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 +1,72 @@
+---
+library_name: transformers
+license: other
+base_model: hon9kon9ize/Qwen2.5-7B-cpt
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: CantoneseLLMChat-v1.0
+  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. -->
+
+# CantoneseLLMChat-v1.0
+
+This model is a fine-tuned version of [hon9kon9ize/Qwen2.5-7B-cpt](https://huggingface.co/hon9kon9ize/Qwen2.5-7B-cpt) on the dpo_v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3170
+- Rewards/chosen: -0.7307
+- Rewards/rejected: -3.1239
+- Rewards/accuracies: 0.8464
+- Rewards/margins: 2.3931
+- Logps/rejected: -226.0627
+- Logps/chosen: -191.7517
+- Logits/rejected: -1.5777
+- Logits/chosen: -1.5363
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.0835        | 1.3495 | 500  | 0.3282          | -0.6181        | -2.8043          | 0.8494             | 2.1862          | -222.8677      | -190.6253    | -1.5563         | -1.5215       |
+| 0.1151        | 2.6991 | 1000 | 0.3186          | -0.7277        | -3.1230          | 0.8524             | 2.3953          | -226.0546      | -191.7211    | -1.5777         | -1.5363       |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.4.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.20.0

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 +1,20 @@
+{
+    "epoch": 2.9959514170040484,
+    "eval_logits/chosen": -1.5362521409988403,
+    "eval_logits/rejected": -1.577704906463623,
+    "eval_logps/chosen": -191.7516632080078,
+    "eval_logps/rejected": -226.06272888183594,
+    "eval_loss": 0.31698280572891235,
+    "eval_rewards/accuracies": 0.8463855385780334,
+    "eval_rewards/chosen": -0.7307406663894653,
+    "eval_rewards/margins": 2.3931150436401367,
+    "eval_rewards/rejected": -3.1238558292388916,
+    "eval_runtime": 23.3432,
+    "eval_samples_per_second": 14.137,
+    "eval_steps_per_second": 3.556,
+    "total_flos": 4.5615607240812134e+17,
+    "train_loss": 0.26195224279218965,
+    "train_runtime": 3105.2921,
+    "train_samples_per_second": 2.862,
+    "train_steps_per_second": 0.357
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/pj24001684/ku40000295/jc/models/Qwen2.5-7B-sft",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151644,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "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": "4.45.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.9959514170040484,
+    "eval_logits/chosen": -1.5362521409988403,
+    "eval_logits/rejected": -1.577704906463623,
+    "eval_logps/chosen": -191.7516632080078,
+    "eval_logps/rejected": -226.06272888183594,
+    "eval_loss": 0.31698280572891235,
+    "eval_rewards/accuracies": 0.8463855385780334,
+    "eval_rewards/chosen": -0.7307406663894653,
+    "eval_rewards/margins": 2.3931150436401367,
+    "eval_rewards/rejected": -3.1238558292388916,
+    "eval_runtime": 23.3432,
+    "eval_samples_per_second": 14.137,
+    "eval_steps_per_second": 3.556
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151644,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a79228c8074f3a3dfff18c2f21e5f863f95b349a31b6d21a947f4e909c6f26
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fae4dffdb2d66b9ba2236d298a23e03ab0dc4de179f81bbdec38bce9e37057e
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6709fe3e67979ee59a4f19cd0cb471837c09c2b251b88495d2d70f3a233097
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13117fa1a4e8e35f74c8c2ce20d2d07397a836866a947029f13c0f683275f2c
+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"
+  }
+}

runs/Oct03_20-25-11_c0002/events.out.tfevents.1727954738.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a31609646bf38adc0f07135ab769953cfe7eb35fd76441603e7918ef116571b0
+size 5291

runs/Oct04_23-59-22_c0002/events.out.tfevents.1728053991.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cae35c2bbdcfb64050523b2437c8ac145b578f0b424b7c9ed97cac0c7f809a8d
+size 159564

runs/Oct04_23-59-22_c0002/events.out.tfevents.1728057140.c0002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddfc616c7f4035da2eb4c5bf847858ef72a711836a2a055b30730adefb663d7
+size 780

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 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 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": 2.9959514170040484,
+    "total_flos": 4.5615607240812134e+17,
+    "train_loss": 0.26195224279218965,
+    "train_runtime": 3105.2921,
+    "train_samples_per_second": 2.862,
+    "train_steps_per_second": 0.357
+}

trainer_log.jsonl

@@ -0,0 +1,225 @@
+{"current_steps": 5, "total_steps": 1110, "loss": 0.6946, "accuracy": 0.3499999940395355, "learning_rate": 2.2522522522522524e-07, "epoch": 0.01349527665317139, "percentage": 0.45, "elapsed_time": "0:00:23", "remaining_time": "1:25:32"}
+{"current_steps": 10, "total_steps": 1110, "loss": 0.7035, "accuracy": 0.30000001192092896, "learning_rate": 4.504504504504505e-07, "epoch": 0.02699055330634278, "percentage": 0.9, "elapsed_time": "0:00:35", "remaining_time": "1:04:32"}
+{"current_steps": 15, "total_steps": 1110, "loss": 0.6966, "accuracy": 0.44999998807907104, "learning_rate": 6.756756756756758e-07, "epoch": 0.04048582995951417, "percentage": 1.35, "elapsed_time": "0:00:47", "remaining_time": "0:57:37"}
+{"current_steps": 20, "total_steps": 1110, "loss": 0.6843, "accuracy": 0.5249999761581421, "learning_rate": 9.00900900900901e-07, "epoch": 0.05398110661268556, "percentage": 1.8, "elapsed_time": "0:00:59", "remaining_time": "0:53:47"}
+{"current_steps": 25, "total_steps": 1110, "loss": 0.6911, "accuracy": 0.625, "learning_rate": 1.1261261261261262e-06, "epoch": 0.06747638326585695, "percentage": 2.25, "elapsed_time": "0:01:10", "remaining_time": "0:51:10"}
+{"current_steps": 30, "total_steps": 1110, "loss": 0.688, "accuracy": 0.4749999940395355, "learning_rate": 1.3513513513513515e-06, "epoch": 0.08097165991902834, "percentage": 2.7, "elapsed_time": "0:01:22", "remaining_time": "0:49:17"}
+{"current_steps": 35, "total_steps": 1110, "loss": 0.6811, "accuracy": 0.6499999761581421, "learning_rate": 1.5765765765765766e-06, "epoch": 0.09446693657219973, "percentage": 3.15, "elapsed_time": "0:01:33", "remaining_time": "0:47:56"}
+{"current_steps": 40, "total_steps": 1110, "loss": 0.6808, "accuracy": 0.6000000238418579, "learning_rate": 1.801801801801802e-06, "epoch": 0.10796221322537113, "percentage": 3.6, "elapsed_time": "0:01:44", "remaining_time": "0:46:32"}
+{"current_steps": 45, "total_steps": 1110, "loss": 0.6846, "accuracy": 0.550000011920929, "learning_rate": 2.0270270270270273e-06, "epoch": 0.1214574898785425, "percentage": 4.05, "elapsed_time": "0:01:55", "remaining_time": "0:45:22"}
+{"current_steps": 50, "total_steps": 1110, "loss": 0.6684, "accuracy": 0.75, "learning_rate": 2.2522522522522524e-06, "epoch": 0.1349527665317139, "percentage": 4.5, "elapsed_time": "0:02:06", "remaining_time": "0:44:46"}
