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 +1,59 @@
+---
+library_name: transformers
+license: other
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-7B-Instruct-method3
+  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. -->
+
+# Qwen2.5-7B-Instruct-method3
+
+This model is a fine-tuned version of [/share/project/zhipengchen/model/Qwen2.5-7B-Instruct](https://huggingface.co//share/project/zhipengchen/model/Qwen2.5-7B-Instruct) on the method3 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.3.2
+- 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": 3.0,
+    "total_flos": 150195282509824.0,
+    "train_loss": 0.3441459048878063,
+    "train_runtime": 5442.3628,
+    "train_samples_per_second": 1.937,
+    "train_steps_per_second": 0.243
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/share/project/zhipengchen/model/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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "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": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5125d4eae40d53cd870f75038ae6e14cee5313f0f5786bb181089ede59707455
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128f0c9b5f4c6167b512f322ad3f06a1f0cc921d4373e66f526fe2038f58940a
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49d12c67342a30b359e30e609eb887be7bf27bae669ed7d40eac35b19f5d499
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b87c235d4b1693752e252f4ebb7a3ad5a114526584ef9739cfa8cb665dc664d
+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": 3.0,
+    "total_flos": 150195282509824.0,
+    "train_loss": 0.3441459048878063,
+    "train_runtime": 5442.3628,
+    "train_samples_per_second": 1.937,
+    "train_steps_per_second": 0.243
+}

trainer_log.jsonl

@@ -0,0 +1,133 @@
+{"current_steps": 10, "total_steps": 1320, "loss": 0.7684, "lr": 7.575757575757576e-07, "epoch": 0.022727272727272728, "percentage": 0.76, "elapsed_time": "0:00:54", "remaining_time": "1:58:16"}
+{"current_steps": 20, "total_steps": 1320, "loss": 0.6837, "lr": 1.5151515151515152e-06, "epoch": 0.045454545454545456, "percentage": 1.52, "elapsed_time": "0:01:34", "remaining_time": "1:42:02"}
+{"current_steps": 30, "total_steps": 1320, "loss": 0.6466, "lr": 2.2727272727272728e-06, "epoch": 0.06818181818181818, "percentage": 2.27, "elapsed_time": "0:02:13", "remaining_time": "1:35:28"}
+{"current_steps": 40, "total_steps": 1320, "loss": 0.5912, "lr": 3.0303030303030305e-06, "epoch": 0.09090909090909091, "percentage": 3.03, "elapsed_time": "0:02:52", "remaining_time": "1:31:58"}
+{"current_steps": 50, "total_steps": 1320, "loss": 0.5324, "lr": 3.7878787878787882e-06, "epoch": 0.11363636363636363, "percentage": 3.79, "elapsed_time": "0:03:30", "remaining_time": "1:29:07"}
+{"current_steps": 60, "total_steps": 1320, "loss": 0.519, "lr": 4.5454545454545455e-06, "epoch": 0.13636363636363635, "percentage": 4.55, "elapsed_time": "0:04:13", "remaining_time": "1:28:39"}
+{"current_steps": 70, "total_steps": 1320, "loss": 0.5089, "lr": 5.303030303030303e-06, "epoch": 0.1590909090909091, "percentage": 5.3, "elapsed_time": "0:04:51", "remaining_time": "1:26:53"}
+{"current_steps": 80, "total_steps": 1320, "loss": 0.4981, "lr": 6.060606060606061e-06, "epoch": 0.18181818181818182, "percentage": 6.06, "elapsed_time": "0:05:29", "remaining_time": "1:25:05"}
+{"current_steps": 90, "total_steps": 1320, "loss": 0.5116, "lr": 6.818181818181818e-06, "epoch": 0.20454545454545456, "percentage": 6.82, "elapsed_time": "0:06:14", "remaining_time": "1:25:19"}
+{"current_steps": 100, "total_steps": 1320, "loss": 0.4969, "lr": 7.5757575757575764e-06, "epoch": 0.22727272727272727, "percentage": 7.58, "elapsed_time": "0:06:54", "remaining_time": "1:24:17"}
+{"current_steps": 110, "total_steps": 1320, "loss": 0.4667, "lr": 8.333333333333334e-06, "epoch": 0.25, "percentage": 8.33, "elapsed_time": "0:07:36", "remaining_time": "1:23:40"}
+{"current_steps": 120, "total_steps": 1320, "loss": 0.4538, "lr": 9.090909090909091e-06, "epoch": 0.2727272727272727, "percentage": 9.09, "elapsed_time": "0:08:16", "remaining_time": "1:22:47"}
+{"current_steps": 130, "total_steps": 1320, "loss": 0.4547, "lr": 9.84848484848485e-06, "epoch": 0.29545454545454547, "percentage": 9.85, "elapsed_time": "0:08:58", "remaining_time": "1:22:07"}
+{"current_steps": 140, "total_steps": 1320, "loss": 0.4857, "lr": 9.99888115313551e-06, "epoch": 0.3181818181818182, "percentage": 10.61, "elapsed_time": "0:09:43", "remaining_time": "1:22:01"}
+{"current_steps": 150, "total_steps": 1320, "loss": 0.4805, "lr": 9.994336695915041e-06, "epoch": 0.3409090909090909, "percentage": 11.36, "elapsed_time": "0:10:21", "remaining_time": "1:20:50"}
+{"current_steps": 160, "total_steps": 1320, "loss": 0.4629, "lr": 9.986299875742612e-06, "epoch": 0.36363636363636365, "percentage": 12.12, "elapsed_time": "0:10:56", "remaining_time": "1:19:18"}
+{"current_steps": 170, "total_steps": 1320, "loss": 0.4791, "lr": 9.97477631248223e-06, "epoch": 0.38636363636363635, "percentage": 12.88, "elapsed_time": "0:11:43", "remaining_time": "1:19:21"}
+{"current_steps": 180, "total_steps": 1320, "loss": 0.452, "lr": 9.959774064153977e-06, "epoch": 0.4090909090909091, "percentage": 13.64, "elapsed_time": "0:12:27", "remaining_time": "1:18:55"}
+{"current_steps": 190, "total_steps": 1320, "loss": 0.4505, "lr": 9.941303621299332e-06, "epoch": 0.4318181818181818, "percentage": 14.39, "elapsed_time": "0:13:12", "remaining_time": "1:18:34"}
+{"current_steps": 200, "total_steps": 1320, "loss": 0.4539, "lr": 9.919377899645497e-06, "epoch": 0.45454545454545453, "percentage": 15.15, "elapsed_time": "0:13:55", "remaining_time": "1:18:01"}
+{"current_steps": 210, "total_steps": 1320, "loss": 0.4473, "lr": 9.894012231073895e-06, "epoch": 0.4772727272727273, "percentage": 15.91, "elapsed_time": "0:14:35", "remaining_time": "1:17:07"}
+{"current_steps": 220, "total_steps": 1320, "loss": 0.4794, "lr": 9.86522435289912e-06, "epoch": 0.5, "percentage": 16.67, "elapsed_time": "0:15:15", "remaining_time": "1:16:19"}
+{"current_steps": 230, "total_steps": 1320, "loss": 0.4437, "lr": 9.833034395465866e-06, "epoch": 0.5227272727272727, "percentage": 17.42, "elapsed_time": "0:15:55", "remaining_time": "1:15:29"}
