Add files using upload-large-folder tool

.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: MATH_training_response_Qwen2.5_32B
+  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. -->
+
+# MATH_training_response_Qwen2.5_32B
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the MATH_training_response_Qwen2.5_32B dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0895
+
+## 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- 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
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- 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 +1,12 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.08945156633853912,
+    "eval_runtime": 1.575,
+    "eval_samples_per_second": 3.809,
+    "eval_steps_per_second": 1.27,
+    "total_flos": 8781261963264.0,
+    "train_loss": 0.05639281026574213,
+    "train_runtime": 528.9145,
+    "train_samples_per_second": 2.0,
+    "train_steps_per_second": 0.253
+}

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
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.08945156633853912,
+    "eval_runtime": 1.575,
+    "eval_samples_per_second": 3.809,
+    "eval_steps_per_second": 1.27
+}

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 sha256:1e9dd198d7273dff50c8766e2030b27a5ddea6f2aff688d5f561c3706a8d2abd
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d6fdb0771615c6f68a7c162aa558be5d5aeba575882a913ded8e1373521911
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24514ab42065cdb10cb197ec050dc87c2e142e22835bcfddd64e3e758fa04ecd
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220e75313320fc0415f85e50277e1f6b4aec07c9e605aef9666623bb1f3844f6
+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": "<|im_end|>",
+    "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": "<|im_end|>",
+  "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": 2.0,
+    "total_flos": 8781261963264.0,
+    "train_loss": 0.05639281026574213,
+    "train_runtime": 528.9145,
+    "train_samples_per_second": 2.0,
+    "train_steps_per_second": 0.253
+}

trainer_log.jsonl

@@ -0,0 +1,135 @@
+{"current_steps": 1, "total_steps": 134, "loss": 0.1709, "lr": 9.99862592554908e-06, "epoch": 0.014925373134328358, "percentage": 0.75, "elapsed_time": "0:00:04", "remaining_time": "0:10:49"}
+{"current_steps": 2, "total_steps": 134, "loss": 0.1095, "lr": 9.994504457428557e-06, "epoch": 0.029850746268656716, "percentage": 1.49, "elapsed_time": "0:00:08", "remaining_time": "0:09:12"}
+{"current_steps": 3, "total_steps": 134, "loss": 0.1123, "lr": 9.987637860920053e-06, "epoch": 0.04477611940298507, "percentage": 2.24, "elapsed_time": "0:00:11", "remaining_time": "0:08:37"}
+{"current_steps": 4, "total_steps": 134, "loss": 0.0897, "lr": 9.978029910109491e-06, "epoch": 0.05970149253731343, "percentage": 2.99, "elapsed_time": "0:00:15", "remaining_time": "0:08:17"}
+{"current_steps": 5, "total_steps": 134, "loss": 0.0804, "lr": 9.965685885812773e-06, "epoch": 0.07462686567164178, "percentage": 3.73, "elapsed_time": "0:00:18", "remaining_time": "0:08:04"}
+{"current_steps": 6, "total_steps": 134, "loss": 0.1197, "lr": 9.950612572673255e-06, "epoch": 0.08955223880597014, "percentage": 4.48, "elapsed_time": "0:00:22", "remaining_time": "0:07:54"}
+{"current_steps": 7, "total_steps": 134, "loss": 0.1052, "lr": 9.932818255432733e-06, "epoch": 0.1044776119402985, "percentage": 5.22, "elapsed_time": "0:00:25", "remaining_time": "0:07:45"}
+{"current_steps": 8, "total_steps": 134, "loss": 0.09, "lr": 9.91231271437788e-06, "epoch": 0.11940298507462686, "percentage": 5.97, "elapsed_time": "0:00:29", "remaining_time": "0:07:38"}
+{"current_steps": 9, "total_steps": 134, "loss": 0.0847, "lr": 9.889107219964726e-06, "epoch": 0.13432835820895522, "percentage": 6.72, "elapsed_time": "0:00:32", "remaining_time": "0:07:32"}
+{"current_steps": 10, "total_steps": 134, "loss": 0.0899, "lr": 9.863214526624065e-06, "epoch": 0.14925373134328357, "percentage": 7.46, "elapsed_time": "0:00:36", "remaining_time": "0:07:27"}
+{"current_steps": 11, "total_steps": 134, "loss": 0.0885, "lr": 9.834648865751254e-06, "epoch": 0.16417910447761194, "percentage": 8.21, "elapsed_time": "0:00:39", "remaining_time": "0:07:22"}
+{"current_steps": 12, "total_steps": 134, "loss": 0.078, "lr": 9.803425937884202e-06, "epoch": 0.1791044776119403, "percentage": 8.96, "elapsed_time": "0:00:43", "remaining_time": "0:07:17"}
+{"current_steps": 13, "total_steps": 134, "loss": 0.0878, "lr": 9.769562904073896e-06, "epoch": 0.19402985074626866, "percentage": 9.7, "elapsed_time": "0:00:46", "remaining_time": "0:07:12"}
+{"current_steps": 14, "total_steps": 134, "loss": 0.0881, "lr": 9.733078376452172e-06, "epoch": 0.208955223880597, "percentage": 10.45, "elapsed_time": "0:00:49", "remaining_time": "0:07:08"}
+{"current_steps": 15, "total_steps": 134, "loss": 0.091, "lr": 9.693992408001934e-06, "epoch": 0.22388059701492538, "percentage": 11.19, "elapsed_time": "0:00:53", "remaining_time": "0:07:03"}
+{"current_steps": 16, "total_steps": 134, "loss": 0.0847, "lr": 9.652326481535434e-06, "epoch": 0.23880597014925373, "percentage": 11.94, "elapsed_time": "0:00:56", "remaining_time": "0:07:00"}
+{"current_steps": 17, "total_steps": 134, "loss": 0.0751, "lr": 9.608103497886687e-06, "epoch": 0.2537313432835821, "percentage": 12.69, "elapsed_time": "0:01:00", "remaining_time": "0:06:55"}
+{"current_steps": 18, "total_steps": 134, "loss": 0.0757, "lr": 9.561347763324484e-06, "epoch": 0.26865671641791045, "percentage": 13.43, "elapsed_time": "0:01:03", "remaining_time": "0:06:51"}
+{"current_steps": 19, "total_steps": 134, "loss": 0.0832, "lr": 9.512084976192944e-06, "epoch": 0.2835820895522388, "percentage": 14.18, "elapsed_time": "0:01:07", "remaining_time": "0:06:47"}
+{"current_steps": 20, "total_steps": 134, "loss": 0.0785, "lr": 9.460342212786933e-06, "epoch": 0.29850746268656714, "percentage": 14.93, "elapsed_time": "0:01:10", "remaining_time": "0:06:43"}
+{"current_steps": 21, "total_steps": 134, "loss": 0.0832, "lr": 9.406147912470142e-06, "epoch": 0.31343283582089554, "percentage": 15.67, "elapsed_time": "0:01:14", "remaining_time": "0:06:39"}
+{"current_steps": 22, "total_steps": 134, "loss": 0.0909, "lr": 9.349531862043952e-06, "epoch": 0.3283582089552239, "percentage": 16.42, "elapsed_time": "0:01:17", "remaining_time": "0:06:35"}
+{"current_steps": 23, "total_steps": 134, "loss": 0.0817, "lr": 9.290525179375722e-06, "epoch": 0.34328358208955223, "percentage": 17.16, "elapsed_time": "0:01:21", "remaining_time": "0:06:32"}