+{"current_steps": 55, "total_steps": 1110, "loss": 0.6639, "accuracy": 0.75, "learning_rate": 2.4774774774774775e-06, "epoch": 0.1484480431848853, "percentage": 4.95, "elapsed_time": "0:02:18", "remaining_time": "0:44:18"}
+{"current_steps": 60, "total_steps": 1110, "loss": 0.6501, "accuracy": 0.75, "learning_rate": 2.702702702702703e-06, "epoch": 0.16194331983805668, "percentage": 5.41, "elapsed_time": "0:02:29", "remaining_time": "0:43:41"}
+{"current_steps": 65, "total_steps": 1110, "loss": 0.6846, "accuracy": 0.6499999761581421, "learning_rate": 2.927927927927928e-06, "epoch": 0.17543859649122806, "percentage": 5.86, "elapsed_time": "0:02:41", "remaining_time": "0:43:15"}
+{"current_steps": 70, "total_steps": 1110, "loss": 0.6538, "accuracy": 0.800000011920929, "learning_rate": 3.1531531531531532e-06, "epoch": 0.18893387314439947, "percentage": 6.31, "elapsed_time": "0:02:54", "remaining_time": "0:43:13"}
+{"current_steps": 75, "total_steps": 1110, "loss": 0.6316, "accuracy": 0.75, "learning_rate": 3.3783783783783788e-06, "epoch": 0.20242914979757085, "percentage": 6.76, "elapsed_time": "0:03:06", "remaining_time": "0:42:54"}
+{"current_steps": 80, "total_steps": 1110, "loss": 0.6296, "accuracy": 0.7250000238418579, "learning_rate": 3.603603603603604e-06, "epoch": 0.21592442645074225, "percentage": 7.21, "elapsed_time": "0:03:17", "remaining_time": "0:42:22"}
+{"current_steps": 85, "total_steps": 1110, "loss": 0.6112, "accuracy": 0.7749999761581421, "learning_rate": 3.828828828828829e-06, "epoch": 0.22941970310391363, "percentage": 7.66, "elapsed_time": "0:03:29", "remaining_time": "0:42:05"}
+{"current_steps": 90, "total_steps": 1110, "loss": 0.5947, "accuracy": 0.8500000238418579, "learning_rate": 4.0540540540540545e-06, "epoch": 0.242914979757085, "percentage": 8.11, "elapsed_time": "0:03:41", "remaining_time": "0:41:49"}
+{"current_steps": 95, "total_steps": 1110, "loss": 0.6261, "accuracy": 0.675000011920929, "learning_rate": 4.27927927927928e-06, "epoch": 0.2564102564102564, "percentage": 8.56, "elapsed_time": "0:03:51", "remaining_time": "0:41:14"}
+{"current_steps": 100, "total_steps": 1110, "loss": 0.5388, "accuracy": 0.8500000238418579, "learning_rate": 4.504504504504505e-06, "epoch": 0.2699055330634278, "percentage": 9.01, "elapsed_time": "0:04:04", "remaining_time": "0:41:14"}
+{"current_steps": 105, "total_steps": 1110, "loss": 0.5332, "accuracy": 0.800000011920929, "learning_rate": 4.72972972972973e-06, "epoch": 0.2834008097165992, "percentage": 9.46, "elapsed_time": "0:04:52", "remaining_time": "0:46:41"}
+{"current_steps": 110, "total_steps": 1110, "loss": 0.639, "accuracy": 0.699999988079071, "learning_rate": 4.954954954954955e-06, "epoch": 0.2968960863697706, "percentage": 9.91, "elapsed_time": "0:05:05", "remaining_time": "0:46:14"}
+{"current_steps": 115, "total_steps": 1110, "loss": 0.4953, "accuracy": 0.800000011920929, "learning_rate": 4.999802215142814e-06, "epoch": 0.31039136302294196, "percentage": 10.36, "elapsed_time": "0:05:17", "remaining_time": "0:45:45"}
+{"current_steps": 120, "total_steps": 1110, "loss": 0.5188, "accuracy": 0.75, "learning_rate": 4.998998767795805e-06, "epoch": 0.32388663967611336, "percentage": 10.81, "elapsed_time": "0:05:28", "remaining_time": "0:45:09"}
+{"current_steps": 125, "total_steps": 1110, "loss": 0.5878, "accuracy": 0.7250000238418579, "learning_rate": 4.9975774948882615e-06, "epoch": 0.33738191632928477, "percentage": 11.26, "elapsed_time": "0:05:40", "remaining_time": "0:44:40"}
+{"current_steps": 130, "total_steps": 1110, "loss": 0.555, "accuracy": 0.7250000238418579, "learning_rate": 4.995538747800403e-06, "epoch": 0.3508771929824561, "percentage": 11.71, "elapsed_time": "0:05:52", "remaining_time": "0:44:19"}
+{"current_steps": 135, "total_steps": 1110, "loss": 0.4598, "accuracy": 0.75, "learning_rate": 4.9928830305701164e-06, "epoch": 0.3643724696356275, "percentage": 12.16, "elapsed_time": "0:06:04", "remaining_time": "0:43:52"}
+{"current_steps": 140, "total_steps": 1110, "loss": 0.4536, "accuracy": 0.8500000238418579, "learning_rate": 4.98961099976835e-06, "epoch": 0.37786774628879893, "percentage": 12.61, "elapsed_time": "0:06:16", "remaining_time": "0:43:31"}
+{"current_steps": 145, "total_steps": 1110, "loss": 0.4902, "accuracy": 0.824999988079071, "learning_rate": 4.985723464336783e-06, "epoch": 0.3913630229419703, "percentage": 13.06, "elapsed_time": "0:06:29", "remaining_time": "0:43:14"}
+{"current_steps": 150, "total_steps": 1110, "loss": 0.4942, "accuracy": 0.7749999761581421, "learning_rate": 4.9812213853878376e-06, "epoch": 0.4048582995951417, "percentage": 13.51, "elapsed_time": "0:06:41", "remaining_time": "0:42:52"}
+{"current_steps": 155, "total_steps": 1110, "loss": 0.5805, "accuracy": 0.7250000238418579, "learning_rate": 4.9761058759670625e-06, "epoch": 0.4183535762483131, "percentage": 13.96, "elapsed_time": "0:06:53", "remaining_time": "0:42:25"}
+{"current_steps": 160, "total_steps": 1110, "loss": 0.3726, "accuracy": 0.824999988079071, "learning_rate": 4.970378200777949e-06, "epoch": 0.4318488529014845, "percentage": 14.41, "elapsed_time": "0:07:03", "remaining_time": "0:41:56"}
+{"current_steps": 165, "total_steps": 1110, "loss": 0.4821, "accuracy": 0.800000011920929, "learning_rate": 4.964039775869271e-06, "epoch": 0.44534412955465585, "percentage": 14.86, "elapsed_time": "0:07:15", "remaining_time": "0:41:33"}
+{"current_steps": 170, "total_steps": 1110, "loss": 0.4522, "accuracy": 0.7749999761581421, "learning_rate": 4.957092168284987e-06, "epoch": 0.45883940620782726, "percentage": 15.32, "elapsed_time": "0:07:27", "remaining_time": "0:41:15"}
+{"current_steps": 175, "total_steps": 1110, "loss": 0.45, "accuracy": 0.7749999761581421, "learning_rate": 4.949537095676824e-06, "epoch": 0.47233468286099867, "percentage": 15.77, "elapsed_time": "0:07:39", "remaining_time": "0:40:55"}
+{"current_steps": 180, "total_steps": 1110, "loss": 0.5881, "accuracy": 0.625, "learning_rate": 4.9413764258796236e-06, "epoch": 0.48582995951417, "percentage": 16.22, "elapsed_time": "0:07:51", "remaining_time": "0:40:36"}
+{"current_steps": 185, "total_steps": 1110, "loss": 0.4912, "accuracy": 0.800000011920929, "learning_rate": 4.93261217644956e-06, "epoch": 0.4993252361673414, "percentage": 16.67, "elapsed_time": "0:08:03", "remaining_time": "0:40:19"}
+{"current_steps": 190, "total_steps": 1110, "loss": 0.3841, "accuracy": 0.824999988079071, "learning_rate": 4.923246514165339e-06, "epoch": 0.5128205128205128, "percentage": 17.12, "elapsed_time": "0:08:15", "remaining_time": "0:40:00"}
+{"current_steps": 195, "total_steps": 1110, "loss": 0.439, "accuracy": 0.800000011920929, "learning_rate": 4.913281754492509e-06, "epoch": 0.5263157894736842, "percentage": 17.57, "elapsed_time": "0:08:27", "remaining_time": "0:39:42"}
+{"current_steps": 200, "total_steps": 1110, "loss": 0.436, "accuracy": 0.800000011920929, "learning_rate": 4.902720361011007e-06, "epoch": 0.5398110661268556, "percentage": 18.02, "elapsed_time": "0:08:39", "remaining_time": "0:39:21"}