+{"current_steps": 240, "total_steps": 1320, "loss": 0.4667, "lr": 9.797464868072489e-06, "epoch": 0.5454545454545454, "percentage": 18.18, "elapsed_time": "0:16:41", "remaining_time": "1:15:07"}
+{"current_steps": 250, "total_steps": 1320, "loss": 0.4545, "lr": 9.758540643231041e-06, "epoch": 0.5681818181818182, "percentage": 18.94, "elapsed_time": "0:17:19", "remaining_time": "1:14:08"}
+{"current_steps": 260, "total_steps": 1320, "loss": 0.4632, "lr": 9.716288939274818e-06, "epoch": 0.5909090909090909, "percentage": 19.7, "elapsed_time": "0:18:04", "remaining_time": "1:13:43"}
+{"current_steps": 270, "total_steps": 1320, "loss": 0.461, "lr": 9.670739301325534e-06, "epoch": 0.6136363636363636, "percentage": 20.45, "elapsed_time": "0:18:40", "remaining_time": "1:12:36"}
+{"current_steps": 280, "total_steps": 1320, "loss": 0.4503, "lr": 9.621923580633462e-06, "epoch": 0.6363636363636364, "percentage": 21.21, "elapsed_time": "0:19:29", "remaining_time": "1:12:24"}
+{"current_steps": 290, "total_steps": 1320, "loss": 0.448, "lr": 9.56987591230498e-06, "epoch": 0.6590909090909091, "percentage": 21.97, "elapsed_time": "0:20:09", "remaining_time": "1:11:34"}
+{"current_steps": 300, "total_steps": 1320, "loss": 0.4233, "lr": 9.514632691433108e-06, "epoch": 0.6818181818181818, "percentage": 22.73, "elapsed_time": "0:20:47", "remaining_time": "1:10:40"}
+{"current_steps": 310, "total_steps": 1320, "loss": 0.4611, "lr": 9.456232547647695e-06, "epoch": 0.7045454545454546, "percentage": 23.48, "elapsed_time": "0:21:26", "remaining_time": "1:09:51"}
+{"current_steps": 320, "total_steps": 1320, "loss": 0.4666, "lr": 9.394716318103098e-06, "epoch": 0.7272727272727273, "percentage": 24.24, "elapsed_time": "0:22:07", "remaining_time": "1:09:09"}
+{"current_steps": 330, "total_steps": 1320, "loss": 0.4311, "lr": 9.330127018922195e-06, "epoch": 0.75, "percentage": 25.0, "elapsed_time": "0:22:47", "remaining_time": "1:08:22"}
+{"current_steps": 340, "total_steps": 1320, "loss": 0.4625, "lr": 9.262509815116732e-06, "epoch": 0.7727272727272727, "percentage": 25.76, "elapsed_time": "0:23:31", "remaining_time": "1:07:47"}
+{"current_steps": 350, "total_steps": 1320, "loss": 0.4385, "lr": 9.191911989005038e-06, "epoch": 0.7954545454545454, "percentage": 26.52, "elapsed_time": "0:24:09", "remaining_time": "1:06:56"}
+{"current_steps": 360, "total_steps": 1320, "loss": 0.4504, "lr": 9.118382907149164e-06, "epoch": 0.8181818181818182, "percentage": 27.27, "elapsed_time": "0:24:48", "remaining_time": "1:06:09"}
+{"current_steps": 370, "total_steps": 1320, "loss": 0.4201, "lr": 9.041973985834595e-06, "epoch": 0.8409090909090909, "percentage": 28.03, "elapsed_time": "0:25:24", "remaining_time": "1:05:13"}
+{"current_steps": 380, "total_steps": 1320, "loss": 0.4332, "lr": 8.96273865511666e-06, "epoch": 0.8636363636363636, "percentage": 28.79, "elapsed_time": "0:26:05", "remaining_time": "1:04:31"}
+{"current_steps": 390, "total_steps": 1320, "loss": 0.4688, "lr": 8.880732321458785e-06, "epoch": 0.8863636363636364, "percentage": 29.55, "elapsed_time": "0:26:43", "remaining_time": "1:03:43"}
+{"current_steps": 400, "total_steps": 1320, "loss": 0.4486, "lr": 8.796012328988716e-06, "epoch": 0.9090909090909091, "percentage": 30.3, "elapsed_time": "0:27:11", "remaining_time": "1:02:31"}
+{"current_steps": 410, "total_steps": 1320, "loss": 0.4769, "lr": 8.708637919399798e-06, "epoch": 0.9318181818181818, "percentage": 31.06, "elapsed_time": "0:27:50", "remaining_time": "1:01:47"}
+{"current_steps": 420, "total_steps": 1320, "loss": 0.432, "lr": 8.61867019052535e-06, "epoch": 0.9545454545454546, "percentage": 31.82, "elapsed_time": "0:28:34", "remaining_time": "1:01:13"}
+{"current_steps": 430, "total_steps": 1320, "loss": 0.4345, "lr": 8.526172053615122e-06, "epoch": 0.9772727272727273, "percentage": 32.58, "elapsed_time": "0:29:14", "remaining_time": "1:00:31"}
+{"current_steps": 440, "total_steps": 1320, "loss": 0.4371, "lr": 8.43120818934367e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:29:54", "remaining_time": "0:59:48"}
+{"current_steps": 450, "total_steps": 1320, "loss": 0.3547, "lr": 8.33384500258146e-06, "epoch": 1.0227272727272727, "percentage": 34.09, "elapsed_time": "0:31:02", "remaining_time": "1:00:00"}
+{"current_steps": 460, "total_steps": 1320, "loss": 0.344, "lr": 8.234150575960288e-06, "epoch": 1.0454545454545454, "percentage": 34.85, "elapsed_time": "0:31:45", "remaining_time": "0:59:21"}
+{"current_steps": 470, "total_steps": 1320, "loss": 0.3462, "lr": 8.132194622265508e-06, "epoch": 1.0681818181818181, "percentage": 35.61, "elapsed_time": "0:32:28", "remaining_time": "0:58:44"}
+{"current_steps": 480, "total_steps": 1320, "loss": 0.3285, "lr": 8.028048435688333e-06, "epoch": 1.0909090909090908, "percentage": 36.36, "elapsed_time": "0:33:07", "remaining_time": "0:57:58"}
+{"current_steps": 490, "total_steps": 1320, "loss": 0.344, "lr": 7.921784841972355e-06, "epoch": 1.1136363636363635, "percentage": 37.12, "elapsed_time": "0:33:57", "remaining_time": "0:57:32"}
+{"current_steps": 500, "total_steps": 1320, "loss": 0.3357, "lr": 7.813478147489052e-06, "epoch": 1.1363636363636362, "percentage": 37.88, "elapsed_time": "0:34:29", "remaining_time": "0:56:34"}
+{"current_steps": 510, "total_steps": 1320, "loss": 0.3536, "lr": 7.703204087277989e-06, "epoch": 1.1590909090909092, "percentage": 38.64, "elapsed_time": "0:35:12", "remaining_time": "0:55:54"}
+{"current_steps": 520, "total_steps": 1320, "loss": 0.3366, "lr": 7.5910397720879785e-06, "epoch": 1.1818181818181819, "percentage": 39.39, "elapsed_time": "0:35:58", "remaining_time": "0:55:20"}
+{"current_steps": 530, "total_steps": 1320, "loss": 0.31, "lr": 7.477063634456263e-06, "epoch": 1.2045454545454546, "percentage": 40.15, "elapsed_time": "0:36:35", "remaining_time": "0:54:32"}
+{"current_steps": 540, "total_steps": 1320, "loss": 0.3211, "lr": 7.361355373863415e-06, "epoch": 1.2272727272727273, "percentage": 40.91, "elapsed_time": "0:37:09", "remaining_time": "0:53:39"}
+{"current_steps": 550, "total_steps": 1320, "loss": 0.3532, "lr": 7.243995901002312e-06, "epoch": 1.25, "percentage": 41.67, "elapsed_time": "0:37:48", "remaining_time": "0:52:55"}
+{"current_steps": 560, "total_steps": 1320, "loss": 0.3113, "lr": 7.1250672812001505e-06, "epoch": 1.2727272727272727, "percentage": 42.42, "elapsed_time": "0:38:27", "remaining_time": "0:52:11"}
