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: orpo_trained_2
+  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. -->
+
+# orpo_trained_2
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the lightblue_orpo_data 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: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 8
+- 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: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.4.0+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9982859101816935,
+    "total_flos": 58779245903872.0,
+    "train_loss": 0.7302135016236987,
+    "train_runtime": 13700.9712,
+    "train_samples_per_second": 1.703,
+    "train_steps_per_second": 0.013
+}

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75d15ff973fedfb592907883d81ae7310b55d85a0174aea5f0da8a04cb33e0d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32fd0747bad48e5baa6364d57c6944fc9c6dd2d071cca0804ea985dbeae33349
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700f0550c69e3ce046a13cc451cf5f968356cee53d7174a27340868274fbafe8
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d24169e962a22e96df9522be97b2696410356790cceea65e30f18320262616
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9982859101816935,
+    "total_flos": 58779245903872.0,
+    "train_loss": 0.7302135016236987,
+    "train_runtime": 13700.9712,
+    "train_samples_per_second": 1.703,
+    "train_steps_per_second": 0.013
+}

trainer_log.jsonl

@@ -0,0 +1,183 @@
+{"current_steps": 1, "total_steps": 182, "loss": 0.8549, "accuracy": 0.328125, "lr": 5.263157894736843e-07, "epoch": 0.005485087418580734, "percentage": 0.55, "elapsed_time": "0:01:19", "remaining_time": "4:00:52"}
+{"current_steps": 2, "total_steps": 182, "loss": 0.8261, "accuracy": 0.3671875, "lr": 1.0526315789473685e-06, "epoch": 0.010970174837161468, "percentage": 1.1, "elapsed_time": "0:02:33", "remaining_time": "3:50:21"}
+{"current_steps": 3, "total_steps": 182, "loss": 0.8054, "accuracy": 0.375, "lr": 1.5789473684210526e-06, "epoch": 0.0164552622557422, "percentage": 1.65, "elapsed_time": "0:03:53", "remaining_time": "3:51:46"}
+{"current_steps": 4, "total_steps": 182, "loss": 0.8329, "accuracy": 0.4140625, "lr": 2.105263157894737e-06, "epoch": 0.021940349674322936, "percentage": 2.2, "elapsed_time": "0:05:08", "remaining_time": "3:49:09"}
+{"current_steps": 5, "total_steps": 182, "loss": 0.7966, "accuracy": 0.3359375, "lr": 2.631578947368421e-06, "epoch": 0.027425437092903668, "percentage": 2.75, "elapsed_time": "0:06:26", "remaining_time": "3:47:58"}
+{"current_steps": 6, "total_steps": 182, "loss": 0.8222, "accuracy": 0.375, "lr": 3.157894736842105e-06, "epoch": 0.0329105245114844, "percentage": 3.3, "elapsed_time": "0:07:41", "remaining_time": "3:45:33"}
+{"current_steps": 7, "total_steps": 182, "loss": 0.7481, "accuracy": 0.4140625, "lr": 3.6842105263157896e-06, "epoch": 0.03839561193006513, "percentage": 3.85, "elapsed_time": "0:08:56", "remaining_time": "3:43:39"}
+{"current_steps": 8, "total_steps": 182, "loss": 0.7817, "accuracy": 0.390625, "lr": 4.210526315789474e-06, "epoch": 0.04388069934864587, "percentage": 4.4, "elapsed_time": "0:10:15", "remaining_time": "3:43:04"}
+{"current_steps": 9, "total_steps": 182, "loss": 0.8647, "accuracy": 0.265625, "lr": 4.736842105263158e-06, "epoch": 0.049365786767226603, "percentage": 4.95, "elapsed_time": "0:11:33", "remaining_time": "3:42:07"}
+{"current_steps": 10, "total_steps": 182, "loss": 0.8793, "accuracy": 0.28125, "lr": 5.263157894736842e-06, "epoch": 0.054850874185807336, "percentage": 5.49, "elapsed_time": "0:12:48", "remaining_time": "3:40:24"}
+{"current_steps": 11, "total_steps": 182, "loss": 0.8159, "accuracy": 0.3359375, "lr": 5.789473684210527e-06, "epoch": 0.06033596160438807, "percentage": 6.04, "elapsed_time": "0:14:04", "remaining_time": "3:38:47"}
+{"current_steps": 12, "total_steps": 182, "loss": 0.8272, "accuracy": 0.296875, "lr": 6.31578947368421e-06, "epoch": 0.0658210490229688, "percentage": 6.59, "elapsed_time": "0:15:19", "remaining_time": "3:37:09"}
+{"current_steps": 13, "total_steps": 182, "loss": 0.7821, "accuracy": 0.34375, "lr": 6.842105263157896e-06, "epoch": 0.07130613644154954, "percentage": 7.14, "elapsed_time": "0:16:35", "remaining_time": "3:35:36"}
+{"current_steps": 14, "total_steps": 182, "loss": 0.8562, "accuracy": 0.3515625, "lr": 7.368421052631579e-06, "epoch": 0.07679122386013026, "percentage": 7.69, "elapsed_time": "0:17:53", "remaining_time": "3:34:41"}
+{"current_steps": 15, "total_steps": 182, "loss": 0.8106, "accuracy": 0.375, "lr": 7.894736842105265e-06, "epoch": 0.082276311278711, "percentage": 8.24, "elapsed_time": "0:19:06", "remaining_time": "3:32:48"}
+{"current_steps": 16, "total_steps": 182, "loss": 0.8113, "accuracy": 0.359375, "lr": 8.421052631578948e-06, "epoch": 0.08776139869729174, "percentage": 8.79, "elapsed_time": "0:20:24", "remaining_time": "3:31:45"}
+{"current_steps": 17, "total_steps": 182, "loss": 0.8323, "accuracy": 0.3125, "lr": 8.947368421052632e-06, "epoch": 0.09324648611587247, "percentage": 9.34, "elapsed_time": "0:21:41", "remaining_time": "3:30:30"}
