Upload 16 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 data/whole_data_v2.json filter=lfs diff=lfs merge=lfs -text
+model_weights/tokenizer.json filter=lfs diff=lfs merge=lfs -text

model_weights/README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: /ailab/user/zhouhao1/LLaMA-Factory/saves/Qwen2.5-7B-Instruct/full/sft/varify_yaoying_knowledge/1epoch/1e-5
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 1e-5
+  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. -->
+
+# 1e-5
+
+This model is a fine-tuned version of [/ailab/user/zhouhao1/LLaMA-Factory/saves/Qwen2.5-7B-Instruct/full/sft/varify_yaoying_knowledge/1epoch/1e-5](https://huggingface.co//ailab/user/zhouhao1/LLaMA-Factory/saves/Qwen2.5-7B-Instruct/full/sft/varify_yaoying_knowledge/1epoch/1e-5) on the mix_yaoying_paradigm dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0+cu118
+- Datasets 3.0.2
+- Tokenizers 0.20.1

model_weights/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
+}

model_weights/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1461730443264.0,
+    "train_loss": 0.2801128467130992,
+    "train_runtime": 1050.1951,
+    "train_samples_per_second": 2.718,
+    "train_steps_per_second": 0.086
+}

model_weights/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/ailab/user/zhouhao1/LLaMA-Factory/saves/Qwen2.5-7B-Instruct/full/sft/varify_yaoying_knowledge/1epoch/1e-5",
+  "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
+}

model_weights/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_weights/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"
+  }
+}

model_weights/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
+  }
+}

model_weights/tokenizer.json

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

model_weights/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
+}

model_weights/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1461730443264.0,
+    "train_loss": 0.2801128467130992,
+    "train_runtime": 1050.1951,
+    "train_samples_per_second": 2.718,
+    "train_steps_per_second": 0.086
+}

