Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 7b_isntruct_pretrain
+  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. -->
+
+# 7b_isntruct_pretrain
+
+This model is a fine-tuned version of [/home/export/base/sc100182/sc100182/online1/code/models/Qwen2.5-7B-Instruct](https://huggingface.co//home/export/base/sc100182/sc100182/online1/code/models/Qwen2.5-7B-Instruct) on the S1_1k_noq 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: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 6
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.48.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 118427603697664.0,
+    "train_loss": 0.662273271560669,
+    "train_runtime": 26488.1763,
+    "train_samples_per_second": 0.227,
+    "train_steps_per_second": 0.028
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/export/base/sc100182/sc100182/online1/code/models/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": "4.48.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7060fe413112a60b2b6b6f61b3a1040ec329b5786f3a21c8cd08e5a82bd55e53
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b050ac38686bcb291fca6e981bbbe25646ffa888c9f8666160a49f647a5b202
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa081e0fe5d48a9994f2ff9b01c49c3b3a4a911964500a34f2dc080cbc3ca91
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5134a5ca62f20771ca474bf990b6b6245011e359af72cd64d89a59b4d0da866
+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 +1,209 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 24000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "total_flos": 118427603697664.0,
+    "train_loss": 0.662273271560669,
+    "train_runtime": 26488.1763,
+    "train_samples_per_second": 0.227,
+    "train_steps_per_second": 0.028
+}

trainer_log.jsonl

@@ -0,0 +1,76 @@
+{"current_steps": 10, "total_steps": 750, "loss": 1.2535, "lr": 1.3333333333333334e-06, "epoch": 0.08, "percentage": 1.33, "elapsed_time": "0:05:55", "remaining_time": "7:18:59"}
+{"current_steps": 20, "total_steps": 750, "loss": 1.1389, "lr": 2.666666666666667e-06, "epoch": 0.16, "percentage": 2.67, "elapsed_time": "0:11:56", "remaining_time": "7:15:57"}
+{"current_steps": 30, "total_steps": 750, "loss": 1.1137, "lr": 4.000000000000001e-06, "epoch": 0.24, "percentage": 4.0, "elapsed_time": "0:17:56", "remaining_time": "7:10:44"}
+{"current_steps": 40, "total_steps": 750, "loss": 1.0243, "lr": 5.333333333333334e-06, "epoch": 0.32, "percentage": 5.33, "elapsed_time": "0:23:47", "remaining_time": "7:02:13"}
+{"current_steps": 50, "total_steps": 750, "loss": 1.0505, "lr": 6.666666666666667e-06, "epoch": 0.4, "percentage": 6.67, "elapsed_time": "0:30:05", "remaining_time": "7:01:23"}
+{"current_steps": 60, "total_steps": 750, "loss": 0.9779, "lr": 8.000000000000001e-06, "epoch": 0.48, "percentage": 8.0, "elapsed_time": "0:35:32", "remaining_time": "6:48:47"}
+{"current_steps": 70, "total_steps": 750, "loss": 0.9797, "lr": 9.333333333333334e-06, "epoch": 0.56, "percentage": 9.33, "elapsed_time": "0:41:21", "remaining_time": "6:41:45"}
+{"current_steps": 80, "total_steps": 750, "loss": 0.9878, "lr": 9.99864620589731e-06, "epoch": 0.64, "percentage": 10.67, "elapsed_time": "0:47:18", "remaining_time": "6:36:10"}
+{"current_steps": 90, "total_steps": 750, "loss": 0.9352, "lr": 9.987820251299121e-06, "epoch": 0.72, "percentage": 12.0, "elapsed_time": "0:52:51", "remaining_time": "6:27:34"}
+{"current_steps": 100, "total_steps": 750, "loss": 0.9205, "lr": 9.966191788709716e-06, "epoch": 0.8, "percentage": 13.33, "elapsed_time": "0:58:59", "remaining_time": "6:23:26"}
+{"current_steps": 110, "total_steps": 750, "loss": 0.9168, "lr": 9.933807660562898e-06, "epoch": 0.88, "percentage": 14.67, "elapsed_time": "1:04:33", "remaining_time": "6:15:39"}
+{"current_steps": 120, "total_steps": 750, "loss": 0.9345, "lr": 9.890738003669029e-06, "epoch": 0.96, "percentage": 16.0, "elapsed_time": "1:10:53", "remaining_time": "6:12:10"}