+{"current_steps": 18, "total_steps": 182, "loss": 0.8107, "accuracy": 0.453125, "lr": 9.473684210526315e-06, "epoch": 0.09873157353445321, "percentage": 9.89, "elapsed_time": "0:22:56", "remaining_time": "3:28:58"}
+{"current_steps": 19, "total_steps": 182, "loss": 0.7743, "accuracy": 0.375, "lr": 1e-05, "epoch": 0.10421666095303393, "percentage": 10.44, "elapsed_time": "0:24:06", "remaining_time": "3:26:50"}
+{"current_steps": 20, "total_steps": 182, "loss": 0.7844, "accuracy": 0.359375, "lr": 9.999071352056676e-06, "epoch": 0.10970174837161467, "percentage": 10.99, "elapsed_time": "0:25:21", "remaining_time": "3:25:27"}
+{"current_steps": 21, "total_steps": 182, "loss": 0.8091, "accuracy": 0.3359375, "lr": 9.996285753181499e-06, "epoch": 0.11518683579019541, "percentage": 11.54, "elapsed_time": "0:26:35", "remaining_time": "3:23:51"}
+{"current_steps": 22, "total_steps": 182, "loss": 0.7769, "accuracy": 0.328125, "lr": 9.991644238110741e-06, "epoch": 0.12067192320877614, "percentage": 12.09, "elapsed_time": "0:27:50", "remaining_time": "3:22:28"}
+{"current_steps": 23, "total_steps": 182, "loss": 0.7573, "accuracy": 0.3203125, "lr": 9.985148530977767e-06, "epoch": 0.12615701062735687, "percentage": 12.64, "elapsed_time": "0:29:03", "remaining_time": "3:20:53"}
+{"current_steps": 24, "total_steps": 182, "loss": 0.7376, "accuracy": 0.3984375, "lr": 9.976801044672608e-06, "epoch": 0.1316420980459376, "percentage": 13.19, "elapsed_time": "0:30:16", "remaining_time": "3:19:20"}
+{"current_steps": 25, "total_steps": 182, "loss": 0.735, "accuracy": 0.40625, "lr": 9.966604879945659e-06, "epoch": 0.13712718546451835, "percentage": 13.74, "elapsed_time": "0:31:30", "remaining_time": "3:17:54"}
+{"current_steps": 26, "total_steps": 182, "loss": 0.7183, "accuracy": 0.4296875, "lr": 9.954563824255879e-06, "epoch": 0.14261227288309908, "percentage": 14.29, "elapsed_time": "0:32:46", "remaining_time": "3:16:36"}
+{"current_steps": 27, "total_steps": 182, "loss": 0.7592, "accuracy": 0.328125, "lr": 9.940682350363913e-06, "epoch": 0.1480973603016798, "percentage": 14.84, "elapsed_time": "0:34:01", "remaining_time": "3:15:20"}
+{"current_steps": 28, "total_steps": 182, "loss": 0.7587, "accuracy": 0.3828125, "lr": 9.924965614670629e-06, "epoch": 0.15358244772026053, "percentage": 15.38, "elapsed_time": "0:35:17", "remaining_time": "3:14:03"}
+{"current_steps": 29, "total_steps": 182, "loss": 0.873, "accuracy": 0.2890625, "lr": 9.90741945530174e-06, "epoch": 0.15906753513884128, "percentage": 15.93, "elapsed_time": "0:36:29", "remaining_time": "3:12:31"}
+{"current_steps": 30, "total_steps": 182, "loss": 0.796, "accuracy": 0.4140625, "lr": 9.888050389939172e-06, "epoch": 0.164552622557422, "percentage": 16.48, "elapsed_time": "0:37:44", "remaining_time": "3:11:13"}
+{"current_steps": 31, "total_steps": 182, "loss": 0.8005, "accuracy": 0.3828125, "lr": 9.866865613400008e-06, "epoch": 0.17003770997600273, "percentage": 17.03, "elapsed_time": "0:39:03", "remaining_time": "3:10:16"}
+{"current_steps": 32, "total_steps": 182, "loss": 0.754, "accuracy": 0.34375, "lr": 9.843872994963912e-06, "epoch": 0.17552279739458349, "percentage": 17.58, "elapsed_time": "0:40:20", "remaining_time": "3:09:05"}
+{"current_steps": 33, "total_steps": 182, "loss": 0.7394, "accuracy": 0.4453125, "lr": 9.819081075450014e-06, "epoch": 0.1810078848131642, "percentage": 18.13, "elapsed_time": "0:41:32", "remaining_time": "3:07:35"}
+{"current_steps": 34, "total_steps": 182, "loss": 0.7765, "accuracy": 0.3671875, "lr": 9.792499064044343e-06, "epoch": 0.18649297223174494, "percentage": 18.68, "elapsed_time": "0:42:49", "remaining_time": "3:06:26"}
+{"current_steps": 35, "total_steps": 182, "loss": 0.7545, "accuracy": 0.390625, "lr": 9.764136834878987e-06, "epoch": 0.1919780596503257, "percentage": 19.23, "elapsed_time": "0:44:06", "remaining_time": "3:05:14"}
+{"current_steps": 36, "total_steps": 182, "loss": 0.8155, "accuracy": 0.375, "lr": 9.734004923364258e-06, "epoch": 0.19746314706890641, "percentage": 19.78, "elapsed_time": "0:45:26", "remaining_time": "3:04:18"}
+{"current_steps": 37, "total_steps": 182, "loss": 0.7927, "accuracy": 0.375, "lr": 9.702114522275216e-06, "epoch": 0.20294823448748714, "percentage": 20.33, "elapsed_time": "0:46:41", "remaining_time": "3:03:00"}
+{"current_steps": 38, "total_steps": 182, "loss": 0.7763, "accuracy": 0.4375, "lr": 9.668477477594021e-06, "epoch": 0.20843332190606786, "percentage": 20.88, "elapsed_time": "0:47:53", "remaining_time": "3:01:29"}
+{"current_steps": 39, "total_steps": 182, "loss": 0.7526, "accuracy": 0.3515625, "lr": 9.633106284109612e-06, "epoch": 0.21391840932464862, "percentage": 21.43, "elapsed_time": "0:49:12", "remaining_time": "3:00:24"}
+{"current_steps": 40, "total_steps": 182, "loss": 0.8228, "accuracy": 0.3125, "lr": 9.596014080776424e-06, "epoch": 0.21940349674322934, "percentage": 21.98, "elapsed_time": "0:50:28", "remaining_time": "2:59:11"}
+{"current_steps": 41, "total_steps": 182, "loss": 0.7528, "accuracy": 0.3515625, "lr": 9.557214645833792e-06, "epoch": 0.22488858416181007, "percentage": 22.53, "elapsed_time": "0:51:43", "remaining_time": "2:57:54"}