+{"current_steps": 205, "total_steps": 1110, "loss": 0.4408, "accuracy": 0.75, "learning_rate": 4.891564944806095e-06, "epoch": 0.553306342780027, "percentage": 18.47, "elapsed_time": "0:09:26", "remaining_time": "0:41:39"}
+{"current_steps": 210, "total_steps": 1110, "loss": 0.4359, "accuracy": 0.800000011920929, "learning_rate": 4.879818263822816e-06, "epoch": 0.5668016194331984, "percentage": 18.92, "elapsed_time": "0:09:37", "remaining_time": "0:41:14"}
+{"current_steps": 215, "total_steps": 1110, "loss": 0.4083, "accuracy": 0.8500000238418579, "learning_rate": 4.867483222184158e-06, "epoch": 0.5802968960863698, "percentage": 19.37, "elapsed_time": "0:09:48", "remaining_time": "0:40:48"}
+{"current_steps": 220, "total_steps": 1110, "loss": 0.5288, "accuracy": 0.7250000238418579, "learning_rate": 4.854562869473063e-06, "epoch": 0.5937921727395412, "percentage": 19.82, "elapsed_time": "0:09:58", "remaining_time": "0:40:21"}
+{"current_steps": 225, "total_steps": 1110, "loss": 0.467, "accuracy": 0.824999988079071, "learning_rate": 4.841060399978481e-06, "epoch": 0.6072874493927125, "percentage": 20.27, "elapsed_time": "0:10:09", "remaining_time": "0:39:57"}
+{"current_steps": 230, "total_steps": 1110, "loss": 0.3819, "accuracy": 0.8500000238418579, "learning_rate": 4.826979151905655e-06, "epoch": 0.6207827260458839, "percentage": 20.72, "elapsed_time": "0:10:20", "remaining_time": "0:39:34"}
+{"current_steps": 235, "total_steps": 1110, "loss": 0.403, "accuracy": 0.875, "learning_rate": 4.812322606550813e-06, "epoch": 0.6342780026990553, "percentage": 21.17, "elapsed_time": "0:10:31", "remaining_time": "0:39:11"}
+{"current_steps": 240, "total_steps": 1110, "loss": 0.4905, "accuracy": 0.7749999761581421, "learning_rate": 4.7970943874404904e-06, "epoch": 0.6477732793522267, "percentage": 21.62, "elapsed_time": "0:10:43", "remaining_time": "0:38:54"}
+{"current_steps": 245, "total_steps": 1110, "loss": 0.3498, "accuracy": 0.875, "learning_rate": 4.781298259435691e-06, "epoch": 0.6612685560053981, "percentage": 22.07, "elapsed_time": "0:10:56", "remaining_time": "0:38:38"}
+{"current_steps": 250, "total_steps": 1110, "loss": 0.4596, "accuracy": 0.800000011920929, "learning_rate": 4.7649381278011e-06, "epoch": 0.6747638326585695, "percentage": 22.52, "elapsed_time": "0:11:08", "remaining_time": "0:38:18"}
+{"current_steps": 255, "total_steps": 1110, "loss": 0.377, "accuracy": 0.824999988079071, "learning_rate": 4.748018037239592e-06, "epoch": 0.6882591093117408, "percentage": 22.97, "elapsed_time": "0:11:20", "remaining_time": "0:38:03"}
+{"current_steps": 260, "total_steps": 1110, "loss": 0.5013, "accuracy": 0.8500000238418579, "learning_rate": 4.7305421708922596e-06, "epoch": 0.7017543859649122, "percentage": 23.42, "elapsed_time": "0:11:32", "remaining_time": "0:37:45"}
+{"current_steps": 265, "total_steps": 1110, "loss": 0.3704, "accuracy": 0.8500000238418579, "learning_rate": 4.712514849304219e-06, "epoch": 0.7152496626180836, "percentage": 23.87, "elapsed_time": "0:11:45", "remaining_time": "0:37:28"}
+{"current_steps": 270, "total_steps": 1110, "loss": 0.4081, "accuracy": 0.875, "learning_rate": 4.693940529356444e-06, "epoch": 0.728744939271255, "percentage": 24.32, "elapsed_time": "0:11:57", "remaining_time": "0:37:11"}
+{"current_steps": 275, "total_steps": 1110, "loss": 0.2792, "accuracy": 0.8500000238418579, "learning_rate": 4.674823803163899e-06, "epoch": 0.7422402159244265, "percentage": 24.77, "elapsed_time": "0:12:09", "remaining_time": "0:36:54"}
+{"current_steps": 280, "total_steps": 1110, "loss": 0.3756, "accuracy": 0.8500000238418579, "learning_rate": 4.655169396940229e-06, "epoch": 0.7557354925775979, "percentage": 25.23, "elapsed_time": "0:12:22", "remaining_time": "0:36:39"}
+{"current_steps": 285, "total_steps": 1110, "loss": 0.3639, "accuracy": 0.8500000238418579, "learning_rate": 4.6349821698293025e-06, "epoch": 0.7692307692307693, "percentage": 25.68, "elapsed_time": "0:12:34", "remaining_time": "0:36:24"}
+{"current_steps": 290, "total_steps": 1110, "loss": 0.3855, "accuracy": 0.824999988079071, "learning_rate": 4.6142671127038905e-06, "epoch": 0.7827260458839406, "percentage": 26.13, "elapsed_time": "0:12:46", "remaining_time": "0:36:06"}
+{"current_steps": 295, "total_steps": 1110, "loss": 0.4094, "accuracy": 0.8999999761581421, "learning_rate": 4.593029346931777e-06, "epoch": 0.796221322537112, "percentage": 26.58, "elapsed_time": "0:12:58", "remaining_time": "0:35:50"}
+{"current_steps": 300, "total_steps": 1110, "loss": 0.5103, "accuracy": 0.75, "learning_rate": 4.571274123109606e-06, "epoch": 0.8097165991902834, "percentage": 27.03, "elapsed_time": "0:13:10", "remaining_time": "0:35:34"}
+{"current_steps": 305, "total_steps": 1110, "loss": 0.6645, "accuracy": 0.7250000238418579, "learning_rate": 4.549006819764779e-06, "epoch": 0.8232118758434548, "percentage": 27.48, "elapsed_time": "0:13:57", "remaining_time": "0:36:51"}
+{"current_steps": 310, "total_steps": 1110, "loss": 0.3625, "accuracy": 0.8999999761581421, "learning_rate": 4.52623294202573e-06, "epoch": 0.8367071524966262, "percentage": 27.93, "elapsed_time": "0:14:09", "remaining_time": "0:36:31"}
+{"current_steps": 315, "total_steps": 1110, "loss": 0.3943, "accuracy": 0.800000011920929, "learning_rate": 4.502958120260894e-06, "epoch": 0.8502024291497976, "percentage": 28.38, "elapsed_time": "0:14:20", "remaining_time": "0:36:11"}
+{"current_steps": 320, "total_steps": 1110, "loss": 0.393, "accuracy": 0.8500000238418579, "learning_rate": 4.479188108686714e-06, "epoch": 0.863697705802969, "percentage": 28.83, "elapsed_time": "0:14:33", "remaining_time": "0:35:56"}
+{"current_steps": 325, "total_steps": 1110, "loss": 0.3673, "accuracy": 0.8999999761581421, "learning_rate": 4.454928783945033e-06, "epoch": 0.8771929824561403, "percentage": 29.28, "elapsed_time": "0:14:45", "remaining_time": "0:35:37"}
+{"current_steps": 330, "total_steps": 1110, "loss": 0.4332, "accuracy": 0.8500000238418579, "learning_rate": 4.430186143650216e-06, "epoch": 0.8906882591093117, "percentage": 29.73, "elapsed_time": "0:14:56", "remaining_time": "0:35:19"}
+{"current_steps": 335, "total_steps": 1110, "loss": 0.2851, "accuracy": 0.875, "learning_rate": 4.404966304906363e-06, "epoch": 0.9041835357624831, "percentage": 30.18, "elapsed_time": "0:15:09", "remaining_time": "0:35:03"}
+{"current_steps": 340, "total_steps": 1110, "loss": 0.3974, "accuracy": 0.925000011920929, "learning_rate": 4.379275502794984e-06, "epoch": 0.9176788124156545, "percentage": 30.63, "elapsed_time": "0:15:20", "remaining_time": "0:34:45"}
+{"current_steps": 345, "total_steps": 1110, "loss": 0.3399, "accuracy": 0.875, "learning_rate": 4.3531200888335015e-06, "epoch": 0.9311740890688259, "percentage": 31.08, "elapsed_time": "0:15:32", "remaining_time": "0:34:26"}
+{"current_steps": 350, "total_steps": 1110, "loss": 0.4954, "accuracy": 0.824999988079071, "learning_rate": 4.326506529404973e-06, "epoch": 0.9446693657219973, "percentage": 31.53, "elapsed_time": "0:15:44", "remaining_time": "0:34:10"}
