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: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the emo 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-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- 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: 0.05
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- 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": 1.0,
+    "total_flos": 6384023396352.0,
+    "train_loss": 1.047203412950039,
+    "train_runtime": 2682.144,
+    "train_samples_per_second": 9.545,
+    "train_steps_per_second": 0.037
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "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": "4.50.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbdb7912cf9ba0b953fc5e85534e03b591574e18b2d0d4a6a1d35d8e3999a8f6
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2146f8333b8d482a0a6cd18136621b9c370da9bc553d4b5276bc831abfd1af
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f9f905008990ec922ddee495deb72a2d159c67c467eefe1f4280aa010ca8c42
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e694d63973be09009bba8677b140486d73caf447ad5b08f64124595629188629
+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": 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": 1.0,
+    "total_flos": 6384023396352.0,
+    "train_loss": 1.047203412950039,
+    "train_runtime": 2682.144,
+    "train_samples_per_second": 9.545,
+    "train_steps_per_second": 0.037
+}

trainer_log.jsonl

@@ -0,0 +1,101 @@
+{"current_steps": 1, "total_steps": 100, "loss": 7.1138, "lr": 2e-07, "epoch": 0.01, "percentage": 1.0, "elapsed_time": "0:00:30", "remaining_time": "0:50:08"}
+{"current_steps": 2, "total_steps": 100, "loss": 6.8466, "lr": 4e-07, "epoch": 0.02, "percentage": 2.0, "elapsed_time": "0:00:56", "remaining_time": "0:45:56"}
+{"current_steps": 3, "total_steps": 100, "loss": 6.8936, "lr": 6e-07, "epoch": 0.03, "percentage": 3.0, "elapsed_time": "0:01:23", "remaining_time": "0:44:58"}
+{"current_steps": 4, "total_steps": 100, "loss": 7.1196, "lr": 8e-07, "epoch": 0.04, "percentage": 4.0, "elapsed_time": "0:01:50", "remaining_time": "0:44:17"}
+{"current_steps": 5, "total_steps": 100, "loss": 6.7063, "lr": 1e-06, "epoch": 0.05, "percentage": 5.0, "elapsed_time": "0:02:17", "remaining_time": "0:43:40"}
+{"current_steps": 6, "total_steps": 100, "loss": 6.028, "lr": 9.99726628670463e-07, "epoch": 0.06, "percentage": 6.0, "elapsed_time": "0:02:44", "remaining_time": "0:43:00"}
+{"current_steps": 7, "total_steps": 100, "loss": 5.593, "lr": 9.989068136093872e-07, "epoch": 0.07, "percentage": 7.0, "elapsed_time": "0:03:10", "remaining_time": "0:42:16"}
+{"current_steps": 8, "total_steps": 100, "loss": 4.1199, "lr": 9.975414512725056e-07, "epoch": 0.08, "percentage": 8.0, "elapsed_time": "0:03:37", "remaining_time": "0:41:44"}
+{"current_steps": 9, "total_steps": 100, "loss": 3.8539, "lr": 9.956320346634875e-07, "epoch": 0.09, "percentage": 9.0, "elapsed_time": "0:04:04", "remaining_time": "0:41:11"}
+{"current_steps": 10, "total_steps": 100, "loss": 3.364, "lr": 9.931806517013612e-07, "epoch": 0.1, "percentage": 10.0, "elapsed_time": "0:04:30", "remaining_time": "0:40:35"}
+{"current_steps": 11, "total_steps": 100, "loss": 3.2359, "lr": 9.901899829374047e-07, "epoch": 0.11, "percentage": 11.0, "elapsed_time": "0:04:56", "remaining_time": "0:40:01"}
+{"current_steps": 12, "total_steps": 100, "loss": 2.0694, "lr": 9.866632986240029e-07, "epoch": 0.12, "percentage": 12.0, "elapsed_time": "0:05:20", "remaining_time": "0:39:12"}
+{"current_steps": 13, "total_steps": 100, "loss": 1.8041, "lr": 9.826044551386742e-07, "epoch": 0.13, "percentage": 13.0, "elapsed_time": "0:05:46", "remaining_time": "0:38:36"}
+{"current_steps": 14, "total_steps": 100, "loss": 1.8221, "lr": 9.780178907671788e-07, "epoch": 0.14, "percentage": 14.0, "elapsed_time": "0:06:11", "remaining_time": "0:38:03"}
+{"current_steps": 15, "total_steps": 100, "loss": 1.5577, "lr": 9.729086208503173e-07, "epoch": 0.15, "percentage": 15.0, "elapsed_time": "0:06:38", "remaining_time": "0:37:39"}
+{"current_steps": 16, "total_steps": 100, "loss": 1.3898, "lr": 9.672822322997304e-07, "epoch": 0.16, "percentage": 16.0, "elapsed_time": "0:07:04", "remaining_time": "0:37:06"}
+{"current_steps": 17, "total_steps": 100, "loss": 1.2839, "lr": 9.611448774886923e-07, "epoch": 0.17, "percentage": 17.0, "elapsed_time": "0:07:30", "remaining_time": "0:36:38"}