+{"current_steps": 130, "total_steps": 750, "loss": 0.8842, "lr": 9.83707609731432e-06, "epoch": 1.04, "percentage": 17.33, "elapsed_time": "1:16:32", "remaining_time": "6:05:01"}
+{"current_steps": 140, "total_steps": 750, "loss": 0.8496, "lr": 9.77293816123866e-06, "epoch": 1.12, "percentage": 18.67, "elapsed_time": "1:22:31", "remaining_time": "5:59:34"}
+{"current_steps": 150, "total_steps": 750, "loss": 0.8134, "lr": 9.698463103929542e-06, "epoch": 1.2, "percentage": 20.0, "elapsed_time": "1:28:13", "remaining_time": "5:52:55"}
+{"current_steps": 160, "total_steps": 750, "loss": 0.8645, "lr": 9.613812221777212e-06, "epoch": 1.28, "percentage": 21.33, "elapsed_time": "1:34:52", "remaining_time": "5:49:49"}
+{"current_steps": 170, "total_steps": 750, "loss": 0.8339, "lr": 9.519168849742603e-06, "epoch": 1.3599999999999999, "percentage": 22.67, "elapsed_time": "1:40:50", "remaining_time": "5:44:03"}
+{"current_steps": 180, "total_steps": 750, "loss": 0.8524, "lr": 9.414737964294636e-06, "epoch": 1.44, "percentage": 24.0, "elapsed_time": "1:46:41", "remaining_time": "5:37:51"}
+{"current_steps": 190, "total_steps": 750, "loss": 0.8566, "lr": 9.30074573947683e-06, "epoch": 1.52, "percentage": 25.33, "elapsed_time": "1:52:33", "remaining_time": "5:31:44"}
+{"current_steps": 200, "total_steps": 750, "loss": 0.8107, "lr": 9.177439057064684e-06, "epoch": 1.6, "percentage": 26.67, "elapsed_time": "1:58:20", "remaining_time": "5:25:26"}
+{"current_steps": 210, "total_steps": 750, "loss": 0.9001, "lr": 9.045084971874738e-06, "epoch": 1.6800000000000002, "percentage": 28.0, "elapsed_time": "2:04:28", "remaining_time": "5:20:03"}
+{"current_steps": 220, "total_steps": 750, "loss": 0.8522, "lr": 8.903970133383297e-06, "epoch": 1.76, "percentage": 29.33, "elapsed_time": "2:10:20", "remaining_time": "5:14:00"}
+{"current_steps": 230, "total_steps": 750, "loss": 0.8164, "lr": 8.754400164907496e-06, "epoch": 1.8399999999999999, "percentage": 30.67, "elapsed_time": "2:16:05", "remaining_time": "5:07:41"}
+{"current_steps": 240, "total_steps": 750, "loss": 0.8739, "lr": 8.596699001693257e-06, "epoch": 1.92, "percentage": 32.0, "elapsed_time": "2:21:38", "remaining_time": "5:00:58"}
+{"current_steps": 250, "total_steps": 750, "loss": 0.8353, "lr": 8.43120818934367e-06, "epoch": 2.0, "percentage": 33.33, "elapsed_time": "2:27:39", "remaining_time": "4:55:18"}
+{"current_steps": 260, "total_steps": 750, "loss": 0.7376, "lr": 8.258286144107277e-06, "epoch": 2.08, "percentage": 34.67, "elapsed_time": "2:33:25", "remaining_time": "4:49:09"}
+{"current_steps": 270, "total_steps": 750, "loss": 0.7247, "lr": 8.078307376628292e-06, "epoch": 2.16, "percentage": 36.0, "elapsed_time": "2:39:35", "remaining_time": "4:43:43"}
+{"current_steps": 280, "total_steps": 750, "loss": 0.6993, "lr": 7.891661680839932e-06, "epoch": 2.24, "percentage": 37.33, "elapsed_time": "2:45:21", "remaining_time": "4:37:34"}
+{"current_steps": 290, "total_steps": 750, "loss": 0.6871, "lr": 7.698753289757565e-06, "epoch": 2.32, "percentage": 38.67, "elapsed_time": "2:50:35", "remaining_time": "4:30:35"}
+{"current_steps": 300, "total_steps": 750, "loss": 0.7247, "lr": 7.500000000000001e-06, "epoch": 2.4, "percentage": 40.0, "elapsed_time": "2:56:45", "remaining_time": "4:25:08"}
+{"current_steps": 310, "total_steps": 750, "loss": 0.7549, "lr": 7.295832266935059e-06, "epoch": 2.48, "percentage": 41.33, "elapsed_time": "3:03:39", "remaining_time": "4:20:40"}
+{"current_steps": 320, "total_steps": 750, "loss": 0.6858, "lr": 7.08669227240909e-06, "epoch": 2.56, "percentage": 42.67, "elapsed_time": "3:09:49", "remaining_time": "4:15:05"}
+{"current_steps": 330, "total_steps": 750, "loss": 0.6737, "lr": 6.873032967079562e-06, "epoch": 2.64, "percentage": 44.0, "elapsed_time": "3:15:05", "remaining_time": "4:08:17"}
+{"current_steps": 340, "total_steps": 750, "loss": 0.7092, "lr": 6.655317089424791e-06, "epoch": 2.7199999999999998, "percentage": 45.33, "elapsed_time": "3:20:49", "remaining_time": "4:02:10"}