+{"current_steps": 570, "total_steps": 1320, "loss": 0.3264, "lr": 7.004652677033069e-06, "epoch": 1.2954545454545454, "percentage": 43.18, "elapsed_time": "0:39:06", "remaining_time": "0:51:27"}
+{"current_steps": 580, "total_steps": 1320, "loss": 0.3233, "lr": 6.882836290173493e-06, "epoch": 1.3181818181818181, "percentage": 43.94, "elapsed_time": "0:39:44", "remaining_time": "0:50:41"}
+{"current_steps": 590, "total_steps": 1320, "loss": 0.3352, "lr": 6.759703302510898e-06, "epoch": 1.3409090909090908, "percentage": 44.7, "elapsed_time": "0:40:31", "remaining_time": "0:50:08"}
+{"current_steps": 600, "total_steps": 1320, "loss": 0.3177, "lr": 6.635339816587109e-06, "epoch": 1.3636363636363638, "percentage": 45.45, "elapsed_time": "0:41:05", "remaining_time": "0:49:18"}
+{"current_steps": 610, "total_steps": 1320, "loss": 0.3468, "lr": 6.5098327953878585e-06, "epoch": 1.3863636363636362, "percentage": 46.21, "elapsed_time": "0:41:51", "remaining_time": "0:48:43"}
+{"current_steps": 620, "total_steps": 1320, "loss": 0.3253, "lr": 6.383270001532636e-06, "epoch": 1.4090909090909092, "percentage": 46.97, "elapsed_time": "0:42:30", "remaining_time": "0:47:59"}
+{"current_steps": 630, "total_steps": 1320, "loss": 0.3261, "lr": 6.255739935905396e-06, "epoch": 1.4318181818181819, "percentage": 47.73, "elapsed_time": "0:43:13", "remaining_time": "0:47:21"}
+{"current_steps": 640, "total_steps": 1320, "loss": 0.314, "lr": 6.127331775769023e-06, "epoch": 1.4545454545454546, "percentage": 48.48, "elapsed_time": "0:43:57", "remaining_time": "0:46:42"}
+{"current_steps": 650, "total_steps": 1320, "loss": 0.3113, "lr": 5.998135312406821e-06, "epoch": 1.4772727272727273, "percentage": 49.24, "elapsed_time": "0:44:37", "remaining_time": "0:46:00"}
+{"current_steps": 660, "total_steps": 1320, "loss": 0.3261, "lr": 5.8682408883346535e-06, "epoch": 1.5, "percentage": 50.0, "elapsed_time": "0:45:15", "remaining_time": "0:45:15"}
+{"current_steps": 670, "total_steps": 1320, "loss": 0.3195, "lr": 5.737739334127611e-06, "epoch": 1.5227272727272727, "percentage": 50.76, "elapsed_time": "0:45:52", "remaining_time": "0:44:30"}
+{"current_steps": 680, "total_steps": 1320, "loss": 0.3242, "lr": 5.60672190490541e-06, "epoch": 1.5454545454545454, "percentage": 51.52, "elapsed_time": "0:46:29", "remaining_time": "0:43:45"}
+{"current_steps": 690, "total_steps": 1320, "loss": 0.3272, "lr": 5.475280216520913e-06, "epoch": 1.5681818181818183, "percentage": 52.27, "elapsed_time": "0:47:16", "remaining_time": "0:43:10"}
+{"current_steps": 700, "total_steps": 1320, "loss": 0.3221, "lr": 5.343506181496405e-06, "epoch": 1.5909090909090908, "percentage": 53.03, "elapsed_time": "0:47:49", "remaining_time": "0:42:21"}
+{"current_steps": 710, "total_steps": 1320, "loss": 0.3333, "lr": 5.2114919447524155e-06, "epoch": 1.6136363636363638, "percentage": 53.79, "elapsed_time": "0:48:25", "remaining_time": "0:41:36"}
+{"current_steps": 720, "total_steps": 1320, "loss": 0.3451, "lr": 5.07932981917404e-06, "epoch": 1.6363636363636362, "percentage": 54.55, "elapsed_time": "0:49:08", "remaining_time": "0:40:57"}
+{"current_steps": 730, "total_steps": 1320, "loss": 0.3215, "lr": 4.947112221059803e-06, "epoch": 1.6590909090909092, "percentage": 55.3, "elapsed_time": "0:49:45", "remaining_time": "0:40:12"}
+{"current_steps": 740, "total_steps": 1320, "loss": 0.32, "lr": 4.81493160549821e-06, "epoch": 1.6818181818181817, "percentage": 56.06, "elapsed_time": "0:50:20", "remaining_time": "0:39:27"}
+{"current_steps": 750, "total_steps": 1320, "loss": 0.3295, "lr": 4.682880401717178e-06, "epoch": 1.7045454545454546, "percentage": 56.82, "elapsed_time": "0:51:06", "remaining_time": "0:38:50"}
+{"current_steps": 760, "total_steps": 1320, "loss": 0.3216, "lr": 4.551050948451542e-06, "epoch": 1.7272727272727273, "percentage": 57.58, "elapsed_time": "0:51:49", "remaining_time": "0:38:11"}
+{"current_steps": 770, "total_steps": 1320, "loss": 0.3047, "lr": 4.4195354293738484e-06, "epoch": 1.75, "percentage": 58.33, "elapsed_time": "0:52:30", "remaining_time": "0:37:30"}
+{"current_steps": 780, "total_steps": 1320, "loss": 0.3441, "lr": 4.2884258086335755e-06, "epoch": 1.7727272727272727, "percentage": 59.09, "elapsed_time": "0:53:16", "remaining_time": "0:36:52"}
+{"current_steps": 790, "total_steps": 1320, "loss": 0.322, "lr": 4.1578137665498485e-06, "epoch": 1.7954545454545454, "percentage": 59.85, "elapsed_time": "0:53:55", "remaining_time": "0:36:10"}
+{"current_steps": 800, "total_steps": 1320, "loss": 0.3217, "lr": 4.027790635502646e-06, "epoch": 1.8181818181818183, "percentage": 60.61, "elapsed_time": "0:54:34", "remaining_time": "0:35:28"}
+{"current_steps": 810, "total_steps": 1320, "loss": 0.331, "lr": 3.898447336067297e-06, "epoch": 1.8409090909090908, "percentage": 61.36, "elapsed_time": "0:55:07", "remaining_time": "0:34:42"}
+{"current_steps": 820, "total_steps": 1320, "loss": 0.3632, "lr": 3.769874313436933e-06, "epoch": 1.8636363636363638, "percentage": 62.12, "elapsed_time": "0:55:49", "remaining_time": "0:34:02"}
+{"current_steps": 830, "total_steps": 1320, "loss": 0.3134, "lr": 3.6421614741773702e-06, "epoch": 1.8863636363636362, "percentage": 62.88, "elapsed_time": "0:56:29", "remaining_time": "0:33:21"}
+{"current_steps": 840, "total_steps": 1320, "loss": 0.3105, "lr": 3.5153981233586277e-06, "epoch": 1.9090909090909092, "percentage": 63.64, "elapsed_time": "0:57:08", "remaining_time": "0:32:39"}
+{"current_steps": 850, "total_steps": 1320, "loss": 0.3276, "lr": 3.389672902107044e-06, "epoch": 1.9318181818181817, "percentage": 64.39, "elapsed_time": "0:57:45", "remaining_time": "0:31:56"}
+{"current_steps": 860, "total_steps": 1320, "loss": 0.3139, "lr": 3.2650737256216885e-06, "epoch": 1.9545454545454546, "percentage": 65.15, "elapsed_time": "0:58:16", "remaining_time": "0:31:09"}
+{"current_steps": 870, "total_steps": 1320, "loss": 0.3083, "lr": 3.141687721698363e-06, "epoch": 1.9772727272727273, "percentage": 65.91, "elapsed_time": "0:59:00", "remaining_time": "0:30:31"}
+{"current_steps": 880, "total_steps": 1320, "loss": 0.3335, "lr": 3.019601169804216e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:59:37", "remaining_time": "0:29:48"}