+{"current_steps": 24, "total_steps": 134, "loss": 0.0847, "lr": 9.229160296295488e-06, "epoch": 0.3582089552238806, "percentage": 17.91, "elapsed_time": "0:01:24", "remaining_time": "0:06:28"}
+{"current_steps": 25, "total_steps": 134, "loss": 0.0739, "lr": 9.165470940770458e-06, "epoch": 0.373134328358209, "percentage": 18.66, "elapsed_time": "0:01:28", "remaining_time": "0:06:24"}
+{"current_steps": 26, "total_steps": 134, "loss": 0.0861, "lr": 9.099492118367123e-06, "epoch": 0.3880597014925373, "percentage": 19.4, "elapsed_time": "0:01:31", "remaining_time": "0:06:21"}
+{"current_steps": 27, "total_steps": 134, "loss": 0.0943, "lr": 9.03126009301115e-06, "epoch": 0.40298507462686567, "percentage": 20.15, "elapsed_time": "0:01:35", "remaining_time": "0:06:17"}
+{"current_steps": 28, "total_steps": 134, "loss": 0.0892, "lr": 8.960812367055646e-06, "epoch": 0.417910447761194, "percentage": 20.9, "elapsed_time": "0:01:38", "remaining_time": "0:06:13"}
+{"current_steps": 29, "total_steps": 134, "loss": 0.0832, "lr": 8.888187660668762e-06, "epoch": 0.43283582089552236, "percentage": 21.64, "elapsed_time": "0:01:42", "remaining_time": "0:06:10"}
+{"current_steps": 30, "total_steps": 134, "loss": 0.0906, "lr": 8.81342589055191e-06, "epoch": 0.44776119402985076, "percentage": 22.39, "elapsed_time": "0:01:45", "remaining_time": "0:06:06"}
+{"current_steps": 31, "total_steps": 134, "loss": 0.0968, "lr": 8.736568148000386e-06, "epoch": 0.4626865671641791, "percentage": 23.13, "elapsed_time": "0:01:49", "remaining_time": "0:06:02"}
+{"current_steps": 32, "total_steps": 134, "loss": 0.0847, "lr": 8.657656676318346e-06, "epoch": 0.47761194029850745, "percentage": 23.88, "elapsed_time": "0:01:52", "remaining_time": "0:05:59"}
+{"current_steps": 33, "total_steps": 134, "loss": 0.0853, "lr": 8.576734847600639e-06, "epoch": 0.4925373134328358, "percentage": 24.63, "elapsed_time": "0:01:56", "remaining_time": "0:05:55"}
+{"current_steps": 34, "total_steps": 134, "loss": 0.0899, "lr": 8.49384713889421e-06, "epoch": 0.5074626865671642, "percentage": 25.37, "elapsed_time": "0:01:59", "remaining_time": "0:05:51"}
+{"current_steps": 35, "total_steps": 134, "loss": 0.0827, "lr": 8.40903910775219e-06, "epoch": 0.5223880597014925, "percentage": 26.12, "elapsed_time": "0:02:03", "remaining_time": "0:05:48"}
+{"current_steps": 36, "total_steps": 134, "loss": 0.0888, "lr": 8.32235736719411e-06, "epoch": 0.5373134328358209, "percentage": 26.87, "elapsed_time": "0:02:06", "remaining_time": "0:05:44"}
+{"current_steps": 37, "total_steps": 134, "loss": 0.0846, "lr": 8.233849560085994e-06, "epoch": 0.5522388059701493, "percentage": 27.61, "elapsed_time": "0:02:10", "remaining_time": "0:05:41"}
+{"current_steps": 38, "total_steps": 134, "loss": 0.1031, "lr": 8.143564332954426e-06, "epoch": 0.5671641791044776, "percentage": 28.36, "elapsed_time": "0:02:13", "remaining_time": "0:05:37"}
+{"current_steps": 39, "total_steps": 134, "loss": 0.0849, "lr": 8.051551309248961e-06, "epoch": 0.582089552238806, "percentage": 29.1, "elapsed_time": "0:02:17", "remaining_time": "0:05:33"}
+{"current_steps": 40, "total_steps": 134, "loss": 0.0852, "lr": 7.957861062067614e-06, "epoch": 0.5970149253731343, "percentage": 29.85, "elapsed_time": "0:02:20", "remaining_time": "0:05:30"}
+{"current_steps": 41, "total_steps": 134, "loss": 0.0887, "lr": 7.86254508636036e-06, "epoch": 0.6119402985074627, "percentage": 30.6, "elapsed_time": "0:02:24", "remaining_time": "0:05:26"}
+{"current_steps": 42, "total_steps": 134, "loss": 0.0855, "lr": 7.765655770625997e-06, "epoch": 0.6268656716417911, "percentage": 31.34, "elapsed_time": "0:02:27", "remaining_time": "0:05:23"}
+{"current_steps": 43, "total_steps": 134, "loss": 0.0818, "lr": 7.667246368117852e-06, "epoch": 0.6417910447761194, "percentage": 32.09, "elapsed_time": "0:02:31", "remaining_time": "0:05:19"}
+{"current_steps": 44, "total_steps": 134, "loss": 0.0856, "lr": 7.56737096757421e-06, "epoch": 0.6567164179104478, "percentage": 32.84, "elapsed_time": "0:02:34", "remaining_time": "0:05:16"}
+{"current_steps": 45, "total_steps": 134, "loss": 0.0801, "lr": 7.466084463489537e-06, "epoch": 0.6716417910447762, "percentage": 33.58, "elapsed_time": "0:02:37", "remaining_time": "0:05:12"}
+{"current_steps": 46, "total_steps": 134, "loss": 0.0844, "lr": 7.363442525942827e-06, "epoch": 0.6865671641791045, "percentage": 34.33, "elapsed_time": "0:02:41", "remaining_time": "0:05:08"}
+{"current_steps": 47, "total_steps": 134, "loss": 0.0894, "lr": 7.25950156999967e-06, "epoch": 0.7014925373134329, "percentage": 35.07, "elapsed_time": "0:02:44", "remaining_time": "0:05:05"}
+{"current_steps": 48, "total_steps": 134, "loss": 0.0906, "lr": 7.1543187247048525e-06, "epoch": 0.7164179104477612, "percentage": 35.82, "elapsed_time": "0:02:48", "remaining_time": "0:05:01"}
+{"current_steps": 49, "total_steps": 134, "loss": 0.0775, "lr": 7.047951801682533e-06, "epoch": 0.7313432835820896, "percentage": 36.57, "elapsed_time": "0:02:51", "remaining_time": "0:04:58"}
+{"current_steps": 50, "total_steps": 134, "loss": 0.08, "lr": 6.9404592633612486e-06, "epoch": 0.746268656716418, "percentage": 37.31, "elapsed_time": "0:02:55", "remaining_time": "0:04:54"}
+{"current_steps": 51, "total_steps": 134, "loss": 0.0852, "lr": 6.831900190841232e-06, "epoch": 0.7611940298507462, "percentage": 38.06, "elapsed_time": "0:02:58", "remaining_time": "0:04:51"}
+{"current_steps": 52, "total_steps": 134, "loss": 0.0786, "lr": 6.722334251421665e-06, "epoch": 0.7761194029850746, "percentage": 38.81, "elapsed_time": "0:03:02", "remaining_time": "0:04:47"}
+{"current_steps": 53, "total_steps": 134, "loss": 0.0859, "lr": 6.611821665805769e-06, "epoch": 0.7910447761194029, "percentage": 39.55, "elapsed_time": "0:03:05", "remaining_time": "0:04:44"}
+{"current_steps": 54, "total_steps": 134, "loss": 0.0918, "lr": 6.500423175001705e-06, "epoch": 0.8059701492537313, "percentage": 40.3, "elapsed_time": "0:03:09", "remaining_time": "0:04:40"}
+{"current_steps": 55, "total_steps": 134, "loss": 0.089, "lr": 6.388200006937503e-06, "epoch": 0.8208955223880597, "percentage": 41.04, "elapsed_time": "0:03:12", "remaining_time": "0:04:36"}
+{"current_steps": 56, "total_steps": 134, "loss": 0.0731, "lr": 6.275213842808383e-06, "epoch": 0.835820895522388, "percentage": 41.79, "elapsed_time": "0:03:16", "remaining_time": "0:04:33"}
+{"current_steps": 57, "total_steps": 134, "loss": 0.0762, "lr": 6.161526783174917e-06, "epoch": 0.8507462686567164, "percentage": 42.54, "elapsed_time": "0:03:19", "remaining_time": "0:04:29"}