+{"current_steps": 350, "total_steps": 750, "loss": 0.6878, "lr": 6.434016163555452e-06, "epoch": 2.8, "percentage": 46.67, "elapsed_time": "3:26:18", "remaining_time": "3:55:46"}
+{"current_steps": 360, "total_steps": 750, "loss": 0.6883, "lr": 6.209609477998339e-06, "epoch": 2.88, "percentage": 48.0, "elapsed_time": "3:31:57", "remaining_time": "3:49:36"}
+{"current_steps": 370, "total_steps": 750, "loss": 0.7312, "lr": 5.982583047664151e-06, "epoch": 2.96, "percentage": 49.33, "elapsed_time": "3:37:36", "remaining_time": "3:43:29"}
+{"current_steps": 380, "total_steps": 750, "loss": 0.6466, "lr": 5.753428561247416e-06, "epoch": 3.04, "percentage": 50.67, "elapsed_time": "3:43:27", "remaining_time": "3:37:34"}
+{"current_steps": 390, "total_steps": 750, "loss": 0.5745, "lr": 5.522642316338268e-06, "epoch": 3.12, "percentage": 52.0, "elapsed_time": "3:49:28", "remaining_time": "3:31:49"}
+{"current_steps": 400, "total_steps": 750, "loss": 0.6074, "lr": 5.290724144552379e-06, "epoch": 3.2, "percentage": 53.33, "elapsed_time": "3:55:54", "remaining_time": "3:26:25"}
+{"current_steps": 410, "total_steps": 750, "loss": 0.5958, "lr": 5.0581763290069865e-06, "epoch": 3.2800000000000002, "percentage": 54.67, "elapsed_time": "4:01:53", "remaining_time": "3:20:35"}
+{"current_steps": 420, "total_steps": 750, "loss": 0.517, "lr": 4.825502516487497e-06, "epoch": 3.36, "percentage": 56.0, "elapsed_time": "4:06:59", "remaining_time": "3:14:04"}
+{"current_steps": 430, "total_steps": 750, "loss": 0.6125, "lr": 4.59320662666071e-06, "epoch": 3.44, "percentage": 57.33, "elapsed_time": "4:13:07", "remaining_time": "3:08:22"}
+{"current_steps": 440, "total_steps": 750, "loss": 0.5574, "lr": 4.361791760697027e-06, "epoch": 3.52, "percentage": 58.67, "elapsed_time": "4:18:40", "remaining_time": "3:02:14"}
+{"current_steps": 450, "total_steps": 750, "loss": 0.5619, "lr": 4.131759111665349e-06, "epoch": 3.6, "percentage": 60.0, "elapsed_time": "4:24:38", "remaining_time": "2:56:25"}
+{"current_steps": 460, "total_steps": 750, "loss": 0.5723, "lr": 3.903606879060483e-06, "epoch": 3.68, "percentage": 61.33, "elapsed_time": "4:30:27", "remaining_time": "2:50:30"}
+{"current_steps": 470, "total_steps": 750, "loss": 0.57, "lr": 3.6778291898139907e-06, "epoch": 3.76, "percentage": 62.67, "elapsed_time": "4:36:51", "remaining_time": "2:44:56"}
+{"current_steps": 480, "total_steps": 750, "loss": 0.558, "lr": 3.4549150281252635e-06, "epoch": 3.84, "percentage": 64.0, "elapsed_time": "4:42:21", "remaining_time": "2:38:49"}
+{"current_steps": 490, "total_steps": 750, "loss": 0.5642, "lr": 3.2353471764306567e-06, "epoch": 3.92, "percentage": 65.33, "elapsed_time": "4:48:52", "remaining_time": "2:33:16"}
+{"current_steps": 500, "total_steps": 750, "loss": 0.582, "lr": 3.019601169804216e-06, "epoch": 4.0, "percentage": 66.67, "elapsed_time": "4:54:34", "remaining_time": "2:27:17"}
+{"current_steps": 510, "total_steps": 750, "loss": 0.4826, "lr": 2.8081442660546126e-06, "epoch": 4.08, "percentage": 68.0, "elapsed_time": "5:00:37", "remaining_time": "2:21:28"}
+{"current_steps": 520, "total_steps": 750, "loss": 0.4799, "lr": 2.601434433748771e-06, "epoch": 4.16, "percentage": 69.33, "elapsed_time": "5:06:35", "remaining_time": "2:15:36"}
+{"current_steps": 530, "total_steps": 750, "loss": 0.4595, "lr": 2.3999193603539234e-06, "epoch": 4.24, "percentage": 70.67, "elapsed_time": "5:13:18", "remaining_time": "2:10:03"}
+{"current_steps": 540, "total_steps": 750, "loss": 0.4414, "lr": 2.204035482646267e-06, "epoch": 4.32, "percentage": 72.0, "elapsed_time": "5:18:21", "remaining_time": "2:03:48"}
+{"current_steps": 550, "total_steps": 750, "loss": 0.42, "lr": 2.0142070414860704e-06, "epoch": 4.4, "percentage": 73.33, "elapsed_time": "5:23:52", "remaining_time": "1:57:46"}
+{"current_steps": 560, "total_steps": 750, "loss": 0.4228, "lr": 1.8308451630064484e-06, "epoch": 4.48, "percentage": 74.67, "elapsed_time": "5:29:43", "remaining_time": "1:51:52"}
