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_14B
+  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_14B
+
+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_14B dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0929
+
+## 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": 0.09290952235460281,
+    "eval_runtime": 1.6243,
+    "eval_samples_per_second": 3.694,
+    "eval_steps_per_second": 1.231,
+    "total_flos": 8388071129088.0,
+    "train_loss": 0.06429206915345276,
+    "train_runtime": 510.1652,
+    "train_samples_per_second": 1.98,
+    "train_steps_per_second": 0.251
+}

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": 0.09290952235460281,
+    "eval_runtime": 1.6243,
+    "eval_samples_per_second": 3.694,
+    "eval_steps_per_second": 1.231
+}

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:b2a11fdfdedb8b45f429242544d3b3c9fb6633c3d37bc19b7c1645503d8b6353
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59611d9b1b7b14ca79f0afbb4a8a4ff3165690cd8203efe7874b893d0042bb89
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e208aca56e22642ea2b447232919063cb83cb588a90d269e26880d840e4922
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c69e4eeced8345a78884a434364e7bb2613946e05aea43adb1619cf0b1ed6a65
+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": 8388071129088.0,
+    "train_loss": 0.06429206915345276,
+    "train_runtime": 510.1652,
+    "train_samples_per_second": 1.98,
+    "train_steps_per_second": 0.251
+}

trainer_log.jsonl

@@ -0,0 +1,129 @@
+{"current_steps": 1, "total_steps": 128, "loss": 0.1884, "lr": 9.998494093481022e-06, "epoch": 0.015625, "percentage": 0.78, "elapsed_time": "0:00:04", "remaining_time": "0:10:31"}
+{"current_steps": 2, "total_steps": 128, "loss": 0.1357, "lr": 9.993977281025862e-06, "epoch": 0.03125, "percentage": 1.56, "elapsed_time": "0:00:08", "remaining_time": "0:08:56"}
+{"current_steps": 3, "total_steps": 128, "loss": 0.1269, "lr": 9.986452283393452e-06, "epoch": 0.046875, "percentage": 2.34, "elapsed_time": "0:00:11", "remaining_time": "0:08:19"}
+{"current_steps": 4, "total_steps": 128, "loss": 0.1362, "lr": 9.975923633360985e-06, "epoch": 0.0625, "percentage": 3.12, "elapsed_time": "0:00:15", "remaining_time": "0:07:57"}
+{"current_steps": 5, "total_steps": 128, "loss": 0.1146, "lr": 9.962397672993552e-06, "epoch": 0.078125, "percentage": 3.91, "elapsed_time": "0:00:18", "remaining_time": "0:07:44"}
+{"current_steps": 6, "total_steps": 128, "loss": 0.1168, "lr": 9.945882549823906e-06, "epoch": 0.09375, "percentage": 4.69, "elapsed_time": "0:00:22", "remaining_time": "0:07:34"}
+{"current_steps": 7, "total_steps": 128, "loss": 0.1066, "lr": 9.926388211944707e-06, "epoch": 0.109375, "percentage": 5.47, "elapsed_time": "0:00:25", "remaining_time": "0:07:27"}
+{"current_steps": 8, "total_steps": 128, "loss": 0.1008, "lr": 9.903926402016153e-06, "epoch": 0.125, "percentage": 6.25, "elapsed_time": "0:00:29", "remaining_time": "0:07:20"}
+{"current_steps": 9, "total_steps": 128, "loss": 0.1005, "lr": 9.878510650192644e-06, "epoch": 0.140625, "percentage": 7.03, "elapsed_time": "0:00:32", "remaining_time": "0:07:14"}
+{"current_steps": 10, "total_steps": 128, "loss": 0.0862, "lr": 9.850156265972722e-06, "epoch": 0.15625, "percentage": 7.81, "elapsed_time": "0:00:36", "remaining_time": "0:07:08"}
+{"current_steps": 11, "total_steps": 128, "loss": 0.1033, "lr": 9.8188803289772e-06, "epoch": 0.171875, "percentage": 8.59, "elapsed_time": "0:00:39", "remaining_time": "0:07:03"}
+{"current_steps": 12, "total_steps": 128, "loss": 0.1075, "lr": 9.784701678661045e-06, "epoch": 0.1875, "percentage": 9.38, "elapsed_time": "0:00:43", "remaining_time": "0:06:58"}
+{"current_steps": 13, "total_steps": 128, "loss": 0.1052, "lr": 9.747640902965185e-06, "epoch": 0.203125, "percentage": 10.16, "elapsed_time": "0:00:46", "remaining_time": "0:06:53"}
+{"current_steps": 14, "total_steps": 128, "loss": 0.0961, "lr": 9.707720325915105e-06, "epoch": 0.21875, "percentage": 10.94, "elapsed_time": "0:00:50", "remaining_time": "0:06:49"}
+{"current_steps": 15, "total_steps": 128, "loss": 0.0953, "lr": 9.664963994173695e-06, "epoch": 0.234375, "percentage": 11.72, "elapsed_time": "0:00:53", "remaining_time": "0:06:44"}
+{"current_steps": 16, "total_steps": 128, "loss": 0.1046, "lr": 9.619397662556434e-06, "epoch": 0.25, "percentage": 12.5, "elapsed_time": "0:00:57", "remaining_time": "0:06:40"}
+{"current_steps": 17, "total_steps": 128, "loss": 0.1184, "lr": 9.571048778517655e-06, "epoch": 0.265625, "percentage": 13.28, "elapsed_time": "0:01:00", "remaining_time": "0:06:36"}
+{"current_steps": 18, "total_steps": 128, "loss": 0.1007, "lr": 9.519946465617217e-06, "epoch": 0.28125, "percentage": 14.06, "elapsed_time": "0:01:04", "remaining_time": "0:06:32"}
+{"current_steps": 19, "total_steps": 128, "loss": 0.1024, "lr": 9.466121505977577e-06, "epoch": 0.296875, "percentage": 14.84, "elapsed_time": "0:01:07", "remaining_time": "0:06:28"}
+{"current_steps": 20, "total_steps": 128, "loss": 0.0949, "lr": 9.409606321741776e-06, "epoch": 0.3125, "percentage": 15.62, "elapsed_time": "0:01:11", "remaining_time": "0:06:24"}
+{"current_steps": 21, "total_steps": 128, "loss": 0.0996, "lr": 9.350434955543557e-06, "epoch": 0.328125, "percentage": 16.41, "elapsed_time": "0:01:14", "remaining_time": "0:06:20"}
+{"current_steps": 22, "total_steps": 128, "loss": 0.1065, "lr": 9.288643050001362e-06, "epoch": 0.34375, "percentage": 17.19, "elapsed_time": "0:01:18", "remaining_time": "0:06:16"}
+{"current_steps": 23, "total_steps": 128, "loss": 0.1095, "lr": 9.224267826248536e-06, "epoch": 0.359375, "percentage": 17.97, "elapsed_time": "0:01:21", "remaining_time": "0:06:12"}
+{"current_steps": 24, "total_steps": 128, "loss": 0.1116, "lr": 9.157348061512728e-06, "epoch": 0.375, "percentage": 18.75, "elapsed_time": "0:01:25", "remaining_time": "0:06:08"}
