Add files using upload-large-folder tool

.gitattributes

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

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: agenttuning_v4_10k_tag4
+  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. -->
+
+# agenttuning_v4_10k_tag4
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the agenttuning_v4_10k_tag4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4980
+
+## 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: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9941520467836257,
+    "eval_loss": 0.49801304936408997,
+    "eval_runtime": 1.1994,
+    "eval_samples_per_second": 0.834,
+    "eval_steps_per_second": 0.834,
+    "total_flos": 16222961664000.0,
+    "train_loss": 0.4659844195141512,
+    "train_runtime": 777.4722,
+    "train_samples_per_second": 0.877,
+    "train_steps_per_second": 0.109
+}

config.json

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

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9941520467836257,
+    "eval_loss": 0.49801304936408997,
+    "eval_runtime": 1.1994,
+    "eval_samples_per_second": 0.834,
+    "eval_steps_per_second": 0.834
+}

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f884bc21c4b4d39c9be29b314a816ced7d22245e9efbe953c77578e8bcda611
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b862821390c1e79680b7378c1dd661465ecada095dda99a6f927d6a549f5ae1d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d7c46edc9c74d65f937446fc92802e68339e20c91d889bb6bff784144a0b2b
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73dc92e638b3c85094df487f9553fa17aa5438b76215b3dfd932dc3a719d261
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9941520467836257,
+    "total_flos": 16222961664000.0,
+    "train_loss": 0.4659844195141512,
+    "train_runtime": 777.4722,
+    "train_samples_per_second": 0.877,
+    "train_steps_per_second": 0.109
+}

trainer_log.jsonl

@@ -0,0 +1,86 @@
+{"current_steps": 1, "total_steps": 85, "loss": 1.371, "lr": 4.998292650357558e-06, "epoch": 0.011695906432748537, "percentage": 1.18, "elapsed_time": "0:00:10", "remaining_time": "0:14:01"}
+{"current_steps": 2, "total_steps": 85, "loss": 0.8913, "lr": 4.99317293346447e-06, "epoch": 0.023391812865497075, "percentage": 2.35, "elapsed_time": "0:00:18", "remaining_time": "0:12:51"}
+{"current_steps": 3, "total_steps": 85, "loss": 0.682, "lr": 4.984647842238185e-06, "epoch": 0.03508771929824561, "percentage": 3.53, "elapsed_time": "0:00:27", "remaining_time": "0:12:22"}
+{"current_steps": 4, "total_steps": 85, "loss": 0.6502, "lr": 4.972729020927866e-06, "epoch": 0.04678362573099415, "percentage": 4.71, "elapsed_time": "0:00:35", "remaining_time": "0:12:05"}
+{"current_steps": 5, "total_steps": 85, "loss": 0.6428, "lr": 4.957432749209755e-06, "epoch": 0.05847953216374269, "percentage": 5.88, "elapsed_time": "0:00:44", "remaining_time": "0:11:51"}
+{"current_steps": 6, "total_steps": 85, "loss": 0.6002, "lr": 4.938779919951092e-06, "epoch": 0.07017543859649122, "percentage": 7.06, "elapsed_time": "0:00:53", "remaining_time": "0:11:40"}
+{"current_steps": 7, "total_steps": 85, "loss": 0.5459, "lr": 4.916796010672969e-06, "epoch": 0.08187134502923976, "percentage": 8.24, "elapsed_time": "0:01:01", "remaining_time": "0:11:29"}
+{"current_steps": 8, "total_steps": 85, "loss": 0.5296, "lr": 4.891511048751102e-06, "epoch": 0.0935672514619883, "percentage": 9.41, "elapsed_time": "0:01:10", "remaining_time": "0:11:19"}
+{"current_steps": 9, "total_steps": 85, "loss": 0.5892, "lr": 4.86295957040205e-06, "epoch": 0.10526315789473684, "percentage": 10.59, "elapsed_time": "0:01:19", "remaining_time": "0:11:10"}
+{"current_steps": 10, "total_steps": 85, "loss": 0.5459, "lr": 4.83118057351089e-06, "epoch": 0.11695906432748537, "percentage": 11.76, "elapsed_time": "0:01:28", "remaining_time": "0:11:01"}
+{"current_steps": 11, "total_steps": 85, "loss": 0.5494, "lr": 4.796217464364808e-06, "epoch": 0.1286549707602339, "percentage": 12.94, "elapsed_time": "0:01:37", "remaining_time": "0:10:52"}
+{"current_steps": 12, "total_steps": 85, "loss": 0.5227, "lr": 4.7581179983653224e-06, "epoch": 0.14035087719298245, "percentage": 14.12, "elapsed_time": "0:01:45", "remaining_time": "0:10:43"}