+{"current_steps": 570, "total_steps": 750, "loss": 0.4486, "lr": 1.6543469682057105e-06, "epoch": 4.5600000000000005, "percentage": 76.0, "elapsed_time": "5:35:37", "remaining_time": "1:45:59"}
+{"current_steps": 580, "total_steps": 750, "loss": 0.4064, "lr": 1.4850947128716914e-06, "epoch": 4.64, "percentage": 77.33, "elapsed_time": "5:41:05", "remaining_time": "1:39:58"}
+{"current_steps": 590, "total_steps": 750, "loss": 0.4806, "lr": 1.3234549597008572e-06, "epoch": 4.72, "percentage": 78.67, "elapsed_time": "5:47:08", "remaining_time": "1:34:08"}
+{"current_steps": 600, "total_steps": 750, "loss": 0.4537, "lr": 1.1697777844051105e-06, "epoch": 4.8, "percentage": 80.0, "elapsed_time": "5:53:18", "remaining_time": "1:28:19"}
+{"current_steps": 610, "total_steps": 750, "loss": 0.425, "lr": 1.0243960175257605e-06, "epoch": 4.88, "percentage": 81.33, "elapsed_time": "5:58:35", "remaining_time": "1:22:17"}
+{"current_steps": 620, "total_steps": 750, "loss": 0.4903, "lr": 8.876245235966884e-07, "epoch": 4.96, "percentage": 82.67, "elapsed_time": "6:04:57", "remaining_time": "1:16:31"}
+{"current_steps": 630, "total_steps": 750, "loss": 0.4259, "lr": 7.597595192178702e-07, "epoch": 5.04, "percentage": 84.0, "elapsed_time": "6:10:25", "remaining_time": "1:10:33"}
+{"current_steps": 640, "total_steps": 750, "loss": 0.4243, "lr": 6.410779315161885e-07, "epoch": 5.12, "percentage": 85.33, "elapsed_time": "6:16:28", "remaining_time": "1:04:42"}
+{"current_steps": 650, "total_steps": 750, "loss": 0.3387, "lr": 5.318367983829393e-07, "epoch": 5.2, "percentage": 86.67, "elapsed_time": "6:21:49", "remaining_time": "0:58:44"}
+{"current_steps": 660, "total_steps": 750, "loss": 0.3378, "lr": 4.322727117869951e-07, "epoch": 5.28, "percentage": 88.0, "elapsed_time": "6:27:14", "remaining_time": "0:52:48"}
+{"current_steps": 670, "total_steps": 750, "loss": 0.3857, "lr": 3.426013053692878e-07, "epoch": 5.36, "percentage": 89.33, "elapsed_time": "6:33:20", "remaining_time": "0:46:57"}
+{"current_steps": 680, "total_steps": 750, "loss": 0.3996, "lr": 2.63016787428354e-07, "epoch": 5.44, "percentage": 90.67, "elapsed_time": "6:39:49", "remaining_time": "0:41:09"}
+{"current_steps": 690, "total_steps": 750, "loss": 0.3743, "lr": 1.9369152030840553e-07, "epoch": 5.52, "percentage": 92.0, "elapsed_time": "6:45:35", "remaining_time": "0:35:16"}
+{"current_steps": 700, "total_steps": 750, "loss": 0.3542, "lr": 1.3477564710088097e-07, "epoch": 5.6, "percentage": 93.33, "elapsed_time": "6:50:50", "remaining_time": "0:29:20"}
+{"current_steps": 710, "total_steps": 750, "loss": 0.3587, "lr": 8.639676646793382e-08, "epoch": 5.68, "percentage": 94.67, "elapsed_time": "6:56:39", "remaining_time": "0:23:28"}
+{"current_steps": 720, "total_steps": 750, "loss": 0.414, "lr": 4.865965629214819e-08, "epoch": 5.76, "percentage": 96.0, "elapsed_time": "7:02:48", "remaining_time": "0:17:37"}
+{"current_steps": 730, "total_steps": 750, "loss": 0.3887, "lr": 2.1646046750978255e-08, "epoch": 5.84, "percentage": 97.33, "elapsed_time": "7:09:00", "remaining_time": "0:11:45"}
+{"current_steps": 740, "total_steps": 750, "loss": 0.3811, "lr": 5.414443307377171e-09, "epoch": 5.92, "percentage": 98.67, "elapsed_time": "7:15:06", "remaining_time": "0:05:52"}
+{"current_steps": 750, "total_steps": 750, "loss": 0.3763, "lr": 0.0, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "7:20:47", "remaining_time": "0:00:00"}
+{"current_steps": 750, "total_steps": 750, "epoch": 6.0, "percentage": 100.0, "elapsed_time": "7:21:28", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,567 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 3.1039228439331055,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 1.2535,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.9736298322677612,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 1.1389,
+      "step": 20