+{"current_steps": 18, "total_steps": 100, "loss": 1.1126, "lr": 9.545032675245813e-07, "epoch": 0.18, "percentage": 18.0, "elapsed_time": "0:07:57", "remaining_time": "0:36:15"}
+{"current_steps": 19, "total_steps": 100, "loss": 0.9637, "lr": 9.473646649103817e-07, "epoch": 0.19, "percentage": 19.0, "elapsed_time": "0:08:25", "remaining_time": "0:35:57"}
+{"current_steps": 20, "total_steps": 100, "loss": 0.6976, "lr": 9.397368756032444e-07, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:08:51", "remaining_time": "0:35:26"}
+{"current_steps": 21, "total_steps": 100, "loss": 0.6686, "lr": 9.316282404787869e-07, "epoch": 0.21, "percentage": 21.0, "elapsed_time": "0:09:18", "remaining_time": "0:34:59"}
+{"current_steps": 22, "total_steps": 100, "loss": 0.6055, "lr": 9.230476262104676e-07, "epoch": 0.22, "percentage": 22.0, "elapsed_time": "0:09:47", "remaining_time": "0:34:42"}
+{"current_steps": 23, "total_steps": 100, "loss": 0.5312, "lr": 9.1400441557401e-07, "epoch": 0.23, "percentage": 23.0, "elapsed_time": "0:10:12", "remaining_time": "0:34:11"}
+{"current_steps": 24, "total_steps": 100, "loss": 0.5334, "lr": 9.045084971874737e-07, "epoch": 0.24, "percentage": 24.0, "elapsed_time": "0:10:38", "remaining_time": "0:33:43"}
+{"current_steps": 25, "total_steps": 100, "loss": 0.5246, "lr": 8.945702546981968e-07, "epoch": 0.25, "percentage": 25.0, "elapsed_time": "0:11:04", "remaining_time": "0:33:13"}
+{"current_steps": 26, "total_steps": 100, "loss": 0.4586, "lr": 8.842005554284295e-07, "epoch": 0.26, "percentage": 26.0, "elapsed_time": "0:11:30", "remaining_time": "0:32:46"}
+{"current_steps": 27, "total_steps": 100, "loss": 0.514, "lr": 8.734107384920769e-07, "epoch": 0.27, "percentage": 27.0, "elapsed_time": "0:11:58", "remaining_time": "0:32:23"}
+{"current_steps": 28, "total_steps": 100, "loss": 0.469, "lr": 8.622126023955445e-07, "epoch": 0.28, "percentage": 28.0, "elapsed_time": "0:12:24", "remaining_time": "0:31:55"}
+{"current_steps": 29, "total_steps": 100, "loss": 0.4928, "lr": 8.506183921362442e-07, "epoch": 0.29, "percentage": 29.0, "elapsed_time": "0:12:50", "remaining_time": "0:31:27"}
+{"current_steps": 30, "total_steps": 100, "loss": 0.416, "lr": 8.386407858128706e-07, "epoch": 0.3, "percentage": 30.0, "elapsed_time": "0:13:18", "remaining_time": "0:31:02"}
+{"current_steps": 31, "total_steps": 100, "loss": 0.4065, "lr": 8.262928807620843e-07, "epoch": 0.31, "percentage": 31.0, "elapsed_time": "0:13:47", "remaining_time": "0:30:40"}
+{"current_steps": 32, "total_steps": 100, "loss": 0.4302, "lr": 8.135881792367685e-07, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:14:13", "remaining_time": "0:30:14"}
+{"current_steps": 33, "total_steps": 100, "loss": 0.475, "lr": 8.005405736415125e-07, "epoch": 0.33, "percentage": 33.0, "elapsed_time": "0:14:39", "remaining_time": "0:29:45"}
+{"current_steps": 34, "total_steps": 100, "loss": 0.4418, "lr": 7.871643313414718e-07, "epoch": 0.34, "percentage": 34.0, "elapsed_time": "0:15:04", "remaining_time": "0:29:15"}
+{"current_steps": 35, "total_steps": 100, "loss": 0.4074, "lr": 7.734740790612136e-07, "epoch": 0.35, "percentage": 35.0, "elapsed_time": "0:15:30", "remaining_time": "0:28:47"}
+{"current_steps": 36, "total_steps": 100, "loss": 0.4006, "lr": 7.594847868906076e-07, "epoch": 0.36, "percentage": 36.0, "elapsed_time": "0:15:54", "remaining_time": "0:28:17"}
+{"current_steps": 37, "total_steps": 100, "loss": 0.4099, "lr": 7.452117519152541e-07, "epoch": 0.37, "percentage": 37.0, "elapsed_time": "0:16:20", "remaining_time": "0:27:49"}
+{"current_steps": 38, "total_steps": 100, "loss": 0.4258, "lr": 7.306705814893439e-07, "epoch": 0.38, "percentage": 38.0, "elapsed_time": "0:16:47", "remaining_time": "0:27:23"}
+{"current_steps": 39, "total_steps": 100, "loss": 0.4066, "lr": 7.158771761692464e-07, "epoch": 0.39, "percentage": 39.0, "elapsed_time": "0:17:13", "remaining_time": "0:26:55"}
+{"current_steps": 40, "total_steps": 100, "loss": 0.4272, "lr": 7.008477123264847e-07, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:17:37", "remaining_time": "0:26:26"}
+{"current_steps": 41, "total_steps": 100, "loss": 0.4166, "lr": 6.855986244591103e-07, "epoch": 0.41, "percentage": 41.0, "elapsed_time": "0:18:05", "remaining_time": "0:26:01"}
+{"current_steps": 42, "total_steps": 100, "loss": 0.3928, "lr": 6.701465872208216e-07, "epoch": 0.42, "percentage": 42.0, "elapsed_time": "0:18:30", "remaining_time": "0:25:33"}