+{"current_steps": 355, "total_steps": 1110, "loss": 0.3882, "accuracy": 0.8500000238418579, "learning_rate": 4.299441404159409e-06, "epoch": 0.9581646423751687, "percentage": 31.98, "elapsed_time": "0:15:55", "remaining_time": "0:33:52"}
+{"current_steps": 360, "total_steps": 1110, "loss": 0.3129, "accuracy": 0.8500000238418579, "learning_rate": 4.271931404387096e-06, "epoch": 0.97165991902834, "percentage": 32.43, "elapsed_time": "0:16:08", "remaining_time": "0:33:37"}
+{"current_steps": 365, "total_steps": 1110, "loss": 0.4821, "accuracy": 0.7749999761581421, "learning_rate": 4.243983331364307e-06, "epoch": 0.9851551956815114, "percentage": 32.88, "elapsed_time": "0:16:20", "remaining_time": "0:33:20"}
+{"current_steps": 370, "total_steps": 1110, "loss": 0.4743, "accuracy": 0.824999988079071, "learning_rate": 4.215604094671835e-06, "epoch": 0.9986504723346828, "percentage": 33.33, "elapsed_time": "0:16:33", "remaining_time": "0:33:06"}
+{"current_steps": 375, "total_steps": 1110, "loss": 0.2691, "accuracy": 0.949999988079071, "learning_rate": 4.186800710486732e-06, "epoch": 1.0121457489878543, "percentage": 33.78, "elapsed_time": "0:16:45", "remaining_time": "0:32:49"}
+{"current_steps": 380, "total_steps": 1110, "loss": 0.126, "accuracy": 1.0, "learning_rate": 4.157580299847717e-06, "epoch": 1.0256410256410255, "percentage": 34.23, "elapsed_time": "0:16:56", "remaining_time": "0:32:32"}
+{"current_steps": 385, "total_steps": 1110, "loss": 0.2329, "accuracy": 0.925000011920929, "learning_rate": 4.12795008689464e-06, "epoch": 1.039136302294197, "percentage": 34.68, "elapsed_time": "0:17:09", "remaining_time": "0:32:18"}
+{"current_steps": 390, "total_steps": 1110, "loss": 0.1885, "accuracy": 1.0, "learning_rate": 4.0979173970824626e-06, "epoch": 1.0526315789473684, "percentage": 35.14, "elapsed_time": "0:17:21", "remaining_time": "0:32:01"}
+{"current_steps": 395, "total_steps": 1110, "loss": 0.1103, "accuracy": 1.0, "learning_rate": 4.067489655370197e-06, "epoch": 1.0661268556005399, "percentage": 35.59, "elapsed_time": "0:17:33", "remaining_time": "0:31:47"}
+{"current_steps": 400, "total_steps": 1110, "loss": 0.1189, "accuracy": 1.0, "learning_rate": 4.0366743843852315e-06, "epoch": 1.0796221322537112, "percentage": 36.04, "elapsed_time": "0:17:44", "remaining_time": "0:31:29"}
+{"current_steps": 405, "total_steps": 1110, "loss": 0.113, "accuracy": 0.9750000238418579, "learning_rate": 4.005479202563524e-06, "epoch": 1.0931174089068827, "percentage": 36.49, "elapsed_time": "0:18:30", "remaining_time": "0:32:12"}
+{"current_steps": 410, "total_steps": 1110, "loss": 0.1506, "accuracy": 0.9750000238418579, "learning_rate": 3.973911822266099e-06, "epoch": 1.106612685560054, "percentage": 36.94, "elapsed_time": "0:18:42", "remaining_time": "0:31:56"}
+{"current_steps": 415, "total_steps": 1110, "loss": 0.2229, "accuracy": 0.949999988079071, "learning_rate": 3.941980047872324e-06, "epoch": 1.1201079622132253, "percentage": 37.39, "elapsed_time": "0:18:53", "remaining_time": "0:31:39"}
+{"current_steps": 420, "total_steps": 1110, "loss": 0.2023, "accuracy": 0.949999988079071, "learning_rate": 3.9096917738504445e-06, "epoch": 1.1336032388663968, "percentage": 37.84, "elapsed_time": "0:19:06", "remaining_time": "0:31:24"}
+{"current_steps": 425, "total_steps": 1110, "loss": 0.2, "accuracy": 0.949999988079071, "learning_rate": 3.877054982805835e-06, "epoch": 1.147098515519568, "percentage": 38.29, "elapsed_time": "0:19:18", "remaining_time": "0:31:07"}
+{"current_steps": 430, "total_steps": 1110, "loss": 0.1763, "accuracy": 0.925000011920929, "learning_rate": 3.844077743507468e-06, "epoch": 1.1605937921727396, "percentage": 38.74, "elapsed_time": "0:19:30", "remaining_time": "0:30:50"}
+{"current_steps": 435, "total_steps": 1110, "loss": 0.2875, "accuracy": 0.8500000238418579, "learning_rate": 3.8107682088930797e-06, "epoch": 1.174089068825911, "percentage": 39.19, "elapsed_time": "0:19:42", "remaining_time": "0:30:34"}
+{"current_steps": 440, "total_steps": 1110, "loss": 0.2094, "accuracy": 0.925000011920929, "learning_rate": 3.777134614053522e-06, "epoch": 1.1875843454790824, "percentage": 39.64, "elapsed_time": "0:19:52", "remaining_time": "0:30:15"}
+{"current_steps": 445, "total_steps": 1110, "loss": 0.2674, "accuracy": 0.8999999761581421, "learning_rate": 3.7431852741968104e-06, "epoch": 1.2010796221322537, "percentage": 40.09, "elapsed_time": "0:20:04", "remaining_time": "0:30:00"}
+{"current_steps": 450, "total_steps": 1110, "loss": 0.216, "accuracy": 0.949999988079071, "learning_rate": 3.7089285825923614e-06, "epoch": 1.214574898785425, "percentage": 40.54, "elapsed_time": "0:20:15", "remaining_time": "0:29:42"}
+{"current_steps": 455, "total_steps": 1110, "loss": 0.1606, "accuracy": 0.9750000238418579, "learning_rate": 3.6743730084959275e-06, "epoch": 1.2280701754385965, "percentage": 40.99, "elapsed_time": "0:20:27", "remaining_time": "0:29:27"}
+{"current_steps": 460, "total_steps": 1110, "loss": 0.1515, "accuracy": 0.9750000238418579, "learning_rate": 3.639527095055753e-06, "epoch": 1.2415654520917678, "percentage": 41.44, "elapsed_time": "0:20:40", "remaining_time": "0:29:12"}
+{"current_steps": 465, "total_steps": 1110, "loss": 0.1586, "accuracy": 0.9750000238418579, "learning_rate": 3.604399457200458e-06, "epoch": 1.2550607287449393, "percentage": 41.89, "elapsed_time": "0:20:52", "remaining_time": "0:28:57"}
+{"current_steps": 470, "total_steps": 1110, "loss": 0.1666, "accuracy": 0.949999988079071, "learning_rate": 3.5689987795091735e-06, "epoch": 1.2685560053981106, "percentage": 42.34, "elapsed_time": "0:21:04", "remaining_time": "0:28:41"}
+{"current_steps": 475, "total_steps": 1110, "loss": 0.1562, "accuracy": 0.949999988079071, "learning_rate": 3.5333338140644602e-06, "epoch": 1.282051282051282, "percentage": 42.79, "elapsed_time": "0:21:16", "remaining_time": "0:28:26"}
+{"current_steps": 480, "total_steps": 1110, "loss": 0.1537, "accuracy": 0.9750000238418579, "learning_rate": 3.497413378288541e-06, "epoch": 1.2955465587044535, "percentage": 43.24, "elapsed_time": "0:21:28", "remaining_time": "0:28:11"}
+{"current_steps": 485, "total_steps": 1110, "loss": 0.1097, "accuracy": 1.0, "learning_rate": 3.4612463527633728e-06, "epoch": 1.3090418353576248, "percentage": 43.69, "elapsed_time": "0:21:39", "remaining_time": "0:27:55"}
+{"current_steps": 490, "total_steps": 1110, "loss": 0.1741, "accuracy": 0.949999988079071, "learning_rate": 3.4248416790351086e-06, "epoch": 1.3225371120107963, "percentage": 44.14, "elapsed_time": "0:21:52", "remaining_time": "0:27:41"}
+{"current_steps": 495, "total_steps": 1110, "loss": 0.1075, "accuracy": 1.0, "learning_rate": 3.3882083574034847e-06, "epoch": 1.3360323886639676, "percentage": 44.59, "elapsed_time": "0:22:05", "remaining_time": "0:27:27"}