model_weights/trainer_log.jsonl

@@ -0,0 +1,91 @@
+{"current_steps": 1, "total_steps": 90, "loss": 3.7127, "lr": 0.0, "epoch": 0.022222222222222223, "percentage": 1.11, "elapsed_time": "0:00:17", "remaining_time": "0:25:50"}
+{"current_steps": 2, "total_steps": 90, "loss": 4.2617, "lr": 3.0102999566398115e-06, "epoch": 0.044444444444444446, "percentage": 2.22, "elapsed_time": "0:00:28", "remaining_time": "0:20:43"}
+{"current_steps": 3, "total_steps": 90, "loss": 3.9337, "lr": 4.771212547196624e-06, "epoch": 0.06666666666666667, "percentage": 3.33, "elapsed_time": "0:00:39", "remaining_time": "0:19:04"}
+{"current_steps": 4, "total_steps": 90, "loss": 4.0501, "lr": 6.020599913279623e-06, "epoch": 0.08888888888888889, "percentage": 4.44, "elapsed_time": "0:00:50", "remaining_time": "0:18:02"}
+{"current_steps": 5, "total_steps": 90, "loss": 2.6747, "lr": 6.989700043360187e-06, "epoch": 0.1111111111111111, "percentage": 5.56, "elapsed_time": "0:01:01", "remaining_time": "0:17:17"}
+{"current_steps": 6, "total_steps": 90, "loss": 2.0696, "lr": 7.781512503836437e-06, "epoch": 0.13333333333333333, "percentage": 6.67, "elapsed_time": "0:01:11", "remaining_time": "0:16:43"}
+{"current_steps": 7, "total_steps": 90, "loss": 1.2472, "lr": 8.450980400142568e-06, "epoch": 0.15555555555555556, "percentage": 7.78, "elapsed_time": "0:01:22", "remaining_time": "0:16:16"}
+{"current_steps": 8, "total_steps": 90, "loss": 1.1584, "lr": 9.030899869919434e-06, "epoch": 0.17777777777777778, "percentage": 8.89, "elapsed_time": "0:01:33", "remaining_time": "0:15:53"}
+{"current_steps": 9, "total_steps": 90, "loss": 0.577, "lr": 9.542425094393249e-06, "epoch": 0.2, "percentage": 10.0, "elapsed_time": "0:01:43", "remaining_time": "0:15:33"}
+{"current_steps": 10, "total_steps": 90, "loss": 0.441, "lr": 9.999999999999999e-06, "epoch": 0.2222222222222222, "percentage": 11.11, "elapsed_time": "0:01:54", "remaining_time": "0:15:15"}
+{"current_steps": 11, "total_steps": 90, "loss": 0.1955, "lr": 1e-05, "epoch": 0.24444444444444444, "percentage": 12.22, "elapsed_time": "0:02:05", "remaining_time": "0:14:57"}
+{"current_steps": 12, "total_steps": 90, "loss": 0.1112, "lr": 1e-05, "epoch": 0.26666666666666666, "percentage": 13.33, "elapsed_time": "0:02:15", "remaining_time": "0:14:41"}
+{"current_steps": 13, "total_steps": 90, "loss": 0.0295, "lr": 1e-05, "epoch": 0.28888888888888886, "percentage": 14.44, "elapsed_time": "0:02:26", "remaining_time": "0:14:26"}
+{"current_steps": 14, "total_steps": 90, "loss": 0.0212, "lr": 1e-05, "epoch": 0.3111111111111111, "percentage": 15.56, "elapsed_time": "0:02:36", "remaining_time": "0:14:12"}
+{"current_steps": 15, "total_steps": 90, "loss": 0.0196, "lr": 1e-05, "epoch": 0.3333333333333333, "percentage": 16.67, "elapsed_time": "0:02:47", "remaining_time": "0:13:58"}
+{"current_steps": 16, "total_steps": 90, "loss": 0.0574, "lr": 1e-05, "epoch": 0.35555555555555557, "percentage": 17.78, "elapsed_time": "0:02:58", "remaining_time": "0:13:44"}
+{"current_steps": 17, "total_steps": 90, "loss": 0.05, "lr": 1e-05, "epoch": 0.37777777777777777, "percentage": 18.89, "elapsed_time": "0:03:08", "remaining_time": "0:13:31"}