+{"current_steps": 13, "total_steps": 85, "loss": 0.5084, "lr": 4.716934214800155e-06, "epoch": 0.15204678362573099, "percentage": 15.29, "elapsed_time": "0:01:54", "remaining_time": "0:10:35"}
+{"current_steps": 14, "total_steps": 85, "loss": 0.4717, "lr": 4.672722365763821e-06, "epoch": 0.16374269005847952, "percentage": 16.47, "elapsed_time": "0:02:03", "remaining_time": "0:10:26"}
+{"current_steps": 15, "total_steps": 85, "loss": 0.4987, "lr": 4.625542839324036e-06, "epoch": 0.17543859649122806, "percentage": 17.65, "elapsed_time": "0:02:12", "remaining_time": "0:10:18"}
+{"current_steps": 16, "total_steps": 85, "loss": 0.4652, "lr": 4.575460077038877e-06, "epoch": 0.1871345029239766, "percentage": 18.82, "elapsed_time": "0:02:21", "remaining_time": "0:10:09"}
+{"current_steps": 17, "total_steps": 85, "loss": 0.4737, "lr": 4.522542485937369e-06, "epoch": 0.19883040935672514, "percentage": 20.0, "elapsed_time": "0:02:30", "remaining_time": "0:10:00"}
+{"current_steps": 18, "total_steps": 85, "loss": 0.481, "lr": 4.4668623450837085e-06, "epoch": 0.21052631578947367, "percentage": 21.18, "elapsed_time": "0:02:38", "remaining_time": "0:09:51"}
+{"current_steps": 19, "total_steps": 85, "loss": 0.4894, "lr": 4.408495706852758e-06, "epoch": 0.2222222222222222, "percentage": 22.35, "elapsed_time": "0:02:47", "remaining_time": "0:09:42"}
+{"current_steps": 20, "total_steps": 85, "loss": 0.4589, "lr": 4.3475222930516484e-06, "epoch": 0.23391812865497075, "percentage": 23.53, "elapsed_time": "0:02:56", "remaining_time": "0:09:33"}
+{"current_steps": 21, "total_steps": 85, "loss": 0.4542, "lr": 4.284025386029381e-06, "epoch": 0.24561403508771928, "percentage": 24.71, "elapsed_time": "0:03:05", "remaining_time": "0:09:24"}
+{"current_steps": 22, "total_steps": 85, "loss": 0.4264, "lr": 4.218091714923157e-06, "epoch": 0.2573099415204678, "percentage": 25.88, "elapsed_time": "0:03:14", "remaining_time": "0:09:15"}
+{"current_steps": 23, "total_steps": 85, "loss": 0.4607, "lr": 4.149811337196808e-06, "epoch": 0.26900584795321636, "percentage": 27.06, "elapsed_time": "0:03:22", "remaining_time": "0:09:07"}
+{"current_steps": 24, "total_steps": 85, "loss": 0.4843, "lr": 4.079277515633127e-06, "epoch": 0.2807017543859649, "percentage": 28.24, "elapsed_time": "0:03:31", "remaining_time": "0:08:58"}
+{"current_steps": 25, "total_steps": 85, "loss": 0.4324, "lr": 4.006586590948141e-06, "epoch": 0.29239766081871343, "percentage": 29.41, "elapsed_time": "0:03:40", "remaining_time": "0:08:49"}
+{"current_steps": 26, "total_steps": 85, "loss": 0.4724, "lr": 3.9318378502012636e-06, "epoch": 0.30409356725146197, "percentage": 30.59, "elapsed_time": "0:03:49", "remaining_time": "0:08:40"}
+{"current_steps": 27, "total_steps": 85, "loss": 0.4414, "lr": 3.855133391181124e-06, "epoch": 0.3157894736842105, "percentage": 31.76, "elapsed_time": "0:03:58", "remaining_time": "0:08:31"}
+{"current_steps": 28, "total_steps": 85, "loss": 0.4174, "lr": 3.7765779829522674e-06, "epoch": 0.32748538011695905, "percentage": 32.94, "elapsed_time": "0:04:07", "remaining_time": "0:08:23"}
+{"current_steps": 29, "total_steps": 85, "loss": 0.4193, "lr": 3.6962789227532165e-06, "epoch": 0.3391812865497076, "percentage": 34.12, "elapsed_time": "0:04:16", "remaining_time": "0:08:14"}
+{"current_steps": 30, "total_steps": 85, "loss": 0.4759, "lr": 3.6143458894413463e-06, "epoch": 0.3508771929824561, "percentage": 35.29, "elapsed_time": "0:04:24", "remaining_time": "0:08:05"}
+{"current_steps": 31, "total_steps": 85, "loss": 0.4392, "lr": 3.530890793684759e-06, "epoch": 0.36257309941520466, "percentage": 36.47, "elapsed_time": "0:04:33", "remaining_time": "0:07:56"}
+{"current_steps": 32, "total_steps": 85, "loss": 0.4827, "lr": 3.446027625105776e-06, "epoch": 0.3742690058479532, "percentage": 37.65, "elapsed_time": "0:04:42", "remaining_time": "0:07:47"}
+{"current_steps": 33, "total_steps": 85, "loss": 0.453, "lr": 3.359872296584821e-06, "epoch": 0.38596491228070173, "percentage": 38.82, "elapsed_time": "0:04:51", "remaining_time": "0:07:38"}
+{"current_steps": 34, "total_steps": 85, "loss": 0.4166, "lr": 3.272542485937369e-06, "epoch": 0.39766081871345027, "percentage": 40.0, "elapsed_time": "0:05:00", "remaining_time": "0:07:30"}