+{"current_steps": 500, "total_steps": 1110, "loss": 0.0835, "accuracy": 0.9750000238418579, "learning_rate": 3.3513554446966846e-06, "epoch": 1.349527665317139, "percentage": 45.05, "elapsed_time": "0:22:18", "remaining_time": "0:27:12"}
+{"current_steps": 500, "total_steps": 1110, "eval_loss": 0.3281523883342743, "epoch": 1.349527665317139, "percentage": 45.05, "elapsed_time": "0:22:41", "remaining_time": "0:27:41"}
+{"current_steps": 505, "total_steps": 1110, "loss": 0.2057, "accuracy": 0.949999988079071, "learning_rate": 3.314292052032227e-06, "epoch": 1.3630229419703104, "percentage": 45.5, "elapsed_time": "0:23:28", "remaining_time": "0:28:07"}
+{"current_steps": 510, "total_steps": 1110, "loss": 0.1862, "accuracy": 0.925000011920929, "learning_rate": 3.2770273425644285e-06, "epoch": 1.376518218623482, "percentage": 45.95, "elapsed_time": "0:23:39", "remaining_time": "0:27:49"}
+{"current_steps": 515, "total_steps": 1110, "loss": 0.1711, "accuracy": 0.9750000238418579, "learning_rate": 3.2395705292190067e-06, "epoch": 1.3900134952766532, "percentage": 46.4, "elapsed_time": "0:23:50", "remaining_time": "0:27:32"}
+{"current_steps": 520, "total_steps": 1110, "loss": 0.114, "accuracy": 1.0, "learning_rate": 3.2019308724153743e-06, "epoch": 1.4035087719298245, "percentage": 46.85, "elapsed_time": "0:24:02", "remaining_time": "0:27:16"}
+{"current_steps": 525, "total_steps": 1110, "loss": 0.1757, "accuracy": 0.949999988079071, "learning_rate": 3.164117677777191e-06, "epoch": 1.417004048582996, "percentage": 47.3, "elapsed_time": "0:24:12", "remaining_time": "0:26:58"}
+{"current_steps": 530, "total_steps": 1110, "loss": 0.1532, "accuracy": 0.9750000238418579, "learning_rate": 3.1261402938317465e-06, "epoch": 1.4304993252361673, "percentage": 47.75, "elapsed_time": "0:24:25", "remaining_time": "0:26:43"}
+{"current_steps": 535, "total_steps": 1110, "loss": 0.1892, "accuracy": 0.949999988079071, "learning_rate": 3.088008109698726e-06, "epoch": 1.4439946018893388, "percentage": 48.2, "elapsed_time": "0:24:37", "remaining_time": "0:26:27"}
+{"current_steps": 540, "total_steps": 1110, "loss": 0.1852, "accuracy": 0.949999988079071, "learning_rate": 3.0497305527689446e-06, "epoch": 1.45748987854251, "percentage": 48.65, "elapsed_time": "0:24:49", "remaining_time": "0:26:11"}
+{"current_steps": 545, "total_steps": 1110, "loss": 0.1847, "accuracy": 0.949999988079071, "learning_rate": 3.011317086373628e-06, "epoch": 1.4709851551956814, "percentage": 49.1, "elapsed_time": "0:25:01", "remaining_time": "0:25:56"}
+{"current_steps": 550, "total_steps": 1110, "loss": 0.1473, "accuracy": 0.925000011920929, "learning_rate": 2.9727772074447916e-06, "epoch": 1.484480431848853, "percentage": 49.55, "elapsed_time": "0:25:13", "remaining_time": "0:25:40"}
+{"current_steps": 555, "total_steps": 1110, "loss": 0.2029, "accuracy": 0.8999999761581421, "learning_rate": 2.9341204441673267e-06, "epoch": 1.4979757085020242, "percentage": 50.0, "elapsed_time": "0:25:24", "remaining_time": "0:25:24"}
+{"current_steps": 560, "total_steps": 1110, "loss": 0.186, "accuracy": 0.9750000238418579, "learning_rate": 2.8953563536233525e-06, "epoch": 1.5114709851551957, "percentage": 50.45, "elapsed_time": "0:25:36", "remaining_time": "0:25:08"}
+{"current_steps": 565, "total_steps": 1110, "loss": 0.168, "accuracy": 0.949999988079071, "learning_rate": 2.8564945194294273e-06, "epoch": 1.524966261808367, "percentage": 50.9, "elapsed_time": "0:25:48", "remaining_time": "0:24:53"}
+{"current_steps": 570, "total_steps": 1110, "loss": 0.1935, "accuracy": 0.9750000238418579, "learning_rate": 2.817544549367197e-06, "epoch": 1.5384615384615383, "percentage": 51.35, "elapsed_time": "0:26:00", "remaining_time": "0:24:37"}
+{"current_steps": 575, "total_steps": 1110, "loss": 0.2049, "accuracy": 0.949999988079071, "learning_rate": 2.778516073008071e-06, "epoch": 1.5519568151147098, "percentage": 51.8, "elapsed_time": "0:26:10", "remaining_time": "0:24:21"}
+{"current_steps": 580, "total_steps": 1110, "loss": 0.2601, "accuracy": 0.8999999761581421, "learning_rate": 2.7394187393325107e-06, "epoch": 1.5654520917678814, "percentage": 52.25, "elapsed_time": "0:26:22", "remaining_time": "0:24:06"}
+{"current_steps": 585, "total_steps": 1110, "loss": 0.1305, "accuracy": 0.949999988079071, "learning_rate": 2.7002622143445177e-06, "epoch": 1.5789473684210527, "percentage": 52.7, "elapsed_time": "0:26:34", "remaining_time": "0:23:50"}
+{"current_steps": 590, "total_steps": 1110, "loss": 0.1715, "accuracy": 0.925000011920929, "learning_rate": 2.6610561786819207e-06, "epoch": 1.592442645074224, "percentage": 53.15, "elapsed_time": "0:26:44", "remaining_time": "0:23:34"}
+{"current_steps": 595, "total_steps": 1110, "loss": 0.1382, "accuracy": 1.0, "learning_rate": 2.6218103252230302e-06, "epoch": 1.6059379217273952, "percentage": 53.6, "elapsed_time": "0:26:56", "remaining_time": "0:23:19"}
+{"current_steps": 600, "total_steps": 1110, "loss": 0.111, "accuracy": 1.0, "learning_rate": 2.582534356690284e-06, "epoch": 1.6194331983805668, "percentage": 54.05, "elapsed_time": "0:27:09", "remaining_time": "0:23:04"}
+{"current_steps": 605, "total_steps": 1110, "loss": 0.2301, "accuracy": 0.8999999761581421, "learning_rate": 2.5432379832514437e-06, "epoch": 1.6329284750337383, "percentage": 54.5, "elapsed_time": "0:27:55", "remaining_time": "0:23:18"}
+{"current_steps": 610, "total_steps": 1110, "loss": 0.1597, "accuracy": 0.949999988079071, "learning_rate": 2.5039309201189618e-06, "epoch": 1.6464237516869096, "percentage": 54.95, "elapsed_time": "0:28:07", "remaining_time": "0:23:03"}
+{"current_steps": 615, "total_steps": 1110, "loss": 0.2172, "accuracy": 0.9750000238418579, "learning_rate": 2.4646228851480957e-06, "epoch": 1.6599190283400809, "percentage": 55.41, "elapsed_time": "0:28:19", "remaining_time": "0:22:47"}
+{"current_steps": 620, "total_steps": 1110, "loss": 0.1116, "accuracy": 0.9750000238418579, "learning_rate": 2.4253235964343677e-06, "epoch": 1.6734143049932524, "percentage": 55.86, "elapsed_time": "0:28:32", "remaining_time": "0:22:33"}
+{"current_steps": 625, "total_steps": 1110, "loss": 0.2869, "accuracy": 0.875, "learning_rate": 2.3860427699109726e-06, "epoch": 1.686909581646424, "percentage": 56.31, "elapsed_time": "0:28:44", "remaining_time": "0:22:17"}
+{"current_steps": 630, "total_steps": 1110, "loss": 0.1194, "accuracy": 1.0, "learning_rate": 2.34679011694671e-06, "epoch": 1.7004048582995952, "percentage": 56.76, "elapsed_time": "0:28:55", "remaining_time": "0:22:02"}
+{"current_steps": 635, "total_steps": 1110, "loss": 0.2026, "accuracy": 0.949999988079071, "learning_rate": 2.3075753419450524e-06, "epoch": 1.7139001349527665, "percentage": 57.21, "elapsed_time": "0:29:08", "remaining_time": "0:21:47"}
+{"current_steps": 640, "total_steps": 1110, "loss": 0.269, "accuracy": 0.925000011920929, "learning_rate": 2.2684081399449327e-06, "epoch": 1.7273954116059378, "percentage": 57.66, "elapsed_time": "0:29:20", "remaining_time": "0:21:32"}