+{"current_steps": 42, "total_steps": 182, "loss": 0.846, "accuracy": 0.25, "lr": 9.516722391687903e-06, "epoch": 0.23037367158039082, "percentage": 23.08, "elapsed_time": "0:53:01", "remaining_time": "2:56:44"}
+{"current_steps": 43, "total_steps": 182, "loss": 0.736, "accuracy": 0.375, "lr": 9.474552359558167e-06, "epoch": 0.23585875899897155, "percentage": 23.63, "elapsed_time": "0:54:14", "remaining_time": "2:55:20"}
+{"current_steps": 44, "total_steps": 182, "loss": 0.7783, "accuracy": 0.375, "lr": 9.43072021389003e-06, "epoch": 0.24134384641755227, "percentage": 24.18, "elapsed_time": "0:55:27", "remaining_time": "2:53:55"}
+{"current_steps": 45, "total_steps": 182, "loss": 0.7556, "accuracy": 0.40625, "lr": 9.385242236536259e-06, "epoch": 0.24682893383613302, "percentage": 24.73, "elapsed_time": "0:56:43", "remaining_time": "2:52:40"}
+{"current_steps": 46, "total_steps": 182, "loss": 0.7338, "accuracy": 0.359375, "lr": 9.338135320708912e-06, "epoch": 0.25231402125471375, "percentage": 25.27, "elapsed_time": "0:57:55", "remaining_time": "2:51:15"}
+{"current_steps": 47, "total_steps": 182, "loss": 0.7248, "accuracy": 0.3359375, "lr": 9.289416964704186e-06, "epoch": 0.2577991086732945, "percentage": 25.82, "elapsed_time": "0:59:19", "remaining_time": "2:50:24"}
+{"current_steps": 48, "total_steps": 182, "loss": 0.692, "accuracy": 0.40625, "lr": 9.239105265402525e-06, "epoch": 0.2632841960918752, "percentage": 26.37, "elapsed_time": "1:00:33", "remaining_time": "2:49:02"}
+{"current_steps": 49, "total_steps": 182, "loss": 0.7632, "accuracy": 0.34375, "lr": 9.187218911546363e-06, "epoch": 0.2687692835104559, "percentage": 26.92, "elapsed_time": "1:01:47", "remaining_time": "2:47:42"}
+{"current_steps": 50, "total_steps": 182, "loss": 0.7371, "accuracy": 0.4453125, "lr": 9.133777176798013e-06, "epoch": 0.2742543709290367, "percentage": 27.47, "elapsed_time": "1:03:01", "remaining_time": "2:46:23"}
+{"current_steps": 51, "total_steps": 182, "loss": 0.6819, "accuracy": 0.40625, "lr": 9.078799912580305e-06, "epoch": 0.27973945834761743, "percentage": 28.02, "elapsed_time": "1:04:16", "remaining_time": "2:45:06"}
+{"current_steps": 52, "total_steps": 182, "loss": 0.7754, "accuracy": 0.34375, "lr": 9.022307540702576e-06, "epoch": 0.28522454576619816, "percentage": 28.57, "elapsed_time": "1:05:28", "remaining_time": "2:43:40"}
+{"current_steps": 53, "total_steps": 182, "loss": 0.7415, "accuracy": 0.4140625, "lr": 8.964321045774808e-06, "epoch": 0.2907096331847789, "percentage": 29.12, "elapsed_time": "1:06:40", "remaining_time": "2:42:16"}
+{"current_steps": 54, "total_steps": 182, "loss": 0.7525, "accuracy": 0.390625, "lr": 8.904861967412702e-06, "epoch": 0.2961947206033596, "percentage": 29.67, "elapsed_time": "1:07:54", "remaining_time": "2:40:58"}
+{"current_steps": 55, "total_steps": 182, "loss": 0.8548, "accuracy": 0.40625, "lr": 8.843952392236595e-06, "epoch": 0.30167980802194033, "percentage": 30.22, "elapsed_time": "1:09:09", "remaining_time": "2:39:40"}
+{"current_steps": 56, "total_steps": 182, "loss": 0.7044, "accuracy": 0.421875, "lr": 8.78161494566717e-06, "epoch": 0.30716489544052106, "percentage": 30.77, "elapsed_time": "1:10:25", "remaining_time": "2:38:26"}
+{"current_steps": 57, "total_steps": 182, "loss": 0.7258, "accuracy": 0.453125, "lr": 8.717872783521048e-06, "epoch": 0.31264998285910184, "percentage": 31.32, "elapsed_time": "1:11:42", "remaining_time": "2:37:16"}
+{"current_steps": 58, "total_steps": 182, "loss": 0.7223, "accuracy": 0.4453125, "lr": 8.65274958340934e-06, "epoch": 0.31813507027768256, "percentage": 31.87, "elapsed_time": "1:12:56", "remaining_time": "2:35:55"}
+{"current_steps": 59, "total_steps": 182, "loss": 0.7387, "accuracy": 0.4140625, "lr": 8.586269535942386e-06, "epoch": 0.3236201576962633, "percentage": 32.42, "elapsed_time": "1:14:08", "remaining_time": "2:34:33"}
+{"current_steps": 60, "total_steps": 182, "loss": 0.7221, "accuracy": 0.4609375, "lr": 8.518457335743927e-06, "epoch": 0.329105245114844, "percentage": 32.97, "elapsed_time": "1:15:27", "remaining_time": "2:33:25"}
+{"current_steps": 61, "total_steps": 182, "loss": 0.7851, "accuracy": 0.3828125, "lr": 8.44933817227806e-06, "epoch": 0.33459033253342474, "percentage": 33.52, "elapsed_time": "1:16:41", "remaining_time": "2:32:07"}
+{"current_steps": 62, "total_steps": 182, "loss": 0.7209, "accuracy": 0.4609375, "lr": 8.378937720492384e-06, "epoch": 0.34007541995200546, "percentage": 34.07, "elapsed_time": "1:17:59", "remaining_time": "2:30:57"}
+{"current_steps": 63, "total_steps": 182, "loss": 0.7043, "accuracy": 0.3984375, "lr": 8.307282131280805e-06, "epoch": 0.34556050737058625, "percentage": 34.62, "elapsed_time": "1:19:14", "remaining_time": "2:29:41"}
+{"current_steps": 64, "total_steps": 182, "loss": 0.718, "accuracy": 0.4609375, "lr": 8.234398021769541e-06, "epoch": 0.35104559478916697, "percentage": 35.16, "elapsed_time": "1:20:31", "remaining_time": "2:28:28"}
+{"current_steps": 65, "total_steps": 182, "loss": 0.7207, "accuracy": 0.4609375, "lr": 8.160312465429952e-06, "epoch": 0.3565306822077477, "percentage": 35.71, "elapsed_time": "1:21:53", "remaining_time": "2:27:23"}