+{"current_steps": 43, "total_steps": 100, "loss": 0.4291, "lr": 6.545084971874736e-07, "epoch": 0.43, "percentage": 43.0, "elapsed_time": "0:18:56", "remaining_time": "0:25:06"}
+{"current_steps": 44, "total_steps": 100, "loss": 0.3841, "lr": 6.387014543809223e-07, "epoch": 0.44, "percentage": 44.0, "elapsed_time": "0:19:20", "remaining_time": "0:24:36"}
+{"current_steps": 45, "total_steps": 100, "loss": 0.3897, "lr": 6.227427435703995e-07, "epoch": 0.45, "percentage": 45.0, "elapsed_time": "0:19:46", "remaining_time": "0:24:10"}
+{"current_steps": 46, "total_steps": 100, "loss": 0.3938, "lr": 6.066498153718734e-07, "epoch": 0.46, "percentage": 46.0, "elapsed_time": "0:20:12", "remaining_time": "0:23:43"}
+{"current_steps": 47, "total_steps": 100, "loss": 0.3722, "lr": 5.90440267166055e-07, "epoch": 0.47, "percentage": 47.0, "elapsed_time": "0:20:40", "remaining_time": "0:23:18"}
+{"current_steps": 48, "total_steps": 100, "loss": 0.4295, "lr": 5.741318238559209e-07, "epoch": 0.48, "percentage": 48.0, "elapsed_time": "0:21:08", "remaining_time": "0:22:53"}
+{"current_steps": 49, "total_steps": 100, "loss": 0.3834, "lr": 5.577423184847931e-07, "epoch": 0.49, "percentage": 49.0, "elapsed_time": "0:21:34", "remaining_time": "0:22:27"}
+{"current_steps": 50, "total_steps": 100, "loss": 0.3391, "lr": 5.412896727361662e-07, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:21:59", "remaining_time": "0:21:59"}
+{"current_steps": 51, "total_steps": 100, "loss": 0.3942, "lr": 5.247918773366111e-07, "epoch": 0.51, "percentage": 51.0, "elapsed_time": "0:22:26", "remaining_time": "0:21:33"}
+{"current_steps": 52, "total_steps": 100, "loss": 0.3848, "lr": 5.082669723831793e-07, "epoch": 0.52, "percentage": 52.0, "elapsed_time": "0:22:50", "remaining_time": "0:21:05"}
+{"current_steps": 53, "total_steps": 100, "loss": 0.385, "lr": 4.917330276168208e-07, "epoch": 0.53, "percentage": 53.0, "elapsed_time": "0:23:17", "remaining_time": "0:20:39"}
+{"current_steps": 54, "total_steps": 100, "loss": 0.3694, "lr": 4.752081226633888e-07, "epoch": 0.54, "percentage": 54.0, "elapsed_time": "0:23:44", "remaining_time": "0:20:13"}
+{"current_steps": 55, "total_steps": 100, "loss": 0.3615, "lr": 4.5871032726383385e-07, "epoch": 0.55, "percentage": 55.0, "elapsed_time": "0:24:11", "remaining_time": "0:19:47"}
+{"current_steps": 56, "total_steps": 100, "loss": 0.3257, "lr": 4.4225768151520694e-07, "epoch": 0.56, "percentage": 56.0, "elapsed_time": "0:24:38", "remaining_time": "0:19:22"}
+{"current_steps": 57, "total_steps": 100, "loss": 0.351, "lr": 4.258681761440789e-07, "epoch": 0.57, "percentage": 57.0, "elapsed_time": "0:25:04", "remaining_time": "0:18:54"}
+{"current_steps": 58, "total_steps": 100, "loss": 0.3964, "lr": 4.095597328339452e-07, "epoch": 0.58, "percentage": 58.0, "elapsed_time": "0:25:30", "remaining_time": "0:18:28"}
+{"current_steps": 59, "total_steps": 100, "loss": 0.3783, "lr": 3.9335018462812664e-07, "epoch": 0.59, "percentage": 59.0, "elapsed_time": "0:25:55", "remaining_time": "0:18:01"}
+{"current_steps": 60, "total_steps": 100, "loss": 0.3617, "lr": 3.772572564296004e-07, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:26:20", "remaining_time": "0:17:33"}
+{"current_steps": 61, "total_steps": 100, "loss": 0.3997, "lr": 3.612985456190778e-07, "epoch": 0.61, "percentage": 61.0, "elapsed_time": "0:26:47", "remaining_time": "0:17:08"}
+{"current_steps": 62, "total_steps": 100, "loss": 0.3582, "lr": 3.454915028125263e-07, "epoch": 0.62, "percentage": 62.0, "elapsed_time": "0:27:13", "remaining_time": "0:16:41"}
+{"current_steps": 63, "total_steps": 100, "loss": 0.3804, "lr": 3.2985341277917846e-07, "epoch": 0.63, "percentage": 63.0, "elapsed_time": "0:27:39", "remaining_time": "0:16:14"}
+{"current_steps": 64, "total_steps": 100, "loss": 0.3646, "lr": 3.1440137554088953e-07, "epoch": 0.64, "percentage": 64.0, "elapsed_time": "0:28:07", "remaining_time": "0:15:49"}
+{"current_steps": 65, "total_steps": 100, "loss": 0.3387, "lr": 2.9915228767351535e-07, "epoch": 0.65, "percentage": 65.0, "elapsed_time": "0:28:35", "remaining_time": "0:15:23"}
+{"current_steps": 66, "total_steps": 100, "loss": 0.3839, "lr": 2.841228238307536e-07, "epoch": 0.66, "percentage": 66.0, "elapsed_time": "0:29:01", "remaining_time": "0:14:57"}
+{"current_steps": 67, "total_steps": 100, "loss": 0.3635, "lr": 2.6932941851065615e-07, "epoch": 0.67, "percentage": 67.0, "elapsed_time": "0:29:28", "remaining_time": "0:14:30"}