+{"current_steps": 35, "total_steps": 85, "loss": 0.4316, "lr": 3.184157475180208e-06, "epoch": 0.4093567251461988, "percentage": 41.18, "elapsed_time": "0:05:08", "remaining_time": "0:07:21"}
+{"current_steps": 36, "total_steps": 85, "loss": 0.4363, "lr": 3.094837987606547e-06, "epoch": 0.42105263157894735, "percentage": 42.35, "elapsed_time": "0:05:17", "remaining_time": "0:07:12"}
+{"current_steps": 37, "total_steps": 85, "loss": 0.4254, "lr": 3.0047060228925256e-06, "epoch": 0.4327485380116959, "percentage": 43.53, "elapsed_time": "0:05:26", "remaining_time": "0:07:03"}
+{"current_steps": 38, "total_steps": 85, "loss": 0.4409, "lr": 2.913884690460325e-06, "epoch": 0.4444444444444444, "percentage": 44.71, "elapsed_time": "0:05:35", "remaining_time": "0:06:55"}
+{"current_steps": 39, "total_steps": 85, "loss": 0.4228, "lr": 2.822498041325509e-06, "epoch": 0.45614035087719296, "percentage": 45.88, "elapsed_time": "0:05:44", "remaining_time": "0:06:46"}
+{"current_steps": 40, "total_steps": 85, "loss": 0.399, "lr": 2.730670898658255e-06, "epoch": 0.4678362573099415, "percentage": 47.06, "elapsed_time": "0:05:53", "remaining_time": "0:06:37"}
+{"current_steps": 41, "total_steps": 85, "loss": 0.4658, "lr": 2.638528687289925e-06, "epoch": 0.47953216374269003, "percentage": 48.24, "elapsed_time": "0:06:02", "remaining_time": "0:06:28"}
+{"current_steps": 42, "total_steps": 85, "loss": 0.4294, "lr": 2.546197262397825e-06, "epoch": 0.49122807017543857, "percentage": 49.41, "elapsed_time": "0:06:10", "remaining_time": "0:06:19"}
+{"current_steps": 43, "total_steps": 85, "loss": 0.4679, "lr": 2.453802737602176e-06, "epoch": 0.5029239766081871, "percentage": 50.59, "elapsed_time": "0:06:19", "remaining_time": "0:06:10"}
+{"current_steps": 44, "total_steps": 85, "loss": 0.4459, "lr": 2.3614713127100752e-06, "epoch": 0.5146198830409356, "percentage": 51.76, "elapsed_time": "0:06:28", "remaining_time": "0:06:02"}
+{"current_steps": 45, "total_steps": 85, "loss": 0.4298, "lr": 2.269329101341745e-06, "epoch": 0.5263157894736842, "percentage": 52.94, "elapsed_time": "0:06:37", "remaining_time": "0:05:53"}
+{"current_steps": 46, "total_steps": 85, "loss": 0.4263, "lr": 2.1775019586744924e-06, "epoch": 0.5380116959064327, "percentage": 54.12, "elapsed_time": "0:06:46", "remaining_time": "0:05:44"}
+{"current_steps": 47, "total_steps": 85, "loss": 0.3993, "lr": 2.086115309539675e-06, "epoch": 0.5497076023391813, "percentage": 55.29, "elapsed_time": "0:06:55", "remaining_time": "0:05:35"}
+{"current_steps": 48, "total_steps": 85, "loss": 0.435, "lr": 1.995293977107475e-06, "epoch": 0.5614035087719298, "percentage": 56.47, "elapsed_time": "0:07:03", "remaining_time": "0:05:26"}
+{"current_steps": 49, "total_steps": 85, "loss": 0.4273, "lr": 1.9051620123934538e-06, "epoch": 0.5730994152046783, "percentage": 57.65, "elapsed_time": "0:07:12", "remaining_time": "0:05:17"}
+{"current_steps": 50, "total_steps": 85, "loss": 0.4051, "lr": 1.8158425248197931e-06, "epoch": 0.5847953216374269, "percentage": 58.82, "elapsed_time": "0:07:21", "remaining_time": "0:05:09"}
+{"current_steps": 51, "total_steps": 85, "loss": 0.4408, "lr": 1.7274575140626318e-06, "epoch": 0.5964912280701754, "percentage": 60.0, "elapsed_time": "0:07:30", "remaining_time": "0:05:00"}
+{"current_steps": 52, "total_steps": 85, "loss": 0.4305, "lr": 1.6401277034151798e-06, "epoch": 0.6081871345029239, "percentage": 61.18, "elapsed_time": "0:07:39", "remaining_time": "0:04:51"}
+{"current_steps": 53, "total_steps": 85, "loss": 0.4193, "lr": 1.5539723748942246e-06, "epoch": 0.6198830409356725, "percentage": 62.35, "elapsed_time": "0:07:48", "remaining_time": "0:04:42"}
+{"current_steps": 54, "total_steps": 85, "loss": 0.4088, "lr": 1.4691092063152417e-06, "epoch": 0.631578947368421, "percentage": 63.53, "elapsed_time": "0:07:56", "remaining_time": "0:04:33"}
+{"current_steps": 55, "total_steps": 85, "loss": 0.4402, "lr": 1.3856541105586545e-06, "epoch": 0.6432748538011696, "percentage": 64.71, "elapsed_time": "0:08:05", "remaining_time": "0:04:24"}
+{"current_steps": 56, "total_steps": 85, "loss": 0.4159, "lr": 1.303721077246784e-06, "epoch": 0.6549707602339181, "percentage": 65.88, "elapsed_time": "0:08:14", "remaining_time": "0:04:16"}