+{"current_steps": 645, "total_steps": 1110, "loss": 0.3528, "accuracy": 0.875, "learning_rate": 2.2292981942238454e-06, "epoch": 1.7408906882591093, "percentage": 58.11, "elapsed_time": "0:29:31", "remaining_time": "0:21:17"}
+{"current_steps": 650, "total_steps": 1110, "loss": 0.2386, "accuracy": 0.949999988079071, "learning_rate": 2.1902551739038624e-06, "epoch": 1.7543859649122808, "percentage": 58.56, "elapsed_time": "0:29:42", "remaining_time": "0:21:01"}
+{"current_steps": 655, "total_steps": 1110, "loss": 0.1651, "accuracy": 0.925000011920929, "learning_rate": 2.151288731561136e-06, "epoch": 1.7678812415654521, "percentage": 59.01, "elapsed_time": "0:29:54", "remaining_time": "0:20:46"}
+{"current_steps": 660, "total_steps": 1110, "loss": 0.1999, "accuracy": 0.949999988079071, "learning_rate": 2.1124085008395056e-06, "epoch": 1.7813765182186234, "percentage": 59.46, "elapsed_time": "0:30:06", "remaining_time": "0:20:31"}
+{"current_steps": 665, "total_steps": 1110, "loss": 0.2781, "accuracy": 0.8999999761581421, "learning_rate": 2.073624094068776e-06, "epoch": 1.7948717948717947, "percentage": 59.91, "elapsed_time": "0:30:18", "remaining_time": "0:20:16"}
+{"current_steps": 670, "total_steps": 1110, "loss": 0.1212, "accuracy": 1.0, "learning_rate": 2.03494509988827e-06, "epoch": 1.8083670715249662, "percentage": 60.36, "elapsed_time": "0:30:30", "remaining_time": "0:20:02"}
+{"current_steps": 675, "total_steps": 1110, "loss": 0.1177, "accuracy": 0.9750000238418579, "learning_rate": 1.996381080876237e-06, "epoch": 1.8218623481781377, "percentage": 60.81, "elapsed_time": "0:30:43", "remaining_time": "0:19:47"}
+{"current_steps": 680, "total_steps": 1110, "loss": 0.2672, "accuracy": 0.949999988079071, "learning_rate": 1.957941571185702e-06, "epoch": 1.835357624831309, "percentage": 61.26, "elapsed_time": "0:30:55", "remaining_time": "0:19:33"}
+{"current_steps": 685, "total_steps": 1110, "loss": 0.1468, "accuracy": 0.9750000238418579, "learning_rate": 1.919636074187346e-06, "epoch": 1.8488529014844803, "percentage": 61.71, "elapsed_time": "0:31:07", "remaining_time": "0:19:18"}
+{"current_steps": 690, "total_steps": 1110, "loss": 0.2666, "accuracy": 0.925000011920929, "learning_rate": 1.8814740601199943e-06, "epoch": 1.8623481781376519, "percentage": 62.16, "elapsed_time": "0:31:18", "remaining_time": "0:19:03"}
+{"current_steps": 695, "total_steps": 1110, "loss": 0.1718, "accuracy": 1.0, "learning_rate": 1.8434649637492952e-06, "epoch": 1.8758434547908234, "percentage": 62.61, "elapsed_time": "0:31:30", "remaining_time": "0:18:48"}
+{"current_steps": 700, "total_steps": 1110, "loss": 0.1734, "accuracy": 0.925000011920929, "learning_rate": 1.8056181820351737e-06, "epoch": 1.8893387314439947, "percentage": 63.06, "elapsed_time": "0:31:42", "remaining_time": "0:18:34"}
+{"current_steps": 705, "total_steps": 1110, "loss": 0.0641, "accuracy": 1.0, "learning_rate": 1.7679430718086244e-06, "epoch": 1.902834008097166, "percentage": 63.51, "elapsed_time": "0:32:29", "remaining_time": "0:18:40"}
+{"current_steps": 710, "total_steps": 1110, "loss": 0.123, "accuracy": 0.949999988079071, "learning_rate": 1.7304489474584307e-06, "epoch": 1.9163292847503373, "percentage": 63.96, "elapsed_time": "0:32:41", "remaining_time": "0:18:25"}
+{"current_steps": 715, "total_steps": 1110, "loss": 0.1255, "accuracy": 0.9750000238418579, "learning_rate": 1.693145078628377e-06, "epoch": 1.9298245614035088, "percentage": 64.41, "elapsed_time": "0:32:53", "remaining_time": "0:18:10"}
+{"current_steps": 720, "total_steps": 1110, "loss": 0.1608, "accuracy": 0.949999988079071, "learning_rate": 1.6560406879255192e-06, "epoch": 1.9433198380566803, "percentage": 64.86, "elapsed_time": "0:33:05", "remaining_time": "0:17:55"}
+{"current_steps": 725, "total_steps": 1110, "loss": 0.1858, "accuracy": 0.925000011920929, "learning_rate": 1.6191449486400893e-06, "epoch": 1.9568151147098516, "percentage": 65.32, "elapsed_time": "0:33:16", "remaining_time": "0:17:40"}
+{"current_steps": 730, "total_steps": 1110, "loss": 0.1935, "accuracy": 0.949999988079071, "learning_rate": 1.5824669824775868e-06, "epoch": 1.9703103913630229, "percentage": 65.77, "elapsed_time": "0:33:29", "remaining_time": "0:17:26"}
+{"current_steps": 735, "total_steps": 1110, "loss": 0.1763, "accuracy": 0.949999988079071, "learning_rate": 1.5460158573036288e-06, "epoch": 1.9838056680161942, "percentage": 66.22, "elapsed_time": "0:33:42", "remaining_time": "0:17:11"}
+{"current_steps": 740, "total_steps": 1110, "loss": 0.2088, "accuracy": 0.925000011920929, "learning_rate": 1.509800584902108e-06, "epoch": 1.9973009446693657, "percentage": 66.67, "elapsed_time": "0:33:53", "remaining_time": "0:16:56"}
+{"current_steps": 745, "total_steps": 1110, "loss": 0.1035, "accuracy": 1.0, "learning_rate": 1.473830118747216e-06, "epoch": 2.010796221322537, "percentage": 67.12, "elapsed_time": "0:34:03", "remaining_time": "0:16:41"}
+{"current_steps": 750, "total_steps": 1110, "loss": 0.068, "accuracy": 1.0, "learning_rate": 1.4381133517898803e-06, "epoch": 2.0242914979757085, "percentage": 67.57, "elapsed_time": "0:34:17", "remaining_time": "0:16:27"}
+{"current_steps": 755, "total_steps": 1110, "loss": 0.1633, "accuracy": 0.949999988079071, "learning_rate": 1.4026591142591733e-06, "epoch": 2.03778677462888, "percentage": 68.02, "elapsed_time": "0:34:29", "remaining_time": "0:16:12"}
+{"current_steps": 760, "total_steps": 1110, "loss": 0.0739, "accuracy": 0.9750000238418579, "learning_rate": 1.3674761714792153e-06, "epoch": 2.051282051282051, "percentage": 68.47, "elapsed_time": "0:34:40", "remaining_time": "0:15:58"}
+{"current_steps": 765, "total_steps": 1110, "loss": 0.1002, "accuracy": 0.9750000238418579, "learning_rate": 1.33257322170213e-06, "epoch": 2.064777327935223, "percentage": 68.92, "elapsed_time": "0:34:52", "remaining_time": "0:15:43"}
+{"current_steps": 770, "total_steps": 1110, "loss": 0.1696, "accuracy": 0.925000011920929, "learning_rate": 1.2979588939575879e-06, "epoch": 2.078272604588394, "percentage": 69.37, "elapsed_time": "0:35:03", "remaining_time": "0:15:28"}
+{"current_steps": 775, "total_steps": 1110, "loss": 0.0593, "accuracy": 1.0, "learning_rate": 1.2636417459194536e-06, "epoch": 2.0917678812415654, "percentage": 69.82, "elapsed_time": "0:35:15", "remaining_time": "0:15:14"}
+{"current_steps": 780, "total_steps": 1110, "loss": 0.0845, "accuracy": 0.9750000238418579, "learning_rate": 1.2296302617900772e-06, "epoch": 2.1052631578947367, "percentage": 70.27, "elapsed_time": "0:35:27", "remaining_time": "0:14:59"}
+{"current_steps": 785, "total_steps": 1110, "loss": 0.1138, "accuracy": 1.0, "learning_rate": 1.1959328502027556e-06, "epoch": 2.118758434547908, "percentage": 70.72, "elapsed_time": "0:35:38", "remaining_time": "0:14:45"}
+{"current_steps": 790, "total_steps": 1110, "loss": 0.1239, "accuracy": 0.9750000238418579, "learning_rate": 1.1625578421428714e-06, "epoch": 2.1322537112010798, "percentage": 71.17, "elapsed_time": "0:35:50", "remaining_time": "0:14:31"}