+{"current_steps": 18, "total_steps": 90, "loss": 0.0295, "lr": 1e-05, "epoch": 0.4, "percentage": 20.0, "elapsed_time": "0:03:19", "remaining_time": "0:13:18"}
+{"current_steps": 19, "total_steps": 90, "loss": 0.0265, "lr": 1e-05, "epoch": 0.4222222222222222, "percentage": 21.11, "elapsed_time": "0:03:30", "remaining_time": "0:13:05"}
+{"current_steps": 20, "total_steps": 90, "loss": 0.019, "lr": 1e-05, "epoch": 0.4444444444444444, "percentage": 22.22, "elapsed_time": "0:03:40", "remaining_time": "0:12:52"}
+{"current_steps": 21, "total_steps": 90, "loss": 0.0112, "lr": 1e-05, "epoch": 0.4666666666666667, "percentage": 23.33, "elapsed_time": "0:03:51", "remaining_time": "0:12:40"}
+{"current_steps": 22, "total_steps": 90, "loss": 0.0063, "lr": 1e-05, "epoch": 0.4888888888888889, "percentage": 24.44, "elapsed_time": "0:04:02", "remaining_time": "0:12:28"}
+{"current_steps": 23, "total_steps": 90, "loss": 0.008, "lr": 1e-05, "epoch": 0.5111111111111111, "percentage": 25.56, "elapsed_time": "0:04:12", "remaining_time": "0:12:16"}
+{"current_steps": 24, "total_steps": 90, "loss": 0.0118, "lr": 1e-05, "epoch": 0.5333333333333333, "percentage": 26.67, "elapsed_time": "0:04:23", "remaining_time": "0:12:04"}
+{"current_steps": 25, "total_steps": 90, "loss": 0.0097, "lr": 1e-05, "epoch": 0.5555555555555556, "percentage": 27.78, "elapsed_time": "0:04:34", "remaining_time": "0:11:53"}
+{"current_steps": 26, "total_steps": 90, "loss": 0.014, "lr": 1e-05, "epoch": 0.5777777777777777, "percentage": 28.89, "elapsed_time": "0:04:44", "remaining_time": "0:11:41"}
+{"current_steps": 27, "total_steps": 90, "loss": 0.0089, "lr": 1e-05, "epoch": 0.6, "percentage": 30.0, "elapsed_time": "0:04:55", "remaining_time": "0:11:30"}
+{"current_steps": 28, "total_steps": 90, "loss": 0.0088, "lr": 1e-05, "epoch": 0.6222222222222222, "percentage": 31.11, "elapsed_time": "0:05:06", "remaining_time": "0:11:18"}
+{"current_steps": 29, "total_steps": 90, "loss": 0.0139, "lr": 1e-05, "epoch": 0.6444444444444445, "percentage": 32.22, "elapsed_time": "0:05:17", "remaining_time": "0:11:06"}
+{"current_steps": 30, "total_steps": 90, "loss": 0.0079, "lr": 1e-05, "epoch": 0.6666666666666666, "percentage": 33.33, "elapsed_time": "0:05:27", "remaining_time": "0:10:55"}
+{"current_steps": 31, "total_steps": 90, "loss": 0.006, "lr": 1e-05, "epoch": 0.6888888888888889, "percentage": 34.44, "elapsed_time": "0:05:38", "remaining_time": "0:10:44"}
+{"current_steps": 32, "total_steps": 90, "loss": 0.0111, "lr": 1e-05, "epoch": 0.7111111111111111, "percentage": 35.56, "elapsed_time": "0:05:49", "remaining_time": "0:10:32"}
+{"current_steps": 33, "total_steps": 90, "loss": 0.0065, "lr": 1e-05, "epoch": 0.7333333333333333, "percentage": 36.67, "elapsed_time": "0:05:59", "remaining_time": "0:10:21"}
+{"current_steps": 34, "total_steps": 90, "loss": 0.0128, "lr": 1e-05, "epoch": 0.7555555555555555, "percentage": 37.78, "elapsed_time": "0:06:10", "remaining_time": "0:10:10"}
+{"current_steps": 35, "total_steps": 90, "loss": 0.0072, "lr": 1e-05, "epoch": 0.7777777777777778, "percentage": 38.89, "elapsed_time": "0:06:21", "remaining_time": "0:09:59"}
+{"current_steps": 36, "total_steps": 90, "loss": 0.0047, "lr": 1e-05, "epoch": 0.8, "percentage": 40.0, "elapsed_time": "0:06:31", "remaining_time": "0:09:47"}