+{"current_steps": 57, "total_steps": 85, "loss": 0.4032, "lr": 1.2234220170477332e-06, "epoch": 0.6666666666666666, "percentage": 67.06, "elapsed_time": "0:08:23", "remaining_time": "0:04:07"}
+{"current_steps": 58, "total_steps": 85, "loss": 0.3936, "lr": 1.1448666088188766e-06, "epoch": 0.6783625730994152, "percentage": 68.24, "elapsed_time": "0:08:32", "remaining_time": "0:03:58"}
+{"current_steps": 59, "total_steps": 85, "loss": 0.4115, "lr": 1.068162149798737e-06, "epoch": 0.6900584795321637, "percentage": 69.41, "elapsed_time": "0:08:41", "remaining_time": "0:03:49"}
+{"current_steps": 60, "total_steps": 85, "loss": 0.4263, "lr": 9.934134090518593e-07, "epoch": 0.7017543859649122, "percentage": 70.59, "elapsed_time": "0:08:49", "remaining_time": "0:03:40"}
+{"current_steps": 61, "total_steps": 85, "loss": 0.4031, "lr": 9.207224843668733e-07, "epoch": 0.7134502923976608, "percentage": 71.76, "elapsed_time": "0:08:58", "remaining_time": "0:03:31"}
+{"current_steps": 62, "total_steps": 85, "loss": 0.4236, "lr": 8.501886628031941e-07, "epoch": 0.7251461988304093, "percentage": 72.94, "elapsed_time": "0:09:07", "remaining_time": "0:03:23"}
+{"current_steps": 63, "total_steps": 85, "loss": 0.4105, "lr": 7.819082850768433e-07, "epoch": 0.7368421052631579, "percentage": 74.12, "elapsed_time": "0:09:16", "remaining_time": "0:03:14"}
+{"current_steps": 64, "total_steps": 85, "loss": 0.4206, "lr": 7.159746139706194e-07, "epoch": 0.7485380116959064, "percentage": 75.29, "elapsed_time": "0:09:25", "remaining_time": "0:03:05"}
+{"current_steps": 65, "total_steps": 85, "loss": 0.4203, "lr": 6.524777069483526e-07, "epoch": 0.7602339181286549, "percentage": 76.47, "elapsed_time": "0:09:33", "remaining_time": "0:02:56"}
+{"current_steps": 66, "total_steps": 85, "loss": 0.4204, "lr": 5.915042931472426e-07, "epoch": 0.7719298245614035, "percentage": 77.65, "elapsed_time": "0:09:42", "remaining_time": "0:02:47"}
+{"current_steps": 67, "total_steps": 85, "loss": 0.432, "lr": 5.33137654916292e-07, "epoch": 0.783625730994152, "percentage": 78.82, "elapsed_time": "0:09:51", "remaining_time": "0:02:38"}
+{"current_steps": 68, "total_steps": 85, "loss": 0.409, "lr": 4.774575140626317e-07, "epoch": 0.7953216374269005, "percentage": 80.0, "elapsed_time": "0:10:00", "remaining_time": "0:02:30"}
+{"current_steps": 69, "total_steps": 85, "loss": 0.4437, "lr": 4.2453992296112384e-07, "epoch": 0.8070175438596491, "percentage": 81.18, "elapsed_time": "0:10:09", "remaining_time": "0:02:21"}
+{"current_steps": 70, "total_steps": 85, "loss": 0.4064, "lr": 3.7445716067596506e-07, "epoch": 0.8187134502923976, "percentage": 82.35, "elapsed_time": "0:10:18", "remaining_time": "0:02:12"}
+{"current_steps": 71, "total_steps": 85, "loss": 0.3909, "lr": 3.2727763423617915e-07, "epoch": 0.8304093567251462, "percentage": 83.53, "elapsed_time": "0:10:26", "remaining_time": "0:02:03"}
+{"current_steps": 72, "total_steps": 85, "loss": 0.3945, "lr": 2.8306578519984526e-07, "epoch": 0.8421052631578947, "percentage": 84.71, "elapsed_time": "0:10:35", "remaining_time": "0:01:54"}
+{"current_steps": 73, "total_steps": 85, "loss": 0.4184, "lr": 2.418820016346779e-07, "epoch": 0.8538011695906432, "percentage": 85.88, "elapsed_time": "0:10:44", "remaining_time": "0:01:45"}
+{"current_steps": 74, "total_steps": 85, "loss": 0.4195, "lr": 2.0378253563519247e-07, "epoch": 0.8654970760233918, "percentage": 87.06, "elapsed_time": "0:10:53", "remaining_time": "0:01:37"}
+{"current_steps": 75, "total_steps": 85, "loss": 0.4132, "lr": 1.6881942648911077e-07, "epoch": 0.8771929824561403, "percentage": 88.24, "elapsed_time": "0:11:02", "remaining_time": "0:01:28"}
+{"current_steps": 76, "total_steps": 85, "loss": 0.4107, "lr": 1.3704042959795132e-07, "epoch": 0.8888888888888888, "percentage": 89.41, "elapsed_time": "0:11:11", "remaining_time": "0:01:19"}
+{"current_steps": 77, "total_steps": 85, "loss": 0.4046, "lr": 1.0848895124889819e-07, "epoch": 0.9005847953216374, "percentage": 90.59, "elapsed_time": "0:11:19", "remaining_time": "0:01:10"}