+{"current_steps": 890, "total_steps": 1320, "loss": 0.2373, "lr": 2.898899440745569e-06, "epoch": 2.022727272727273, "percentage": 67.42, "elapsed_time": "1:00:34", "remaining_time": "0:29:16"}
+{"current_steps": 900, "total_steps": 1320, "loss": 0.205, "lr": 2.7796669369711294e-06, "epoch": 2.0454545454545454, "percentage": 68.18, "elapsed_time": "1:01:14", "remaining_time": "0:28:34"}
+{"current_steps": 910, "total_steps": 1320, "loss": 0.2443, "lr": 2.6619870335523434e-06, "epoch": 2.0681818181818183, "percentage": 68.94, "elapsed_time": "1:01:57", "remaining_time": "0:27:54"}
+{"current_steps": 920, "total_steps": 1320, "loss": 0.2284, "lr": 2.5459420198821604e-06, "epoch": 2.090909090909091, "percentage": 69.7, "elapsed_time": "1:02:46", "remaining_time": "0:27:17"}
+{"current_steps": 930, "total_steps": 1320, "loss": 0.2161, "lr": 2.4316130421329696e-06, "epoch": 2.1136363636363638, "percentage": 70.45, "elapsed_time": "1:03:27", "remaining_time": "0:26:36"}
+{"current_steps": 940, "total_steps": 1320, "loss": 0.2294, "lr": 2.319080046513954e-06, "epoch": 2.1363636363636362, "percentage": 71.21, "elapsed_time": "1:04:04", "remaining_time": "0:25:54"}
+{"current_steps": 950, "total_steps": 1320, "loss": 0.2321, "lr": 2.2084217233675386e-06, "epoch": 2.159090909090909, "percentage": 71.97, "elapsed_time": "1:04:45", "remaining_time": "0:25:13"}
+{"current_steps": 960, "total_steps": 1320, "loss": 0.2141, "lr": 2.09971545214401e-06, "epoch": 2.1818181818181817, "percentage": 72.73, "elapsed_time": "1:05:23", "remaining_time": "0:24:31"}
+{"current_steps": 970, "total_steps": 1320, "loss": 0.2249, "lr": 1.9930372472928095e-06, "epoch": 2.2045454545454546, "percentage": 73.48, "elapsed_time": "1:06:08", "remaining_time": "0:23:51"}
+{"current_steps": 980, "total_steps": 1320, "loss": 0.2377, "lr": 1.8884617051083183e-06, "epoch": 2.227272727272727, "percentage": 74.24, "elapsed_time": "1:06:57", "remaining_time": "0:23:13"}
+{"current_steps": 990, "total_steps": 1320, "loss": 0.2034, "lr": 1.7860619515673034e-06, "epoch": 2.25, "percentage": 75.0, "elapsed_time": "1:07:28", "remaining_time": "0:22:29"}
+{"current_steps": 1000, "total_steps": 1320, "loss": 0.2349, "lr": 1.68590959119452e-06, "epoch": 2.2727272727272725, "percentage": 75.76, "elapsed_time": "1:08:08", "remaining_time": "0:21:48"}
+{"current_steps": 1010, "total_steps": 1320, "loss": 0.2165, "lr": 1.5880746569921867e-06, "epoch": 2.2954545454545454, "percentage": 76.52, "elapsed_time": "1:08:51", "remaining_time": "0:21:07"}
+{"current_steps": 1020, "total_steps": 1320, "loss": 0.218, "lr": 1.4926255614683931e-06, "epoch": 2.3181818181818183, "percentage": 77.27, "elapsed_time": "1:09:39", "remaining_time": "0:20:29"}
+{"current_steps": 1030, "total_steps": 1320, "loss": 0.2157, "lr": 1.3996290487986568e-06, "epoch": 2.340909090909091, "percentage": 78.03, "elapsed_time": "1:10:18", "remaining_time": "0:19:47"}
+{"current_steps": 1040, "total_steps": 1320, "loss": 0.2223, "lr": 1.3091501481540676e-06, "epoch": 2.3636363636363638, "percentage": 78.79, "elapsed_time": "1:11:00", "remaining_time": "0:19:07"}
+{"current_steps": 1050, "total_steps": 1320, "loss": 0.2052, "lr": 1.2212521282287093e-06, "epoch": 2.3863636363636362, "percentage": 79.55, "elapsed_time": "1:11:37", "remaining_time": "0:18:25"}
+{"current_steps": 1060, "total_steps": 1320, "loss": 0.2216, "lr": 1.135996452998085e-06, "epoch": 2.409090909090909, "percentage": 80.3, "elapsed_time": "1:12:16", "remaining_time": "0:17:43"}
+{"current_steps": 1070, "total_steps": 1320, "loss": 0.2199, "lr": 1.0534427387395391e-06, "epoch": 2.4318181818181817, "percentage": 81.06, "elapsed_time": "1:12:55", "remaining_time": "0:17:02"}
+{"current_steps": 1080, "total_steps": 1320, "loss": 0.2125, "lr": 9.73648712344707e-07, "epoch": 2.4545454545454546, "percentage": 81.82, "elapsed_time": "1:13:35", "remaining_time": "0:16:21"}
+{"current_steps": 1090, "total_steps": 1320, "loss": 0.1929, "lr": 8.966701709531344e-07, "epoch": 2.4772727272727275, "percentage": 82.58, "elapsed_time": "1:14:04", "remaining_time": "0:15:37"}
+{"current_steps": 1100, "total_steps": 1320, "loss": 0.2425, "lr": 8.225609429353187e-07, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:14:45", "remaining_time": "0:14:57"}
+{"current_steps": 1110, "total_steps": 1320, "loss": 0.2292, "lr": 7.513728502524286e-07, "epoch": 2.5227272727272725, "percentage": 84.09, "elapsed_time": "1:15:26", "remaining_time": "0:14:16"}
+{"current_steps": 1120, "total_steps": 1320, "loss": 0.2256, "lr": 6.831556722190453e-07, "epoch": 2.5454545454545454, "percentage": 84.85, "elapsed_time": "1:16:06", "remaining_time": "0:13:35"}
+{"current_steps": 1130, "total_steps": 1320, "loss": 0.2154, "lr": 6.179571106942466e-07, "epoch": 2.5681818181818183, "percentage": 85.61, "elapsed_time": "1:16:52", "remaining_time": "0:12:55"}
+{"current_steps": 1140, "total_steps": 1320, "loss": 0.2237, "lr": 5.558227567253832e-07, "epoch": 2.590909090909091, "percentage": 86.36, "elapsed_time": "1:17:32", "remaining_time": "0:12:14"}
+{"current_steps": 1150, "total_steps": 1320, "loss": 0.2166, "lr": 4.967960586678722e-07, "epoch": 2.6136363636363638, "percentage": 87.12, "elapsed_time": "1:18:08", "remaining_time": "0:11:33"}
+{"current_steps": 1160, "total_steps": 1320, "loss": 0.2125, "lr": 4.4091829180330503e-07, "epoch": 2.6363636363636362, "percentage": 87.88, "elapsed_time": "1:18:51", "remaining_time": "0:10:52"}
+{"current_steps": 1170, "total_steps": 1320, "loss": 0.2209, "lr": 3.882285294770938e-07, "epoch": 2.659090909090909, "percentage": 88.64, "elapsed_time": "1:19:31", "remaining_time": "0:10:11"}
+{"current_steps": 1180, "total_steps": 1320, "loss": 0.2407, "lr": 3.3876361577587115e-07, "epoch": 2.6818181818181817, "percentage": 89.39, "elapsed_time": "1:20:12", "remaining_time": "0:09:31"}
+{"current_steps": 1190, "total_steps": 1320, "loss": 0.2343, "lr": 2.9255813976372227e-07, "epoch": 2.7045454545454546, "percentage": 90.15, "elapsed_time": "1:20:54", "remaining_time": "0:08:50"}
+{"current_steps": 1200, "total_steps": 1320, "loss": 0.2453, "lr": 2.4964441129527337e-07, "epoch": 2.7272727272727275, "percentage": 90.91, "elapsed_time": "1:21:32", "remaining_time": "0:08:09"}