+{"current_steps": 66, "total_steps": 182, "loss": 0.7019, "accuracy": 0.3984375, "lr": 8.085052982021849e-06, "epoch": 0.3620157696263284, "percentage": 36.26, "elapsed_time": "1:23:07", "remaining_time": "2:26:05"}
+{"current_steps": 67, "total_steps": 182, "loss": 0.7664, "accuracy": 0.4609375, "lr": 8.008647527371022e-06, "epoch": 0.36750085704490915, "percentage": 36.81, "elapsed_time": "1:24:18", "remaining_time": "2:24:42"}
+{"current_steps": 68, "total_steps": 182, "loss": 0.7721, "accuracy": 0.359375, "lr": 7.931124482984802e-06, "epoch": 0.37298594446348987, "percentage": 37.36, "elapsed_time": "1:25:34", "remaining_time": "2:23:27"}
+{"current_steps": 69, "total_steps": 182, "loss": 0.7495, "accuracy": 0.4609375, "lr": 7.85251264550948e-06, "epoch": 0.3784710318820706, "percentage": 37.91, "elapsed_time": "1:26:48", "remaining_time": "2:22:10"}
+{"current_steps": 70, "total_steps": 182, "loss": 0.7216, "accuracy": 0.4609375, "lr": 7.772841216033534e-06, "epoch": 0.3839561193006514, "percentage": 38.46, "elapsed_time": "1:28:02", "remaining_time": "2:20:52"}
+{"current_steps": 71, "total_steps": 182, "loss": 0.7136, "accuracy": 0.375, "lr": 7.692139789240611e-06, "epoch": 0.3894412067192321, "percentage": 39.01, "elapsed_time": "1:29:13", "remaining_time": "2:19:29"}
+{"current_steps": 72, "total_steps": 182, "loss": 0.7414, "accuracy": 0.421875, "lr": 7.61043834241632e-06, "epoch": 0.39492629413781283, "percentage": 39.56, "elapsed_time": "1:30:27", "remaining_time": "2:18:11"}
+{"current_steps": 73, "total_steps": 182, "loss": 0.7309, "accuracy": 0.4296875, "lr": 7.527767224312883e-06, "epoch": 0.40041138155639355, "percentage": 40.11, "elapsed_time": "1:31:41", "remaining_time": "2:16:54"}
+{"current_steps": 74, "total_steps": 182, "loss": 0.7423, "accuracy": 0.390625, "lr": 7.44415714387582e-06, "epoch": 0.4058964689749743, "percentage": 40.66, "elapsed_time": "1:32:54", "remaining_time": "2:15:36"}
+{"current_steps": 75, "total_steps": 182, "loss": 0.7437, "accuracy": 0.4375, "lr": 7.359639158836828e-06, "epoch": 0.411381556393555, "percentage": 41.21, "elapsed_time": "1:34:13", "remaining_time": "2:14:26"}
+{"current_steps": 76, "total_steps": 182, "loss": 0.7396, "accuracy": 0.3359375, "lr": 7.2742446641770985e-06, "epoch": 0.41686664381213573, "percentage": 41.76, "elapsed_time": "1:35:29", "remaining_time": "2:13:11"}
+{"current_steps": 77, "total_steps": 182, "loss": 0.6869, "accuracy": 0.4765625, "lr": 7.188005380465365e-06, "epoch": 0.4223517312307165, "percentage": 42.31, "elapsed_time": "1:36:46", "remaining_time": "2:11:57"}
+{"current_steps": 78, "total_steps": 182, "loss": 0.7559, "accuracy": 0.390625, "lr": 7.10095334207501e-06, "epoch": 0.42783681864929723, "percentage": 42.86, "elapsed_time": "1:38:02", "remaining_time": "2:10:42"}
+{"current_steps": 79, "total_steps": 182, "loss": 0.6881, "accuracy": 0.453125, "lr": 7.013120885284599e-06, "epoch": 0.43332190606787796, "percentage": 43.41, "elapsed_time": "1:39:16", "remaining_time": "2:09:26"}
+{"current_steps": 80, "total_steps": 182, "loss": 0.7421, "accuracy": 0.3515625, "lr": 6.924540636266272e-06, "epoch": 0.4388069934864587, "percentage": 43.96, "elapsed_time": "1:40:30", "remaining_time": "2:08:08"}
+{"current_steps": 81, "total_steps": 182, "loss": 0.7341, "accuracy": 0.4140625, "lr": 6.835245498966461e-06, "epoch": 0.4442920809050394, "percentage": 44.51, "elapsed_time": "1:41:51", "remaining_time": "2:07:01"}
+{"current_steps": 82, "total_steps": 182, "loss": 0.73, "accuracy": 0.4140625, "lr": 6.7452686428834045e-06, "epoch": 0.44977716832362014, "percentage": 45.05, "elapsed_time": "1:43:06", "remaining_time": "2:05:44"}
+{"current_steps": 83, "total_steps": 182, "loss": 0.7136, "accuracy": 0.4375, "lr": 6.654643490746042e-06, "epoch": 0.4552622557422009, "percentage": 45.6, "elapsed_time": "1:44:22", "remaining_time": "2:04:30"}
+{"current_steps": 84, "total_steps": 182, "loss": 0.7196, "accuracy": 0.46875, "lr": 6.563403706098833e-06, "epoch": 0.46074734316078164, "percentage": 46.15, "elapsed_time": "1:45:36", "remaining_time": "2:03:12"}
+{"current_steps": 85, "total_steps": 182, "loss": 0.726, "accuracy": 0.40625, "lr": 6.471583180797121e-06, "epoch": 0.46623243057936237, "percentage": 46.7, "elapsed_time": "1:46:52", "remaining_time": "2:01:58"}
+{"current_steps": 86, "total_steps": 182, "loss": 0.7491, "accuracy": 0.453125, "lr": 6.379216022417695e-06, "epoch": 0.4717175179979431, "percentage": 47.25, "elapsed_time": "1:48:12", "remaining_time": "2:00:47"}
+{"current_steps": 87, "total_steps": 182, "loss": 0.7141, "accuracy": 0.4765625, "lr": 6.286336541589224e-06, "epoch": 0.4772026054165238, "percentage": 47.8, "elapsed_time": "1:49:26", "remaining_time": "1:59:30"}
+{"current_steps": 88, "total_steps": 182, "loss": 0.7336, "accuracy": 0.390625, "lr": 6.192979239247243e-06, "epoch": 0.48268769283510454, "percentage": 48.35, "elapsed_time": "1:50:40", "remaining_time": "1:58:13"}