+{"current_steps": 37, "total_steps": 90, "loss": 0.0201, "lr": 1e-05, "epoch": 0.8222222222222222, "percentage": 41.11, "elapsed_time": "0:06:42", "remaining_time": "0:09:36"}
+{"current_steps": 38, "total_steps": 90, "loss": 0.0038, "lr": 1e-05, "epoch": 0.8444444444444444, "percentage": 42.22, "elapsed_time": "0:06:53", "remaining_time": "0:09:25"}
+{"current_steps": 39, "total_steps": 90, "loss": 0.0119, "lr": 1e-05, "epoch": 0.8666666666666667, "percentage": 43.33, "elapsed_time": "0:07:03", "remaining_time": "0:09:14"}
+{"current_steps": 40, "total_steps": 90, "loss": 0.0201, "lr": 1e-05, "epoch": 0.8888888888888888, "percentage": 44.44, "elapsed_time": "0:07:14", "remaining_time": "0:09:03"}
+{"current_steps": 41, "total_steps": 90, "loss": 0.0094, "lr": 1e-05, "epoch": 0.9111111111111111, "percentage": 45.56, "elapsed_time": "0:07:25", "remaining_time": "0:08:52"}
+{"current_steps": 42, "total_steps": 90, "loss": 0.0095, "lr": 1e-05, "epoch": 0.9333333333333333, "percentage": 46.67, "elapsed_time": "0:07:36", "remaining_time": "0:08:41"}
+{"current_steps": 43, "total_steps": 90, "loss": 0.0094, "lr": 1e-05, "epoch": 0.9555555555555556, "percentage": 47.78, "elapsed_time": "0:07:46", "remaining_time": "0:08:30"}
+{"current_steps": 44, "total_steps": 90, "loss": 0.0167, "lr": 1e-05, "epoch": 0.9777777777777777, "percentage": 48.89, "elapsed_time": "0:07:57", "remaining_time": "0:08:19"}
+{"current_steps": 45, "total_steps": 90, "loss": 0.0052, "lr": 1e-05, "epoch": 1.0, "percentage": 50.0, "elapsed_time": "0:08:08", "remaining_time": "0:08:08"}
+{"current_steps": 46, "total_steps": 90, "loss": 0.0099, "lr": 1e-05, "epoch": 1.0222222222222221, "percentage": 51.11, "elapsed_time": "0:08:18", "remaining_time": "0:07:57"}
+{"current_steps": 47, "total_steps": 90, "loss": 0.0155, "lr": 1e-05, "epoch": 1.0444444444444445, "percentage": 52.22, "elapsed_time": "0:08:29", "remaining_time": "0:07:46"}
+{"current_steps": 48, "total_steps": 90, "loss": 0.0055, "lr": 1e-05, "epoch": 1.0666666666666667, "percentage": 53.33, "elapsed_time": "0:08:40", "remaining_time": "0:07:35"}
+{"current_steps": 49, "total_steps": 90, "loss": 0.005, "lr": 1e-05, "epoch": 1.0888888888888888, "percentage": 54.44, "elapsed_time": "0:08:50", "remaining_time": "0:07:24"}
+{"current_steps": 50, "total_steps": 90, "loss": 0.0162, "lr": 1e-05, "epoch": 1.1111111111111112, "percentage": 55.56, "elapsed_time": "0:09:01", "remaining_time": "0:07:13"}
+{"current_steps": 51, "total_steps": 90, "loss": 0.0044, "lr": 1e-05, "epoch": 1.1333333333333333, "percentage": 56.67, "elapsed_time": "0:09:12", "remaining_time": "0:07:02"}
+{"current_steps": 52, "total_steps": 90, "loss": 0.0035, "lr": 1e-05, "epoch": 1.1555555555555554, "percentage": 57.78, "elapsed_time": "0:09:22", "remaining_time": "0:06:51"}
+{"current_steps": 53, "total_steps": 90, "loss": 0.0039, "lr": 1e-05, "epoch": 1.1777777777777778, "percentage": 58.89, "elapsed_time": "0:09:33", "remaining_time": "0:06:40"}
+{"current_steps": 54, "total_steps": 90, "loss": 0.0043, "lr": 1e-05, "epoch": 1.2, "percentage": 60.0, "elapsed_time": "0:09:44", "remaining_time": "0:06:29"}