+{"current_steps": 25, "total_steps": 128, "loss": 0.0942, "lr": 9.08792406575792e-06, "epoch": 0.390625, "percentage": 19.53, "elapsed_time": "0:01:28", "remaining_time": "0:06:05"}
+{"current_steps": 26, "total_steps": 128, "loss": 0.0967, "lr": 9.016037657403225e-06, "epoch": 0.40625, "percentage": 20.31, "elapsed_time": "0:01:32", "remaining_time": "0:06:01"}
+{"current_steps": 27, "total_steps": 128, "loss": 0.0948, "lr": 8.941732138133032e-06, "epoch": 0.421875, "percentage": 21.09, "elapsed_time": "0:01:35", "remaining_time": "0:05:57"}
+{"current_steps": 28, "total_steps": 128, "loss": 0.1014, "lr": 8.865052266813686e-06, "epoch": 0.4375, "percentage": 21.88, "elapsed_time": "0:01:39", "remaining_time": "0:05:53"}
+{"current_steps": 29, "total_steps": 128, "loss": 0.0877, "lr": 8.786044232532423e-06, "epoch": 0.453125, "percentage": 22.66, "elapsed_time": "0:01:42", "remaining_time": "0:05:50"}
+{"current_steps": 30, "total_steps": 128, "loss": 0.0965, "lr": 8.704755626774796e-06, "epoch": 0.46875, "percentage": 23.44, "elapsed_time": "0:01:46", "remaining_time": "0:05:46"}
+{"current_steps": 31, "total_steps": 128, "loss": 0.1162, "lr": 8.621235414757337e-06, "epoch": 0.484375, "percentage": 24.22, "elapsed_time": "0:01:49", "remaining_time": "0:05:42"}
+{"current_steps": 32, "total_steps": 128, "loss": 0.1022, "lr": 8.535533905932739e-06, "epoch": 0.5, "percentage": 25.0, "elapsed_time": "0:01:53", "remaining_time": "0:05:39"}
+{"current_steps": 33, "total_steps": 128, "loss": 0.0826, "lr": 8.447702723685335e-06, "epoch": 0.515625, "percentage": 25.78, "elapsed_time": "0:01:56", "remaining_time": "0:05:35"}
+{"current_steps": 34, "total_steps": 128, "loss": 0.0918, "lr": 8.357794774235094e-06, "epoch": 0.53125, "percentage": 26.56, "elapsed_time": "0:02:00", "remaining_time": "0:05:31"}
+{"current_steps": 35, "total_steps": 128, "loss": 0.0811, "lr": 8.265864214768883e-06, "epoch": 0.546875, "percentage": 27.34, "elapsed_time": "0:02:03", "remaining_time": "0:05:28"}
+{"current_steps": 36, "total_steps": 128, "loss": 0.085, "lr": 8.171966420818227e-06, "epoch": 0.5625, "percentage": 28.12, "elapsed_time": "0:02:07", "remaining_time": "0:05:24"}
+{"current_steps": 37, "total_steps": 128, "loss": 0.0991, "lr": 8.076157952903134e-06, "epoch": 0.578125, "percentage": 28.91, "elapsed_time": "0:02:10", "remaining_time": "0:05:21"}
+{"current_steps": 38, "total_steps": 128, "loss": 0.1088, "lr": 7.978496522462167e-06, "epoch": 0.59375, "percentage": 29.69, "elapsed_time": "0:02:14", "remaining_time": "0:05:17"}
+{"current_steps": 39, "total_steps": 128, "loss": 0.0894, "lr": 7.879040957089229e-06, "epoch": 0.609375, "percentage": 30.47, "elapsed_time": "0:02:17", "remaining_time": "0:05:14"}
+{"current_steps": 40, "total_steps": 128, "loss": 0.1003, "lr": 7.777851165098012e-06, "epoch": 0.625, "percentage": 31.25, "elapsed_time": "0:02:21", "remaining_time": "0:05:10"}
+{"current_steps": 41, "total_steps": 128, "loss": 0.0862, "lr": 7.674988099435487e-06, "epoch": 0.640625, "percentage": 32.03, "elapsed_time": "0:02:24", "remaining_time": "0:05:06"}
+{"current_steps": 42, "total_steps": 128, "loss": 0.0986, "lr": 7.570513720966108e-06, "epoch": 0.65625, "percentage": 32.81, "elapsed_time": "0:02:28", "remaining_time": "0:05:03"}
+{"current_steps": 43, "total_steps": 128, "loss": 0.0839, "lr": 7.464490961148921e-06, "epoch": 0.671875, "percentage": 33.59, "elapsed_time": "0:02:31", "remaining_time": "0:04:59"}
+{"current_steps": 44, "total_steps": 128, "loss": 0.0884, "lr": 7.3569836841299905e-06, "epoch": 0.6875, "percentage": 34.38, "elapsed_time": "0:02:35", "remaining_time": "0:04:56"}
+{"current_steps": 45, "total_steps": 128, "loss": 0.0954, "lr": 7.248056648273034e-06, "epoch": 0.703125, "percentage": 35.16, "elapsed_time": "0:02:38", "remaining_time": "0:04:52"}
+{"current_steps": 46, "total_steps": 128, "loss": 0.0914, "lr": 7.137775467151411e-06, "epoch": 0.71875, "percentage": 35.94, "elapsed_time": "0:02:42", "remaining_time": "0:04:48"}
+{"current_steps": 47, "total_steps": 128, "loss": 0.0973, "lr": 7.026206570024949e-06, "epoch": 0.734375, "percentage": 36.72, "elapsed_time": "0:02:45", "remaining_time": "0:04:45"}
+{"current_steps": 48, "total_steps": 128, "loss": 0.1002, "lr": 6.913417161825449e-06, "epoch": 0.75, "percentage": 37.5, "elapsed_time": "0:02:49", "remaining_time": "0:04:41"}
+{"current_steps": 49, "total_steps": 128, "loss": 0.1046, "lr": 6.799475182674942e-06, "epoch": 0.765625, "percentage": 38.28, "elapsed_time": "0:02:52", "remaining_time": "0:04:38"}
+{"current_steps": 50, "total_steps": 128, "loss": 0.0928, "lr": 6.684449266961101e-06, "epoch": 0.78125, "percentage": 39.06, "elapsed_time": "0:02:56", "remaining_time": "0:04:34"}
+{"current_steps": 51, "total_steps": 128, "loss": 0.0869, "lr": 6.568408701994459e-06, "epoch": 0.796875, "percentage": 39.84, "elapsed_time": "0:02:59", "remaining_time": "0:04:31"}
+{"current_steps": 52, "total_steps": 128, "loss": 0.091, "lr": 6.451423386272312e-06, "epoch": 0.8125, "percentage": 40.62, "elapsed_time": "0:03:03", "remaining_time": "0:04:27"}
+{"current_steps": 53, "total_steps": 128, "loss": 0.0918, "lr": 6.333563787374493e-06, "epoch": 0.828125, "percentage": 41.41, "elapsed_time": "0:03:06", "remaining_time": "0:04:24"}
+{"current_steps": 54, "total_steps": 128, "loss": 0.0868, "lr": 6.21490089951632e-06, "epoch": 0.84375, "percentage": 42.19, "elapsed_time": "0:03:10", "remaining_time": "0:04:20"}
+{"current_steps": 55, "total_steps": 128, "loss": 0.0844, "lr": 6.095506200784349e-06, "epoch": 0.859375, "percentage": 42.97, "elapsed_time": "0:03:13", "remaining_time": "0:04:16"}
+{"current_steps": 56, "total_steps": 128, "loss": 0.0875, "lr": 5.975451610080643e-06, "epoch": 0.875, "percentage": 43.75, "elapsed_time": "0:03:17", "remaining_time": "0:04:13"}