+{"current_steps": 78, "total_steps": 85, "loss": 0.4163, "lr": 8.320398932703145e-08, "epoch": 0.9122807017543859, "percentage": 91.76, "elapsed_time": "0:11:28", "remaining_time": "0:01:01"}
+{"current_steps": 79, "total_steps": 85, "loss": 0.3935, "lr": 6.12200800489085e-08, "epoch": 0.9239766081871345, "percentage": 92.94, "elapsed_time": "0:11:37", "remaining_time": "0:00:52"}
+{"current_steps": 80, "total_steps": 85, "loss": 0.4094, "lr": 4.256725079024554e-08, "epoch": 0.935672514619883, "percentage": 94.12, "elapsed_time": "0:11:46", "remaining_time": "0:00:44"}
+{"current_steps": 81, "total_steps": 85, "loss": 0.3987, "lr": 2.7270979072135106e-08, "epoch": 0.9473684210526315, "percentage": 95.29, "elapsed_time": "0:11:55", "remaining_time": "0:00:35"}
+{"current_steps": 82, "total_steps": 85, "loss": 0.4257, "lr": 1.5352157761815978e-08, "epoch": 0.9590643274853801, "percentage": 96.47, "elapsed_time": "0:12:04", "remaining_time": "0:00:26"}
+{"current_steps": 83, "total_steps": 85, "loss": 0.397, "lr": 6.827066535529947e-09, "epoch": 0.9707602339181286, "percentage": 97.65, "elapsed_time": "0:12:12", "remaining_time": "0:00:17"}
+{"current_steps": 84, "total_steps": 85, "loss": 0.4064, "lr": 1.707349642442735e-09, "epoch": 0.9824561403508771, "percentage": 98.82, "elapsed_time": "0:12:21", "remaining_time": "0:00:08"}
+{"current_steps": 85, "total_steps": 85, "loss": 0.3992, "lr": 0.0, "epoch": 0.9941520467836257, "percentage": 100.0, "elapsed_time": "0:12:30", "remaining_time": "0:00:00"}
+{"current_steps": 85, "total_steps": 85, "epoch": 0.9941520467836257, "percentage": 100.0, "elapsed_time": "0:12:57", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,637 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9941520467836257,
+  "eval_steps": 100,
+  "global_step": 85,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011695906432748537,
+      "grad_norm": 35.025693359198776,
+      "learning_rate": 4.998292650357558e-06,
+      "loss": 1.371,
+      "step": 1
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 16.663018388823748,
+      "learning_rate": 4.99317293346447e-06,
+      "loss": 0.8913,
+      "step": 2
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 5.63477865361655,
+      "learning_rate": 4.984647842238185e-06,
+      "loss": 0.682,
+      "step": 3
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 4.393718514605396,
+      "learning_rate": 4.972729020927866e-06,
+      "loss": 0.6502,
+      "step": 4
+    },
+    {
+      "epoch": 0.05847953216374269,
+      "grad_norm": 4.8303971389860445,
+      "learning_rate": 4.957432749209755e-06,
+      "loss": 0.6428,
+      "step": 5
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 3.645841355616713,
+      "learning_rate": 4.938779919951092e-06,
+      "loss": 0.6002,
+      "step": 6
+    },
+    {
+      "epoch": 0.08187134502923976,
+      "grad_norm": 3.029856387382791,
+      "learning_rate": 4.916796010672969e-06,
+      "loss": 0.5459,
+      "step": 7
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "grad_norm": 3.624881910351262,
+      "learning_rate": 4.891511048751102e-06,
+      "loss": 0.5296,
+      "step": 8
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 3.6464395239589154,
+      "learning_rate": 4.86295957040205e-06,
+      "loss": 0.5892,
+      "step": 9
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 2.8188073270060365,
+      "learning_rate": 4.83118057351089e-06,
+      "loss": 0.5459,
+      "step": 10
+    },
+    {
+      "epoch": 0.1286549707602339,
+      "grad_norm": 2.7383055735017305,
+      "learning_rate": 4.796217464364808e-06,
+      "loss": 0.5494,
+      "step": 11
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 2.358116375783895,
+      "learning_rate": 4.7581179983653224e-06,
+      "loss": 0.5227,
+      "step": 12
+    },
+    {
+      "epoch": 0.15204678362573099,
+      "grad_norm": 2.0714421741385665,
+      "learning_rate": 4.716934214800155e-06,
+      "loss": 0.5084,
+      "step": 13
+    },
+    {
+      "epoch": 0.16374269005847952,
+      "grad_norm": 1.9915649749680084,
+      "learning_rate": 4.672722365763821e-06,
+      "loss": 0.4717,
+      "step": 14
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.8808874150573223,