+{"current_steps": 58, "total_steps": 134, "loss": 0.0921, "lr": 6.047201313830724e-06, "epoch": 0.8656716417910447, "percentage": 43.28, "elapsed_time": "0:03:23", "remaining_time": "0:04:26"}
+{"current_steps": 59, "total_steps": 134, "loss": 0.0692, "lr": 5.932300271458406e-06, "epoch": 0.8805970149253731, "percentage": 44.03, "elapsed_time": "0:03:26", "remaining_time": "0:04:22"}
+{"current_steps": 60, "total_steps": 134, "loss": 0.0777, "lr": 5.816886809092651e-06, "epoch": 0.8955223880597015, "percentage": 44.78, "elapsed_time": "0:03:30", "remaining_time": "0:04:19"}
+{"current_steps": 61, "total_steps": 134, "loss": 0.0803, "lr": 5.701024361409431e-06, "epoch": 0.9104477611940298, "percentage": 45.52, "elapsed_time": "0:03:33", "remaining_time": "0:04:15"}
+{"current_steps": 62, "total_steps": 134, "loss": 0.0893, "lr": 5.584776609860414e-06, "epoch": 0.9253731343283582, "percentage": 46.27, "elapsed_time": "0:03:37", "remaining_time": "0:04:12"}
+{"current_steps": 63, "total_steps": 134, "loss": 0.0844, "lr": 5.468207447671755e-06, "epoch": 0.9402985074626866, "percentage": 47.01, "elapsed_time": "0:03:40", "remaining_time": "0:04:08"}
+{"current_steps": 64, "total_steps": 134, "loss": 0.0836, "lr": 5.351380944726465e-06, "epoch": 0.9552238805970149, "percentage": 47.76, "elapsed_time": "0:03:44", "remaining_time": "0:04:05"}
+{"current_steps": 65, "total_steps": 134, "loss": 0.0951, "lr": 5.234361312349701e-06, "epoch": 0.9701492537313433, "percentage": 48.51, "elapsed_time": "0:03:47", "remaining_time": "0:04:01"}
+{"current_steps": 66, "total_steps": 134, "loss": 0.0655, "lr": 5.117212868016303e-06, "epoch": 0.9850746268656716, "percentage": 49.25, "elapsed_time": "0:03:50", "remaining_time": "0:03:57"}
+{"current_steps": 67, "total_steps": 134, "loss": 0.0424, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:03:54", "remaining_time": "0:03:54"}
+{"current_steps": 68, "total_steps": 134, "loss": 0.0319, "lr": 4.882787131983698e-06, "epoch": 1.0149253731343284, "percentage": 50.75, "elapsed_time": "0:03:57", "remaining_time": "0:03:50"}
+{"current_steps": 69, "total_steps": 134, "loss": 0.0397, "lr": 4.765638687650299e-06, "epoch": 1.0298507462686568, "percentage": 51.49, "elapsed_time": "0:04:01", "remaining_time": "0:03:47"}
+{"current_steps": 70, "total_steps": 134, "loss": 0.0335, "lr": 4.6486190552735375e-06, "epoch": 1.044776119402985, "percentage": 52.24, "elapsed_time": "0:04:04", "remaining_time": "0:03:43"}
+{"current_steps": 71, "total_steps": 134, "loss": 0.0285, "lr": 4.531792552328247e-06, "epoch": 1.0597014925373134, "percentage": 52.99, "elapsed_time": "0:04:08", "remaining_time": "0:03:40"}
+{"current_steps": 72, "total_steps": 134, "loss": 0.0326, "lr": 4.415223390139588e-06, "epoch": 1.0746268656716418, "percentage": 53.73, "elapsed_time": "0:04:11", "remaining_time": "0:03:36"}
+{"current_steps": 73, "total_steps": 134, "loss": 0.0244, "lr": 4.2989756385905715e-06, "epoch": 1.0895522388059702, "percentage": 54.48, "elapsed_time": "0:04:15", "remaining_time": "0:03:33"}
+{"current_steps": 74, "total_steps": 134, "loss": 0.027, "lr": 4.183113190907349e-06, "epoch": 1.1044776119402986, "percentage": 55.22, "elapsed_time": "0:04:18", "remaining_time": "0:03:29"}
+{"current_steps": 75, "total_steps": 134, "loss": 0.0316, "lr": 4.067699728541595e-06, "epoch": 1.1194029850746268, "percentage": 55.97, "elapsed_time": "0:04:22", "remaining_time": "0:03:26"}
+{"current_steps": 76, "total_steps": 134, "loss": 0.0303, "lr": 3.952798686169279e-06, "epoch": 1.1343283582089552, "percentage": 56.72, "elapsed_time": "0:04:25", "remaining_time": "0:03:22"}
+{"current_steps": 77, "total_steps": 134, "loss": 0.0282, "lr": 3.838473216825085e-06, "epoch": 1.1492537313432836, "percentage": 57.46, "elapsed_time": "0:04:29", "remaining_time": "0:03:19"}
+{"current_steps": 78, "total_steps": 134, "loss": 0.0272, "lr": 3.7247861571916183e-06, "epoch": 1.164179104477612, "percentage": 58.21, "elapsed_time": "0:04:32", "remaining_time": "0:03:15"}
+{"current_steps": 79, "total_steps": 134, "loss": 0.0351, "lr": 3.611799993062497e-06, "epoch": 1.1791044776119404, "percentage": 58.96, "elapsed_time": "0:04:36", "remaining_time": "0:03:12"}
+{"current_steps": 80, "total_steps": 134, "loss": 0.0377, "lr": 3.4995768249982975e-06, "epoch": 1.1940298507462686, "percentage": 59.7, "elapsed_time": "0:04:39", "remaining_time": "0:03:08"}
+{"current_steps": 81, "total_steps": 134, "loss": 0.0254, "lr": 3.388178334194232e-06, "epoch": 1.208955223880597, "percentage": 60.45, "elapsed_time": "0:04:43", "remaining_time": "0:03:05"}
+{"current_steps": 82, "total_steps": 134, "loss": 0.0217, "lr": 3.2776657485783357e-06, "epoch": 1.2238805970149254, "percentage": 61.19, "elapsed_time": "0:04:46", "remaining_time": "0:03:01"}
+{"current_steps": 83, "total_steps": 134, "loss": 0.0257, "lr": 3.168099809158769e-06, "epoch": 1.2388059701492538, "percentage": 61.94, "elapsed_time": "0:04:50", "remaining_time": "0:02:58"}
+{"current_steps": 84, "total_steps": 134, "loss": 0.0291, "lr": 3.059540736638751e-06, "epoch": 1.2537313432835822, "percentage": 62.69, "elapsed_time": "0:04:53", "remaining_time": "0:02:54"}
+{"current_steps": 85, "total_steps": 134, "loss": 0.0249, "lr": 2.9520481983174675e-06, "epoch": 1.2686567164179103, "percentage": 63.43, "elapsed_time": "0:04:56", "remaining_time": "0:02:51"}
+{"current_steps": 86, "total_steps": 134, "loss": 0.0226, "lr": 2.8456812752951483e-06, "epoch": 1.2835820895522387, "percentage": 64.18, "elapsed_time": "0:05:00", "remaining_time": "0:02:47"}
+{"current_steps": 87, "total_steps": 134, "loss": 0.0262, "lr": 2.740498430000332e-06, "epoch": 1.2985074626865671, "percentage": 64.93, "elapsed_time": "0:05:03", "remaining_time": "0:02:44"}
+{"current_steps": 88, "total_steps": 134, "loss": 0.0171, "lr": 2.636557474057173e-06, "epoch": 1.3134328358208955, "percentage": 65.67, "elapsed_time": "0:05:07", "remaining_time": "0:02:40"}
+{"current_steps": 89, "total_steps": 134, "loss": 0.0249, "lr": 2.533915536510464e-06, "epoch": 1.328358208955224, "percentage": 66.42, "elapsed_time": "0:05:10", "remaining_time": "0:02:37"}
+{"current_steps": 90, "total_steps": 134, "loss": 0.0246, "lr": 2.4326290324257896e-06, "epoch": 1.3432835820895521, "percentage": 67.16, "elapsed_time": "0:05:14", "remaining_time": "0:02:33"}
+{"current_steps": 91, "total_steps": 134, "loss": 0.0183, "lr": 2.3327536318821496e-06, "epoch": 1.3582089552238805, "percentage": 67.91, "elapsed_time": "0:05:17", "remaining_time": "0:02:30"}