+{"current_steps": 1210, "total_steps": 1320, "loss": 0.2083, "lr": 2.1005243842255552e-07, "epoch": 2.75, "percentage": 91.67, "elapsed_time": "1:22:12", "remaining_time": "0:07:28"}
+{"current_steps": 1220, "total_steps": 1320, "loss": 0.2088, "lr": 1.738099064114368e-07, "epoch": 2.7727272727272725, "percentage": 92.42, "elapsed_time": "1:22:51", "remaining_time": "0:06:47"}
+{"current_steps": 1230, "total_steps": 1320, "loss": 0.2446, "lr": 1.4094215838229176e-07, "epoch": 2.7954545454545454, "percentage": 93.18, "elapsed_time": "1:23:35", "remaining_time": "0:06:06"}
+{"current_steps": 1240, "total_steps": 1320, "loss": 0.223, "lr": 1.1147217758845752e-07, "epoch": 2.8181818181818183, "percentage": 93.94, "elapsed_time": "1:24:20", "remaining_time": "0:05:26"}
+{"current_steps": 1250, "total_steps": 1320, "loss": 0.2366, "lr": 8.542057134485638e-08, "epoch": 2.840909090909091, "percentage": 94.7, "elapsed_time": "1:25:01", "remaining_time": "0:04:45"}
+{"current_steps": 1260, "total_steps": 1320, "loss": 0.1889, "lr": 6.280555661802857e-08, "epoch": 2.8636363636363638, "percentage": 95.45, "elapsed_time": "1:25:46", "remaining_time": "0:04:05"}
+{"current_steps": 1270, "total_steps": 1320, "loss": 0.2269, "lr": 4.3642947287654284e-08, "epoch": 2.8863636363636362, "percentage": 96.21, "elapsed_time": "1:26:25", "remaining_time": "0:03:24"}
+{"current_steps": 1280, "total_steps": 1320, "loss": 0.2184, "lr": 2.7946143088466437e-08, "epoch": 2.909090909090909, "percentage": 96.97, "elapsed_time": "1:27:05", "remaining_time": "0:02:43"}
+{"current_steps": 1290, "total_steps": 1320, "loss": 0.2115, "lr": 1.5726120240288632e-08, "epoch": 2.9318181818181817, "percentage": 97.73, "elapsed_time": "1:27:48", "remaining_time": "0:02:02"}
+{"current_steps": 1300, "total_steps": 1320, "loss": 0.2235, "lr": 6.991423772753636e-09, "epoch": 2.9545454545454546, "percentage": 98.48, "elapsed_time": "1:28:32", "remaining_time": "0:01:21"}
+{"current_steps": 1310, "total_steps": 1320, "loss": 0.2189, "lr": 1.7481615500691829e-09, "epoch": 2.9772727272727275, "percentage": 99.24, "elapsed_time": "1:29:13", "remaining_time": "0:00:40"}
+{"current_steps": 1320, "total_steps": 1320, "loss": 0.2345, "lr": 0.0, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:30:01", "remaining_time": "0:00:00"}
+{"current_steps": 1320, "total_steps": 1320, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:30:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,966 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022727272727272728,
+      "grad_norm": 6.35440244262687,
+      "learning_rate": 7.575757575757576e-07,
+      "loss": 0.7684,
+      "step": 10
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 2.539886425067851,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 0.6837,
+      "step": 20
+    },
+    {
+      "epoch": 0.06818181818181818,
+      "grad_norm": 2.459810303110342,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.6466,
+      "step": 30
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 1.770796632740967,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 0.5912,
+      "step": 40
+    },
+    {
+      "epoch": 0.11363636363636363,
+      "grad_norm": 1.2695649352744178,
+      "learning_rate": 3.7878787878787882e-06,
+      "loss": 0.5324,
+      "step": 50
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 1.1616146630386306,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 0.519,
+      "step": 60
+    },
+    {
+      "epoch": 0.1590909090909091,
+      "grad_norm": 1.2275679597942535,
+      "learning_rate": 5.303030303030303e-06,
+      "loss": 0.5089,
+      "step": 70
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 1.2356666530916727,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 0.4981,
+      "step": 80
+    },
+    {
+      "epoch": 0.20454545454545456,
+      "grad_norm": 1.0321368603514207,
+      "learning_rate": 6.818181818181818e-06,
+      "loss": 0.5116,
+      "step": 90
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 1.2554331662611178,
+      "learning_rate": 7.5757575757575764e-06,
+      "loss": 0.4969,
+      "step": 100
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.108592526031677,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.4667,
+      "step": 110
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 1.2536541822586402,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 0.4538,
+      "step": 120
+    },
+    {
+      "epoch": 0.29545454545454547,
+      "grad_norm": 1.085405743643047,
+      "learning_rate": 9.84848484848485e-06,
+      "loss": 0.4547,
+      "step": 130
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 1.3093680137962422,
+      "learning_rate": 9.99888115313551e-06,
+      "loss": 0.4857,
+      "step": 140
+    },
+    {
+      "epoch": 0.3409090909090909,
+      "grad_norm": 1.3773445549991983,
+      "learning_rate": 9.994336695915041e-06,
+      "loss": 0.4805,
+      "step": 150
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 1.591560589841802,
+      "learning_rate": 9.986299875742612e-06,
+      "loss": 0.4629,
+      "step": 160
+    },
+    {
+      "epoch": 0.38636363636363635,
+      "grad_norm": 1.4004153271538835,
+      "learning_rate": 9.97477631248223e-06,
+      "loss": 0.4791,
+      "step": 170
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 1.0354548471138036,
+      "learning_rate": 9.959774064153977e-06,
+      "loss": 0.452,
+      "step": 180
+    },
+    {
+      "epoch": 0.4318181818181818,
+      "grad_norm": 1.2208714972404657,
+      "learning_rate": 9.941303621299332e-06,
+      "loss": 0.4505,
+      "step": 190
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 1.1847279130783284,
+      "learning_rate": 9.919377899645497e-06,
+      "loss": 0.4539,
+      "step": 200
+    },
+    {
+      "epoch": 0.4772727272727273,
+      "grad_norm": 1.1879951591803597,
+      "learning_rate": 9.894012231073895e-06,
+      "loss": 0.4473,
+      "step": 210
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.705038237865607,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 0.4794,
+      "step": 220
+    },
+    {
+      "epoch": 0.5227272727272727,
+      "grad_norm": 1.3352984955766194,
+      "learning_rate": 9.833034395465866e-06,
+      "loss": 0.4437,
+      "step": 230