+{"current_steps": 57, "total_steps": 128, "loss": 0.0838, "lr": 5.8548094438015065e-06, "epoch": 0.890625, "percentage": 44.53, "elapsed_time": "0:03:20", "remaining_time": "0:04:09"}
+{"current_steps": 58, "total_steps": 128, "loss": 0.0948, "lr": 5.733652372276809e-06, "epoch": 0.90625, "percentage": 45.31, "elapsed_time": "0:03:24", "remaining_time": "0:04:06"}
+{"current_steps": 59, "total_steps": 128, "loss": 0.1121, "lr": 5.612053375996082e-06, "epoch": 0.921875, "percentage": 46.09, "elapsed_time": "0:03:27", "remaining_time": "0:04:02"}
+{"current_steps": 60, "total_steps": 128, "loss": 0.0889, "lr": 5.490085701647805e-06, "epoch": 0.9375, "percentage": 46.88, "elapsed_time": "0:03:31", "remaining_time": "0:03:59"}
+{"current_steps": 61, "total_steps": 128, "loss": 0.0895, "lr": 5.367822817998338e-06, "epoch": 0.953125, "percentage": 47.66, "elapsed_time": "0:03:34", "remaining_time": "0:03:55"}
+{"current_steps": 62, "total_steps": 128, "loss": 0.0884, "lr": 5.245338371637091e-06, "epoch": 0.96875, "percentage": 48.44, "elapsed_time": "0:03:38", "remaining_time": "0:03:52"}
+{"current_steps": 63, "total_steps": 128, "loss": 0.1007, "lr": 5.122706142614562e-06, "epoch": 0.984375, "percentage": 49.22, "elapsed_time": "0:03:41", "remaining_time": "0:03:48"}
+{"current_steps": 64, "total_steps": 128, "loss": 0.0545, "lr": 5e-06, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:03:45", "remaining_time": "0:03:45"}
+{"current_steps": 65, "total_steps": 128, "loss": 0.0356, "lr": 4.87729385738544e-06, "epoch": 1.015625, "percentage": 50.78, "elapsed_time": "0:03:48", "remaining_time": "0:03:41"}
+{"current_steps": 66, "total_steps": 128, "loss": 0.0353, "lr": 4.75466162836291e-06, "epoch": 1.03125, "percentage": 51.56, "elapsed_time": "0:03:52", "remaining_time": "0:03:37"}
+{"current_steps": 67, "total_steps": 128, "loss": 0.0409, "lr": 4.6321771820016635e-06, "epoch": 1.046875, "percentage": 52.34, "elapsed_time": "0:03:55", "remaining_time": "0:03:34"}
+{"current_steps": 68, "total_steps": 128, "loss": 0.0341, "lr": 4.509914298352197e-06, "epoch": 1.0625, "percentage": 53.12, "elapsed_time": "0:03:59", "remaining_time": "0:03:30"}
+{"current_steps": 69, "total_steps": 128, "loss": 0.0389, "lr": 4.38794662400392e-06, "epoch": 1.078125, "percentage": 53.91, "elapsed_time": "0:04:02", "remaining_time": "0:03:27"}
+{"current_steps": 70, "total_steps": 128, "loss": 0.0362, "lr": 4.266347627723192e-06, "epoch": 1.09375, "percentage": 54.69, "elapsed_time": "0:04:05", "remaining_time": "0:03:23"}
+{"current_steps": 71, "total_steps": 128, "loss": 0.0346, "lr": 4.145190556198494e-06, "epoch": 1.109375, "percentage": 55.47, "elapsed_time": "0:04:09", "remaining_time": "0:03:20"}
+{"current_steps": 72, "total_steps": 128, "loss": 0.0405, "lr": 4.02454838991936e-06, "epoch": 1.125, "percentage": 56.25, "elapsed_time": "0:04:12", "remaining_time": "0:03:16"}
+{"current_steps": 73, "total_steps": 128, "loss": 0.0302, "lr": 3.904493799215652e-06, "epoch": 1.140625, "percentage": 57.03, "elapsed_time": "0:04:16", "remaining_time": "0:03:13"}
+{"current_steps": 74, "total_steps": 128, "loss": 0.0256, "lr": 3.7850991004836813e-06, "epoch": 1.15625, "percentage": 57.81, "elapsed_time": "0:04:19", "remaining_time": "0:03:09"}
+{"current_steps": 75, "total_steps": 128, "loss": 0.0337, "lr": 3.6664362126255087e-06, "epoch": 1.171875, "percentage": 58.59, "elapsed_time": "0:04:23", "remaining_time": "0:03:06"}
+{"current_steps": 76, "total_steps": 128, "loss": 0.0349, "lr": 3.5485766137276894e-06, "epoch": 1.1875, "percentage": 59.38, "elapsed_time": "0:04:26", "remaining_time": "0:03:02"}
+{"current_steps": 77, "total_steps": 128, "loss": 0.0296, "lr": 3.4315912980055433e-06, "epoch": 1.203125, "percentage": 60.16, "elapsed_time": "0:04:30", "remaining_time": "0:02:59"}
+{"current_steps": 78, "total_steps": 128, "loss": 0.0241, "lr": 3.3155507330389004e-06, "epoch": 1.21875, "percentage": 60.94, "elapsed_time": "0:04:34", "remaining_time": "0:02:55"}
+{"current_steps": 79, "total_steps": 128, "loss": 0.0284, "lr": 3.2005248173250593e-06, "epoch": 1.234375, "percentage": 61.72, "elapsed_time": "0:04:37", "remaining_time": "0:02:52"}
+{"current_steps": 80, "total_steps": 128, "loss": 0.025, "lr": 3.0865828381745515e-06, "epoch": 1.25, "percentage": 62.5, "elapsed_time": "0:04:41", "remaining_time": "0:02:48"}
+{"current_steps": 81, "total_steps": 128, "loss": 0.025, "lr": 2.9737934299750514e-06, "epoch": 1.265625, "percentage": 63.28, "elapsed_time": "0:04:44", "remaining_time": "0:02:45"}
+{"current_steps": 82, "total_steps": 128, "loss": 0.0306, "lr": 2.862224532848591e-06, "epoch": 1.28125, "percentage": 64.06, "elapsed_time": "0:04:47", "remaining_time": "0:02:41"}
+{"current_steps": 83, "total_steps": 128, "loss": 0.0305, "lr": 2.7519433517269665e-06, "epoch": 1.296875, "percentage": 64.84, "elapsed_time": "0:04:51", "remaining_time": "0:02:38"}
+{"current_steps": 84, "total_steps": 128, "loss": 0.0266, "lr": 2.6430163158700116e-06, "epoch": 1.3125, "percentage": 65.62, "elapsed_time": "0:04:54", "remaining_time": "0:02:34"}
+{"current_steps": 85, "total_steps": 128, "loss": 0.0284, "lr": 2.5355090388510806e-06, "epoch": 1.328125, "percentage": 66.41, "elapsed_time": "0:04:58", "remaining_time": "0:02:30"}
+{"current_steps": 86, "total_steps": 128, "loss": 0.0323, "lr": 2.429486279033892e-06, "epoch": 1.34375, "percentage": 67.19, "elapsed_time": "0:05:01", "remaining_time": "0:02:27"}
+{"current_steps": 87, "total_steps": 128, "loss": 0.0271, "lr": 2.325011900564515e-06, "epoch": 1.359375, "percentage": 67.97, "elapsed_time": "0:05:05", "remaining_time": "0:02:23"}
+{"current_steps": 88, "total_steps": 128, "loss": 0.028, "lr": 2.2221488349019903e-06, "epoch": 1.375, "percentage": 68.75, "elapsed_time": "0:05:08", "remaining_time": "0:02:20"}