+{"current_steps": 92, "total_steps": 134, "loss": 0.0272, "lr": 2.234344229374003e-06, "epoch": 1.373134328358209, "percentage": 68.66, "elapsed_time": "0:05:21", "remaining_time": "0:02:26"}
+{"current_steps": 93, "total_steps": 134, "loss": 0.0259, "lr": 2.1374549136396417e-06, "epoch": 1.3880597014925373, "percentage": 69.4, "elapsed_time": "0:05:24", "remaining_time": "0:02:23"}
+{"current_steps": 94, "total_steps": 134, "loss": 0.0244, "lr": 2.042138937932388e-06, "epoch": 1.4029850746268657, "percentage": 70.15, "elapsed_time": "0:05:28", "remaining_time": "0:02:19"}
+{"current_steps": 95, "total_steps": 134, "loss": 0.0259, "lr": 1.9484486907510405e-06, "epoch": 1.417910447761194, "percentage": 70.9, "elapsed_time": "0:05:31", "remaining_time": "0:02:16"}
+{"current_steps": 96, "total_steps": 134, "loss": 0.0248, "lr": 1.856435667045577e-06, "epoch": 1.4328358208955223, "percentage": 71.64, "elapsed_time": "0:05:35", "remaining_time": "0:02:12"}
+{"current_steps": 97, "total_steps": 134, "loss": 0.0253, "lr": 1.7661504399140066e-06, "epoch": 1.4477611940298507, "percentage": 72.39, "elapsed_time": "0:05:38", "remaining_time": "0:02:09"}
+{"current_steps": 98, "total_steps": 134, "loss": 0.029, "lr": 1.677642632805892e-06, "epoch": 1.462686567164179, "percentage": 73.13, "elapsed_time": "0:05:42", "remaining_time": "0:02:05"}
+{"current_steps": 99, "total_steps": 134, "loss": 0.0222, "lr": 1.5909608922478108e-06, "epoch": 1.4776119402985075, "percentage": 73.88, "elapsed_time": "0:05:45", "remaining_time": "0:02:02"}
+{"current_steps": 100, "total_steps": 134, "loss": 0.0186, "lr": 1.5061528611057917e-06, "epoch": 1.4925373134328357, "percentage": 74.63, "elapsed_time": "0:05:48", "remaining_time": "0:01:58"}
+{"current_steps": 101, "total_steps": 134, "loss": 0.0246, "lr": 1.4232651523993635e-06, "epoch": 1.5074626865671643, "percentage": 75.37, "elapsed_time": "0:05:52", "remaining_time": "0:01:55"}
+{"current_steps": 102, "total_steps": 134, "loss": 0.0262, "lr": 1.3423433236816563e-06, "epoch": 1.5223880597014925, "percentage": 76.12, "elapsed_time": "0:05:55", "remaining_time": "0:01:51"}
+{"current_steps": 103, "total_steps": 134, "loss": 0.0265, "lr": 1.2634318519996148e-06, "epoch": 1.537313432835821, "percentage": 76.87, "elapsed_time": "0:05:59", "remaining_time": "0:01:48"}
+{"current_steps": 104, "total_steps": 134, "loss": 0.0253, "lr": 1.186574109448091e-06, "epoch": 1.5522388059701493, "percentage": 77.61, "elapsed_time": "0:06:02", "remaining_time": "0:01:44"}
+{"current_steps": 105, "total_steps": 134, "loss": 0.0317, "lr": 1.1118123393312397e-06, "epoch": 1.5671641791044775, "percentage": 78.36, "elapsed_time": "0:06:06", "remaining_time": "0:01:41"}
+{"current_steps": 106, "total_steps": 134, "loss": 0.0248, "lr": 1.0391876329443534e-06, "epoch": 1.582089552238806, "percentage": 79.1, "elapsed_time": "0:06:09", "remaining_time": "0:01:37"}
+{"current_steps": 107, "total_steps": 134, "loss": 0.0253, "lr": 9.687399069888515e-07, "epoch": 1.5970149253731343, "percentage": 79.85, "elapsed_time": "0:06:13", "remaining_time": "0:01:34"}
+{"current_steps": 108, "total_steps": 134, "loss": 0.0208, "lr": 9.005078816328772e-07, "epoch": 1.6119402985074627, "percentage": 80.6, "elapsed_time": "0:06:16", "remaining_time": "0:01:30"}
+{"current_steps": 109, "total_steps": 134, "loss": 0.0256, "lr": 8.345290592295429e-07, "epoch": 1.626865671641791, "percentage": 81.34, "elapsed_time": "0:06:20", "remaining_time": "0:01:27"}
+{"current_steps": 110, "total_steps": 134, "loss": 0.024, "lr": 7.708397037045129e-07, "epoch": 1.6417910447761193, "percentage": 82.09, "elapsed_time": "0:06:23", "remaining_time": "0:01:23"}
+{"current_steps": 111, "total_steps": 134, "loss": 0.0282, "lr": 7.094748206242797e-07, "epoch": 1.6567164179104479, "percentage": 82.84, "elapsed_time": "0:06:27", "remaining_time": "0:01:20"}
+{"current_steps": 112, "total_steps": 134, "loss": 0.0203, "lr": 6.50468137956049e-07, "epoch": 1.671641791044776, "percentage": 83.58, "elapsed_time": "0:06:30", "remaining_time": "0:01:16"}
+{"current_steps": 113, "total_steps": 134, "loss": 0.0262, "lr": 5.938520875298587e-07, "epoch": 1.6865671641791045, "percentage": 84.33, "elapsed_time": "0:06:34", "remaining_time": "0:01:13"}
+{"current_steps": 114, "total_steps": 134, "loss": 0.0234, "lr": 5.396577872130676e-07, "epoch": 1.7014925373134329, "percentage": 85.07, "elapsed_time": "0:06:37", "remaining_time": "0:01:09"}
+{"current_steps": 115, "total_steps": 134, "loss": 0.0235, "lr": 4.879150238070585e-07, "epoch": 1.716417910447761, "percentage": 85.82, "elapsed_time": "0:06:41", "remaining_time": "0:01:06"}
+{"current_steps": 116, "total_steps": 134, "loss": 0.021, "lr": 4.386522366755169e-07, "epoch": 1.7313432835820897, "percentage": 86.57, "elapsed_time": "0:06:44", "remaining_time": "0:01:02"}
+{"current_steps": 117, "total_steps": 134, "loss": 0.0285, "lr": 3.918965021133131e-07, "epoch": 1.7462686567164178, "percentage": 87.31, "elapsed_time": "0:06:47", "remaining_time": "0:00:59"}
+{"current_steps": 118, "total_steps": 134, "loss": 0.0294, "lr": 3.4767351846456744e-07, "epoch": 1.7611940298507462, "percentage": 88.06, "elapsed_time": "0:06:51", "remaining_time": "0:00:55"}
+{"current_steps": 119, "total_steps": 134, "loss": 0.026, "lr": 3.0600759199806815e-07, "epoch": 1.7761194029850746, "percentage": 88.81, "elapsed_time": "0:06:54", "remaining_time": "0:00:52"}
+{"current_steps": 120, "total_steps": 134, "loss": 0.0268, "lr": 2.669216235478295e-07, "epoch": 1.7910447761194028, "percentage": 89.55, "elapsed_time": "0:06:58", "remaining_time": "0:00:48"}
+{"current_steps": 121, "total_steps": 134, "loss": 0.0282, "lr": 2.3043709592610486e-07, "epoch": 1.8059701492537314, "percentage": 90.3, "elapsed_time": "0:07:01", "remaining_time": "0:00:45"}
+{"current_steps": 122, "total_steps": 134, "loss": 0.0276, "lr": 1.9657406211579966e-07, "epoch": 1.8208955223880596, "percentage": 91.04, "elapsed_time": "0:07:05", "remaining_time": "0:00:41"}
+{"current_steps": 123, "total_steps": 134, "loss": 0.0253, "lr": 1.6535113424874683e-07, "epoch": 1.835820895522388, "percentage": 91.79, "elapsed_time": "0:07:08", "remaining_time": "0:00:38"}
+{"current_steps": 124, "total_steps": 134, "loss": 0.0231, "lr": 1.3678547337593494e-07, "epoch": 1.8507462686567164, "percentage": 92.54, "elapsed_time": "0:07:12", "remaining_time": "0:00:34"}