+{"current_steps": 89, "total_steps": 182, "loss": 0.7111, "accuracy": 0.5078125, "lr": 6.099178793818479e-06, "epoch": 0.48817278025368527, "percentage": 48.9, "elapsed_time": "1:51:55", "remaining_time": "1:56:57"}
+{"current_steps": 90, "total_steps": 182, "loss": 0.7411, "accuracy": 0.390625, "lr": 6.0049700483392256e-06, "epoch": 0.49365786767226605, "percentage": 49.45, "elapsed_time": "1:53:07", "remaining_time": "1:55:38"}
+{"current_steps": 91, "total_steps": 182, "loss": 0.7631, "accuracy": 0.3984375, "lr": 5.910387997512573e-06, "epoch": 0.4991429550908468, "percentage": 50.0, "elapsed_time": "1:54:19", "remaining_time": "1:54:19"}
+{"current_steps": 92, "total_steps": 182, "loss": 0.6749, "accuracy": 0.484375, "lr": 5.815467774709314e-06, "epoch": 0.5046280425094275, "percentage": 50.55, "elapsed_time": "1:55:36", "remaining_time": "1:53:06"}
+{"current_steps": 93, "total_steps": 182, "loss": 0.6945, "accuracy": 0.5078125, "lr": 5.7202446389173225e-06, "epoch": 0.5101131299280083, "percentage": 51.1, "elapsed_time": "1:56:51", "remaining_time": "1:51:50"}
+{"current_steps": 94, "total_steps": 182, "loss": 0.7635, "accuracy": 0.3359375, "lr": 5.624753961644281e-06, "epoch": 0.515598217346589, "percentage": 51.65, "elapsed_time": "1:58:00", "remaining_time": "1:50:28"}
+{"current_steps": 95, "total_steps": 182, "loss": 0.7268, "accuracy": 0.3984375, "lr": 5.529031213778615e-06, "epoch": 0.5210833047651697, "percentage": 52.2, "elapsed_time": "1:59:14", "remaining_time": "1:49:12"}
+{"current_steps": 96, "total_steps": 182, "loss": 0.6895, "accuracy": 0.5234375, "lr": 5.433111952413496e-06, "epoch": 0.5265683921837504, "percentage": 52.75, "elapsed_time": "2:00:30", "remaining_time": "1:47:57"}
+{"current_steps": 97, "total_steps": 182, "loss": 0.7607, "accuracy": 0.390625, "lr": 5.3370318076388405e-06, "epoch": 0.5320534796023312, "percentage": 53.3, "elapsed_time": "2:01:44", "remaining_time": "1:46:41"}
+{"current_steps": 98, "total_steps": 182, "loss": 0.7188, "accuracy": 0.46875, "lr": 5.240826469306187e-06, "epoch": 0.5375385670209119, "percentage": 53.85, "elapsed_time": "2:03:04", "remaining_time": "1:45:29"}
+{"current_steps": 99, "total_steps": 182, "loss": 0.7596, "accuracy": 0.3984375, "lr": 5.144531673771364e-06, "epoch": 0.5430236544394926, "percentage": 54.4, "elapsed_time": "2:04:23", "remaining_time": "1:44:17"}
+{"current_steps": 100, "total_steps": 182, "loss": 0.7085, "accuracy": 0.5, "lr": 5.048183190619904e-06, "epoch": 0.5485087418580734, "percentage": 54.95, "elapsed_time": "2:05:41", "remaining_time": "1:43:04"}
+{"current_steps": 101, "total_steps": 182, "loss": 0.6656, "accuracy": 0.4765625, "lr": 4.951816809380098e-06, "epoch": 0.5539938292766541, "percentage": 55.49, "elapsed_time": "2:06:54", "remaining_time": "1:41:46"}
+{"current_steps": 102, "total_steps": 182, "loss": 0.7458, "accuracy": 0.40625, "lr": 4.855468326228638e-06, "epoch": 0.5594789166952349, "percentage": 56.04, "elapsed_time": "2:08:09", "remaining_time": "1:40:30"}
+{"current_steps": 103, "total_steps": 182, "loss": 0.6848, "accuracy": 0.4140625, "lr": 4.7591735306938144e-06, "epoch": 0.5649640041138155, "percentage": 56.59, "elapsed_time": "2:09:22", "remaining_time": "1:39:13"}
+{"current_steps": 104, "total_steps": 182, "loss": 0.6869, "accuracy": 0.4453125, "lr": 4.662968192361161e-06, "epoch": 0.5704490915323963, "percentage": 57.14, "elapsed_time": "2:10:37", "remaining_time": "1:37:57"}
+{"current_steps": 105, "total_steps": 182, "loss": 0.6716, "accuracy": 0.46875, "lr": 4.5668880475865074e-06, "epoch": 0.575934178950977, "percentage": 57.69, "elapsed_time": "2:11:47", "remaining_time": "1:36:38"}
+{"current_steps": 106, "total_steps": 182, "loss": 0.7281, "accuracy": 0.4765625, "lr": 4.4709687862213866e-06, "epoch": 0.5814192663695578, "percentage": 58.24, "elapsed_time": "2:13:03", "remaining_time": "1:35:24"}
+{"current_steps": 107, "total_steps": 182, "loss": 0.7412, "accuracy": 0.390625, "lr": 4.3752460383557195e-06, "epoch": 0.5869043537881385, "percentage": 58.79, "elapsed_time": "2:14:17", "remaining_time": "1:34:07"}
+{"current_steps": 108, "total_steps": 182, "loss": 0.6546, "accuracy": 0.453125, "lr": 4.27975536108268e-06, "epoch": 0.5923894412067192, "percentage": 59.34, "elapsed_time": "2:15:30", "remaining_time": "1:32:50"}
+{"current_steps": 109, "total_steps": 182, "loss": 0.7067, "accuracy": 0.4921875, "lr": 4.184532225290687e-06, "epoch": 0.5978745286253, "percentage": 59.89, "elapsed_time": "2:16:45", "remaining_time": "1:31:35"}
+{"current_steps": 110, "total_steps": 182, "loss": 0.6908, "accuracy": 0.515625, "lr": 4.089612002487428e-06, "epoch": 0.6033596160438807, "percentage": 60.44, "elapsed_time": "2:18:00", "remaining_time": "1:30:19"}
+{"current_steps": 111, "total_steps": 182, "loss": 0.7648, "accuracy": 0.3984375, "lr": 3.995029951660777e-06, "epoch": 0.6088447034624614, "percentage": 60.99, "elapsed_time": "2:19:13", "remaining_time": "1:29:03"}
+{"current_steps": 112, "total_steps": 182, "loss": 0.7087, "accuracy": 0.5078125, "lr": 3.900821206181521e-06, "epoch": 0.6143297908810421, "percentage": 61.54, "elapsed_time": "2:20:27", "remaining_time": "1:27:47"}