+{"current_steps": 89, "total_steps": 128, "loss": 0.0219, "lr": 2.1209590429107734e-06, "epoch": 1.390625, "percentage": 69.53, "elapsed_time": "0:05:12", "remaining_time": "0:02:16"}
+{"current_steps": 90, "total_steps": 128, "loss": 0.0301, "lr": 2.0215034775378336e-06, "epoch": 1.40625, "percentage": 70.31, "elapsed_time": "0:05:15", "remaining_time": "0:02:13"}
+{"current_steps": 91, "total_steps": 128, "loss": 0.0276, "lr": 1.9238420470968665e-06, "epoch": 1.421875, "percentage": 71.09, "elapsed_time": "0:05:19", "remaining_time": "0:02:09"}
+{"current_steps": 92, "total_steps": 128, "loss": 0.0308, "lr": 1.8280335791817733e-06, "epoch": 1.4375, "percentage": 71.88, "elapsed_time": "0:05:22", "remaining_time": "0:02:06"}
+{"current_steps": 93, "total_steps": 128, "loss": 0.0281, "lr": 1.7341357852311175e-06, "epoch": 1.453125, "percentage": 72.66, "elapsed_time": "0:05:26", "remaining_time": "0:02:02"}
+{"current_steps": 94, "total_steps": 128, "loss": 0.0268, "lr": 1.642205225764908e-06, "epoch": 1.46875, "percentage": 73.44, "elapsed_time": "0:05:29", "remaining_time": "0:01:59"}
+{"current_steps": 95, "total_steps": 128, "loss": 0.0299, "lr": 1.5522972763146653e-06, "epoch": 1.484375, "percentage": 74.22, "elapsed_time": "0:05:33", "remaining_time": "0:01:55"}
+{"current_steps": 96, "total_steps": 128, "loss": 0.0253, "lr": 1.4644660940672628e-06, "epoch": 1.5, "percentage": 75.0, "elapsed_time": "0:05:36", "remaining_time": "0:01:52"}
+{"current_steps": 97, "total_steps": 128, "loss": 0.025, "lr": 1.3787645852426663e-06, "epoch": 1.515625, "percentage": 75.78, "elapsed_time": "0:05:40", "remaining_time": "0:01:48"}
+{"current_steps": 98, "total_steps": 128, "loss": 0.0256, "lr": 1.2952443732252058e-06, "epoch": 1.53125, "percentage": 76.56, "elapsed_time": "0:05:43", "remaining_time": "0:01:45"}
+{"current_steps": 99, "total_steps": 128, "loss": 0.0277, "lr": 1.2139557674675773e-06, "epoch": 1.546875, "percentage": 77.34, "elapsed_time": "0:05:47", "remaining_time": "0:01:41"}
+{"current_steps": 100, "total_steps": 128, "loss": 0.0294, "lr": 1.134947733186315e-06, "epoch": 1.5625, "percentage": 78.12, "elapsed_time": "0:05:50", "remaining_time": "0:01:38"}
+{"current_steps": 101, "total_steps": 128, "loss": 0.0275, "lr": 1.058267861866969e-06, "epoch": 1.578125, "percentage": 78.91, "elapsed_time": "0:05:54", "remaining_time": "0:01:34"}
+{"current_steps": 102, "total_steps": 128, "loss": 0.0316, "lr": 9.83962342596776e-07, "epoch": 1.59375, "percentage": 79.69, "elapsed_time": "0:05:57", "remaining_time": "0:01:31"}
+{"current_steps": 103, "total_steps": 128, "loss": 0.0321, "lr": 9.120759342420821e-07, "epoch": 1.609375, "percentage": 80.47, "elapsed_time": "0:06:01", "remaining_time": "0:01:27"}
+{"current_steps": 104, "total_steps": 128, "loss": 0.0236, "lr": 8.426519384872733e-07, "epoch": 1.625, "percentage": 81.25, "elapsed_time": "0:06:04", "remaining_time": "0:01:24"}
+{"current_steps": 105, "total_steps": 128, "loss": 0.031, "lr": 7.757321737514645e-07, "epoch": 1.640625, "percentage": 82.03, "elapsed_time": "0:06:08", "remaining_time": "0:01:20"}
+{"current_steps": 106, "total_steps": 128, "loss": 0.0305, "lr": 7.113569499986401e-07, "epoch": 1.65625, "percentage": 82.81, "elapsed_time": "0:06:11", "remaining_time": "0:01:17"}
+{"current_steps": 107, "total_steps": 128, "loss": 0.0266, "lr": 6.495650444564433e-07, "epoch": 1.671875, "percentage": 83.59, "elapsed_time": "0:06:15", "remaining_time": "0:01:13"}
+{"current_steps": 108, "total_steps": 128, "loss": 0.0273, "lr": 5.903936782582253e-07, "epoch": 1.6875, "percentage": 84.38, "elapsed_time": "0:06:18", "remaining_time": "0:01:10"}
+{"current_steps": 109, "total_steps": 128, "loss": 0.0282, "lr": 5.338784940224239e-07, "epoch": 1.703125, "percentage": 85.16, "elapsed_time": "0:06:22", "remaining_time": "0:01:06"}
+{"current_steps": 110, "total_steps": 128, "loss": 0.0297, "lr": 4.800535343827834e-07, "epoch": 1.71875, "percentage": 85.94, "elapsed_time": "0:06:25", "remaining_time": "0:01:03"}
+{"current_steps": 111, "total_steps": 128, "loss": 0.0279, "lr": 4.289512214823466e-07, "epoch": 1.734375, "percentage": 86.72, "elapsed_time": "0:06:28", "remaining_time": "0:00:59"}
+{"current_steps": 112, "total_steps": 128, "loss": 0.0235, "lr": 3.8060233744356634e-07, "epoch": 1.75, "percentage": 87.5, "elapsed_time": "0:06:32", "remaining_time": "0:00:56"}
+{"current_steps": 113, "total_steps": 128, "loss": 0.0277, "lr": 3.350360058263058e-07, "epoch": 1.765625, "percentage": 88.28, "elapsed_time": "0:06:36", "remaining_time": "0:00:52"}
+{"current_steps": 114, "total_steps": 128, "loss": 0.0274, "lr": 2.9227967408489653e-07, "epoch": 1.78125, "percentage": 89.06, "elapsed_time": "0:06:39", "remaining_time": "0:00:49"}
+{"current_steps": 115, "total_steps": 128, "loss": 0.0285, "lr": 2.523590970348166e-07, "epoch": 1.796875, "percentage": 89.84, "elapsed_time": "0:06:42", "remaining_time": "0:00:45"}
+{"current_steps": 116, "total_steps": 128, "loss": 0.0297, "lr": 2.152983213389559e-07, "epoch": 1.8125, "percentage": 90.62, "elapsed_time": "0:06:46", "remaining_time": "0:00:42"}
+{"current_steps": 117, "total_steps": 128, "loss": 0.0302, "lr": 1.8111967102280082e-07, "epoch": 1.828125, "percentage": 91.41, "elapsed_time": "0:06:49", "remaining_time": "0:00:38"}
+{"current_steps": 118, "total_steps": 128, "loss": 0.0293, "lr": 1.4984373402728014e-07, "epoch": 1.84375, "percentage": 92.19, "elapsed_time": "0:06:53", "remaining_time": "0:00:35"}
+{"current_steps": 119, "total_steps": 128, "loss": 0.0328, "lr": 1.2148934980735772e-07, "epoch": 1.859375, "percentage": 92.97, "elapsed_time": "0:06:56", "remaining_time": "0:00:31"}
+{"current_steps": 120, "total_steps": 128, "loss": 0.0232, "lr": 9.607359798384785e-08, "epoch": 1.875, "percentage": 93.75, "elapsed_time": "0:07:00", "remaining_time": "0:00:28"}