+{"current_steps": 55, "total_steps": 90, "loss": 0.0053, "lr": 1e-05, "epoch": 1.2222222222222223, "percentage": 61.11, "elapsed_time": "0:09:54", "remaining_time": "0:06:18"}
+{"current_steps": 56, "total_steps": 90, "loss": 0.0054, "lr": 1e-05, "epoch": 1.2444444444444445, "percentage": 62.22, "elapsed_time": "0:10:05", "remaining_time": "0:06:07"}
+{"current_steps": 57, "total_steps": 90, "loss": 0.0043, "lr": 1e-05, "epoch": 1.2666666666666666, "percentage": 63.33, "elapsed_time": "0:10:16", "remaining_time": "0:05:56"}
+{"current_steps": 58, "total_steps": 90, "loss": 0.0043, "lr": 1e-05, "epoch": 1.2888888888888888, "percentage": 64.44, "elapsed_time": "0:10:26", "remaining_time": "0:05:45"}
+{"current_steps": 59, "total_steps": 90, "loss": 0.0035, "lr": 1e-05, "epoch": 1.3111111111111111, "percentage": 65.56, "elapsed_time": "0:10:37", "remaining_time": "0:05:34"}
+{"current_steps": 60, "total_steps": 90, "loss": 0.013, "lr": 1e-05, "epoch": 1.3333333333333333, "percentage": 66.67, "elapsed_time": "0:10:48", "remaining_time": "0:05:24"}
+{"current_steps": 61, "total_steps": 90, "loss": 0.0066, "lr": 1e-05, "epoch": 1.3555555555555556, "percentage": 67.78, "elapsed_time": "0:10:58", "remaining_time": "0:05:13"}
+{"current_steps": 62, "total_steps": 90, "loss": 0.0028, "lr": 1e-05, "epoch": 1.3777777777777778, "percentage": 68.89, "elapsed_time": "0:11:09", "remaining_time": "0:05:02"}
+{"current_steps": 63, "total_steps": 90, "loss": 0.0028, "lr": 1e-05, "epoch": 1.4, "percentage": 70.0, "elapsed_time": "0:11:20", "remaining_time": "0:04:51"}
+{"current_steps": 64, "total_steps": 90, "loss": 0.0033, "lr": 1e-05, "epoch": 1.4222222222222223, "percentage": 71.11, "elapsed_time": "0:11:30", "remaining_time": "0:04:40"}
+{"current_steps": 65, "total_steps": 90, "loss": 0.0047, "lr": 1e-05, "epoch": 1.4444444444444444, "percentage": 72.22, "elapsed_time": "0:11:41", "remaining_time": "0:04:29"}
+{"current_steps": 66, "total_steps": 90, "loss": 0.0043, "lr": 1e-05, "epoch": 1.4666666666666668, "percentage": 73.33, "elapsed_time": "0:11:52", "remaining_time": "0:04:19"}
+{"current_steps": 67, "total_steps": 90, "loss": 0.0048, "lr": 1e-05, "epoch": 1.488888888888889, "percentage": 74.44, "elapsed_time": "0:12:02", "remaining_time": "0:04:08"}
+{"current_steps": 68, "total_steps": 90, "loss": 0.0046, "lr": 1e-05, "epoch": 1.511111111111111, "percentage": 75.56, "elapsed_time": "0:12:13", "remaining_time": "0:03:57"}
+{"current_steps": 69, "total_steps": 90, "loss": 0.0109, "lr": 1e-05, "epoch": 1.5333333333333332, "percentage": 76.67, "elapsed_time": "0:12:24", "remaining_time": "0:03:46"}
+{"current_steps": 70, "total_steps": 90, "loss": 0.0031, "lr": 1e-05, "epoch": 1.5555555555555556, "percentage": 77.78, "elapsed_time": "0:12:34", "remaining_time": "0:03:35"}
+{"current_steps": 71, "total_steps": 90, "loss": 0.0043, "lr": 1e-05, "epoch": 1.5777777777777777, "percentage": 78.89, "elapsed_time": "0:12:45", "remaining_time": "0:03:24"}
+{"current_steps": 72, "total_steps": 90, "loss": 0.0061, "lr": 1e-05, "epoch": 1.6, "percentage": 80.0, "elapsed_time": "0:12:56", "remaining_time": "0:03:14"}