+{"current_steps": 113, "total_steps": 182, "loss": 0.7676, "accuracy": 0.390625, "lr": 3.8070207607527587e-06, "epoch": 0.6198148782996229, "percentage": 62.09, "elapsed_time": "2:21:38", "remaining_time": "1:26:29"}
+{"current_steps": 114, "total_steps": 182, "loss": 0.6863, "accuracy": 0.453125, "lr": 3.7136634584107787e-06, "epoch": 0.6252999657182037, "percentage": 62.64, "elapsed_time": "2:22:48", "remaining_time": "1:25:11"}
+{"current_steps": 115, "total_steps": 182, "loss": 0.6943, "accuracy": 0.421875, "lr": 3.620783977582305e-06, "epoch": 0.6307850531367843, "percentage": 63.19, "elapsed_time": "2:24:04", "remaining_time": "1:23:56"}
+{"current_steps": 116, "total_steps": 182, "loss": 0.7016, "accuracy": 0.390625, "lr": 3.528416819202881e-06, "epoch": 0.6362701405553651, "percentage": 63.74, "elapsed_time": "2:25:18", "remaining_time": "1:22:40"}
+{"current_steps": 117, "total_steps": 182, "loss": 0.7539, "accuracy": 0.4140625, "lr": 3.43659629390117e-06, "epoch": 0.6417552279739458, "percentage": 64.29, "elapsed_time": "2:26:33", "remaining_time": "1:21:25"}
+{"current_steps": 118, "total_steps": 182, "loss": 0.694, "accuracy": 0.4296875, "lr": 3.3453565092539586e-06, "epoch": 0.6472403153925266, "percentage": 64.84, "elapsed_time": "2:27:50", "remaining_time": "1:20:11"}
+{"current_steps": 119, "total_steps": 182, "loss": 0.6878, "accuracy": 0.4375, "lr": 3.254731357116597e-06, "epoch": 0.6527254028111072, "percentage": 65.38, "elapsed_time": "2:29:09", "remaining_time": "1:18:57"}
+{"current_steps": 120, "total_steps": 182, "loss": 0.614, "accuracy": 0.5, "lr": 3.16475450103354e-06, "epoch": 0.658210490229688, "percentage": 65.93, "elapsed_time": "2:30:23", "remaining_time": "1:17:42"}
+{"current_steps": 121, "total_steps": 182, "loss": 0.6938, "accuracy": 0.3828125, "lr": 3.0754593637337276e-06, "epoch": 0.6636955776482688, "percentage": 66.48, "elapsed_time": "2:31:35", "remaining_time": "1:16:25"}
+{"current_steps": 122, "total_steps": 182, "loss": 0.6794, "accuracy": 0.453125, "lr": 2.986879114715403e-06, "epoch": 0.6691806650668495, "percentage": 67.03, "elapsed_time": "2:32:47", "remaining_time": "1:15:08"}
+{"current_steps": 123, "total_steps": 182, "loss": 0.6844, "accuracy": 0.4375, "lr": 2.899046657924992e-06, "epoch": 0.6746657524854303, "percentage": 67.58, "elapsed_time": "2:34:04", "remaining_time": "1:13:54"}
+{"current_steps": 124, "total_steps": 182, "loss": 0.6998, "accuracy": 0.515625, "lr": 2.8119946195346375e-06, "epoch": 0.6801508399040109, "percentage": 68.13, "elapsed_time": "2:35:20", "remaining_time": "1:12:39"}
+{"current_steps": 125, "total_steps": 182, "loss": 0.7058, "accuracy": 0.484375, "lr": 2.725755335822903e-06, "epoch": 0.6856359273225917, "percentage": 68.68, "elapsed_time": "2:36:37", "remaining_time": "1:11:25"}
+{"current_steps": 126, "total_steps": 182, "loss": 0.735, "accuracy": 0.3671875, "lr": 2.6403608411631744e-06, "epoch": 0.6911210147411725, "percentage": 69.23, "elapsed_time": "2:37:50", "remaining_time": "1:10:09"}
+{"current_steps": 127, "total_steps": 182, "loss": 0.678, "accuracy": 0.5, "lr": 2.555842856124182e-06, "epoch": 0.6966061021597532, "percentage": 69.78, "elapsed_time": "2:39:04", "remaining_time": "1:08:53"}
+{"current_steps": 128, "total_steps": 182, "loss": 0.6958, "accuracy": 0.4375, "lr": 2.472232775687119e-06, "epoch": 0.7020911895783339, "percentage": 70.33, "elapsed_time": "2:40:23", "remaining_time": "1:07:39"}
+{"current_steps": 129, "total_steps": 182, "loss": 0.7323, "accuracy": 0.3828125, "lr": 2.389561657583681e-06, "epoch": 0.7075762769969146, "percentage": 70.88, "elapsed_time": "2:41:40", "remaining_time": "1:06:25"}
+{"current_steps": 130, "total_steps": 182, "loss": 0.7064, "accuracy": 0.4453125, "lr": 2.30786021075939e-06, "epoch": 0.7130613644154954, "percentage": 71.43, "elapsed_time": "2:42:53", "remaining_time": "1:05:09"}
+{"current_steps": 131, "total_steps": 182, "loss": 0.7054, "accuracy": 0.453125, "lr": 2.2271587839664673e-06, "epoch": 0.7185464518340761, "percentage": 71.98, "elapsed_time": "2:44:10", "remaining_time": "1:03:54"}
+{"current_steps": 132, "total_steps": 182, "loss": 0.7147, "accuracy": 0.4765625, "lr": 2.1474873544905204e-06, "epoch": 0.7240315392526568, "percentage": 72.53, "elapsed_time": "2:45:24", "remaining_time": "1:02:39"}
+{"current_steps": 133, "total_steps": 182, "loss": 0.6755, "accuracy": 0.453125, "lr": 2.0688755170152e-06, "epoch": 0.7295166266712376, "percentage": 73.08, "elapsed_time": "2:46:35", "remaining_time": "1:01:22"}
+{"current_steps": 134, "total_steps": 182, "loss": 0.6632, "accuracy": 0.484375, "lr": 1.9913524726289784e-06, "epoch": 0.7350017140898183, "percentage": 73.63, "elapsed_time": "2:47:46", "remaining_time": "1:00:06"}
+{"current_steps": 135, "total_steps": 182, "loss": 0.6827, "accuracy": 0.453125, "lr": 1.914947017978153e-06, "epoch": 0.7404868015083991, "percentage": 74.18, "elapsed_time": "2:49:03", "remaining_time": "0:58:51"}
+{"current_steps": 136, "total_steps": 182, "loss": 0.7068, "accuracy": 0.453125, "lr": 1.8396875345700498e-06, "epoch": 0.7459718889269797, "percentage": 74.73, "elapsed_time": "2:50:19", "remaining_time": "0:57:36"}