+{"current_steps": 68, "total_steps": 100, "loss": 0.3905, "lr": 2.547882480847461e-07, "epoch": 0.68, "percentage": 68.0, "elapsed_time": "0:29:55", "remaining_time": "0:14:04"}
+{"current_steps": 69, "total_steps": 100, "loss": 0.3666, "lr": 2.4051521310939254e-07, "epoch": 0.69, "percentage": 69.0, "elapsed_time": "0:30:21", "remaining_time": "0:13:38"}
+{"current_steps": 70, "total_steps": 100, "loss": 0.3317, "lr": 2.2652592093878665e-07, "epoch": 0.7, "percentage": 70.0, "elapsed_time": "0:30:49", "remaining_time": "0:13:12"}
+{"current_steps": 71, "total_steps": 100, "loss": 0.3231, "lr": 2.128356686585282e-07, "epoch": 0.71, "percentage": 71.0, "elapsed_time": "0:31:17", "remaining_time": "0:12:46"}
+{"current_steps": 72, "total_steps": 100, "loss": 0.3447, "lr": 1.9945942635848745e-07, "epoch": 0.72, "percentage": 72.0, "elapsed_time": "0:31:40", "remaining_time": "0:12:19"}
+{"current_steps": 73, "total_steps": 100, "loss": 0.3284, "lr": 1.8641182076323148e-07, "epoch": 0.73, "percentage": 73.0, "elapsed_time": "0:32:08", "remaining_time": "0:11:53"}
+{"current_steps": 74, "total_steps": 100, "loss": 0.3591, "lr": 1.7370711923791564e-07, "epoch": 0.74, "percentage": 74.0, "elapsed_time": "0:32:34", "remaining_time": "0:11:26"}
+{"current_steps": 75, "total_steps": 100, "loss": 0.3444, "lr": 1.6135921418712955e-07, "epoch": 0.75, "percentage": 75.0, "elapsed_time": "0:33:02", "remaining_time": "0:11:00"}
+{"current_steps": 76, "total_steps": 100, "loss": 0.4039, "lr": 1.493816078637557e-07, "epoch": 0.76, "percentage": 76.0, "elapsed_time": "0:33:26", "remaining_time": "0:10:33"}
+{"current_steps": 77, "total_steps": 100, "loss": 0.3203, "lr": 1.3778739760445552e-07, "epoch": 0.77, "percentage": 77.0, "elapsed_time": "0:33:50", "remaining_time": "0:10:06"}
+{"current_steps": 78, "total_steps": 100, "loss": 0.3715, "lr": 1.2658926150792322e-07, "epoch": 0.78, "percentage": 78.0, "elapsed_time": "0:34:16", "remaining_time": "0:09:39"}
+{"current_steps": 79, "total_steps": 100, "loss": 0.3226, "lr": 1.1579944457157059e-07, "epoch": 0.79, "percentage": 79.0, "elapsed_time": "0:34:41", "remaining_time": "0:09:13"}
+{"current_steps": 80, "total_steps": 100, "loss": 0.3627, "lr": 1.0542974530180327e-07, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:35:06", "remaining_time": "0:08:46"}
+{"current_steps": 81, "total_steps": 100, "loss": 0.3646, "lr": 9.549150281252632e-08, "epoch": 0.81, "percentage": 81.0, "elapsed_time": "0:35:35", "remaining_time": "0:08:20"}
+{"current_steps": 82, "total_steps": 100, "loss": 0.3506, "lr": 8.599558442598998e-08, "epoch": 0.82, "percentage": 82.0, "elapsed_time": "0:36:00", "remaining_time": "0:07:54"}
+{"current_steps": 83, "total_steps": 100, "loss": 0.3471, "lr": 7.695237378953224e-08, "epoch": 0.83, "percentage": 83.0, "elapsed_time": "0:36:29", "remaining_time": "0:07:28"}
+{"current_steps": 84, "total_steps": 100, "loss": 0.3362, "lr": 6.837175952121304e-08, "epoch": 0.84, "percentage": 84.0, "elapsed_time": "0:36:57", "remaining_time": "0:07:02"}
+{"current_steps": 85, "total_steps": 100, "loss": 0.354, "lr": 6.026312439675551e-08, "epoch": 0.85, "percentage": 85.0, "elapsed_time": "0:37:24", "remaining_time": "0:06:36"}
+{"current_steps": 86, "total_steps": 100, "loss": 0.3589, "lr": 5.263533508961826e-08, "epoch": 0.86, "percentage": 86.0, "elapsed_time": "0:37:50", "remaining_time": "0:06:09"}
+{"current_steps": 87, "total_steps": 100, "loss": 0.3209, "lr": 4.549673247541874e-08, "epoch": 0.87, "percentage": 87.0, "elapsed_time": "0:38:17", "remaining_time": "0:05:43"}
+{"current_steps": 88, "total_steps": 100, "loss": 0.3707, "lr": 3.8855122511307626e-08, "epoch": 0.88, "percentage": 88.0, "elapsed_time": "0:38:44", "remaining_time": "0:05:16"}
+{"current_steps": 89, "total_steps": 100, "loss": 0.3314, "lr": 3.271776770026963e-08, "epoch": 0.89, "percentage": 89.0, "elapsed_time": "0:39:09", "remaining_time": "0:04:50"}
+{"current_steps": 90, "total_steps": 100, "loss": 0.3634, "lr": 2.7091379149682682e-08, "epoch": 0.9, "percentage": 90.0, "elapsed_time": "0:39:34", "remaining_time": "0:04:23"}
+{"current_steps": 91, "total_steps": 100, "loss": 0.3762, "lr": 2.1982109232821176e-08, "epoch": 0.91, "percentage": 91.0, "elapsed_time": "0:40:00", "remaining_time": "0:03:57"}
+{"current_steps": 92, "total_steps": 100, "loss": 0.3393, "lr": 1.7395544861325718e-08, "epoch": 0.92, "percentage": 92.0, "elapsed_time": "0:40:26", "remaining_time": "0:03:30"}