+{"current_steps": 795, "total_steps": 1110, "loss": 0.0922, "accuracy": 0.9750000238418579, "learning_rate": 1.1295134888882258e-06, "epoch": 2.145748987854251, "percentage": 71.62, "elapsed_time": "0:36:02", "remaining_time": "0:14:16"}
+{"current_steps": 800, "total_steps": 1110, "loss": 0.112, "accuracy": 0.949999988079071, "learning_rate": 1.0968079599690872e-06, "epoch": 2.1592442645074224, "percentage": 72.07, "elapsed_time": "0:36:13", "remaining_time": "0:14:02"}
+{"current_steps": 805, "total_steps": 1110, "loss": 0.1216, "accuracy": 0.949999988079071, "learning_rate": 1.064449341148442e-06, "epoch": 2.1727395411605936, "percentage": 72.52, "elapsed_time": "0:37:00", "remaining_time": "0:14:01"}
+{"current_steps": 810, "total_steps": 1110, "loss": 0.0775, "accuracy": 1.0, "learning_rate": 1.0324456324229536e-06, "epoch": 2.1862348178137654, "percentage": 72.97, "elapsed_time": "0:37:12", "remaining_time": "0:13:46"}
+{"current_steps": 815, "total_steps": 1110, "loss": 0.1111, "accuracy": 0.9750000238418579, "learning_rate": 1.000804746045138e-06, "epoch": 2.1997300944669367, "percentage": 73.42, "elapsed_time": "0:37:24", "remaining_time": "0:13:32"}
+{"current_steps": 820, "total_steps": 1110, "loss": 0.118, "accuracy": 0.9750000238418579, "learning_rate": 9.695345045672167e-07, "epoch": 2.213225371120108, "percentage": 73.87, "elapsed_time": "0:37:36", "remaining_time": "0:13:18"}
+{"current_steps": 825, "total_steps": 1110, "loss": 0.0961, "accuracy": 0.9750000238418579, "learning_rate": 9.386426389071532e-07, "epoch": 2.2267206477732793, "percentage": 74.32, "elapsed_time": "0:37:47", "remaining_time": "0:13:03"}
+{"current_steps": 830, "total_steps": 1110, "loss": 0.0944, "accuracy": 1.0, "learning_rate": 9.081367864373489e-07, "epoch": 2.2402159244264506, "percentage": 74.77, "elapsed_time": "0:37:58", "remaining_time": "0:12:48"}
+{"current_steps": 835, "total_steps": 1110, "loss": 0.0698, "accuracy": 1.0, "learning_rate": 8.780244890964567e-07, "epoch": 2.2537112010796223, "percentage": 75.23, "elapsed_time": "0:38:10", "remaining_time": "0:12:34"}
+{"current_steps": 840, "total_steps": 1110, "loss": 0.0949, "accuracy": 0.949999988079071, "learning_rate": 8.483131915247969e-07, "epoch": 2.2672064777327936, "percentage": 75.68, "elapsed_time": "0:38:22", "remaining_time": "0:12:20"}
+{"current_steps": 845, "total_steps": 1110, "loss": 0.0783, "accuracy": 1.0, "learning_rate": 8.190102392238191e-07, "epoch": 2.280701754385965, "percentage": 76.13, "elapsed_time": "0:38:33", "remaining_time": "0:12:05"}
+{"current_steps": 850, "total_steps": 1110, "loss": 0.0577, "accuracy": 1.0, "learning_rate": 7.90122876740086e-07, "epoch": 2.294197031039136, "percentage": 76.58, "elapsed_time": "0:38:46", "remaining_time": "0:11:51"}
+{"current_steps": 855, "total_steps": 1110, "loss": 0.0519, "accuracy": 1.0, "learning_rate": 7.616582458742059e-07, "epoch": 2.3076923076923075, "percentage": 77.03, "elapsed_time": "0:38:57", "remaining_time": "0:11:37"}
+{"current_steps": 860, "total_steps": 1110, "loss": 0.1057, "accuracy": 0.949999988079071, "learning_rate": 7.336233839151693e-07, "epoch": 2.3211875843454792, "percentage": 77.48, "elapsed_time": "0:39:10", "remaining_time": "0:11:23"}
+{"current_steps": 865, "total_steps": 1110, "loss": 0.0774, "accuracy": 1.0, "learning_rate": 7.060252219005304e-07, "epoch": 2.3346828609986505, "percentage": 77.93, "elapsed_time": "0:39:22", "remaining_time": "0:11:09"}
+{"current_steps": 870, "total_steps": 1110, "loss": 0.1022, "accuracy": 1.0, "learning_rate": 6.788705829028483e-07, "epoch": 2.348178137651822, "percentage": 78.38, "elapsed_time": "0:39:34", "remaining_time": "0:10:55"}
+{"current_steps": 875, "total_steps": 1110, "loss": 0.0955, "accuracy": 1.0, "learning_rate": 6.521661803428225e-07, "epoch": 2.361673414304993, "percentage": 78.83, "elapsed_time": "0:39:47", "remaining_time": "0:10:41"}
+{"current_steps": 880, "total_steps": 1110, "loss": 0.0983, "accuracy": 1.0, "learning_rate": 6.259186163295439e-07, "epoch": 2.375168690958165, "percentage": 79.28, "elapsed_time": "0:39:58", "remaining_time": "0:10:26"}
+{"current_steps": 885, "total_steps": 1110, "loss": 0.0783, "accuracy": 0.9750000238418579, "learning_rate": 6.001343800282569e-07, "epoch": 2.388663967611336, "percentage": 79.73, "elapsed_time": "0:40:09", "remaining_time": "0:10:12"}
+{"current_steps": 890, "total_steps": 1110, "loss": 0.0806, "accuracy": 1.0, "learning_rate": 5.748198460560475e-07, "epoch": 2.4021592442645074, "percentage": 80.18, "elapsed_time": "0:40:22", "remaining_time": "0:09:58"}
+{"current_steps": 895, "total_steps": 1110, "loss": 0.1433, "accuracy": 0.949999988079071, "learning_rate": 5.499812729058546e-07, "epoch": 2.4156545209176787, "percentage": 80.63, "elapsed_time": "0:40:34", "remaining_time": "0:09:44"}
+{"current_steps": 900, "total_steps": 1110, "loss": 0.0715, "accuracy": 1.0, "learning_rate": 5.256248013991857e-07, "epoch": 2.42914979757085, "percentage": 81.08, "elapsed_time": "0:40:46", "remaining_time": "0:09:30"}
+{"current_steps": 905, "total_steps": 1110, "loss": 0.0683, "accuracy": 0.9750000238418579, "learning_rate": 5.01756453167925e-07, "epoch": 2.4426450742240218, "percentage": 81.53, "elapsed_time": "0:41:32", "remaining_time": "0:09:24"}
+{"current_steps": 910, "total_steps": 1110, "loss": 0.1049, "accuracy": 1.0, "learning_rate": 4.78382129165613e-07, "epoch": 2.456140350877193, "percentage": 81.98, "elapsed_time": "0:41:45", "remaining_time": "0:09:10"}
+{"current_steps": 915, "total_steps": 1110, "loss": 0.118, "accuracy": 0.9750000238418579, "learning_rate": 4.5550760820855633e-07, "epoch": 2.4696356275303644, "percentage": 82.43, "elapsed_time": "0:41:56", "remaining_time": "0:08:56"}
+{"current_steps": 920, "total_steps": 1110, "loss": 0.0716, "accuracy": 1.0, "learning_rate": 4.3313854554713457e-07, "epoch": 2.4831309041835357, "percentage": 82.88, "elapsed_time": "0:42:08", "remaining_time": "0:08:42"}
+{"current_steps": 925, "total_steps": 1110, "loss": 0.1007, "accuracy": 1.0, "learning_rate": 4.1128047146765936e-07, "epoch": 2.4966261808367074, "percentage": 83.33, "elapsed_time": "0:42:19", "remaining_time": "0:08:27"}
+{"current_steps": 930, "total_steps": 1110, "loss": 0.0808, "accuracy": 1.0, "learning_rate": 3.899387899251242e-07, "epoch": 2.5101214574898787, "percentage": 83.78, "elapsed_time": "0:42:31", "remaining_time": "0:08:13"}
+{"current_steps": 935, "total_steps": 1110, "loss": 0.1245, "accuracy": 1.0, "learning_rate": 3.6911877720719053e-07, "epoch": 2.52361673414305, "percentage": 84.23, "elapsed_time": "0:42:42", "remaining_time": "0:07:59"}
+{"current_steps": 940, "total_steps": 1110, "loss": 0.1901, "accuracy": 0.949999988079071, "learning_rate": 3.488255806297311e-07, "epoch": 2.5371120107962213, "percentage": 84.68, "elapsed_time": "0:42:54", "remaining_time": "0:07:45"}