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 1.3789144895455978,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.4667,
+      "step": 240
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 1.0952159859041897,
+      "learning_rate": 9.758540643231041e-06,
+      "loss": 0.4545,
+      "step": 250
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 1.071210265571984,
+      "learning_rate": 9.716288939274818e-06,
+      "loss": 0.4632,
+      "step": 260
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "grad_norm": 1.2854473189577795,
+      "learning_rate": 9.670739301325534e-06,
+      "loss": 0.461,
+      "step": 270
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 1.0349444641905114,
+      "learning_rate": 9.621923580633462e-06,
+      "loss": 0.4503,
+      "step": 280
+    },
+    {
+      "epoch": 0.6590909090909091,
+      "grad_norm": 1.0305581230268586,
+      "learning_rate": 9.56987591230498e-06,
+      "loss": 0.448,
+      "step": 290
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 1.0379340882310921,
+      "learning_rate": 9.514632691433108e-06,
+      "loss": 0.4233,
+      "step": 300
+    },
+    {
+      "epoch": 0.7045454545454546,
+      "grad_norm": 1.0211063705976775,
+      "learning_rate": 9.456232547647695e-06,
+      "loss": 0.4611,
+      "step": 310
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 1.270861551615867,
+      "learning_rate": 9.394716318103098e-06,
+      "loss": 0.4666,
+      "step": 320
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.4358106750611455,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.4311,
+      "step": 330
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 0.9211243850184648,
+      "learning_rate": 9.262509815116732e-06,
+      "loss": 0.4625,
+      "step": 340
+    },
+    {
+      "epoch": 0.7954545454545454,
+      "grad_norm": 1.0471205669074248,
+      "learning_rate": 9.191911989005038e-06,
+      "loss": 0.4385,
+      "step": 350
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 1.1367135885228616,
+      "learning_rate": 9.118382907149164e-06,
+      "loss": 0.4504,
+      "step": 360
+    },
+    {
+      "epoch": 0.8409090909090909,
+      "grad_norm": 0.8937203983205025,
+      "learning_rate": 9.041973985834595e-06,
+      "loss": 0.4201,
+      "step": 370
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 1.1449338266575286,
+      "learning_rate": 8.96273865511666e-06,
+      "loss": 0.4332,
+      "step": 380
+    },
+    {
+      "epoch": 0.8863636363636364,
+      "grad_norm": 1.0137721464541551,
+      "learning_rate": 8.880732321458785e-06,
+      "loss": 0.4688,
+      "step": 390
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.141330043928384,
+      "learning_rate": 8.796012328988716e-06,
+      "loss": 0.4486,
+      "step": 400
+    },
+    {
+      "epoch": 0.9318181818181818,
+      "grad_norm": 0.9565319534405999,
+      "learning_rate": 8.708637919399798e-06,
+      "loss": 0.4769,
+      "step": 410
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 0.8984018100341509,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.432,
+      "step": 420
+    },
+    {
+      "epoch": 0.9772727272727273,
+      "grad_norm": 0.9304841359661392,
+      "learning_rate": 8.526172053615122e-06,
+      "loss": 0.4345,
+      "step": 430
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8768633210220393,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.4371,
+      "step": 440
+    },
+    {
+      "epoch": 1.0227272727272727,
+      "grad_norm": 1.1311095568028267,
+      "learning_rate": 8.33384500258146e-06,
+      "loss": 0.3547,
+      "step": 450
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 0.8562280421736388,
+      "learning_rate": 8.234150575960288e-06,
+      "loss": 0.344,
+      "step": 460
+    },
+    {
+      "epoch": 1.0681818181818181,
+      "grad_norm": 0.9841335785316842,
+      "learning_rate": 8.132194622265508e-06,
+      "loss": 0.3462,
+      "step": 470
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 1.045774931721029,
+      "learning_rate": 8.028048435688333e-06,
+      "loss": 0.3285,
+      "step": 480
+    },
+    {
+      "epoch": 1.1136363636363635,
+      "grad_norm": 0.8604729577213927,
+      "learning_rate": 7.921784841972355e-06,
+      "loss": 0.344,
+      "step": 490
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.9278271486506232,
+      "learning_rate": 7.813478147489052e-06,
+      "loss": 0.3357,
+      "step": 500
+    },
+    {
+      "epoch": 1.1590909090909092,
+      "grad_norm": 1.0237784505259664,
+      "learning_rate": 7.703204087277989e-06,
+      "loss": 0.3536,
+      "step": 510
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.8356075391269556,
+      "learning_rate": 7.5910397720879785e-06,
+      "loss": 0.3366,
+      "step": 520
+    },
+    {
+      "epoch": 1.2045454545454546,
+      "grad_norm": 0.9979040732435491,
+      "learning_rate": 7.477063634456263e-06,
+      "loss": 0.31,
+      "step": 530
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 1.0044525302301133,
+      "learning_rate": 7.361355373863415e-06,
+      "loss": 0.3211,
+      "step": 540
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 2.2937575511435897,
+      "learning_rate": 7.243995901002312e-06,
+      "loss": 0.3532,
+      "step": 550
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 1.02382051382484,
+      "learning_rate": 7.1250672812001505e-06,
+      "loss": 0.3113,
+      "step": 560
+    },
+    {
+      "epoch": 1.2954545454545454,
+      "grad_norm": 0.8952595339853402,
+      "learning_rate": 7.004652677033069e-06,
+      "loss": 0.3264,
+      "step": 570
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 0.8831005766886504,
+      "learning_rate": 6.882836290173493e-06,
+      "loss": 0.3233,
+      "step": 580
+    },
+    {
+      "epoch": 1.3409090909090908,
+      "grad_norm": 0.7901321424383204,
+      "learning_rate": 6.759703302510898e-06,
+      "loss": 0.3352,
+      "step": 590
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 1.2262968003160024,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.3177,
+      "step": 600
+    },
+    {
+      "epoch": 1.3863636363636362,
+      "grad_norm": 0.7917420857688439,
+      "learning_rate": 6.5098327953878585e-06,
+      "loss": 0.3468,