+{"current_steps": 73, "total_steps": 90, "loss": 0.0041, "lr": 1e-05, "epoch": 1.6222222222222222, "percentage": 81.11, "elapsed_time": "0:13:07", "remaining_time": "0:03:03"}
+{"current_steps": 74, "total_steps": 90, "loss": 0.0034, "lr": 1e-05, "epoch": 1.6444444444444444, "percentage": 82.22, "elapsed_time": "0:13:17", "remaining_time": "0:02:52"}
+{"current_steps": 75, "total_steps": 90, "loss": 0.0107, "lr": 1e-05, "epoch": 1.6666666666666665, "percentage": 83.33, "elapsed_time": "0:13:28", "remaining_time": "0:02:41"}
+{"current_steps": 76, "total_steps": 90, "loss": 0.0056, "lr": 1e-05, "epoch": 1.6888888888888889, "percentage": 84.44, "elapsed_time": "0:13:39", "remaining_time": "0:02:30"}
+{"current_steps": 77, "total_steps": 90, "loss": 0.0042, "lr": 1e-05, "epoch": 1.7111111111111112, "percentage": 85.56, "elapsed_time": "0:13:49", "remaining_time": "0:02:20"}
+{"current_steps": 78, "total_steps": 90, "loss": 0.0037, "lr": 1e-05, "epoch": 1.7333333333333334, "percentage": 86.67, "elapsed_time": "0:14:00", "remaining_time": "0:02:09"}
+{"current_steps": 79, "total_steps": 90, "loss": 0.0036, "lr": 1e-05, "epoch": 1.7555555555555555, "percentage": 87.78, "elapsed_time": "0:14:11", "remaining_time": "0:01:58"}
+{"current_steps": 80, "total_steps": 90, "loss": 0.0158, "lr": 1e-05, "epoch": 1.7777777777777777, "percentage": 88.89, "elapsed_time": "0:14:21", "remaining_time": "0:01:47"}
+{"current_steps": 81, "total_steps": 90, "loss": 0.0171, "lr": 1e-05, "epoch": 1.8, "percentage": 90.0, "elapsed_time": "0:14:32", "remaining_time": "0:01:36"}
+{"current_steps": 82, "total_steps": 90, "loss": 0.0038, "lr": 1e-05, "epoch": 1.8222222222222222, "percentage": 91.11, "elapsed_time": "0:14:43", "remaining_time": "0:01:26"}
+{"current_steps": 83, "total_steps": 90, "loss": 0.0027, "lr": 1e-05, "epoch": 1.8444444444444446, "percentage": 92.22, "elapsed_time": "0:14:53", "remaining_time": "0:01:15"}
+{"current_steps": 84, "total_steps": 90, "loss": 0.0033, "lr": 1e-05, "epoch": 1.8666666666666667, "percentage": 93.33, "elapsed_time": "0:15:04", "remaining_time": "0:01:04"}
+{"current_steps": 85, "total_steps": 90, "loss": 0.0063, "lr": 1e-05, "epoch": 1.8888888888888888, "percentage": 94.44, "elapsed_time": "0:15:15", "remaining_time": "0:00:53"}
+{"current_steps": 86, "total_steps": 90, "loss": 0.0053, "lr": 1e-05, "epoch": 1.911111111111111, "percentage": 95.56, "elapsed_time": "0:15:25", "remaining_time": "0:00:43"}
+{"current_steps": 87, "total_steps": 90, "loss": 0.0063, "lr": 1e-05, "epoch": 1.9333333333333333, "percentage": 96.67, "elapsed_time": "0:15:36", "remaining_time": "0:00:32"}
+{"current_steps": 88, "total_steps": 90, "loss": 0.0055, "lr": 1e-05, "epoch": 1.9555555555555557, "percentage": 97.78, "elapsed_time": "0:15:47", "remaining_time": "0:00:21"}
+{"current_steps": 89, "total_steps": 90, "loss": 0.0031, "lr": 1e-05, "epoch": 1.9777777777777779, "percentage": 98.89, "elapsed_time": "0:15:58", "remaining_time": "0:00:10"}
+{"current_steps": 90, "total_steps": 90, "loss": 0.0032, "lr": 1e-05, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:16:08", "remaining_time": "0:00:00"}
+{"current_steps": 90, "total_steps": 90, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:17:31", "remaining_time": "0:00:00"}