+{"current_steps": 121, "total_steps": 128, "loss": 0.0283, "lr": 7.36117880552939e-08, "epoch": 1.890625, "percentage": 94.53, "elapsed_time": "0:07:03", "remaining_time": "0:00:24"}
+{"current_steps": 122, "total_steps": 128, "loss": 0.0279, "lr": 5.411745017609493e-08, "epoch": 1.90625, "percentage": 95.31, "elapsed_time": "0:07:07", "remaining_time": "0:00:21"}
+{"current_steps": 123, "total_steps": 128, "loss": 0.0268, "lr": 3.7602327006450166e-08, "epoch": 1.921875, "percentage": 96.09, "elapsed_time": "0:07:10", "remaining_time": "0:00:17"}
+{"current_steps": 124, "total_steps": 128, "loss": 0.0231, "lr": 2.4076366639015914e-08, "epoch": 1.9375, "percentage": 96.88, "elapsed_time": "0:07:14", "remaining_time": "0:00:14"}
+{"current_steps": 125, "total_steps": 128, "loss": 0.0274, "lr": 1.3547716606548967e-08, "epoch": 1.953125, "percentage": 97.66, "elapsed_time": "0:07:17", "remaining_time": "0:00:10"}
+{"current_steps": 126, "total_steps": 128, "loss": 0.033, "lr": 6.022718974137976e-09, "epoch": 1.96875, "percentage": 98.44, "elapsed_time": "0:07:21", "remaining_time": "0:00:07"}
+{"current_steps": 127, "total_steps": 128, "loss": 0.0263, "lr": 1.5059065189787502e-09, "epoch": 1.984375, "percentage": 99.22, "elapsed_time": "0:07:24", "remaining_time": "0:00:03"}
+{"current_steps": 128, "total_steps": 128, "loss": 0.0083, "lr": 0.0, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:07:28", "remaining_time": "0:00:00"}
+{"current_steps": 128, "total_steps": 128, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:08:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,938 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 200,
+  "global_step": 128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015625,
+      "grad_norm": 2.6739093878685534,
+      "learning_rate": 9.998494093481022e-06,
+      "loss": 0.1884,
+      "step": 1
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 1.5150395940979025,
+      "learning_rate": 9.993977281025862e-06,
+      "loss": 0.1357,
+      "step": 2
+    },
+    {
+      "epoch": 0.046875,
+      "grad_norm": 2.16300945908671,
+      "learning_rate": 9.986452283393452e-06,
+      "loss": 0.1269,
+      "step": 3
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 1.5489640346966365,
+      "learning_rate": 9.975923633360985e-06,
+      "loss": 0.1362,
+      "step": 4
+    },
+    {
+      "epoch": 0.078125,
+      "grad_norm": 1.2513126922501931,
+      "learning_rate": 9.962397672993552e-06,
+      "loss": 0.1146,
+      "step": 5
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 0.9793052321212995,
+      "learning_rate": 9.945882549823906e-06,
+      "loss": 0.1168,
+      "step": 6
+    },
+    {
+      "epoch": 0.109375,
+      "grad_norm": 0.820453791626023,
+      "learning_rate": 9.926388211944707e-06,
+      "loss": 0.1066,
+      "step": 7
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.8357123929232244,
+      "learning_rate": 9.903926402016153e-06,
+      "loss": 0.1008,
+      "step": 8
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 0.8009873364303057,
+      "learning_rate": 9.878510650192644e-06,
+      "loss": 0.1005,
+      "step": 9
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.7133506689562682,
+      "learning_rate": 9.850156265972722e-06,
+      "loss": 0.0862,
+      "step": 10
+    },
+    {
+      "epoch": 0.171875,
+      "grad_norm": 0.794798596181329,
+      "learning_rate": 9.8188803289772e-06,
+      "loss": 0.1033,
+      "step": 11
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.9214967897117932,
+      "learning_rate": 9.784701678661045e-06,
+      "loss": 0.1075,
+      "step": 12
+    },
+    {
+      "epoch": 0.203125,
+      "grad_norm": 0.8040392763902259,
+      "learning_rate": 9.747640902965185e-06,
+      "loss": 0.1052,
+      "step": 13
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 0.7637245475364027,
+      "learning_rate": 9.707720325915105e-06,
+      "loss": 0.0961,
+      "step": 14
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 0.7719801074728877,
+      "learning_rate": 9.664963994173695e-06,
+      "loss": 0.0953,
+      "step": 15
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8298026966149673,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 0.1046,
+      "step": 16
+    },
+    {
+      "epoch": 0.265625,
+      "grad_norm": 0.8099234167451864,
+      "learning_rate": 9.571048778517655e-06,
+      "loss": 0.1184,
+      "step": 17
+    },
+    {
+      "epoch": 0.28125,
+      "grad_norm": 0.7058329181221473,
+      "learning_rate": 9.519946465617217e-06,
+      "loss": 0.1007,
+      "step": 18
+    },
+    {
+      "epoch": 0.296875,
+      "grad_norm": 0.6760276718346077,
+      "learning_rate": 9.466121505977577e-06,
+      "loss": 0.1024,
+      "step": 19
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.7030545259444668,
+      "learning_rate": 9.409606321741776e-06,
+      "loss": 0.0949,
+      "step": 20
+    },
+    {
+      "epoch": 0.328125,
+      "grad_norm": 0.646334696265569,
+      "learning_rate": 9.350434955543557e-06,
+      "loss": 0.0996,
+      "step": 21
+    },
+    {
+      "epoch": 0.34375,
+      "grad_norm": 0.7217437829829945,
+      "learning_rate": 9.288643050001362e-06,
+      "loss": 0.1065,
+      "step": 22
+    },
+    {
+      "epoch": 0.359375,
+      "grad_norm": 0.6334419711757079,
+      "learning_rate": 9.224267826248536e-06,
+      "loss": 0.1095,
+      "step": 23
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.6946688321879799,
+      "learning_rate": 9.157348061512728e-06,
+      "loss": 0.1116,
+      "step": 24
+    },
+    {
+      "epoch": 0.390625,
+      "grad_norm": 0.6356726912535626,
+      "learning_rate": 9.08792406575792e-06,
+      "loss": 0.0942,
+      "step": 25
+    },
+    {
+      "epoch": 0.40625,
