+      "step": 173
+    },
+    {
+      "epoch": 1.6690647482014387,
+      "grad_norm": 0.4185022711753845,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 0.5107,
+      "step": 174
+    },
+    {
+      "epoch": 1.6786570743405276,
+      "grad_norm": 0.35726451873779297,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 0.456,
+      "step": 175
+    },
+    {
+      "epoch": 1.6882494004796165,
+      "grad_norm": 0.37981709837913513,
+      "learning_rate": 1.4105921989018112e-06,
+      "loss": 0.4294,
+      "step": 176
+    },
+    {
+      "epoch": 1.6978417266187051,
+      "grad_norm": 0.40331578254699707,
+      "learning_rate": 1.325779961201703e-06,
+      "loss": 0.4907,
+      "step": 177
+    },
+    {
+      "epoch": 1.7074340527577938,
+      "grad_norm": 0.35114678740501404,
+      "learning_rate": 1.2434158663345553e-06,
+      "loss": 0.3882,
+      "step": 178
+    },
+    {
+      "epoch": 1.7170263788968825,
+      "grad_norm": 0.4186091423034668,
+      "learning_rate": 1.1635231600870334e-06,
+      "loss": 0.4902,
+      "step": 179
+    },
+    {
+      "epoch": 1.7266187050359711,
+      "grad_norm": 0.38715124130249023,
+      "learning_rate": 1.086124390740757e-06,
+      "loss": 0.4223,
+      "step": 180
+    },
+    {
+      "epoch": 1.7362110311750598,
+      "grad_norm": 0.40617579221725464,
+      "learning_rate": 1.0112414027084262e-06,
+      "loss": 0.4593,
+      "step": 181
+    },
+    {
+      "epoch": 1.7458033573141487,
+      "grad_norm": 0.40611231327056885,
+      "learning_rate": 9.388953303686587e-07,
+      "loss": 0.507,
+      "step": 182
+    },
+    {
+      "epoch": 1.7553956834532374,
+      "grad_norm": 0.3547835052013397,
+      "learning_rate": 8.691065921011687e-07,
+      "loss": 0.4046,
+      "step": 183
+    },
+    {
+      "epoch": 1.7649880095923263,
+      "grad_norm": 0.3677358329296112,
+      "learning_rate": 8.018948845240538e-07,
+      "loss": 0.4293,
+      "step": 184
+    },
+    {
+      "epoch": 1.774580335731415,
+      "grad_norm": 0.3933480978012085,
+      "learning_rate": 7.372791769347843e-07,
+      "loss": 0.4817,
+      "step": 185
+    },
+    {
+      "epoch": 1.7841726618705036,
+      "grad_norm": 0.3810149133205414,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 0.467,
+      "step": 186
+    },
+    {
+      "epoch": 1.7937649880095923,
+      "grad_norm": 0.36385539174079895,
+      "learning_rate": 6.159079703907823e-07,
+      "loss": 0.4007,
+      "step": 187
+    },
+    {
+      "epoch": 1.803357314148681,
+      "grad_norm": 0.38040924072265625,
+      "learning_rate": 5.591867262794969e-07,
+      "loss": 0.4383,
+      "step": 188
+    },
+    {
+      "epoch": 1.8129496402877698,
+      "grad_norm": 0.44325366616249084,
+      "learning_rate": 5.051299821751254e-07,
+      "loss": 0.4637,
+      "step": 189
+    },
+    {
+      "epoch": 1.8225419664268585,
+      "grad_norm": 0.4270748198032379,
+      "learning_rate": 4.537529946229369e-07,
+      "loss": 0.455,
+      "step": 190
+    },
+    {
+      "epoch": 1.8321342925659474,
+      "grad_norm": 0.36179426312446594,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 0.404,
+      "step": 191
+    },
+    {
+      "epoch": 1.841726618705036,
+      "grad_norm": 0.3940328061580658,
+      "learning_rate": 3.5909552969790376e-07,