+{"current_steps": 125, "total_steps": 134, "loss": 0.0229, "lr": 1.1089278003527438e-07, "epoch": 1.8656716417910446, "percentage": 93.28, "elapsed_time": "0:07:15", "remaining_time": "0:00:31"}
+{"current_steps": 126, "total_steps": 134, "loss": 0.0259, "lr": 8.768728562211948e-08, "epoch": 1.8805970149253732, "percentage": 94.03, "elapsed_time": "0:07:19", "remaining_time": "0:00:27"}
+{"current_steps": 127, "total_steps": 134, "loss": 0.0254, "lr": 6.718174456726789e-08, "epoch": 1.8955223880597014, "percentage": 94.78, "elapsed_time": "0:07:22", "remaining_time": "0:00:24"}
+{"current_steps": 128, "total_steps": 134, "loss": 0.0257, "lr": 4.9387427326745287e-08, "epoch": 1.9104477611940298, "percentage": 95.52, "elapsed_time": "0:07:26", "remaining_time": "0:00:20"}
+{"current_steps": 129, "total_steps": 134, "loss": 0.023, "lr": 3.431411418722941e-08, "epoch": 1.9253731343283582, "percentage": 96.27, "elapsed_time": "0:07:29", "remaining_time": "0:00:17"}
+{"current_steps": 130, "total_steps": 134, "loss": 0.0237, "lr": 2.1970089890509527e-08, "epoch": 1.9402985074626866, "percentage": 97.01, "elapsed_time": "0:07:33", "remaining_time": "0:00:13"}
+{"current_steps": 131, "total_steps": 134, "loss": 0.0193, "lr": 1.2362139079949431e-08, "epoch": 1.955223880597015, "percentage": 97.76, "elapsed_time": "0:07:36", "remaining_time": "0:00:10"}
+{"current_steps": 132, "total_steps": 134, "loss": 0.0227, "lr": 5.495542571443135e-09, "epoch": 1.9701492537313432, "percentage": 98.51, "elapsed_time": "0:07:40", "remaining_time": "0:00:06"}
+{"current_steps": 133, "total_steps": 134, "loss": 0.0209, "lr": 1.3740744509205263e-09, "epoch": 1.9850746268656716, "percentage": 99.25, "elapsed_time": "0:07:43", "remaining_time": "0:00:03"}
+{"current_steps": 134, "total_steps": 134, "loss": 0.013, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:07:46", "remaining_time": "0:00:00"}
+{"current_steps": 134, "total_steps": 134, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:48", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,980 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014925373134328358,
+      "grad_norm": 2.4583136454633454,
+      "learning_rate": 9.99862592554908e-06,
+      "loss": 0.1709,
+      "step": 1
+    },
+    {
+      "epoch": 0.029850746268656716,
+      "grad_norm": 1.2601474874951664,
+      "learning_rate": 9.994504457428557e-06,
+      "loss": 0.1095,
+      "step": 2
+    },
+    {
+      "epoch": 0.04477611940298507,
+      "grad_norm": 1.8921245514823541,
+      "learning_rate": 9.987637860920053e-06,
+      "loss": 0.1123,
+      "step": 3
+    },
+    {
+      "epoch": 0.05970149253731343,
+      "grad_norm": 1.0381477254848812,
+      "learning_rate": 9.978029910109491e-06,
+      "loss": 0.0897,
+      "step": 4
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 0.8231161139163885,
+      "learning_rate": 9.965685885812773e-06,
+      "loss": 0.0804,
+      "step": 5
+    },
+    {
+      "epoch": 0.08955223880597014,
+      "grad_norm": 3.3306861693595704,
+      "learning_rate": 9.950612572673255e-06,
+      "loss": 0.1197,
+      "step": 6
+    },
+    {
+      "epoch": 0.1044776119402985,
+      "grad_norm": 0.8873942793156309,
+      "learning_rate": 9.932818255432733e-06,
+      "loss": 0.1052,
+      "step": 7
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 0.7726110244054883,
+      "learning_rate": 9.91231271437788e-06,
+      "loss": 0.09,
+      "step": 8
+    },
+    {
+      "epoch": 0.13432835820895522,
+      "grad_norm": 0.7713735038013977,
+      "learning_rate": 9.889107219964726e-06,
+      "loss": 0.0847,
+      "step": 9
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 0.8179878874298719,
+      "learning_rate": 9.863214526624065e-06,
+      "loss": 0.0899,
+      "step": 10
+    },
+    {
+      "epoch": 0.16417910447761194,
+      "grad_norm": 0.793854117532711,
+      "learning_rate": 9.834648865751254e-06,
+      "loss": 0.0885,
+      "step": 11
+    },
+    {
+      "epoch": 0.1791044776119403,
+      "grad_norm": 0.6649283964833135,
+      "learning_rate": 9.803425937884202e-06,
+      "loss": 0.078,
+      "step": 12
+    },
+    {
+      "epoch": 0.19402985074626866,
+      "grad_norm": 0.8490726920421898,
+      "learning_rate": 9.769562904073896e-06,
+      "loss": 0.0878,
+      "step": 13
+    },
+    {
+      "epoch": 0.208955223880597,
+      "grad_norm": 0.7411456396869534,
+      "learning_rate": 9.733078376452172e-06,
+      "loss": 0.0881,
+      "step": 14
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 0.7448122603540034,
+      "learning_rate": 9.693992408001934e-06,
+      "loss": 0.091,
+      "step": 15
+    },
+    {
+      "epoch": 0.23880597014925373,
+      "grad_norm": 0.672661340651816,
+      "learning_rate": 9.652326481535434e-06,
+      "loss": 0.0847,
+      "step": 16
+    },
+    {
+      "epoch": 0.2537313432835821,
+      "grad_norm": 0.6295351920280576,
+      "learning_rate": 9.608103497886687e-06,
+      "loss": 0.0751,
+      "step": 17
+    },
+    {
+      "epoch": 0.26865671641791045,
+      "grad_norm": 0.5987419993650692,
+      "learning_rate": 9.561347763324484e-06,
+      "loss": 0.0757,
+      "step": 18
+    },
+    {
+      "epoch": 0.2835820895522388,
+      "grad_norm": 0.6862099670787631,
+      "learning_rate": 9.512084976192944e-06,
+      "loss": 0.0832,
+      "step": 19
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 0.6474317718234073,
+      "learning_rate": 9.460342212786933e-06,
+      "loss": 0.0785,
+      "step": 20
+    },
+    {
+      "epoch": 0.31343283582089554,
+      "grad_norm": 0.6520670338068375,
+      "learning_rate": 9.406147912470142e-06,
+      "loss": 0.0832,
+      "step": 21
+    },
+    {
+      "epoch": 0.3283582089552239,
+      "grad_norm": 0.6875547799836488,
+      "learning_rate": 9.349531862043952e-06,
+      "loss": 0.0909,
+      "step": 22
+    },
+    {
+      "epoch": 0.34328358208955223,
+      "grad_norm": 0.6406155904616685,
+      "learning_rate": 9.290525179375722e-06,
+      "loss": 0.0817,
+      "step": 23
+    },
+    {
+      "epoch": 0.3582089552238806,
+      "grad_norm": 0.6570196434589318,
+      "learning_rate": 9.229160296295488e-06,
+      "loss": 0.0847,
+      "step": 24
+    },
+    {
+      "epoch": 0.373134328358209,
+      "grad_norm": 0.5570171509580777,
+      "learning_rate": 9.165470940770458e-06,
+      "loss": 0.0739,
+      "step": 25
+    },
+    {
+      "epoch": 0.3880597014925373,
+      "grad_norm": 0.620261743808898,