+{"current_steps": 137, "total_steps": 182, "loss": 0.675, "accuracy": 0.4375, "lr": 1.7656019782304602e-06, "epoch": 0.7514569763455605, "percentage": 75.27, "elapsed_time": "2:51:33", "remaining_time": "0:56:21"}
+{"current_steps": 138, "total_steps": 182, "loss": 0.6753, "accuracy": 0.4140625, "lr": 1.6927178687191953e-06, "epoch": 0.7569420637641412, "percentage": 75.82, "elapsed_time": "2:52:44", "remaining_time": "0:55:04"}
+{"current_steps": 139, "total_steps": 182, "loss": 0.6671, "accuracy": 0.4921875, "lr": 1.621062279507617e-06, "epoch": 0.762427151182722, "percentage": 76.37, "elapsed_time": "2:53:57", "remaining_time": "0:53:48"}
+{"current_steps": 140, "total_steps": 182, "loss": 0.6734, "accuracy": 0.484375, "lr": 1.550661827721941e-06, "epoch": 0.7679122386013028, "percentage": 76.92, "elapsed_time": "2:55:13", "remaining_time": "0:52:34"}
+{"current_steps": 141, "total_steps": 182, "loss": 0.6475, "accuracy": 0.46875, "lr": 1.4815426642560753e-06, "epoch": 0.7733973260198834, "percentage": 77.47, "elapsed_time": "2:56:29", "remaining_time": "0:51:19"}
+{"current_steps": 142, "total_steps": 182, "loss": 0.704, "accuracy": 0.4453125, "lr": 1.4137304640576161e-06, "epoch": 0.7788824134384642, "percentage": 78.02, "elapsed_time": "2:57:42", "remaining_time": "0:50:03"}
+{"current_steps": 143, "total_steps": 182, "loss": 0.6721, "accuracy": 0.40625, "lr": 1.3472504165906614e-06, "epoch": 0.7843675008570449, "percentage": 78.57, "elapsed_time": "2:58:58", "remaining_time": "0:48:48"}
+{"current_steps": 144, "total_steps": 182, "loss": 0.6788, "accuracy": 0.453125, "lr": 1.2821272164789544e-06, "epoch": 0.7898525882756257, "percentage": 79.12, "elapsed_time": "3:00:11", "remaining_time": "0:47:32"}
+{"current_steps": 145, "total_steps": 182, "loss": 0.6739, "accuracy": 0.46875, "lr": 1.2183850543328313e-06, "epoch": 0.7953376756942063, "percentage": 79.67, "elapsed_time": "3:01:24", "remaining_time": "0:46:17"}
+{"current_steps": 146, "total_steps": 182, "loss": 0.7249, "accuracy": 0.4140625, "lr": 1.156047607763407e-06, "epoch": 0.8008227631127871, "percentage": 80.22, "elapsed_time": "3:02:41", "remaining_time": "0:45:02"}
+{"current_steps": 147, "total_steps": 182, "loss": 0.6703, "accuracy": 0.4453125, "lr": 1.095138032587298e-06, "epoch": 0.8063078505313679, "percentage": 80.77, "elapsed_time": "3:03:56", "remaining_time": "0:43:47"}
+{"current_steps": 148, "total_steps": 182, "loss": 0.6999, "accuracy": 0.515625, "lr": 1.0356789542251939e-06, "epoch": 0.8117929379499486, "percentage": 81.32, "elapsed_time": "3:05:13", "remaining_time": "0:42:33"}
+{"current_steps": 149, "total_steps": 182, "loss": 0.7172, "accuracy": 0.40625, "lr": 9.776924592974257e-07, "epoch": 0.8172780253685293, "percentage": 81.87, "elapsed_time": "3:06:28", "remaining_time": "0:41:17"}
+{"current_steps": 150, "total_steps": 182, "loss": 0.6697, "accuracy": 0.5078125, "lr": 9.212000874196953e-07, "epoch": 0.82276311278711, "percentage": 82.42, "elapsed_time": "3:07:45", "remaining_time": "0:40:03"}
+{"current_steps": 151, "total_steps": 182, "loss": 0.7277, "accuracy": 0.3984375, "lr": 8.662228232019876e-07, "epoch": 0.8282482002056908, "percentage": 82.97, "elapsed_time": "3:09:07", "remaining_time": "0:38:49"}
+{"current_steps": 152, "total_steps": 182, "loss": 0.7088, "accuracy": 0.421875, "lr": 8.127810884536402e-07, "epoch": 0.8337332876242715, "percentage": 83.52, "elapsed_time": "3:10:21", "remaining_time": "0:37:34"}
+{"current_steps": 153, "total_steps": 182, "loss": 0.6995, "accuracy": 0.3671875, "lr": 7.60894734597476e-07, "epoch": 0.8392183750428522, "percentage": 84.07, "elapsed_time": "3:11:36", "remaining_time": "0:36:19"}
+{"current_steps": 154, "total_steps": 182, "loss": 0.7351, "accuracy": 0.4375, "lr": 7.105830352958143e-07, "epoch": 0.844703462461433, "percentage": 84.62, "elapsed_time": "3:12:51", "remaining_time": "0:35:03"}
+{"current_steps": 155, "total_steps": 182, "loss": 0.6505, "accuracy": 0.5234375, "lr": 6.618646792910893e-07, "epoch": 0.8501885498800137, "percentage": 85.16, "elapsed_time": "3:14:04", "remaining_time": "0:33:48"}
+{"current_steps": 156, "total_steps": 182, "loss": 0.6828, "accuracy": 0.4296875, "lr": 6.147577634637413e-07, "epoch": 0.8556736372985945, "percentage": 85.71, "elapsed_time": "3:15:18", "remaining_time": "0:32:33"}
+{"current_steps": 157, "total_steps": 182, "loss": 0.6692, "accuracy": 0.4453125, "lr": 5.692797861099719e-07, "epoch": 0.8611587247171751, "percentage": 86.26, "elapsed_time": "3:16:35", "remaining_time": "0:31:18"}
+{"current_steps": 158, "total_steps": 182, "loss": 0.6559, "accuracy": 0.4921875, "lr": 5.254476404418341e-07, "epoch": 0.8666438121357559, "percentage": 86.81, "elapsed_time": "3:17:46", "remaining_time": "0:30:02"}
+{"current_steps": 159, "total_steps": 182, "loss": 0.6729, "accuracy": 0.484375, "lr": 4.832776083120983e-07, "epoch": 0.8721288995543367, "percentage": 87.36, "elapsed_time": "3:19:00", "remaining_time": "0:28:47"}