+{"current_steps": 93, "total_steps": 100, "loss": 0.3408, "lr": 1.3336701375997127e-08, "epoch": 0.93, "percentage": 93.0, "elapsed_time": "0:40:53", "remaining_time": "0:03:04"}
+{"current_steps": 94, "total_steps": 100, "loss": 0.3388, "lr": 9.810017062595321e-09, "epoch": 0.94, "percentage": 94.0, "elapsed_time": "0:41:20", "remaining_time": "0:02:38"}
+{"current_steps": 95, "total_steps": 100, "loss": 0.3396, "lr": 6.819348298638839e-09, "epoch": 0.95, "percentage": 95.0, "elapsed_time": "0:41:45", "remaining_time": "0:02:11"}
+{"current_steps": 96, "total_steps": 100, "loss": 0.3292, "lr": 4.367965336512403e-09, "epoch": 0.96, "percentage": 96.0, "elapsed_time": "0:42:11", "remaining_time": "0:01:45"}
+{"current_steps": 97, "total_steps": 100, "loss": 0.3415, "lr": 2.458548727494292e-09, "epoch": 0.97, "percentage": 97.0, "elapsed_time": "0:42:39", "remaining_time": "0:01:19"}
+{"current_steps": 98, "total_steps": 100, "loss": 0.3261, "lr": 1.0931863906127325e-09, "epoch": 0.98, "percentage": 98.0, "elapsed_time": "0:43:04", "remaining_time": "0:00:52"}
+{"current_steps": 99, "total_steps": 100, "loss": 0.3191, "lr": 2.733713295369755e-10, "epoch": 0.99, "percentage": 99.0, "elapsed_time": "0:43:31", "remaining_time": "0:00:26"}
+{"current_steps": 100, "total_steps": 100, "loss": 0.355, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:43:59", "remaining_time": "0:00:00"}
+{"current_steps": 100, "total_steps": 100, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:44:40", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,743 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 284.2696901095738,
+      "learning_rate": 2e-07,
+      "loss": 7.1138,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 280.0890600259792,
+      "learning_rate": 4e-07,
+      "loss": 6.8466,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 296.98995011993617,
+      "learning_rate": 6e-07,
+      "loss": 6.8936,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 284.92519297592935,
+      "learning_rate": 8e-07,
+      "loss": 7.1196,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 296.67655171044885,
+      "learning_rate": 1e-06,
+      "loss": 6.7063,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 281.91608332740634,
+      "learning_rate": 9.99726628670463e-07,
+      "loss": 6.028,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 245.30165342232291,
+      "learning_rate": 9.989068136093872e-07,
+      "loss": 5.593,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 171.71633417584104,
+      "learning_rate": 9.975414512725056e-07,
+      "loss": 4.1199,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 153.69431185375615,
+      "learning_rate": 9.956320346634875e-07,
+      "loss": 3.8539,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 138.4099703250891,
+      "learning_rate": 9.931806517013612e-07,
+      "loss": 3.364,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 121.96592995402922,
+      "learning_rate": 9.901899829374047e-07,
+      "loss": 3.2359,
+      "step": 11
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 83.33555123373614,
+      "learning_rate": 9.866632986240029e-07,
+      "loss": 2.0694,
+      "step": 12
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 69.8343923660202,
+      "learning_rate": 9.826044551386742e-07,
+      "loss": 1.8041,
+      "step": 13
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 61.02444391130647,
+      "learning_rate": 9.780178907671788e-07,
+      "loss": 1.8221,
+      "step": 14
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 51.06086209218741,
+      "learning_rate": 9.729086208503173e-07,
+      "loss": 1.5577,
+      "step": 15
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 39.386178814833706,
+      "learning_rate": 9.672822322997304e-07,
+      "loss": 1.3898,
+      "step": 16
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 33.769199410950286,
+      "learning_rate": 9.611448774886923e-07,
+      "loss": 1.2839,
+      "step": 17
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 32.43709972193044,
+      "learning_rate": 9.545032675245813e-07,
+      "loss": 1.1126,
+      "step": 18
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 29.12905700014587,
+      "learning_rate": 9.473646649103817e-07,
+      "loss": 0.9637,
+      "step": 19