+      "learning_rate": 9.099492118367123e-06,
+      "loss": 0.0861,
+      "step": 26
+    },
+    {
+      "epoch": 0.40298507462686567,
+      "grad_norm": 0.6886602468358877,
+      "learning_rate": 9.03126009301115e-06,
+      "loss": 0.0943,
+      "step": 27
+    },
+    {
+      "epoch": 0.417910447761194,
+      "grad_norm": 0.7131708436753863,
+      "learning_rate": 8.960812367055646e-06,
+      "loss": 0.0892,
+      "step": 28
+    },
+    {
+      "epoch": 0.43283582089552236,
+      "grad_norm": 0.6391387675910597,
+      "learning_rate": 8.888187660668762e-06,
+      "loss": 0.0832,
+      "step": 29
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 0.6940047679170313,
+      "learning_rate": 8.81342589055191e-06,
+      "loss": 0.0906,
+      "step": 30
+    },
+    {
+      "epoch": 0.4626865671641791,
+      "grad_norm": 0.6503008059328946,
+      "learning_rate": 8.736568148000386e-06,
+      "loss": 0.0968,
+      "step": 31
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 0.6090207680984978,
+      "learning_rate": 8.657656676318346e-06,
+      "loss": 0.0847,
+      "step": 32
+    },
+    {
+      "epoch": 0.4925373134328358,
+      "grad_norm": 0.6434605637551735,
+      "learning_rate": 8.576734847600639e-06,
+      "loss": 0.0853,
+      "step": 33
+    },
+    {
+      "epoch": 0.5074626865671642,
+      "grad_norm": 0.6377279956113436,
+      "learning_rate": 8.49384713889421e-06,
+      "loss": 0.0899,
+      "step": 34
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 0.644362530558179,
+      "learning_rate": 8.40903910775219e-06,
+      "loss": 0.0827,
+      "step": 35
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 0.642985561685258,
+      "learning_rate": 8.32235736719411e-06,
+      "loss": 0.0888,
+      "step": 36
+    },
+    {
+      "epoch": 0.5522388059701493,
+      "grad_norm": 0.6790092652999941,
+      "learning_rate": 8.233849560085994e-06,
+      "loss": 0.0846,
+      "step": 37
+    },
+    {
+      "epoch": 0.5671641791044776,
+      "grad_norm": 0.7854755458868027,
+      "learning_rate": 8.143564332954426e-06,
+      "loss": 0.1031,
+      "step": 38
+    },
+    {
+      "epoch": 0.582089552238806,
+      "grad_norm": 0.6030440972462469,
+      "learning_rate": 8.051551309248961e-06,
+      "loss": 0.0849,
+      "step": 39
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.6418639082548031,
+      "learning_rate": 7.957861062067614e-06,
+      "loss": 0.0852,
+      "step": 40
+    },
+    {
+      "epoch": 0.6119402985074627,
+      "grad_norm": 0.6566500879981874,
+      "learning_rate": 7.86254508636036e-06,
+      "loss": 0.0887,
+      "step": 41
+    },
+    {
+      "epoch": 0.6268656716417911,
+      "grad_norm": 0.6290631945385817,
+      "learning_rate": 7.765655770625997e-06,
+      "loss": 0.0855,
+      "step": 42
+    },
+    {
+      "epoch": 0.6417910447761194,
+      "grad_norm": 0.6140886580472066,
+      "learning_rate": 7.667246368117852e-06,
+      "loss": 0.0818,
+      "step": 43
+    },
+    {
+      "epoch": 0.6567164179104478,
+      "grad_norm": 0.6174619223952549,
+      "learning_rate": 7.56737096757421e-06,
+      "loss": 0.0856,
+      "step": 44
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 0.6195862366153396,
+      "learning_rate": 7.466084463489537e-06,
+      "loss": 0.0801,
+      "step": 45
+    },
+    {
+      "epoch": 0.6865671641791045,
+      "grad_norm": 0.6331901290551701,
+      "learning_rate": 7.363442525942827e-06,
+      "loss": 0.0844,
+      "step": 46
+    },
+    {
+      "epoch": 0.7014925373134329,
+      "grad_norm": 0.7083908752048309,
+      "learning_rate": 7.25950156999967e-06,
+      "loss": 0.0894,
+      "step": 47
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 0.6388671244490378,
+      "learning_rate": 7.1543187247048525e-06,
+      "loss": 0.0906,
+      "step": 48
+    },
+    {
+      "epoch": 0.7313432835820896,
+      "grad_norm": 0.5777376817133963,
+      "learning_rate": 7.047951801682533e-06,
+      "loss": 0.0775,
+      "step": 49
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 0.5907825361104937,
+      "learning_rate": 6.9404592633612486e-06,
+      "loss": 0.08,
+      "step": 50
+    },
+    {
+      "epoch": 0.7611940298507462,
+      "grad_norm": 0.6197333346964937,
+      "learning_rate": 6.831900190841232e-06,
+      "loss": 0.0852,
+      "step": 51
+    },
+    {
+      "epoch": 0.7761194029850746,
+      "grad_norm": 0.580913389747538,
+      "learning_rate": 6.722334251421665e-06,
+      "loss": 0.0786,
+      "step": 52
+    },
+    {
+      "epoch": 0.7910447761194029,
+      "grad_norm": 0.6769846397314266,
+      "learning_rate": 6.611821665805769e-06,
+      "loss": 0.0859,
+      "step": 53
+    },
+    {
+      "epoch": 0.8059701492537313,
+      "grad_norm": 0.6493382927830379,
+      "learning_rate": 6.500423175001705e-06,
+      "loss": 0.0918,
+      "step": 54
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "grad_norm": 0.6002157339319569,
+      "learning_rate": 6.388200006937503e-06,
+      "loss": 0.089,
+      "step": 55
+    },
+    {
+      "epoch": 0.835820895522388,
+      "grad_norm": 0.5447504002720616,
+      "learning_rate": 6.275213842808383e-06,
+      "loss": 0.0731,
+      "step": 56
+    },
+    {
+      "epoch": 0.8507462686567164,
+      "grad_norm": 0.5621404387468115,
+      "learning_rate": 6.161526783174917e-06,
+      "loss": 0.0762,
+      "step": 57
+    },
+    {
+      "epoch": 0.8656716417910447,
+      "grad_norm": 0.6279143619008688,
+      "learning_rate": 6.047201313830724e-06,
+      "loss": 0.0921,
+      "step": 58
+    },
+    {
+      "epoch": 0.8805970149253731,
+      "grad_norm": 0.5567853485138207,
+      "learning_rate": 5.932300271458406e-06,
+      "loss": 0.0692,
+      "step": 59
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 0.5831390070498211,
+      "learning_rate": 5.816886809092651e-06,
+      "loss": 0.0777,
+      "step": 60
+    },
+    {
+      "epoch": 0.9104477611940298,
+      "grad_norm": 0.575437949186205,
+      "learning_rate": 5.701024361409431e-06,
+      "loss": 0.0803,
+      "step": 61
+    },
+    {
+      "epoch": 0.9253731343283582,
+      "grad_norm": 0.6339642524977537,
+      "learning_rate": 5.584776609860414e-06,
+      "loss": 0.0893,
+      "step": 62
+    },
+    {
+      "epoch": 0.9402985074626866,
+      "grad_norm": 0.5924535700885266,
+      "learning_rate": 5.468207447671755e-06,
+      "loss": 0.0844,
+      "step": 63
+    },
+    {