+      "loss": 0.5082,
+      "step": 192
+    },
+    {
+      "epoch": 1.8513189448441247,
+      "grad_norm": 0.40083611011505127,
+      "learning_rate": 3.158417676946635e-07,
+      "loss": 0.4359,
+      "step": 193
+    },
+    {
+      "epoch": 1.8609112709832134,
+      "grad_norm": 0.36836743354797363,
+      "learning_rate": 2.753211854428728e-07,
+      "loss": 0.4456,
+      "step": 194
+    },
+    {
+      "epoch": 1.870503597122302,
+      "grad_norm": 0.40756598114967346,
+      "learning_rate": 2.375452191491967e-07,
+      "loss": 0.5353,
+      "step": 195
+    },
+    {
+      "epoch": 1.8800959232613907,
+      "grad_norm": 0.36624136567115784,
+      "learning_rate": 2.0252453040173646e-07,
+      "loss": 0.4546,
+      "step": 196
+    },
+    {
+      "epoch": 1.8896882494004796,
+      "grad_norm": 0.3642793297767639,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 0.4125,
+      "step": 197
+    },
+    {
+      "epoch": 1.8992805755395683,
+      "grad_norm": 0.3520798683166504,
+      "learning_rate": 1.407877409702496e-07,
+      "loss": 0.4024,
+      "step": 198
+    },
+    {
+      "epoch": 1.9088729016786572,
+      "grad_norm": 0.41250428557395935,
+      "learning_rate": 1.1408906438636236e-07,
+      "loss": 0.548,
+      "step": 199
+    },
+    {
+      "epoch": 1.9184652278177459,
+      "grad_norm": 0.3598795235157013,
+      "learning_rate": 9.018050863132566e-08,
+      "loss": 0.4678,
+      "step": 200
+    },
+    {
+      "epoch": 1.9280575539568345,
+      "grad_norm": 0.356637567281723,
+      "learning_rate": 6.906882146565097e-08,
+      "loss": 0.4359,
+      "step": 201
+    },
+    {
+      "epoch": 1.9376498800959232,
+      "grad_norm": 0.41162729263305664,
+      "learning_rate": 5.0759961283911584e-08,
+      "loss": 0.4864,
+      "step": 202
+    },
+    {
+      "epoch": 1.9472422062350119,
+      "grad_norm": 0.398189902305603,
+      "learning_rate": 3.525909543310002e-08,
+      "loss": 0.4142,
+      "step": 203
+    },
+    {
+      "epoch": 1.9568345323741008,
+      "grad_norm": 0.32942283153533936,
+      "learning_rate": 2.257059875423795e-08,
+      "loss": 0.4492,
+      "step": 204
+    },
+    {
+      "epoch": 1.9664268585131894,
+      "grad_norm": 0.34813541173934937,
+      "learning_rate": 1.2698052347649426e-08,
+      "loss": 0.4688,
+      "step": 205
+    },
+    {
+      "epoch": 1.9760191846522783,
+      "grad_norm": 0.3543734550476074,
+      "learning_rate": 5.644242562264923e-09,
+      "loss": 0.467,
+      "step": 206
+    },
+    {
+      "epoch": 1.985611510791367,
+      "grad_norm": 0.39353352785110474,
+      "learning_rate": 1.4111602092226062e-09,
+      "loss": 0.4595,
+      "step": 207
+    },
+    {
+      "epoch": 1.9952038369304557,
+      "grad_norm": 0.3904837667942047,
+      "learning_rate": 0.0,
+      "loss": 0.5022,
+      "step": 208
+    },
+    {
+      "epoch": 1.9952038369304557,
+      "step": 208,
+      "total_flos": 213263567486976.0,
+      "train_loss": 0.5326878637648546,
+      "train_runtime": 19065.5756,
+      "train_samples_per_second": 1.049,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 213263567486976.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:050748f5f2c9368955618810965664aa09a66c8def08d23a28b20109c35ae4f4
+size 7416