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.9868311285972595,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1137,
+      "step": 30
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7625114321708679,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 1.0243,
+      "step": 40
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8334870338439941,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0505,
+      "step": 50
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.7253231406211853,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.9779,
+      "step": 60
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6524099707603455,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.9797,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.68406742811203,
+      "learning_rate": 9.99864620589731e-06,
+      "loss": 0.9878,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6620015501976013,
+      "learning_rate": 9.987820251299121e-06,
+      "loss": 0.9352,
+      "step": 90
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7781227231025696,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 0.9205,
+      "step": 100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.6981615424156189,
+      "learning_rate": 9.933807660562898e-06,
+      "loss": 0.9168,
+      "step": 110
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.5809632539749146,
+      "learning_rate": 9.890738003669029e-06,
+      "loss": 0.9345,
+      "step": 120
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.6306660771369934,
+      "learning_rate": 9.83707609731432e-06,
+      "loss": 0.8842,
+      "step": 130
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.645531952381134,
+      "learning_rate": 9.77293816123866e-06,
+      "loss": 0.8496,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.7515069842338562,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.8134,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.8647974133491516,
+      "learning_rate": 9.613812221777212e-06,
+      "loss": 0.8645,
+      "step": 160
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.5082105398178101,
+      "learning_rate": 9.519168849742603e-06,
+      "loss": 0.8339,
+      "step": 170
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.6905492544174194,
+      "learning_rate": 9.414737964294636e-06,
+      "loss": 0.8524,
+      "step": 180
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.7012932896614075,
+      "learning_rate": 9.30074573947683e-06,
+      "loss": 0.8566,
+      "step": 190
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6087114810943604,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.8107,
+      "step": 200
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.7151578664779663,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 0.9001,
+      "step": 210
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.746478796005249,
+      "learning_rate": 8.903970133383297e-06,
+      "loss": 0.8522,
+      "step": 220
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.5843214392662048,
+      "learning_rate": 8.754400164907496e-06,
+      "loss": 0.8164,
+      "step": 230
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.6262736916542053,
+      "learning_rate": 8.596699001693257e-06,
+      "loss": 0.8739,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6539023518562317,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.8353,
+      "step": 250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.7221904397010803,
+      "learning_rate": 8.258286144107277e-06,
+      "loss": 0.7376,
+      "step": 260
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.6120831966400146,
+      "learning_rate": 8.078307376628292e-06,
+      "loss": 0.7247,
+      "step": 270
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.5770366787910461,
+      "learning_rate": 7.891661680839932e-06,
+      "loss": 0.6993,
+      "step": 280