+      "epoch": 0.9552238805970149,
+      "grad_norm": 0.6155460855755083,
+      "learning_rate": 5.351380944726465e-06,
+      "loss": 0.0836,
+      "step": 64
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "grad_norm": 0.640329747223743,
+      "learning_rate": 5.234361312349701e-06,
+      "loss": 0.0951,
+      "step": 65
+    },
+    {
+      "epoch": 0.9850746268656716,
+      "grad_norm": 0.5300911342515855,
+      "learning_rate": 5.117212868016303e-06,
+      "loss": 0.0655,
+      "step": 66
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4687094870612933,
+      "learning_rate": 5e-06,
+      "loss": 0.0424,
+      "step": 67
+    },
+    {
+      "epoch": 1.0149253731343284,
+      "grad_norm": 0.4076938808158179,
+      "learning_rate": 4.882787131983698e-06,
+      "loss": 0.0319,
+      "step": 68
+    },
+    {
+      "epoch": 1.0298507462686568,
+      "grad_norm": 0.44699344595961127,
+      "learning_rate": 4.765638687650299e-06,
+      "loss": 0.0397,
+      "step": 69
+    },
+    {
+      "epoch": 1.044776119402985,
+      "grad_norm": 0.44767644296408526,
+      "learning_rate": 4.6486190552735375e-06,
+      "loss": 0.0335,
+      "step": 70
+    },
+    {
+      "epoch": 1.0597014925373134,
+      "grad_norm": 0.37505346262796413,
+      "learning_rate": 4.531792552328247e-06,
+      "loss": 0.0285,
+      "step": 71
+    },
+    {
+      "epoch": 1.0746268656716418,
+      "grad_norm": 0.4657077829483448,
+      "learning_rate": 4.415223390139588e-06,
+      "loss": 0.0326,
+      "step": 72
+    },
+    {
+      "epoch": 1.0895522388059702,
+      "grad_norm": 0.34306186183329557,
+      "learning_rate": 4.2989756385905715e-06,
+      "loss": 0.0244,
+      "step": 73
+    },
+    {
+      "epoch": 1.1044776119402986,
+      "grad_norm": 0.39032497882907513,
+      "learning_rate": 4.183113190907349e-06,
+      "loss": 0.027,
+      "step": 74
+    },
+    {
+      "epoch": 1.1194029850746268,
+      "grad_norm": 0.4702211175747881,
+      "learning_rate": 4.067699728541595e-06,
+      "loss": 0.0316,
+      "step": 75
+    },
+    {
+      "epoch": 1.1343283582089552,
+      "grad_norm": 0.4455655473637308,
+      "learning_rate": 3.952798686169279e-06,
+      "loss": 0.0303,
+      "step": 76
+    },
+    {
+      "epoch": 1.1492537313432836,
+      "grad_norm": 0.4371493860049261,
+      "learning_rate": 3.838473216825085e-06,
+      "loss": 0.0282,
+      "step": 77
+    },
+    {
+      "epoch": 1.164179104477612,
+      "grad_norm": 0.4289807711491057,
+      "learning_rate": 3.7247861571916183e-06,
+      "loss": 0.0272,
+      "step": 78
+    },
+    {
+      "epoch": 1.1791044776119404,
+      "grad_norm": 0.5368576489602601,
+      "learning_rate": 3.611799993062497e-06,
+      "loss": 0.0351,
+      "step": 79
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 0.6142429871519881,
+      "learning_rate": 3.4995768249982975e-06,
+      "loss": 0.0377,
+      "step": 80
+    },
+    {
+      "epoch": 1.208955223880597,
+      "grad_norm": 0.4437616080442814,
+      "learning_rate": 3.388178334194232e-06,
+      "loss": 0.0254,
+      "step": 81
+    },
+    {
+      "epoch": 1.2238805970149254,
+      "grad_norm": 0.425005368183552,
+      "learning_rate": 3.2776657485783357e-06,
+      "loss": 0.0217,
+      "step": 82
+    },
+    {
+      "epoch": 1.2388059701492538,
+      "grad_norm": 0.45656133078022915,
+      "learning_rate": 3.168099809158769e-06,
+      "loss": 0.0257,
+      "step": 83
+    },
+    {
+      "epoch": 1.2537313432835822,
+      "grad_norm": 0.543019359956107,
+      "learning_rate": 3.059540736638751e-06,
+      "loss": 0.0291,
+      "step": 84
+    },
+    {
+      "epoch": 1.2686567164179103,
+      "grad_norm": 0.48489281581823257,
+      "learning_rate": 2.9520481983174675e-06,
+      "loss": 0.0249,
+      "step": 85
+    },
+    {
+      "epoch": 1.2835820895522387,
+      "grad_norm": 0.5065165276548232,
+      "learning_rate": 2.8456812752951483e-06,
+      "loss": 0.0226,
+      "step": 86
+    },
+    {
+      "epoch": 1.2985074626865671,
+      "grad_norm": 0.5835532502940851,
+      "learning_rate": 2.740498430000332e-06,
+      "loss": 0.0262,
+      "step": 87
+    },
+    {
+      "epoch": 1.3134328358208955,
+      "grad_norm": 0.41781499689334245,
+      "learning_rate": 2.636557474057173e-06,
+      "loss": 0.0171,
+      "step": 88
+    },
+    {
+      "epoch": 1.328358208955224,
+      "grad_norm": 0.60361339503175,
+      "learning_rate": 2.533915536510464e-06,
+      "loss": 0.0249,
+      "step": 89
+    },
+    {
+      "epoch": 1.3432835820895521,
+      "grad_norm": 0.47456828088394937,
+      "learning_rate": 2.4326290324257896e-06,
+      "loss": 0.0246,
+      "step": 90
+    },
+    {
+      "epoch": 1.3582089552238805,
+      "grad_norm": 0.4465597229891302,
+      "learning_rate": 2.3327536318821496e-06,
+      "loss": 0.0183,
+      "step": 91
+    },
+    {
+      "epoch": 1.373134328358209,
+      "grad_norm": 0.49082928585159896,
+      "learning_rate": 2.234344229374003e-06,
+      "loss": 0.0272,
+      "step": 92
+    },
+    {
+      "epoch": 1.3880597014925373,
+      "grad_norm": 0.4703289245897022,
+      "learning_rate": 2.1374549136396417e-06,
+      "loss": 0.0259,
+      "step": 93
+    },
+    {
+      "epoch": 1.4029850746268657,
+      "grad_norm": 0.4919381501347153,
+      "learning_rate": 2.042138937932388e-06,
+      "loss": 0.0244,
+      "step": 94
+    },
+    {
+      "epoch": 1.417910447761194,
+      "grad_norm": 0.48234747726237315,
+      "learning_rate": 1.9484486907510405e-06,
+      "loss": 0.0259,
+      "step": 95
+    },
+    {
+      "epoch": 1.4328358208955223,
+      "grad_norm": 0.46679191916730023,
+      "learning_rate": 1.856435667045577e-06,
+      "loss": 0.0248,
+      "step": 96
+    },
+    {
+      "epoch": 1.4477611940298507,
+      "grad_norm": 0.4915526917266499,
+      "learning_rate": 1.7661504399140066e-06,
+      "loss": 0.0253,
+      "step": 97
+    },
+    {
+      "epoch": 1.462686567164179,
+      "grad_norm": 0.4959939539468189,
+      "learning_rate": 1.677642632805892e-06,
+      "loss": 0.029,
+      "step": 98
+    },
+    {
+      "epoch": 1.4776119402985075,
+      "grad_norm": 0.47533058613210927,
+      "learning_rate": 1.5909608922478108e-06,
+      "loss": 0.0222,
+      "step": 99
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 0.41184618371805026,
+      "learning_rate": 1.5061528611057917e-06,
+      "loss": 0.0186,
+      "step": 100