+      "learning_rate": 4.625542839324036e-06,
+      "loss": 0.4987,
+      "step": 15
+    },
+    {
+      "epoch": 0.1871345029239766,
+      "grad_norm": 1.8340312081770043,
+      "learning_rate": 4.575460077038877e-06,
+      "loss": 0.4652,
+      "step": 16
+    },
+    {
+      "epoch": 0.19883040935672514,
+      "grad_norm": 1.788650219362879,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.4737,
+      "step": 17
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 1.8260619062758139,
+      "learning_rate": 4.4668623450837085e-06,
+      "loss": 0.481,
+      "step": 18
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.909066432801376,
+      "learning_rate": 4.408495706852758e-06,
+      "loss": 0.4894,
+      "step": 19
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "grad_norm": 1.8210802352044484,
+      "learning_rate": 4.3475222930516484e-06,
+      "loss": 0.4589,
+      "step": 20
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 1.6539175612213122,
+      "learning_rate": 4.284025386029381e-06,
+      "loss": 0.4542,
+      "step": 21
+    },
+    {
+      "epoch": 0.2573099415204678,
+      "grad_norm": 2.130714505058146,
+      "learning_rate": 4.218091714923157e-06,
+      "loss": 0.4264,
+      "step": 22
+    },
+    {
+      "epoch": 0.26900584795321636,
+      "grad_norm": 1.824188621761018,
+      "learning_rate": 4.149811337196808e-06,
+      "loss": 0.4607,
+      "step": 23
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 1.778036183501626,
+      "learning_rate": 4.079277515633127e-06,
+      "loss": 0.4843,
+      "step": 24
+    },
+    {
+      "epoch": 0.29239766081871343,
+      "grad_norm": 1.8627770778609025,
+      "learning_rate": 4.006586590948141e-06,
+      "loss": 0.4324,
+      "step": 25
+    },
+    {
+      "epoch": 0.30409356725146197,
+      "grad_norm": 1.8920248196537022,
+      "learning_rate": 3.9318378502012636e-06,
+      "loss": 0.4724,
+      "step": 26
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 1.6119731457837412,
+      "learning_rate": 3.855133391181124e-06,
+      "loss": 0.4414,
+      "step": 27
+    },
+    {
+      "epoch": 0.32748538011695905,
+      "grad_norm": 1.7383929202565187,
+      "learning_rate": 3.7765779829522674e-06,
+      "loss": 0.4174,
+      "step": 28
+    },
+    {
+      "epoch": 0.3391812865497076,
+      "grad_norm": 1.7806625169286083,
+      "learning_rate": 3.6962789227532165e-06,
+      "loss": 0.4193,
+      "step": 29
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 1.8461224572248136,
+      "learning_rate": 3.6143458894413463e-06,
+      "loss": 0.4759,
+      "step": 30
+    },
+    {
+      "epoch": 0.36257309941520466,
+      "grad_norm": 1.6847191460684066,
+      "learning_rate": 3.530890793684759e-06,
+      "loss": 0.4392,
+      "step": 31
+    },
+    {
+      "epoch": 0.3742690058479532,
+      "grad_norm": 1.7411517120082791,
+      "learning_rate": 3.446027625105776e-06,
+      "loss": 0.4827,
+      "step": 32
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 1.6882683541546895,
+      "learning_rate": 3.359872296584821e-06,
+      "loss": 0.453,
+      "step": 33
+    },
+    {
+      "epoch": 0.39766081871345027,
+      "grad_norm": 1.7502667044238607,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.4166,
+      "step": 34
+    },
+    {
+      "epoch": 0.4093567251461988,
+      "grad_norm": 1.8029525809952547,
+      "learning_rate": 3.184157475180208e-06,
+      "loss": 0.4316,
+      "step": 35
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.550122276581062,
+      "learning_rate": 3.094837987606547e-06,
+      "loss": 0.4363,
+      "step": 36
+    },
+    {
+      "epoch": 0.4327485380116959,
+      "grad_norm": 1.807438926224182,
+      "learning_rate": 3.0047060228925256e-06,
+      "loss": 0.4254,
+      "step": 37
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.7308007711839366,
+      "learning_rate": 2.913884690460325e-06,
+      "loss": 0.4409,
+      "step": 38
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 1.7045946316976472,
+      "learning_rate": 2.822498041325509e-06,
+      "loss": 0.4228,
+      "step": 39
+    },
+    {
+      "epoch": 0.4678362573099415,