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 19.116333899951297,
+      "learning_rate": 9.397368756032444e-07,
+      "loss": 0.6976,
+      "step": 20
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 17.362547626796633,
+      "learning_rate": 9.316282404787869e-07,
+      "loss": 0.6686,
+      "step": 21
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 12.641692912258486,
+      "learning_rate": 9.230476262104676e-07,
+      "loss": 0.6055,
+      "step": 22
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 9.423373458222406,
+      "learning_rate": 9.1400441557401e-07,
+      "loss": 0.5312,
+      "step": 23
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.714449953085253,
+      "learning_rate": 9.045084971874737e-07,
+      "loss": 0.5334,
+      "step": 24
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.3626526485098545,
+      "learning_rate": 8.945702546981968e-07,
+      "loss": 0.5246,
+      "step": 25
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.787541205113461,
+      "learning_rate": 8.842005554284295e-07,
+      "loss": 0.4586,
+      "step": 26
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.217072482502457,
+      "learning_rate": 8.734107384920769e-07,
+      "loss": 0.514,
+      "step": 27
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.69075014149454,
+      "learning_rate": 8.622126023955445e-07,
+      "loss": 0.469,
+      "step": 28
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 5.767332317747505,
+      "learning_rate": 8.506183921362442e-07,
+      "loss": 0.4928,
+      "step": 29
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.29694390512729,
+      "learning_rate": 8.386407858128706e-07,
+      "loss": 0.416,
+      "step": 30
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.4751365453564524,
+      "learning_rate": 8.262928807620843e-07,
+      "loss": 0.4065,
+      "step": 31
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.210968327443881,
+      "learning_rate": 8.135881792367685e-07,
+      "loss": 0.4302,
+      "step": 32
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.889628663080109,
+      "learning_rate": 8.005405736415125e-07,
+      "loss": 0.475,
+      "step": 33
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.01223684022235,
+      "learning_rate": 7.871643313414718e-07,
+      "loss": 0.4418,
+      "step": 34
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.362633576491621,
+      "learning_rate": 7.734740790612136e-07,
+      "loss": 0.4074,
+      "step": 35
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 3.9179637860680874,
+      "learning_rate": 7.594847868906076e-07,
+      "loss": 0.4006,
+      "step": 36
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.8386018601431067,
+      "learning_rate": 7.452117519152541e-07,
+      "loss": 0.4099,
+      "step": 37
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.465384708590031,
+      "learning_rate": 7.306705814893439e-07,
+      "loss": 0.4258,
+      "step": 38
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.869675336079214,
+      "learning_rate": 7.158771761692464e-07,
+      "loss": 0.4066,
+      "step": 39
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.6892092384872255,
+      "learning_rate": 7.008477123264847e-07,
+      "loss": 0.4272,
+      "step": 40
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.282400513219925,
+      "learning_rate": 6.855986244591103e-07,
+      "loss": 0.4166,
+      "step": 41
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.44179530817891,
+      "learning_rate": 6.701465872208216e-07,
+      "loss": 0.3928,
+      "step": 42
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.753857420255081,
+      "learning_rate": 6.545084971874736e-07,
+      "loss": 0.4291,
+      "step": 43
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.121989871402109,
+      "learning_rate": 6.387014543809223e-07,
+      "loss": 0.3841,
+      "step": 44
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 4.306307235348373,
+      "learning_rate": 6.227427435703995e-07,
+      "loss": 0.3897,
+      "step": 45
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.1819998879575095,
+      "learning_rate": 6.066498153718734e-07,
+      "loss": 0.3938,
+      "step": 46
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 3.9858764933030493,
+      "learning_rate": 5.90440267166055e-07,
+      "loss": 0.3722,
+      "step": 47