+      "grad_norm": 0.7321662509467197,
+      "learning_rate": 9.016037657403225e-06,
+      "loss": 0.0967,
+      "step": 26
+    },
+    {
+      "epoch": 0.421875,
+      "grad_norm": 0.6161986715122739,
+      "learning_rate": 8.941732138133032e-06,
+      "loss": 0.0948,
+      "step": 27
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 0.6660290406349066,
+      "learning_rate": 8.865052266813686e-06,
+      "loss": 0.1014,
+      "step": 28
+    },
+    {
+      "epoch": 0.453125,
+      "grad_norm": 0.6900382702080303,
+      "learning_rate": 8.786044232532423e-06,
+      "loss": 0.0877,
+      "step": 29
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.6819465894993961,
+      "learning_rate": 8.704755626774796e-06,
+      "loss": 0.0965,
+      "step": 30
+    },
+    {
+      "epoch": 0.484375,
+      "grad_norm": 0.8163312223253769,
+      "learning_rate": 8.621235414757337e-06,
+      "loss": 0.1162,
+      "step": 31
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.6953145713773954,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 0.1022,
+      "step": 32
+    },
+    {
+      "epoch": 0.515625,
+      "grad_norm": 0.6447805022586731,
+      "learning_rate": 8.447702723685335e-06,
+      "loss": 0.0826,
+      "step": 33
+    },
+    {
+      "epoch": 0.53125,
+      "grad_norm": 0.7110541795861288,
+      "learning_rate": 8.357794774235094e-06,
+      "loss": 0.0918,
+      "step": 34
+    },
+    {
+      "epoch": 0.546875,
+      "grad_norm": 0.6489076619964651,
+      "learning_rate": 8.265864214768883e-06,
+      "loss": 0.0811,
+      "step": 35
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 0.6144097444230083,
+      "learning_rate": 8.171966420818227e-06,
+      "loss": 0.085,
+      "step": 36
+    },
+    {
+      "epoch": 0.578125,
+      "grad_norm": 0.6971479575573085,
+      "learning_rate": 8.076157952903134e-06,
+      "loss": 0.0991,
+      "step": 37
+    },
+    {
+      "epoch": 0.59375,
+      "grad_norm": 0.7448175513314506,
+      "learning_rate": 7.978496522462167e-06,
+      "loss": 0.1088,
+      "step": 38
+    },
+    {
+      "epoch": 0.609375,
+      "grad_norm": 0.6542476368831329,
+      "learning_rate": 7.879040957089229e-06,
+      "loss": 0.0894,
+      "step": 39
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.6961238719843766,
+      "learning_rate": 7.777851165098012e-06,
+      "loss": 0.1003,
+      "step": 40
+    },
+    {
+      "epoch": 0.640625,
+      "grad_norm": 0.6182766917080559,
+      "learning_rate": 7.674988099435487e-06,
+      "loss": 0.0862,
+      "step": 41
+    },
+    {
+      "epoch": 0.65625,
+      "grad_norm": 0.7135356957520481,
+      "learning_rate": 7.570513720966108e-06,
+      "loss": 0.0986,
+      "step": 42
+    },
+    {
+      "epoch": 0.671875,
+      "grad_norm": 0.5588988402555205,
+      "learning_rate": 7.464490961148921e-06,
+      "loss": 0.0839,
+      "step": 43
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 0.6362849856445698,
+      "learning_rate": 7.3569836841299905e-06,
+      "loss": 0.0884,
+      "step": 44
+    },
+    {
+      "epoch": 0.703125,
+      "grad_norm": 0.63889608240053,
+      "learning_rate": 7.248056648273034e-06,
+      "loss": 0.0954,
+      "step": 45
+    },
+    {
+      "epoch": 0.71875,
+      "grad_norm": 0.6352172992397227,
+      "learning_rate": 7.137775467151411e-06,
+      "loss": 0.0914,
+      "step": 46
+    },
+    {
+      "epoch": 0.734375,
+      "grad_norm": 0.6235534667045575,
+      "learning_rate": 7.026206570024949e-06,
+      "loss": 0.0973,
+      "step": 47
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6932880132680317,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.1002,
+      "step": 48
+    },
+    {
+      "epoch": 0.765625,
+      "grad_norm": 0.6753811841355055,
+      "learning_rate": 6.799475182674942e-06,
+      "loss": 0.1046,
+      "step": 49
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.6259011977621143,
+      "learning_rate": 6.684449266961101e-06,
+      "loss": 0.0928,
+      "step": 50
+    },
+    {
+      "epoch": 0.796875,
+      "grad_norm": 0.6381230847102777,
+      "learning_rate": 6.568408701994459e-06,
+      "loss": 0.0869,
+      "step": 51
+    },
+    {
+      "epoch": 0.8125,
+      "grad_norm": 0.6331334051423652,
+      "learning_rate": 6.451423386272312e-06,
+      "loss": 0.091,
+      "step": 52
+    },
+    {
+      "epoch": 0.828125,
+      "grad_norm": 0.6353705242474821,
+      "learning_rate": 6.333563787374493e-06,
+      "loss": 0.0918,
+      "step": 53
+    },
+    {
+      "epoch": 0.84375,
+      "grad_norm": 0.6487508294049062,
+      "learning_rate": 6.21490089951632e-06,
+      "loss": 0.0868,
+      "step": 54
+    },
+    {
+      "epoch": 0.859375,
+      "grad_norm": 0.5924237056373642,
+      "learning_rate": 6.095506200784349e-06,
+      "loss": 0.0844,
+      "step": 55
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.5931187712507139,
+      "learning_rate": 5.975451610080643e-06,
+      "loss": 0.0875,
+      "step": 56
+    },
+    {
+      "epoch": 0.890625,
+      "grad_norm": 0.6071740951835457,
+      "learning_rate": 5.8548094438015065e-06,
+      "loss": 0.0838,
+      "step": 57
+    },
+    {
+      "epoch": 0.90625,
+      "grad_norm": 0.6648426758128066,
+      "learning_rate": 5.733652372276809e-06,
+      "loss": 0.0948,
+      "step": 58
+    },
+    {
+      "epoch": 0.921875,
+      "grad_norm": 0.722531323677584,
+      "learning_rate": 5.612053375996082e-06,
+      "loss": 0.1121,
+      "step": 59
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.6488826648201073,
+      "learning_rate": 5.490085701647805e-06,
+      "loss": 0.0889,
+      "step": 60
+    },
+    {
+      "epoch": 0.953125,
+      "grad_norm": 0.6442896241905133,
+      "learning_rate": 5.367822817998338e-06,