+    },
+    {
+      "epoch": 1.5074626865671643,
+      "grad_norm": 0.5029260437214431,
+      "learning_rate": 1.4232651523993635e-06,
+      "loss": 0.0246,
+      "step": 101
+    },
+    {
+      "epoch": 1.5223880597014925,
+      "grad_norm": 0.4856272674409962,
+      "learning_rate": 1.3423433236816563e-06,
+      "loss": 0.0262,
+      "step": 102
+    },
+    {
+      "epoch": 1.537313432835821,
+      "grad_norm": 0.5515452132397586,
+      "learning_rate": 1.2634318519996148e-06,
+      "loss": 0.0265,
+      "step": 103
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 0.48385801987338495,
+      "learning_rate": 1.186574109448091e-06,
+      "loss": 0.0253,
+      "step": 104
+    },
+    {
+      "epoch": 1.5671641791044775,
+      "grad_norm": 0.4977052401413162,
+      "learning_rate": 1.1118123393312397e-06,
+      "loss": 0.0317,
+      "step": 105
+    },
+    {
+      "epoch": 1.582089552238806,
+      "grad_norm": 0.5013927727792972,
+      "learning_rate": 1.0391876329443534e-06,
+      "loss": 0.0248,
+      "step": 106
+    },
+    {
+      "epoch": 1.5970149253731343,
+      "grad_norm": 0.5012798267287072,
+      "learning_rate": 9.687399069888515e-07,
+      "loss": 0.0253,
+      "step": 107
+    },
+    {
+      "epoch": 1.6119402985074627,
+      "grad_norm": 0.4798753241925998,
+      "learning_rate": 9.005078816328772e-07,
+      "loss": 0.0208,
+      "step": 108
+    },
+    {
+      "epoch": 1.626865671641791,
+      "grad_norm": 0.4892720130785747,
+      "learning_rate": 8.345290592295429e-07,
+      "loss": 0.0256,
+      "step": 109
+    },
+    {
+      "epoch": 1.6417910447761193,
+      "grad_norm": 0.44880610381720976,
+      "learning_rate": 7.708397037045129e-07,
+      "loss": 0.024,
+      "step": 110
+    },
+    {
+      "epoch": 1.6567164179104479,
+      "grad_norm": 0.5198878749228643,
+      "learning_rate": 7.094748206242797e-07,
+      "loss": 0.0282,
+      "step": 111
+    },
+    {
+      "epoch": 1.671641791044776,
+      "grad_norm": 0.4259309199030039,
+      "learning_rate": 6.50468137956049e-07,
+      "loss": 0.0203,
+      "step": 112
+    },
+    {
+      "epoch": 1.6865671641791045,
+      "grad_norm": 0.44723898312223315,
+      "learning_rate": 5.938520875298587e-07,
+      "loss": 0.0262,
+      "step": 113
+    },
+    {
+      "epoch": 1.7014925373134329,
+      "grad_norm": 0.4649229524932995,
+      "learning_rate": 5.396577872130676e-07,
+      "loss": 0.0234,
+      "step": 114
+    },
+    {
+      "epoch": 1.716417910447761,
+      "grad_norm": 0.46689935485099987,
+      "learning_rate": 4.879150238070585e-07,
+      "loss": 0.0235,
+      "step": 115
+    },
+    {
+      "epoch": 1.7313432835820897,
+      "grad_norm": 0.4250501253858005,
+      "learning_rate": 4.386522366755169e-07,
+      "loss": 0.021,
+      "step": 116
+    },
+    {
+      "epoch": 1.7462686567164178,
+      "grad_norm": 0.4965625077414352,
+      "learning_rate": 3.918965021133131e-07,
+      "loss": 0.0285,
+      "step": 117
+    },
+    {
+      "epoch": 1.7611940298507462,
+      "grad_norm": 0.5192751153508381,
+      "learning_rate": 3.4767351846456744e-07,
+      "loss": 0.0294,
+      "step": 118
+    },
+    {
+      "epoch": 1.7761194029850746,
+      "grad_norm": 0.4555879578505303,
+      "learning_rate": 3.0600759199806815e-07,
+      "loss": 0.026,
+      "step": 119
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.4702463723473376,
+      "learning_rate": 2.669216235478295e-07,
+      "loss": 0.0268,
+      "step": 120
+    },
+    {
+      "epoch": 1.8059701492537314,
+      "grad_norm": 0.5014638902986028,
+      "learning_rate": 2.3043709592610486e-07,
+      "loss": 0.0282,
+      "step": 121
+    },
+    {
+      "epoch": 1.8208955223880596,
+      "grad_norm": 0.5015871929717038,
+      "learning_rate": 1.9657406211579966e-07,
+      "loss": 0.0276,
+      "step": 122
+    },
+    {
+      "epoch": 1.835820895522388,
+      "grad_norm": 0.46199043552912816,
+      "learning_rate": 1.6535113424874683e-07,
+      "loss": 0.0253,
+      "step": 123
+    },
+    {
+      "epoch": 1.8507462686567164,
+      "grad_norm": 0.472386855814729,
+      "learning_rate": 1.3678547337593494e-07,
+      "loss": 0.0231,
+      "step": 124
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 0.44628541420234796,
+      "learning_rate": 1.1089278003527438e-07,
+      "loss": 0.0229,
+      "step": 125
+    },
+    {
+      "epoch": 1.8805970149253732,
+      "grad_norm": 0.4945658271403232,
+      "learning_rate": 8.768728562211948e-08,
+      "loss": 0.0259,
+      "step": 126
+    },
+    {
+      "epoch": 1.8955223880597014,
+      "grad_norm": 0.4631666908930044,
+      "learning_rate": 6.718174456726789e-08,
+      "loss": 0.0254,
+      "step": 127
+    },
+    {
+      "epoch": 1.9104477611940298,
+      "grad_norm": 0.47821378359248506,
+      "learning_rate": 4.9387427326745287e-08,
+      "loss": 0.0257,
+      "step": 128
+    },
+    {
+      "epoch": 1.9253731343283582,
+      "grad_norm": 0.4463060792083917,
+      "learning_rate": 3.431411418722941e-08,
+      "loss": 0.023,
+      "step": 129
+    },
+    {
+      "epoch": 1.9402985074626866,
+      "grad_norm": 0.4458879106581698,
+      "learning_rate": 2.1970089890509527e-08,
+      "loss": 0.0237,
+      "step": 130
+    },
+    {
+      "epoch": 1.955223880597015,
+      "grad_norm": 0.39654579447619215,
+      "learning_rate": 1.2362139079949431e-08,
+      "loss": 0.0193,
+      "step": 131
+    },
+    {
+      "epoch": 1.9701492537313432,
+      "grad_norm": 0.4384754664189478,
+      "learning_rate": 5.495542571443135e-09,
+      "loss": 0.0227,
+      "step": 132
+    },
+    {
+      "epoch": 1.9850746268656716,
+      "grad_norm": 0.40331068244695245,
+      "learning_rate": 1.3740744509205263e-09,
+      "loss": 0.0209,
+      "step": 133
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3037784601924941,
+      "learning_rate": 0.0,
+      "loss": 0.013,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "step": 134,
+      "total_flos": 8781261963264.0,
+      "train_loss": 0.05639281026574213,
+      "train_runtime": 528.9145,
+      "train_samples_per_second": 2.0,
+      "train_steps_per_second": 0.253
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 134,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8781261963264.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61aa69ec8272e56d6e47eabac7b8ca89deb857fce646c4690f6a4407cf75c000
+size 7224