+      "step": 610
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 1.0420360755184277,
+      "learning_rate": 6.383270001532636e-06,
+      "loss": 0.3253,
+      "step": 620
+    },
+    {
+      "epoch": 1.4318181818181819,
+      "grad_norm": 1.0205657171970297,
+      "learning_rate": 6.255739935905396e-06,
+      "loss": 0.3261,
+      "step": 630
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.251378392945878,
+      "learning_rate": 6.127331775769023e-06,
+      "loss": 0.314,
+      "step": 640
+    },
+    {
+      "epoch": 1.4772727272727273,
+      "grad_norm": 0.9207759342389322,
+      "learning_rate": 5.998135312406821e-06,
+      "loss": 0.3113,
+      "step": 650
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.931014052691459,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.3261,
+      "step": 660
+    },
+    {
+      "epoch": 1.5227272727272727,
+      "grad_norm": 1.2292042441399877,
+      "learning_rate": 5.737739334127611e-06,
+      "loss": 0.3195,
+      "step": 670
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.908649250490574,
+      "learning_rate": 5.60672190490541e-06,
+      "loss": 0.3242,
+      "step": 680
+    },
+    {
+      "epoch": 1.5681818181818183,
+      "grad_norm": 1.0094095236232232,
+      "learning_rate": 5.475280216520913e-06,
+      "loss": 0.3272,
+      "step": 690
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 1.1176464384766536,
+      "learning_rate": 5.343506181496405e-06,
+      "loss": 0.3221,
+      "step": 700
+    },
+    {
+      "epoch": 1.6136363636363638,
+      "grad_norm": 0.8887736448070302,
+      "learning_rate": 5.2114919447524155e-06,
+      "loss": 0.3333,
+      "step": 710
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 1.1062063033166711,
+      "learning_rate": 5.07932981917404e-06,
+      "loss": 0.3451,
+      "step": 720
+    },
+    {
+      "epoch": 1.6590909090909092,
+      "grad_norm": 0.9814802109483011,
+      "learning_rate": 4.947112221059803e-06,
+      "loss": 0.3215,
+      "step": 730
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 0.9942287700866195,
+      "learning_rate": 4.81493160549821e-06,
+      "loss": 0.32,
+      "step": 740
+    },
+    {
+      "epoch": 1.7045454545454546,
+      "grad_norm": 1.0881777582662082,
+      "learning_rate": 4.682880401717178e-06,
+      "loss": 0.3295,
+      "step": 750
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.8262863481185285,
+      "learning_rate": 4.551050948451542e-06,
+      "loss": 0.3216,
+      "step": 760
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.8739486063657917,
+      "learning_rate": 4.4195354293738484e-06,
+      "loss": 0.3047,
+      "step": 770
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 0.7937933897637206,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.3441,
+      "step": 780
+    },
+    {
+      "epoch": 1.7954545454545454,
+      "grad_norm": 1.0063979195807515,
+      "learning_rate": 4.1578137665498485e-06,
+      "loss": 0.322,
+      "step": 790
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.9811868516252389,
+      "learning_rate": 4.027790635502646e-06,
+      "loss": 0.3217,
+      "step": 800
+    },
+    {
+      "epoch": 1.8409090909090908,
+      "grad_norm": 1.0864122648296841,
+      "learning_rate": 3.898447336067297e-06,
+      "loss": 0.331,
+      "step": 810
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 0.99556848477455,
+      "learning_rate": 3.769874313436933e-06,
+      "loss": 0.3632,
+      "step": 820
+    },
+    {
+      "epoch": 1.8863636363636362,
+      "grad_norm": 0.891576989962014,
+      "learning_rate": 3.6421614741773702e-06,
+      "loss": 0.3134,
+      "step": 830
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.7986035082838789,
+      "learning_rate": 3.5153981233586277e-06,
+      "loss": 0.3105,
+      "step": 840
+    },
+    {
+      "epoch": 1.9318181818181817,
+      "grad_norm": 0.95580966680964,
+      "learning_rate": 3.389672902107044e-06,
+      "loss": 0.3276,
+      "step": 850
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 0.961790704782099,
+      "learning_rate": 3.2650737256216885e-06,
+      "loss": 0.3139,
+      "step": 860
+    },
+    {
+      "epoch": 1.9772727272727273,
+      "grad_norm": 0.8730438224301623,
+      "learning_rate": 3.141687721698363e-06,
+      "loss": 0.3083,
+      "step": 870
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0499453266134642,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.3335,
+      "step": 880
+    },
+    {
+      "epoch": 2.022727272727273,
+      "grad_norm": 0.9956657648694927,
+      "learning_rate": 2.898899440745569e-06,
+      "loss": 0.2373,
+      "step": 890
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.8364788663760782,
+      "learning_rate": 2.7796669369711294e-06,
+      "loss": 0.205,
+      "step": 900
+    },
+    {
+      "epoch": 2.0681818181818183,
+      "grad_norm": 0.7779785577534016,
+      "learning_rate": 2.6619870335523434e-06,
+      "loss": 0.2443,
+      "step": 910
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.7498597657637932,
+      "learning_rate": 2.5459420198821604e-06,
+      "loss": 0.2284,
+      "step": 920
+    },
+    {
+      "epoch": 2.1136363636363638,
+      "grad_norm": 0.7866782800010009,
+      "learning_rate": 2.4316130421329696e-06,
+      "loss": 0.2161,
+      "step": 930
+    },
+    {
+      "epoch": 2.1363636363636362,
+      "grad_norm": 0.8286340462329047,
+      "learning_rate": 2.319080046513954e-06,
+      "loss": 0.2294,
+      "step": 940
+    },
+    {
+      "epoch": 2.159090909090909,
+      "grad_norm": 0.7317679036213534,
+      "learning_rate": 2.2084217233675386e-06,
+      "loss": 0.2321,
+      "step": 950
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.82937017655548,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.2141,
+      "step": 960
+    },
+    {
+      "epoch": 2.2045454545454546,
+      "grad_norm": 1.0909932006216758,
+      "learning_rate": 1.9930372472928095e-06,
+      "loss": 0.2249,
+      "step": 970
+    },
+    {
+      "epoch": 2.227272727272727,
+      "grad_norm": 0.8406918311430651,
+      "learning_rate": 1.8884617051083183e-06,
+      "loss": 0.2377,
+      "step": 980