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.4881764352321625,
+      "learning_rate": 7.698753289757565e-06,
+      "loss": 0.6871,
+      "step": 290
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.6157920360565186,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7247,
+      "step": 300
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.5322688817977905,
+      "learning_rate": 7.295832266935059e-06,
+      "loss": 0.7549,
+      "step": 310
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.7124238014221191,
+      "learning_rate": 7.08669227240909e-06,
+      "loss": 0.6858,
+      "step": 320
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.5642361044883728,
+      "learning_rate": 6.873032967079562e-06,
+      "loss": 0.6737,
+      "step": 330
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.7349158525466919,
+      "learning_rate": 6.655317089424791e-06,
+      "loss": 0.7092,
+      "step": 340
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.6204760670661926,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.6878,
+      "step": 350
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.4934922754764557,
+      "learning_rate": 6.209609477998339e-06,
+      "loss": 0.6883,
+      "step": 360
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.5973473787307739,
+      "learning_rate": 5.982583047664151e-06,
+      "loss": 0.7312,
+      "step": 370
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.9578109979629517,
+      "learning_rate": 5.753428561247416e-06,
+      "loss": 0.6466,
+      "step": 380
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.6420013904571533,
+      "learning_rate": 5.522642316338268e-06,
+      "loss": 0.5745,
+      "step": 390
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.6083827614784241,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.6074,
+      "step": 400
+    },
+    {
+      "epoch": 3.2800000000000002,
+      "grad_norm": 0.5411021709442139,
+      "learning_rate": 5.0581763290069865e-06,
+      "loss": 0.5958,
+      "step": 410
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.542936384677887,
+      "learning_rate": 4.825502516487497e-06,
+      "loss": 0.517,
+      "step": 420
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.643763542175293,
+      "learning_rate": 4.59320662666071e-06,
+      "loss": 0.6125,
+      "step": 430
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 0.5902148485183716,
+      "learning_rate": 4.361791760697027e-06,
+      "loss": 0.5574,
+      "step": 440
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.5409561991691589,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.5619,
+      "step": 450
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 0.5303182601928711,
+      "learning_rate": 3.903606879060483e-06,
+      "loss": 0.5723,
+      "step": 460
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 0.5597081184387207,
+      "learning_rate": 3.6778291898139907e-06,
+      "loss": 0.57,
+      "step": 470
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 0.557049572467804,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.558,
+      "step": 480
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 0.5532881021499634,
+      "learning_rate": 3.2353471764306567e-06,
+      "loss": 0.5642,
+      "step": 490
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6130328178405762,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.582,
+      "step": 500
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 0.6685742139816284,
+      "learning_rate": 2.8081442660546126e-06,
+      "loss": 0.4826,
+      "step": 510
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 0.7372143268585205,
+      "learning_rate": 2.601434433748771e-06,
+      "loss": 0.4799,
+      "step": 520
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 0.5380725860595703,
+      "learning_rate": 2.3999193603539234e-06,
+      "loss": 0.4595,
+      "step": 530