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.768016055450793,
+      "learning_rate": 5.741318238559209e-07,
+      "loss": 0.4295,
+      "step": 48
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.155664350209782,
+      "learning_rate": 5.577423184847931e-07,
+      "loss": 0.3834,
+      "step": 49
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 3.79515186565417,
+      "learning_rate": 5.412896727361662e-07,
+      "loss": 0.3391,
+      "step": 50
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.4230723188666476,
+      "learning_rate": 5.247918773366111e-07,
+      "loss": 0.3942,
+      "step": 51
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.0931484903099773,
+      "learning_rate": 5.082669723831793e-07,
+      "loss": 0.3848,
+      "step": 52
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 4.693387026086119,
+      "learning_rate": 4.917330276168208e-07,
+      "loss": 0.385,
+      "step": 53
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 3.531161429609241,
+      "learning_rate": 4.752081226633888e-07,
+      "loss": 0.3694,
+      "step": 54
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 3.696655191494645,
+      "learning_rate": 4.5871032726383385e-07,
+      "loss": 0.3615,
+      "step": 55
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.798666905310865,
+      "learning_rate": 4.4225768151520694e-07,
+      "loss": 0.3257,
+      "step": 56
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.595957261529934,
+      "learning_rate": 4.258681761440789e-07,
+      "loss": 0.351,
+      "step": 57
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 3.443958917780827,
+      "learning_rate": 4.095597328339452e-07,
+      "loss": 0.3964,
+      "step": 58
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.222996925336396,
+      "learning_rate": 3.9335018462812664e-07,
+      "loss": 0.3783,
+      "step": 59
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.141091647019225,
+      "learning_rate": 3.772572564296004e-07,
+      "loss": 0.3617,
+      "step": 60
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 4.207602140662548,
+      "learning_rate": 3.612985456190778e-07,
+      "loss": 0.3997,
+      "step": 61
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.4580694579960918,
+      "learning_rate": 3.454915028125263e-07,
+      "loss": 0.3582,
+      "step": 62
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 3.422220201677041,
+      "learning_rate": 3.2985341277917846e-07,
+      "loss": 0.3804,
+      "step": 63
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.273283148367399,
+      "learning_rate": 3.1440137554088953e-07,
+      "loss": 0.3646,
+      "step": 64
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 3.099164792571154,
+      "learning_rate": 2.9915228767351535e-07,
+      "loss": 0.3387,
+      "step": 65
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.6768199519226314,
+      "learning_rate": 2.841228238307536e-07,
+      "loss": 0.3839,
+      "step": 66
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 3.684496636177031,
+      "learning_rate": 2.6932941851065615e-07,
+      "loss": 0.3635,
+      "step": 67
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 2.8715160468944236,
+      "learning_rate": 2.547882480847461e-07,
+      "loss": 0.3905,
+      "step": 68
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.542266866557925,
+      "learning_rate": 2.4051521310939254e-07,
+      "loss": 0.3666,
+      "step": 69
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 3.721830078063186,
+      "learning_rate": 2.2652592093878665e-07,
+      "loss": 0.3317,
+      "step": 70
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 3.7314666594735724,
+      "learning_rate": 2.128356686585282e-07,
+      "loss": 0.3231,
+      "step": 71
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.283124086872181,
+      "learning_rate": 1.9945942635848745e-07,
+      "loss": 0.3447,
+      "step": 72
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 3.9554685048457183,
+      "learning_rate": 1.8641182076323148e-07,
+      "loss": 0.3284,
+      "step": 73
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 3.8402484907207435,
+      "learning_rate": 1.7370711923791564e-07,
+      "loss": 0.3591,
+      "step": 74
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.4683454793599884,
+      "learning_rate": 1.6135921418712955e-07,