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.7816214910751722,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.2034,
+      "step": 990
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 1.1472658731628425,
+      "learning_rate": 1.68590959119452e-06,
+      "loss": 0.2349,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2954545454545454,
+      "grad_norm": 0.8364108799897995,
+      "learning_rate": 1.5880746569921867e-06,
+      "loss": 0.2165,
+      "step": 1010
+    },
+    {
+      "epoch": 2.3181818181818183,
+      "grad_norm": 0.8224990407144809,
+      "learning_rate": 1.4926255614683931e-06,
+      "loss": 0.218,
+      "step": 1020
+    },
+    {
+      "epoch": 2.340909090909091,
+      "grad_norm": 0.8119956704092801,
+      "learning_rate": 1.3996290487986568e-06,
+      "loss": 0.2157,
+      "step": 1030
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.7868638178604844,
+      "learning_rate": 1.3091501481540676e-06,
+      "loss": 0.2223,
+      "step": 1040
+    },
+    {
+      "epoch": 2.3863636363636362,
+      "grad_norm": 1.039084974687428,
+      "learning_rate": 1.2212521282287093e-06,
+      "loss": 0.2052,
+      "step": 1050
+    },
+    {
+      "epoch": 2.409090909090909,
+      "grad_norm": 1.0217506234090892,
+      "learning_rate": 1.135996452998085e-06,
+      "loss": 0.2216,
+      "step": 1060
+    },
+    {
+      "epoch": 2.4318181818181817,
+      "grad_norm": 0.849092945674219,
+      "learning_rate": 1.0534427387395391e-06,
+      "loss": 0.2199,
+      "step": 1070
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.8148942381510792,
+      "learning_rate": 9.73648712344707e-07,
+      "loss": 0.2125,
+      "step": 1080
+    },
+    {
+      "epoch": 2.4772727272727275,
+      "grad_norm": 0.8050466872394376,
+      "learning_rate": 8.966701709531344e-07,
+      "loss": 0.1929,
+      "step": 1090
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.8780283448986274,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.2425,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5227272727272725,
+      "grad_norm": 0.7816219793057795,
+      "learning_rate": 7.513728502524286e-07,
+      "loss": 0.2292,
+      "step": 1110
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.9595240653902316,
+      "learning_rate": 6.831556722190453e-07,
+      "loss": 0.2256,
+      "step": 1120
+    },
+    {
+      "epoch": 2.5681818181818183,
+      "grad_norm": 0.792587276105673,
+      "learning_rate": 6.179571106942466e-07,
+      "loss": 0.2154,
+      "step": 1130
+    },
+    {
+      "epoch": 2.590909090909091,
+      "grad_norm": 0.8358451547436763,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.2237,
+      "step": 1140
+    },
+    {
+      "epoch": 2.6136363636363638,
+      "grad_norm": 0.8903944755859766,
+      "learning_rate": 4.967960586678722e-07,
+      "loss": 0.2166,
+      "step": 1150
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.8509792469149934,
+      "learning_rate": 4.4091829180330503e-07,
+      "loss": 0.2125,
+      "step": 1160
+    },
+    {
+      "epoch": 2.659090909090909,
+      "grad_norm": 0.886408398471228,
+      "learning_rate": 3.882285294770938e-07,
+      "loss": 0.2209,
+      "step": 1170
+    },
+    {
+      "epoch": 2.6818181818181817,
+      "grad_norm": 0.8109381117518478,
+      "learning_rate": 3.3876361577587115e-07,
+      "loss": 0.2407,
+      "step": 1180
+    },
+    {
+      "epoch": 2.7045454545454546,
+      "grad_norm": 0.8002247026554093,
+      "learning_rate": 2.9255813976372227e-07,
+      "loss": 0.2343,
+      "step": 1190
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.83770770704907,
+      "learning_rate": 2.4964441129527337e-07,
+      "loss": 0.2453,
+      "step": 1200
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.816464711381253,
+      "learning_rate": 2.1005243842255552e-07,
+      "loss": 0.2083,
+      "step": 1210
+    },
+    {
+      "epoch": 2.7727272727272725,
+      "grad_norm": 0.95604900414777,
+      "learning_rate": 1.738099064114368e-07,
+      "loss": 0.2088,
+      "step": 1220
+    },
+    {
+      "epoch": 2.7954545454545454,
+      "grad_norm": 0.8185862381359805,
+      "learning_rate": 1.4094215838229176e-07,
+      "loss": 0.2446,
+      "step": 1230
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.7499960362919149,
+      "learning_rate": 1.1147217758845752e-07,
+      "loss": 0.223,
+      "step": 1240
+    },
+    {
+      "epoch": 2.840909090909091,
+      "grad_norm": 0.9113822005624685,
+      "learning_rate": 8.542057134485638e-08,
+      "loss": 0.2366,
+      "step": 1250
+    },
+    {
+      "epoch": 2.8636363636363638,
+      "grad_norm": 0.8418617848382326,
+      "learning_rate": 6.280555661802857e-08,
+      "loss": 0.1889,
+      "step": 1260
+    },
+    {
+      "epoch": 2.8863636363636362,
+      "grad_norm": 0.7673661290204885,
+      "learning_rate": 4.3642947287654284e-08,
+      "loss": 0.2269,
+      "step": 1270
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.8092713369674382,
+      "learning_rate": 2.7946143088466437e-08,
+      "loss": 0.2184,
+      "step": 1280
+    },
+    {
+      "epoch": 2.9318181818181817,
+      "grad_norm": 1.0854187395464028,
+      "learning_rate": 1.5726120240288632e-08,
+      "loss": 0.2115,
+      "step": 1290
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 0.8536518727086961,
+      "learning_rate": 6.991423772753636e-09,
+      "loss": 0.2235,
+      "step": 1300
+    },
+    {
+      "epoch": 2.9772727272727275,
+      "grad_norm": 0.8448528485181613,
+      "learning_rate": 1.7481615500691829e-09,
+      "loss": 0.2189,
+      "step": 1310
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.7295128069834027,
+      "learning_rate": 0.0,
+      "loss": 0.2345,
+      "step": 1320
+    },
+    {
+      "epoch": 3.0,
+      "step": 1320,
+      "total_flos": 150195282509824.0,
+      "train_loss": 0.3441459048878063,
+      "train_runtime": 5442.3628,
+      "train_samples_per_second": 1.937,
+      "train_steps_per_second": 0.243
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 150195282509824.0,
+  "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:f5f9b77d293ea7ad3f9481c16f32a9258f942ebb887f89820ce325923bb21e52
+size 7608