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 0.611395537853241,
+      "learning_rate": 2.204035482646267e-06,
+      "loss": 0.4414,
+      "step": 540
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.6131682991981506,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.42,
+      "step": 550
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 0.5948655605316162,
+      "learning_rate": 1.8308451630064484e-06,
+      "loss": 0.4228,
+      "step": 560
+    },
+    {
+      "epoch": 4.5600000000000005,
+      "grad_norm": 0.5260858535766602,
+      "learning_rate": 1.6543469682057105e-06,
+      "loss": 0.4486,
+      "step": 570
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 0.6490086913108826,
+      "learning_rate": 1.4850947128716914e-06,
+      "loss": 0.4064,
+      "step": 580
+    },
+    {
+      "epoch": 4.72,
+      "grad_norm": 0.512779951095581,
+      "learning_rate": 1.3234549597008572e-06,
+      "loss": 0.4806,
+      "step": 590
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.6591514945030212,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.4537,
+      "step": 600
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.5841071605682373,
+      "learning_rate": 1.0243960175257605e-06,
+      "loss": 0.425,
+      "step": 610
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.5767258405685425,
+      "learning_rate": 8.876245235966884e-07,
+      "loss": 0.4903,
+      "step": 620
+    },
+    {
+      "epoch": 5.04,
+      "grad_norm": 0.681662380695343,
+      "learning_rate": 7.597595192178702e-07,
+      "loss": 0.4259,
+      "step": 630
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.6221340894699097,
+      "learning_rate": 6.410779315161885e-07,
+      "loss": 0.4243,
+      "step": 640
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 0.5294339656829834,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.3387,
+      "step": 650
+    },
+    {
+      "epoch": 5.28,
+      "grad_norm": 0.5295357704162598,
+      "learning_rate": 4.322727117869951e-07,
+      "loss": 0.3378,
+      "step": 660
+    },
+    {
+      "epoch": 5.36,
+      "grad_norm": 0.5497756004333496,
+      "learning_rate": 3.426013053692878e-07,
+      "loss": 0.3857,
+      "step": 670
+    },
+    {
+      "epoch": 5.44,
+      "grad_norm": 0.5334697961807251,
+      "learning_rate": 2.63016787428354e-07,
+      "loss": 0.3996,
+      "step": 680
+    },
+    {
+      "epoch": 5.52,
+      "grad_norm": 0.48104792833328247,
+      "learning_rate": 1.9369152030840553e-07,
+      "loss": 0.3743,
+      "step": 690
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 0.53028404712677,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.3542,
+      "step": 700
+    },
+    {
+      "epoch": 5.68,
+      "grad_norm": 0.5596076846122742,
+      "learning_rate": 8.639676646793382e-08,
+      "loss": 0.3587,
+      "step": 710
+    },
+    {
+      "epoch": 5.76,
+      "grad_norm": 0.5660611391067505,
+      "learning_rate": 4.865965629214819e-08,
+      "loss": 0.414,
+      "step": 720
+    },
+    {
+      "epoch": 5.84,
+      "grad_norm": 0.4768368899822235,
+      "learning_rate": 2.1646046750978255e-08,
+      "loss": 0.3887,
+      "step": 730
+    },
+    {
+      "epoch": 5.92,
+      "grad_norm": 0.5675653219223022,
+      "learning_rate": 5.414443307377171e-09,
+      "loss": 0.3811,
+      "step": 740
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5585565567016602,
+      "learning_rate": 0.0,
+      "loss": 0.3763,
+      "step": 750
+    },
+    {
+      "epoch": 6.0,
+      "step": 750,
+      "total_flos": 118427603697664.0,
+      "train_loss": 0.662273271560669,
+      "train_runtime": 26488.1763,
+      "train_samples_per_second": 0.227,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 118427603697664.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7232b091f1fd6d5369baae8e76960a43350fa5e72928a19dc07292824f73fc7b
+size 7864