model_weights/trainer_state.json

@@ -0,0 +1,672 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022222222222222223,
+      "grad_norm": 53.530174255371094,
+      "learning_rate": 0.0,
+      "loss": 3.7127,
+      "step": 1
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 61.59223175048828,
+      "learning_rate": 3.0102999566398115e-06,
+      "loss": 4.2617,
+      "step": 2
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 56.324851989746094,
+      "learning_rate": 4.771212547196624e-06,
+      "loss": 3.9337,
+      "step": 3
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 57.2040901184082,
+      "learning_rate": 6.020599913279623e-06,
+      "loss": 4.0501,
+      "step": 4
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 29.125165939331055,
+      "learning_rate": 6.989700043360187e-06,
+      "loss": 2.6747,
+      "step": 5
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 22.29631996154785,
+      "learning_rate": 7.781512503836437e-06,
+      "loss": 2.0696,
+      "step": 6
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 16.7867374420166,
+      "learning_rate": 8.450980400142568e-06,
+      "loss": 1.2472,
+      "step": 7
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 14.00655460357666,
+      "learning_rate": 9.030899869919434e-06,
+      "loss": 1.1584,
+      "step": 8
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 12.328531265258789,
+      "learning_rate": 9.542425094393249e-06,
+      "loss": 0.577,
+      "step": 9
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 8.245832443237305,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 0.441,
+      "step": 10
+    },
+    {
+      "epoch": 0.24444444444444444,
+      "grad_norm": 5.645260334014893,
+      "learning_rate": 1e-05,
+      "loss": 0.1955,
+      "step": 11
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 4.366610050201416,
+      "learning_rate": 1e-05,
+      "loss": 0.1112,
+      "step": 12
+    },
+    {
+      "epoch": 0.28888888888888886,
+      "grad_norm": 1.9627007246017456,
+      "learning_rate": 1e-05,
+      "loss": 0.0295,
+      "step": 13
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 3.389981746673584,
+      "learning_rate": 1e-05,
+      "loss": 0.0212,
+      "step": 14
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 1.289111614227295,
+      "learning_rate": 1e-05,
+      "loss": 0.0196,
+      "step": 15
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 6.024927616119385,
+      "learning_rate": 1e-05,
+      "loss": 0.0574,
+      "step": 16
+    },
+    {
+      "epoch": 0.37777777777777777,
+      "grad_norm": 2.6915383338928223,
+      "learning_rate": 1e-05,
+      "loss": 0.05,
+      "step": 17
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.6206488609313965,
+      "learning_rate": 1e-05,
+      "loss": 0.0295,
+      "step": 18
+    },
+    {
+      "epoch": 0.4222222222222222,
+      "grad_norm": 2.982672691345215,
+      "learning_rate": 1e-05,
+      "loss": 0.0265,
+      "step": 19
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.7450136542320251,
+      "learning_rate": 1e-05,
+      "loss": 0.019,
+      "step": 20
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 1.3652844429016113,
+      "learning_rate": 1e-05,
+      "loss": 0.0112,
+      "step": 21
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 0.6385069489479065,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 22
+    },
+    {
+      "epoch": 0.5111111111111111,
+      "grad_norm": 1.1325575113296509,
+      "learning_rate": 1e-05,
+      "loss": 0.008,
+      "step": 23
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 2.3933751583099365,
+      "learning_rate": 1e-05,
+      "loss": 0.0118,
+      "step": 24
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.8726178407669067,
+      "learning_rate": 1e-05,
+      "loss": 0.0097,
+      "step": 25
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 1.5952070951461792,
+      "learning_rate": 1e-05,
+      "loss": 0.014,
+      "step": 26
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7280263304710388,
+      "learning_rate": 1e-05,
+      "loss": 0.0089,
+      "step": 27
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 0.8631385564804077,
+      "learning_rate": 1e-05,
+      "loss": 0.0088,
+      "step": 28
+    },
+    {
+      "epoch": 0.6444444444444445,
+      "grad_norm": 1.1149359941482544,
+      "learning_rate": 1e-05,
+      "loss": 0.0139,
+      "step": 29
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.9333624243736267,
+      "learning_rate": 1e-05,
+      "loss": 0.0079,
+      "step": 30
+    },
+    {
+      "epoch": 0.6888888888888889,
+      "grad_norm": 0.4508938491344452,
+      "learning_rate": 1e-05,
+      "loss": 0.006,
+      "step": 31
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.8795773386955261,
+      "learning_rate": 1e-05,
+      "loss": 0.0111,
+      "step": 32
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.3067614436149597,
+      "learning_rate": 1e-05,
+      "loss": 0.0065,
+      "step": 33
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 1.5579835176467896,
+      "learning_rate": 1e-05,
+      "loss": 0.0128,
+      "step": 34
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.582850992679596,
+      "learning_rate": 1e-05,
+      "loss": 0.0072,
+      "step": 35
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6338833570480347,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 36
+    },
+    {
+      "epoch": 0.8222222222222222,
+      "grad_norm": 0.9185447096824646,
+      "learning_rate": 1e-05,
+      "loss": 0.0201,
+      "step": 37
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 0.3918289840221405,
+      "learning_rate": 1e-05,
+      "loss": 0.0038,
+      "step": 38
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 2.437156915664673,
+      "learning_rate": 1e-05,
+      "loss": 0.0119,
+      "step": 39
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.962317943572998,
+      "learning_rate": 1e-05,
+      "loss": 0.0201,
+      "step": 40
+    },
+    {
+      "epoch": 0.9111111111111111,
+      "grad_norm": 0.6251342296600342,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 41
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.47292882204055786,
+      "learning_rate": 1e-05,
+      "loss": 0.0095,
+      "step": 42
+    },
+    {
+      "epoch": 0.9555555555555556,
+      "grad_norm": 0.6480843424797058,
+      "learning_rate": 1e-05,
+      "loss": 0.0094,
+      "step": 43
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.8501760959625244,
+      "learning_rate": 1e-05,
+      "loss": 0.0167,
+      "step": 44
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2330845147371292,
+      "learning_rate": 1e-05,
+      "loss": 0.0052,
+      "step": 45
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 0.5005345344543457,
+      "learning_rate": 1e-05,
+      "loss": 0.0099,
+      "step": 46