+      "loss": 0.0895,
+      "step": 61
+    },
+    {
+      "epoch": 0.96875,
+      "grad_norm": 0.6325206689621374,
+      "learning_rate": 5.245338371637091e-06,
+      "loss": 0.0884,
+      "step": 62
+    },
+    {
+      "epoch": 0.984375,
+      "grad_norm": 0.673453515328055,
+      "learning_rate": 5.122706142614562e-06,
+      "loss": 0.1007,
+      "step": 63
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5392774078549535,
+      "learning_rate": 5e-06,
+      "loss": 0.0545,
+      "step": 64
+    },
+    {
+      "epoch": 1.015625,
+      "grad_norm": 0.4376013738416055,
+      "learning_rate": 4.87729385738544e-06,
+      "loss": 0.0356,
+      "step": 65
+    },
+    {
+      "epoch": 1.03125,
+      "grad_norm": 0.4095985770051886,
+      "learning_rate": 4.75466162836291e-06,
+      "loss": 0.0353,
+      "step": 66
+    },
+    {
+      "epoch": 1.046875,
+      "grad_norm": 0.49049252005104743,
+      "learning_rate": 4.6321771820016635e-06,
+      "loss": 0.0409,
+      "step": 67
+    },
+    {
+      "epoch": 1.0625,
+      "grad_norm": 0.42592657183664556,
+      "learning_rate": 4.509914298352197e-06,
+      "loss": 0.0341,
+      "step": 68
+    },
+    {
+      "epoch": 1.078125,
+      "grad_norm": 0.44087457144025816,
+      "learning_rate": 4.38794662400392e-06,
+      "loss": 0.0389,
+      "step": 69
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 0.4416199597525101,
+      "learning_rate": 4.266347627723192e-06,
+      "loss": 0.0362,
+      "step": 70
+    },
+    {
+      "epoch": 1.109375,
+      "grad_norm": 0.40183811423101806,
+      "learning_rate": 4.145190556198494e-06,
+      "loss": 0.0346,
+      "step": 71
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.5044350489100425,
+      "learning_rate": 4.02454838991936e-06,
+      "loss": 0.0405,
+      "step": 72
+    },
+    {
+      "epoch": 1.140625,
+      "grad_norm": 0.4155854440596093,
+      "learning_rate": 3.904493799215652e-06,
+      "loss": 0.0302,
+      "step": 73
+    },
+    {
+      "epoch": 1.15625,
+      "grad_norm": 0.39292495064929295,
+      "learning_rate": 3.7850991004836813e-06,
+      "loss": 0.0256,
+      "step": 74
+    },
+    {
+      "epoch": 1.171875,
+      "grad_norm": 0.46111326993371976,
+      "learning_rate": 3.6664362126255087e-06,
+      "loss": 0.0337,
+      "step": 75
+    },
+    {
+      "epoch": 1.1875,
+      "grad_norm": 0.492674931519674,
+      "learning_rate": 3.5485766137276894e-06,
+      "loss": 0.0349,
+      "step": 76
+    },
+    {
+      "epoch": 1.203125,
+      "grad_norm": 0.4807469026305343,
+      "learning_rate": 3.4315912980055433e-06,
+      "loss": 0.0296,
+      "step": 77
+    },
+    {
+      "epoch": 1.21875,
+      "grad_norm": 0.49686239139929667,
+      "learning_rate": 3.3155507330389004e-06,
+      "loss": 0.0241,
+      "step": 78
+    },
+    {
+      "epoch": 1.234375,
+      "grad_norm": 0.5006991785363456,
+      "learning_rate": 3.2005248173250593e-06,
+      "loss": 0.0284,
+      "step": 79
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.4611185416821016,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 0.025,
+      "step": 80
+    },
+    {
+      "epoch": 1.265625,
+      "grad_norm": 0.44135348453097484,
+      "learning_rate": 2.9737934299750514e-06,
+      "loss": 0.025,
+      "step": 81
+    },
+    {
+      "epoch": 1.28125,
+      "grad_norm": 0.5602242365372585,
+      "learning_rate": 2.862224532848591e-06,
+      "loss": 0.0306,
+      "step": 82
+    },
+    {
+      "epoch": 1.296875,
+      "grad_norm": 0.5377956256874117,
+      "learning_rate": 2.7519433517269665e-06,
+      "loss": 0.0305,
+      "step": 83
+    },
+    {
+      "epoch": 1.3125,
+      "grad_norm": 0.5133881243493821,
+      "learning_rate": 2.6430163158700116e-06,
+      "loss": 0.0266,
+      "step": 84
+    },
+    {
+      "epoch": 1.328125,
+      "grad_norm": 0.5444012333884268,
+      "learning_rate": 2.5355090388510806e-06,
+      "loss": 0.0284,
+      "step": 85
+    },
+    {
+      "epoch": 1.34375,
+      "grad_norm": 0.5534352410842232,
+      "learning_rate": 2.429486279033892e-06,
+      "loss": 0.0323,
+      "step": 86
+    },
+    {
+      "epoch": 1.359375,
+      "grad_norm": 0.5341689967883586,
+      "learning_rate": 2.325011900564515e-06,
+      "loss": 0.0271,
+      "step": 87
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.5469722181023687,
+      "learning_rate": 2.2221488349019903e-06,
+      "loss": 0.028,
+      "step": 88
+    },
+    {
+      "epoch": 1.390625,
+      "grad_norm": 0.4625514384385154,
+      "learning_rate": 2.1209590429107734e-06,
+      "loss": 0.0219,
+      "step": 89
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 0.521847214934227,
+      "learning_rate": 2.0215034775378336e-06,
+      "loss": 0.0301,
+      "step": 90
+    },
+    {
+      "epoch": 1.421875,
+      "grad_norm": 0.549722662685222,
+      "learning_rate": 1.9238420470968665e-06,
+      "loss": 0.0276,
+      "step": 91
+    },
+    {
+      "epoch": 1.4375,
+      "grad_norm": 0.5150806177028199,
+      "learning_rate": 1.8280335791817733e-06,
+      "loss": 0.0308,
+      "step": 92
+    },
+    {
+      "epoch": 1.453125,
+      "grad_norm": 0.5032030481845989,
+      "learning_rate": 1.7341357852311175e-06,
+      "loss": 0.0281,
+      "step": 93
+    },
+    {
+      "epoch": 1.46875,
+      "grad_norm": 0.5148113625886926,
+      "learning_rate": 1.642205225764908e-06,
+      "loss": 0.0268,
+      "step": 94
+    },
+    {
+      "epoch": 1.484375,
+      "grad_norm": 0.5137472637390804,
+      "learning_rate": 1.5522972763146653e-06,
+      "loss": 0.0299,
+      "step": 95
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5170834403738277,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.0253,
+      "step": 96
+    },
+    {