+      "grad_norm": 1.613372278759582,
+      "learning_rate": 2.730670898658255e-06,
+      "loss": 0.399,
+      "step": 40
+    },
+    {
+      "epoch": 0.47953216374269003,
+      "grad_norm": 1.8621576137099085,
+      "learning_rate": 2.638528687289925e-06,
+      "loss": 0.4658,
+      "step": 41
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 1.9045232238716512,
+      "learning_rate": 2.546197262397825e-06,
+      "loss": 0.4294,
+      "step": 42
+    },
+    {
+      "epoch": 0.5029239766081871,
+      "grad_norm": 1.8468611123858474,
+      "learning_rate": 2.453802737602176e-06,
+      "loss": 0.4679,
+      "step": 43
+    },
+    {
+      "epoch": 0.5146198830409356,
+      "grad_norm": 1.6820536821830685,
+      "learning_rate": 2.3614713127100752e-06,
+      "loss": 0.4459,
+      "step": 44
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.5952313557434428,
+      "learning_rate": 2.269329101341745e-06,
+      "loss": 0.4298,
+      "step": 45
+    },
+    {
+      "epoch": 0.5380116959064327,
+      "grad_norm": 1.5550226549388593,
+      "learning_rate": 2.1775019586744924e-06,
+      "loss": 0.4263,
+      "step": 46
+    },
+    {
+      "epoch": 0.5497076023391813,
+      "grad_norm": 1.586062258840412,
+      "learning_rate": 2.086115309539675e-06,
+      "loss": 0.3993,
+      "step": 47
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 2.008972449673597,
+      "learning_rate": 1.995293977107475e-06,
+      "loss": 0.435,
+      "step": 48
+    },
+    {
+      "epoch": 0.5730994152046783,
+      "grad_norm": 1.542661474629316,
+      "learning_rate": 1.9051620123934538e-06,
+      "loss": 0.4273,
+      "step": 49
+    },
+    {
+      "epoch": 0.5847953216374269,
+      "grad_norm": 1.4253006014872718,
+      "learning_rate": 1.8158425248197931e-06,
+      "loss": 0.4051,
+      "step": 50
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 1.5954374806823395,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.4408,
+      "step": 51
+    },
+    {
+      "epoch": 0.6081871345029239,
+      "grad_norm": 1.596265223377444,
+      "learning_rate": 1.6401277034151798e-06,
+      "loss": 0.4305,
+      "step": 52
+    },
+    {
+      "epoch": 0.6198830409356725,
+      "grad_norm": 1.518233034728287,
+      "learning_rate": 1.5539723748942246e-06,
+      "loss": 0.4193,
+      "step": 53
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 1.4911638636469078,
+      "learning_rate": 1.4691092063152417e-06,
+      "loss": 0.4088,
+      "step": 54
+    },
+    {
+      "epoch": 0.6432748538011696,
+      "grad_norm": 1.5664052562912993,
+      "learning_rate": 1.3856541105586545e-06,
+      "loss": 0.4402,
+      "step": 55
+    },
+    {
+      "epoch": 0.6549707602339181,
+      "grad_norm": 1.6328711831640161,
+      "learning_rate": 1.303721077246784e-06,
+      "loss": 0.4159,
+      "step": 56
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 1.397487233226167,
+      "learning_rate": 1.2234220170477332e-06,
+      "loss": 0.4032,
+      "step": 57
+    },
+    {
+      "epoch": 0.6783625730994152,
+      "grad_norm": 1.533525193694589,
+      "learning_rate": 1.1448666088188766e-06,
+      "loss": 0.3936,
+      "step": 58
+    },
+    {
+      "epoch": 0.6900584795321637,
+      "grad_norm": 1.6602395757808444,
+      "learning_rate": 1.068162149798737e-06,
+      "loss": 0.4115,
+      "step": 59
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 1.4124752571385097,
+      "learning_rate": 9.934134090518593e-07,
+      "loss": 0.4263,
+      "step": 60
+    },
+    {
+      "epoch": 0.7134502923976608,
+      "grad_norm": 1.459600332519551,
+      "learning_rate": 9.207224843668733e-07,
+      "loss": 0.4031,
+      "step": 61
+    },
+    {
+      "epoch": 0.7251461988304093,
+      "grad_norm": 1.4873708880132595,
+      "learning_rate": 8.501886628031941e-07,
+      "loss": 0.4236,
+      "step": 62
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 1.5795763232447244,
+      "learning_rate": 7.819082850768433e-07,
+      "loss": 0.4105,
+      "step": 63
+    },
+    {
+      "epoch": 0.7485380116959064,
+      "grad_norm": 1.4525551317151242,
+      "learning_rate": 7.159746139706194e-07,