+    },
+    {
+      "epoch": 1.0444444444444445,
+      "grad_norm": 0.7536910772323608,
+      "learning_rate": 1e-05,
+      "loss": 0.0155,
+      "step": 47
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.5692221522331238,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 48
+    },
+    {
+      "epoch": 1.0888888888888888,
+      "grad_norm": 0.5457833409309387,
+      "learning_rate": 1e-05,
+      "loss": 0.005,
+      "step": 49
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.9689218401908875,
+      "learning_rate": 1e-05,
+      "loss": 0.0162,
+      "step": 50
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.32389000058174133,
+      "learning_rate": 1e-05,
+      "loss": 0.0044,
+      "step": 51
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 0.2125365138053894,
+      "learning_rate": 1e-05,
+      "loss": 0.0035,
+      "step": 52
+    },
+    {
+      "epoch": 1.1777777777777778,
+      "grad_norm": 0.3343706727027893,
+      "learning_rate": 1e-05,
+      "loss": 0.0039,
+      "step": 53
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.21088644862174988,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 54
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.39174872636795044,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 55
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 0.3518277108669281,
+      "learning_rate": 1e-05,
+      "loss": 0.0054,
+      "step": 56
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.3601788282394409,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 57
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 0.2247372269630432,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 58
+    },
+    {
+      "epoch": 1.3111111111111111,
+      "grad_norm": 0.36479631066322327,
+      "learning_rate": 1e-05,
+      "loss": 0.0035,
+      "step": 59
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.6034692525863647,
+      "learning_rate": 1e-05,
+      "loss": 0.013,
+      "step": 60
+    },
+    {
+      "epoch": 1.3555555555555556,
+      "grad_norm": 0.5383604168891907,
+      "learning_rate": 1e-05,
+      "loss": 0.0066,
+      "step": 61
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 0.27615559101104736,
+      "learning_rate": 1e-05,
+      "loss": 0.0028,
+      "step": 62
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.16325147449970245,
+      "learning_rate": 1e-05,
+      "loss": 0.0028,
+      "step": 63
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 0.2408730387687683,
+      "learning_rate": 1e-05,
+      "loss": 0.0033,
+      "step": 64
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.27461478114128113,
+      "learning_rate": 1e-05,
+      "loss": 0.0047,
+      "step": 65
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.6377409100532532,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 66
+    },
+    {
+      "epoch": 1.488888888888889,
+      "grad_norm": 0.3737064003944397,
+      "learning_rate": 1e-05,
+      "loss": 0.0048,
+      "step": 67
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 0.2964211404323578,
+      "learning_rate": 1e-05,
+      "loss": 0.0046,
+      "step": 68
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.390750914812088,
+      "learning_rate": 1e-05,
+      "loss": 0.0109,
+      "step": 69
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.28001874685287476,
+      "learning_rate": 1e-05,
+      "loss": 0.0031,
+      "step": 70
+    },
+    {
+      "epoch": 1.5777777777777777,
+      "grad_norm": 0.40667039155960083,
+      "learning_rate": 1e-05,
+      "loss": 0.0043,
+      "step": 71
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6238460540771484,
+      "learning_rate": 1e-05,
+      "loss": 0.0061,
+      "step": 72
+    },
+    {
+      "epoch": 1.6222222222222222,
+      "grad_norm": 0.3311893343925476,
+      "learning_rate": 1e-05,
+      "loss": 0.0041,
+      "step": 73
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 0.13802868127822876,
+      "learning_rate": 1e-05,
+      "loss": 0.0034,
+      "step": 74
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.37306132912635803,
+      "learning_rate": 1e-05,
+      "loss": 0.0107,
+      "step": 75
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 0.45896589756011963,
+      "learning_rate": 1e-05,
+      "loss": 0.0056,
+      "step": 76
+    },
+    {
+      "epoch": 1.7111111111111112,
+      "grad_norm": 0.5535783171653748,
+      "learning_rate": 1e-05,
+      "loss": 0.0042,
+      "step": 77
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.30451175570487976,
+      "learning_rate": 1e-05,
+      "loss": 0.0037,
+      "step": 78
+    },
+    {
+      "epoch": 1.7555555555555555,
+      "grad_norm": 0.3809017539024353,
+      "learning_rate": 1e-05,
+      "loss": 0.0036,
+      "step": 79
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.5652432441711426,
+      "learning_rate": 1e-05,
+      "loss": 0.0158,
+      "step": 80
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.9813019037246704,
+      "learning_rate": 1e-05,
+      "loss": 0.0171,
+      "step": 81
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 0.3805609345436096,
+      "learning_rate": 1e-05,
+      "loss": 0.0038,
+      "step": 82
+    },
+    {
+      "epoch": 1.8444444444444446,
+      "grad_norm": 0.14840121567249298,
+      "learning_rate": 1e-05,
+      "loss": 0.0027,
+      "step": 83
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.7610549926757812,
+      "learning_rate": 1e-05,
+      "loss": 0.0033,
+      "step": 84
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.5516621470451355,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 85
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 0.29915738105773926,
+      "learning_rate": 1e-05,
+      "loss": 0.0053,
+      "step": 86
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.503457248210907,
+      "learning_rate": 1e-05,
+      "loss": 0.0063,
+      "step": 87
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 0.7111280560493469,
+      "learning_rate": 1e-05,
+      "loss": 0.0055,
+      "step": 88
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "grad_norm": 0.2871617376804352,
+      "learning_rate": 1e-05,
+      "loss": 0.0031,
+      "step": 89
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.18676067888736725,
+      "learning_rate": 1e-05,
+      "loss": 0.0032,
+      "step": 90
+    },
+    {
+      "epoch": 2.0,
+      "step": 90,
+      "total_flos": 1461730443264.0,
+      "train_loss": 0.2801128467130992,
+      "train_runtime": 1050.1951,
+      "train_samples_per_second": 2.718,
+      "train_steps_per_second": 0.086
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1461730443264.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

model_weights/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3f4a007158e6273e069116c1db1f7fab3288395f8c7ebbc88f25da80ce27a8
+size 7739