+      "epoch": 1.515625,
+      "grad_norm": 0.47370297895978036,
+      "learning_rate": 1.3787645852426663e-06,
+      "loss": 0.025,
+      "step": 97
+    },
+    {
+      "epoch": 1.53125,
+      "grad_norm": 0.4777090892776284,
+      "learning_rate": 1.2952443732252058e-06,
+      "loss": 0.0256,
+      "step": 98
+    },
+    {
+      "epoch": 1.546875,
+      "grad_norm": 0.534024147259357,
+      "learning_rate": 1.2139557674675773e-06,
+      "loss": 0.0277,
+      "step": 99
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 0.5133782827013872,
+      "learning_rate": 1.134947733186315e-06,
+      "loss": 0.0294,
+      "step": 100
+    },
+    {
+      "epoch": 1.578125,
+      "grad_norm": 0.4707474334923019,
+      "learning_rate": 1.058267861866969e-06,
+      "loss": 0.0275,
+      "step": 101
+    },
+    {
+      "epoch": 1.59375,
+      "grad_norm": 0.537283441061544,
+      "learning_rate": 9.83962342596776e-07,
+      "loss": 0.0316,
+      "step": 102
+    },
+    {
+      "epoch": 1.609375,
+      "grad_norm": 0.5533593813848264,
+      "learning_rate": 9.120759342420821e-07,
+      "loss": 0.0321,
+      "step": 103
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.4827736705680129,
+      "learning_rate": 8.426519384872733e-07,
+      "loss": 0.0236,
+      "step": 104
+    },
+    {
+      "epoch": 1.640625,
+      "grad_norm": 0.5228741253702182,
+      "learning_rate": 7.757321737514645e-07,
+      "loss": 0.031,
+      "step": 105
+    },
+    {
+      "epoch": 1.65625,
+      "grad_norm": 0.5080355689100275,
+      "learning_rate": 7.113569499986401e-07,
+      "loss": 0.0305,
+      "step": 106
+    },
+    {
+      "epoch": 1.671875,
+      "grad_norm": 0.48424382102099495,
+      "learning_rate": 6.495650444564433e-07,
+      "loss": 0.0266,
+      "step": 107
+    },
+    {
+      "epoch": 1.6875,
+      "grad_norm": 0.505891735678738,
+      "learning_rate": 5.903936782582253e-07,
+      "loss": 0.0273,
+      "step": 108
+    },
+    {
+      "epoch": 1.703125,
+      "grad_norm": 0.48535517340207013,
+      "learning_rate": 5.338784940224239e-07,
+      "loss": 0.0282,
+      "step": 109
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 0.5082583985009761,
+      "learning_rate": 4.800535343827834e-07,
+      "loss": 0.0297,
+      "step": 110
+    },
+    {
+      "epoch": 1.734375,
+      "grad_norm": 0.4770751669973784,
+      "learning_rate": 4.289512214823466e-07,
+      "loss": 0.0279,
+      "step": 111
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.5068858730922113,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 0.0235,
+      "step": 112
+    },
+    {
+      "epoch": 1.765625,
+      "grad_norm": 0.46398347202121104,
+      "learning_rate": 3.350360058263058e-07,
+      "loss": 0.0277,
+      "step": 113
+    },
+    {
+      "epoch": 1.78125,
+      "grad_norm": 0.48910952726300494,
+      "learning_rate": 2.9227967408489653e-07,
+      "loss": 0.0274,
+      "step": 114
+    },
+    {
+      "epoch": 1.796875,
+      "grad_norm": 0.47504133206678467,
+      "learning_rate": 2.523590970348166e-07,
+      "loss": 0.0285,
+      "step": 115
+    },
+    {
+      "epoch": 1.8125,
+      "grad_norm": 0.5169499364495718,
+      "learning_rate": 2.152983213389559e-07,
+      "loss": 0.0297,
+      "step": 116
+    },
+    {
+      "epoch": 1.828125,
+      "grad_norm": 0.49801365111027146,
+      "learning_rate": 1.8111967102280082e-07,
+      "loss": 0.0302,
+      "step": 117
+    },
+    {
+      "epoch": 1.84375,
+      "grad_norm": 0.5206807127997487,
+      "learning_rate": 1.4984373402728014e-07,
+      "loss": 0.0293,
+      "step": 118
+    },
+    {
+      "epoch": 1.859375,
+      "grad_norm": 0.5430755283834333,
+      "learning_rate": 1.2148934980735772e-07,
+      "loss": 0.0328,
+      "step": 119
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.4685437204332103,
+      "learning_rate": 9.607359798384785e-08,
+      "loss": 0.0232,
+      "step": 120
+    },
+    {
+      "epoch": 1.890625,
+      "grad_norm": 0.46129058037821774,
+      "learning_rate": 7.36117880552939e-08,
+      "loss": 0.0283,
+      "step": 121
+    },
+    {
+      "epoch": 1.90625,
+      "grad_norm": 0.49727346395882577,
+      "learning_rate": 5.411745017609493e-08,
+      "loss": 0.0279,
+      "step": 122
+    },
+    {
+      "epoch": 1.921875,
+      "grad_norm": 0.5083866100352399,
+      "learning_rate": 3.7602327006450166e-08,
+      "loss": 0.0268,
+      "step": 123
+    },
+    {
+      "epoch": 1.9375,
+      "grad_norm": 0.40937582025626196,
+      "learning_rate": 2.4076366639015914e-08,
+      "loss": 0.0231,
+      "step": 124
+    },
+    {
+      "epoch": 1.953125,
+      "grad_norm": 0.448869894081849,
+      "learning_rate": 1.3547716606548967e-08,
+      "loss": 0.0274,
+      "step": 125
+    },
+    {
+      "epoch": 1.96875,
+      "grad_norm": 0.5418824208903777,
+      "learning_rate": 6.022718974137976e-09,
+      "loss": 0.033,
+      "step": 126
+    },
+    {
+      "epoch": 1.984375,
+      "grad_norm": 0.4792037246917596,
+      "learning_rate": 1.5059065189787502e-09,
+      "loss": 0.0263,
+      "step": 127
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22894187513794292,
+      "learning_rate": 0.0,
+      "loss": 0.0083,
+      "step": 128
+    },
+    {
+      "epoch": 2.0,
+      "step": 128,
+      "total_flos": 8388071129088.0,
+      "train_loss": 0.06429206915345276,
+      "train_runtime": 510.1652,
+      "train_samples_per_second": 1.98,
+      "train_steps_per_second": 0.251
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 128,
+  "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": 8388071129088.0,
+  "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 sha256:128c0ad685ececbf13b49dece3837e809c35ed2298ee93ee3bc6095600be7737
+size 7224