+      "loss": 0.3444,
+      "step": 75
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.837469581874028,
+      "learning_rate": 1.493816078637557e-07,
+      "loss": 0.4039,
+      "step": 76
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 3.498682351133943,
+      "learning_rate": 1.3778739760445552e-07,
+      "loss": 0.3203,
+      "step": 77
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.16268013662858,
+      "learning_rate": 1.2658926150792322e-07,
+      "loss": 0.3715,
+      "step": 78
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 3.404009699611626,
+      "learning_rate": 1.1579944457157059e-07,
+      "loss": 0.3226,
+      "step": 79
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.8135862465406904,
+      "learning_rate": 1.0542974530180327e-07,
+      "loss": 0.3627,
+      "step": 80
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.3969260525552616,
+      "learning_rate": 9.549150281252632e-08,
+      "loss": 0.3646,
+      "step": 81
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.9007273599583057,
+      "learning_rate": 8.599558442598998e-08,
+      "loss": 0.3506,
+      "step": 82
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 2.8266227536670523,
+      "learning_rate": 7.695237378953224e-08,
+      "loss": 0.3471,
+      "step": 83
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 2.8680227347397893,
+      "learning_rate": 6.837175952121304e-08,
+      "loss": 0.3362,
+      "step": 84
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 3.017390726560224,
+      "learning_rate": 6.026312439675551e-08,
+      "loss": 0.354,
+      "step": 85
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 2.75220355066635,
+      "learning_rate": 5.263533508961826e-08,
+      "loss": 0.3589,
+      "step": 86
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 2.5609091595597784,
+      "learning_rate": 4.549673247541874e-08,
+      "loss": 0.3209,
+      "step": 87
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 3.366788037939117,
+      "learning_rate": 3.8855122511307626e-08,
+      "loss": 0.3707,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 2.998733006487237,
+      "learning_rate": 3.271776770026963e-08,
+      "loss": 0.3314,
+      "step": 89
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.38338292899199,
+      "learning_rate": 2.7091379149682682e-08,
+      "loss": 0.3634,
+      "step": 90
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 3.62894701397729,
+      "learning_rate": 2.1982109232821176e-08,
+      "loss": 0.3762,
+      "step": 91
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 3.6241096556456243,
+      "learning_rate": 1.7395544861325718e-08,
+      "loss": 0.3393,
+      "step": 92
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 3.681150537295675,
+      "learning_rate": 1.3336701375997127e-08,
+      "loss": 0.3408,
+      "step": 93
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 3.573864183770881,
+      "learning_rate": 9.810017062595321e-09,
+      "loss": 0.3388,
+      "step": 94
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 3.1628676346413824,
+      "learning_rate": 6.819348298638839e-09,
+      "loss": 0.3396,
+      "step": 95
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.253309468483455,
+      "learning_rate": 4.367965336512403e-09,
+      "loss": 0.3292,
+      "step": 96
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 3.3389999287279166,
+      "learning_rate": 2.458548727494292e-09,
+      "loss": 0.3415,
+      "step": 97
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 3.0295989312166327,
+      "learning_rate": 1.0931863906127325e-09,
+      "loss": 0.3261,
+      "step": 98
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 2.9789770023523388,
+      "learning_rate": 2.733713295369755e-10,
+      "loss": 0.3191,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.6932194833157013,
+      "learning_rate": 0.0,
+      "loss": 0.355,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 100,
+      "total_flos": 6384023396352.0,
+      "train_loss": 1.047203412950039,
+      "train_runtime": 2682.144,
+      "train_samples_per_second": 9.545,
+      "train_steps_per_second": 0.037
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6384023396352.0,
+  "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 sha256:2c531ba42481a2d84137aa7548ebc3e7395f37679753c1b2c9683f2fb7b24352
+size 7544