+      "loss": 0.4206,
+      "step": 64
+    },
+    {
+      "epoch": 0.7602339181286549,
+      "grad_norm": 1.6061714695016223,
+      "learning_rate": 6.524777069483526e-07,
+      "loss": 0.4203,
+      "step": 65
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 1.4111045787572132,
+      "learning_rate": 5.915042931472426e-07,
+      "loss": 0.4204,
+      "step": 66
+    },
+    {
+      "epoch": 0.783625730994152,
+      "grad_norm": 1.5171626246799457,
+      "learning_rate": 5.33137654916292e-07,
+      "loss": 0.432,
+      "step": 67
+    },
+    {
+      "epoch": 0.7953216374269005,
+      "grad_norm": 1.4450628738236402,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.409,
+      "step": 68
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 1.5021607634681438,
+      "learning_rate": 4.2453992296112384e-07,
+      "loss": 0.4437,
+      "step": 69
+    },
+    {
+      "epoch": 0.8187134502923976,
+      "grad_norm": 1.4395631922712842,
+      "learning_rate": 3.7445716067596506e-07,
+      "loss": 0.4064,
+      "step": 70
+    },
+    {
+      "epoch": 0.8304093567251462,
+      "grad_norm": 1.429477654505927,
+      "learning_rate": 3.2727763423617915e-07,
+      "loss": 0.3909,
+      "step": 71
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 1.445565697596715,
+      "learning_rate": 2.8306578519984526e-07,
+      "loss": 0.3945,
+      "step": 72
+    },
+    {
+      "epoch": 0.8538011695906432,
+      "grad_norm": 1.5119268943549344,
+      "learning_rate": 2.418820016346779e-07,
+      "loss": 0.4184,
+      "step": 73
+    },
+    {
+      "epoch": 0.8654970760233918,
+      "grad_norm": 1.5678968965257205,
+      "learning_rate": 2.0378253563519247e-07,
+      "loss": 0.4195,
+      "step": 74
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 1.4357936539164116,
+      "learning_rate": 1.6881942648911077e-07,
+      "loss": 0.4132,
+      "step": 75
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.4164005734060698,
+      "learning_rate": 1.3704042959795132e-07,
+      "loss": 0.4107,
+      "step": 76
+    },
+    {
+      "epoch": 0.9005847953216374,
+      "grad_norm": 1.6600282658098175,
+      "learning_rate": 1.0848895124889819e-07,
+      "loss": 0.4046,
+      "step": 77
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 1.4500327371644033,
+      "learning_rate": 8.320398932703145e-08,
+      "loss": 0.4163,
+      "step": 78
+    },
+    {
+      "epoch": 0.9239766081871345,
+      "grad_norm": 1.2589436881169307,
+      "learning_rate": 6.12200800489085e-08,
+      "loss": 0.3935,
+      "step": 79
+    },
+    {
+      "epoch": 0.935672514619883,
+      "grad_norm": 1.5900378417146472,
+      "learning_rate": 4.256725079024554e-08,
+      "loss": 0.4094,
+      "step": 80
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 1.3931405816524673,
+      "learning_rate": 2.7270979072135106e-08,
+      "loss": 0.3987,
+      "step": 81
+    },
+    {
+      "epoch": 0.9590643274853801,
+      "grad_norm": 1.5494797571631138,
+      "learning_rate": 1.5352157761815978e-08,
+      "loss": 0.4257,
+      "step": 82
+    },
+    {
+      "epoch": 0.9707602339181286,
+      "grad_norm": 1.4296532289452526,
+      "learning_rate": 6.827066535529947e-09,
+      "loss": 0.397,
+      "step": 83
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 1.6045124176237864,
+      "learning_rate": 1.707349642442735e-09,
+      "loss": 0.4064,
+      "step": 84
+    },
+    {
+      "epoch": 0.9941520467836257,
+      "grad_norm": 1.4142053576394011,
+      "learning_rate": 0.0,
+      "loss": 0.3992,
+      "step": 85
+    },
+    {
+      "epoch": 0.9941520467836257,
+      "step": 85,
+      "total_flos": 16222961664000.0,
+      "train_loss": 0.4659844195141512,
+      "train_runtime": 777.4722,
+      "train_samples_per_second": 0.877,
+      "train_steps_per_second": 0.109
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 85,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 95000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 16222961664000.0,
+  "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:c1a24c42fb703a8cfb7ac1d22b1c38a7b9303f8d6a58d3a1adbcf1f2b91645f4
+size 7160