+{"current_steps": 160, "total_steps": 182, "loss": 0.6734, "accuracy": 0.4296875, "lr": 4.4278535416620914e-07, "epoch": 0.8776139869729174, "percentage": 87.91, "elapsed_time": "3:20:11", "remaining_time": "0:27:31"}
+{"current_steps": 161, "total_steps": 182, "loss": 0.6609, "accuracy": 0.484375, "lr": 4.0398591922357787e-07, "epoch": 0.8830990743914982, "percentage": 88.46, "elapsed_time": "3:21:24", "remaining_time": "0:26:16"}
+{"current_steps": 162, "total_steps": 182, "loss": 0.7074, "accuracy": 0.46875, "lr": 3.6689371589039013e-07, "epoch": 0.8885841618100788, "percentage": 89.01, "elapsed_time": "3:22:35", "remaining_time": "0:25:00"}
+{"current_steps": 163, "total_steps": 182, "loss": 0.7038, "accuracy": 0.453125, "lr": 3.315225224059809e-07, "epoch": 0.8940692492286596, "percentage": 89.56, "elapsed_time": "3:23:48", "remaining_time": "0:23:45"}
+{"current_steps": 164, "total_steps": 182, "loss": 0.7124, "accuracy": 0.4375, "lr": 2.9788547772478416e-07, "epoch": 0.8995543366472403, "percentage": 90.11, "elapsed_time": "3:25:00", "remaining_time": "0:22:30"}
+{"current_steps": 165, "total_steps": 182, "loss": 0.7082, "accuracy": 0.4453125, "lr": 2.6599507663574387e-07, "epoch": 0.905039424065821, "percentage": 90.66, "elapsed_time": "3:26:13", "remaining_time": "0:21:14"}
+{"current_steps": 166, "total_steps": 182, "loss": 0.6543, "accuracy": 0.5, "lr": 2.3586316512101416e-07, "epoch": 0.9105245114844018, "percentage": 91.21, "elapsed_time": "3:27:30", "remaining_time": "0:20:00"}
+{"current_steps": 167, "total_steps": 182, "loss": 0.681, "accuracy": 0.46875, "lr": 2.0750093595565735e-07, "epoch": 0.9160095989029825, "percentage": 91.76, "elapsed_time": "3:28:44", "remaining_time": "0:18:44"}
+{"current_steps": 168, "total_steps": 182, "loss": 0.7125, "accuracy": 0.4140625, "lr": 1.8091892454998595e-07, "epoch": 0.9214946863215633, "percentage": 92.31, "elapsed_time": "3:30:01", "remaining_time": "0:17:30"}
+{"current_steps": 169, "total_steps": 182, "loss": 0.7055, "accuracy": 0.5078125, "lr": 1.561270050360897e-07, "epoch": 0.926979773740144, "percentage": 92.86, "elapsed_time": "3:31:15", "remaining_time": "0:16:15"}
+{"current_steps": 170, "total_steps": 182, "loss": 0.7325, "accuracy": 0.3984375, "lr": 1.33134386599994e-07, "epoch": 0.9324648611587247, "percentage": 93.41, "elapsed_time": "3:32:31", "remaining_time": "0:15:00"}
+{"current_steps": 171, "total_steps": 182, "loss": 0.7225, "accuracy": 0.453125, "lr": 1.1194961006082972e-07, "epoch": 0.9379499485773054, "percentage": 93.96, "elapsed_time": "3:33:47", "remaining_time": "0:13:45"}
+{"current_steps": 172, "total_steps": 182, "loss": 0.6933, "accuracy": 0.4296875, "lr": 9.258054469825972e-08, "epoch": 0.9434350359958862, "percentage": 94.51, "elapsed_time": "3:34:57", "remaining_time": "0:12:29"}
+{"current_steps": 173, "total_steps": 182, "loss": 0.7091, "accuracy": 0.3984375, "lr": 7.503438532937169e-08, "epoch": 0.948920123414467, "percentage": 95.05, "elapsed_time": "3:36:09", "remaining_time": "0:11:14"}
+{"current_steps": 174, "total_steps": 182, "loss": 0.7149, "accuracy": 0.4765625, "lr": 5.9317649636088656e-08, "epoch": 0.9544052108330476, "percentage": 95.6, "elapsed_time": "3:37:26", "remaining_time": "0:09:59"}
+{"current_steps": 175, "total_steps": 182, "loss": 0.7722, "accuracy": 0.40625, "lr": 4.543617574412185e-08, "epoch": 0.9598902982516284, "percentage": 96.15, "elapsed_time": "3:38:42", "remaining_time": "0:08:44"}
+{"current_steps": 176, "total_steps": 182, "loss": 0.6728, "accuracy": 0.484375, "lr": 3.339512005434309e-08, "epoch": 0.9653753856702091, "percentage": 96.7, "elapsed_time": "3:39:57", "remaining_time": "0:07:29"}
+{"current_steps": 177, "total_steps": 182, "loss": 0.7326, "accuracy": 0.4296875, "lr": 2.319895532739369e-08, "epoch": 0.9708604730887899, "percentage": 97.25, "elapsed_time": "3:41:14", "remaining_time": "0:06:14"}
+{"current_steps": 178, "total_steps": 182, "loss": 0.6743, "accuracy": 0.421875, "lr": 1.4851469022234e-08, "epoch": 0.9763455605073705, "percentage": 97.8, "elapsed_time": "3:42:26", "remaining_time": "0:04:59"}
+{"current_steps": 179, "total_steps": 182, "loss": 0.6574, "accuracy": 0.4375, "lr": 8.35576188926046e-09, "epoch": 0.9818306479259513, "percentage": 98.35, "elapsed_time": "3:43:45", "remaining_time": "0:03:45"}
+{"current_steps": 180, "total_steps": 182, "loss": 0.6931, "accuracy": 0.4453125, "lr": 3.71424681850141e-09, "epoch": 0.9873157353445321, "percentage": 98.9, "elapsed_time": "3:45:04", "remaining_time": "0:02:30"}
+{"current_steps": 181, "total_steps": 182, "loss": 0.6412, "accuracy": 0.546875, "lr": 9.286479433257e-10, "epoch": 0.9928008227631128, "percentage": 99.45, "elapsed_time": "3:46:20", "remaining_time": "0:01:15"}
+{"current_steps": 182, "total_steps": 182, "loss": 0.6649, "accuracy": 0.515625, "lr": 0.0, "epoch": 0.9982859101816935, "percentage": 100.0, "elapsed_time": "3:47:42", "remaining_time": "0:00:00"}
+{"current_steps": 182, "total_steps": 182, "epoch": 0.9982859101816935, "percentage": 100.0, "elapsed_time": "3:48:19", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8dfa53c711ce0c65ab65ffb3ddd32b3e5d09d1813d27f583231028b7c7745b
+size 7288