+{"current_steps": 945, "total_steps": 1110, "loss": 0.0904, "accuracy": 1.0, "learning_rate": 3.2906421726426857e-07, "epoch": 2.5506072874493926, "percentage": 85.14, "elapsed_time": "0:43:05", "remaining_time": "0:07:31"}
+{"current_steps": 950, "total_steps": 1110, "loss": 0.0844, "accuracy": 1.0, "learning_rate": 3.09839572697605e-07, "epoch": 2.564102564102564, "percentage": 85.59, "elapsed_time": "0:43:16", "remaining_time": "0:07:17"}
+{"current_steps": 955, "total_steps": 1110, "loss": 0.1289, "accuracy": 0.949999988079071, "learning_rate": 2.9115639982396166e-07, "epoch": 2.5775978407557356, "percentage": 86.04, "elapsed_time": "0:43:29", "remaining_time": "0:07:03"}
+{"current_steps": 960, "total_steps": 1110, "loss": 0.0916, "accuracy": 1.0, "learning_rate": 2.7301931766992916e-07, "epoch": 2.591093117408907, "percentage": 86.49, "elapsed_time": "0:43:41", "remaining_time": "0:06:49"}
+{"current_steps": 965, "total_steps": 1110, "loss": 0.0516, "accuracy": 1.0, "learning_rate": 2.554328102525022e-07, "epoch": 2.604588394062078, "percentage": 86.94, "elapsed_time": "0:43:54", "remaining_time": "0:06:35"}
+{"current_steps": 970, "total_steps": 1110, "loss": 0.128, "accuracy": 0.949999988079071, "learning_rate": 2.3840122547050482e-07, "epoch": 2.6180836707152495, "percentage": 87.39, "elapsed_time": "0:44:05", "remaining_time": "0:06:21"}
+{"current_steps": 975, "total_steps": 1110, "loss": 0.0971, "accuracy": 0.9750000238418579, "learning_rate": 2.219287740296605e-07, "epoch": 2.6315789473684212, "percentage": 87.84, "elapsed_time": "0:44:16", "remaining_time": "0:06:07"}
+{"current_steps": 980, "total_steps": 1110, "loss": 0.1152, "accuracy": 1.0, "learning_rate": 2.060195284015837e-07, "epoch": 2.6450742240215925, "percentage": 88.29, "elapsed_time": "0:44:27", "remaining_time": "0:05:53"}
+{"current_steps": 985, "total_steps": 1110, "loss": 0.096, "accuracy": 1.0, "learning_rate": 1.9067742181694353e-07, "epoch": 2.658569500674764, "percentage": 88.74, "elapsed_time": "0:44:38", "remaining_time": "0:05:39"}
+{"current_steps": 990, "total_steps": 1110, "loss": 0.118, "accuracy": 0.949999988079071, "learning_rate": 1.75906247293057e-07, "epoch": 2.672064777327935, "percentage": 89.19, "elapsed_time": "0:44:50", "remaining_time": "0:05:26"}
+{"current_steps": 995, "total_steps": 1110, "loss": 0.152, "accuracy": 0.9750000238418579, "learning_rate": 1.617096566961429e-07, "epoch": 2.6855600539811064, "percentage": 89.64, "elapsed_time": "0:45:02", "remaining_time": "0:05:12"}
+{"current_steps": 1000, "total_steps": 1110, "loss": 0.1151, "accuracy": 0.949999988079071, "learning_rate": 1.4809115983847267e-07, "epoch": 2.699055330634278, "percentage": 90.09, "elapsed_time": "0:45:13", "remaining_time": "0:04:58"}
+{"current_steps": 1000, "total_steps": 1110, "eval_loss": 0.31860384345054626, "epoch": 2.699055330634278, "percentage": 90.09, "elapsed_time": "0:45:37", "remaining_time": "0:05:01"}
+{"current_steps": 1005, "total_steps": 1110, "loss": 0.0649, "accuracy": 1.0, "learning_rate": 1.3505412361064395e-07, "epoch": 2.7125506072874495, "percentage": 90.54, "elapsed_time": "0:46:23", "remaining_time": "0:04:50"}
+{"current_steps": 1010, "total_steps": 1110, "loss": 0.0805, "accuracy": 1.0, "learning_rate": 1.226017711491867e-07, "epoch": 2.7260458839406208, "percentage": 90.99, "elapsed_time": "0:46:34", "remaining_time": "0:04:36"}
+{"current_steps": 1015, "total_steps": 1110, "loss": 0.0625, "accuracy": 1.0, "learning_rate": 1.107371810397076e-07, "epoch": 2.739541160593792, "percentage": 91.44, "elapsed_time": "0:46:47", "remaining_time": "0:04:22"}
+{"current_steps": 1020, "total_steps": 1110, "loss": 0.0725, "accuracy": 1.0, "learning_rate": 9.946328655577625e-08, "epoch": 2.753036437246964, "percentage": 91.89, "elapsed_time": "0:46:59", "remaining_time": "0:04:08"}
+{"current_steps": 1025, "total_steps": 1110, "loss": 0.1188, "accuracy": 0.949999988079071, "learning_rate": 8.878287493373245e-08, "epoch": 2.766531713900135, "percentage": 92.34, "elapsed_time": "0:47:11", "remaining_time": "0:03:54"}
+{"current_steps": 1030, "total_steps": 1110, "loss": 0.1028, "accuracy": 1.0, "learning_rate": 7.869858668360042e-08, "epoch": 2.7800269905533064, "percentage": 92.79, "elapsed_time": "0:47:22", "remaining_time": "0:03:40"}
+{"current_steps": 1035, "total_steps": 1110, "loss": 0.0856, "accuracy": 0.9750000238418579, "learning_rate": 6.921291493627747e-08, "epoch": 2.7935222672064777, "percentage": 93.24, "elapsed_time": "0:47:35", "remaining_time": "0:03:26"}
+{"current_steps": 1040, "total_steps": 1110, "loss": 0.1754, "accuracy": 0.8999999761581421, "learning_rate": 6.032820482716001e-08, "epoch": 2.807017543859649, "percentage": 93.69, "elapsed_time": "0:47:47", "remaining_time": "0:03:13"}
+{"current_steps": 1045, "total_steps": 1110, "loss": 0.1038, "accuracy": 0.9750000238418579, "learning_rate": 5.204665291635519e-08, "epoch": 2.8205128205128203, "percentage": 94.14, "elapsed_time": "0:47:59", "remaining_time": "0:02:59"}
+{"current_steps": 1050, "total_steps": 1110, "loss": 0.1639, "accuracy": 0.949999988079071, "learning_rate": 4.437030664562969e-08, "epoch": 2.834008097165992, "percentage": 94.59, "elapsed_time": "0:48:12", "remaining_time": "0:02:45"}
+{"current_steps": 1055, "total_steps": 1110, "loss": 0.0909, "accuracy": 0.9750000238418579, "learning_rate": 3.730106383222132e-08, "epoch": 2.8475033738191633, "percentage": 95.05, "elapsed_time": "0:48:23", "remaining_time": "0:02:31"}
+{"current_steps": 1060, "total_steps": 1110, "loss": 0.2529, "accuracy": 0.8999999761581421, "learning_rate": 3.084067219964182e-08, "epoch": 2.8609986504723346, "percentage": 95.5, "elapsed_time": "0:48:34", "remaining_time": "0:02:17"}
+{"current_steps": 1065, "total_steps": 1110, "loss": 0.1089, "accuracy": 0.9750000238418579, "learning_rate": 2.499072894559057e-08, "epoch": 2.8744939271255063, "percentage": 95.95, "elapsed_time": "0:48:46", "remaining_time": "0:02:03"}
+{"current_steps": 1070, "total_steps": 1110, "loss": 0.0822, "accuracy": 1.0, "learning_rate": 1.975268034707878e-08, "epoch": 2.8879892037786776, "percentage": 96.4, "elapsed_time": "0:48:59", "remaining_time": "0:01:49"}
+{"current_steps": 1075, "total_steps": 1110, "loss": 0.0959, "accuracy": 1.0, "learning_rate": 1.512782140286939e-08, "epoch": 2.901484480431849, "percentage": 96.85, "elapsed_time": "0:49:11", "remaining_time": "0:01:36"}
+{"current_steps": 1080, "total_steps": 1110, "loss": 0.0872, "accuracy": 0.9750000238418579, "learning_rate": 1.1117295513313475e-08, "epoch": 2.91497975708502, "percentage": 97.3, "elapsed_time": "0:49:24", "remaining_time": "0:01:22"}
+{"current_steps": 1085, "total_steps": 1110, "loss": 0.1053, "accuracy": 0.949999988079071, "learning_rate": 7.72209419766995e-09, "epoch": 2.9284750337381915, "percentage": 97.75, "elapsed_time": "0:49:34", "remaining_time": "0:01:08"}
+{"current_steps": 1090, "total_steps": 1110, "loss": 0.0878, "accuracy": 1.0, "learning_rate": 4.943056848972227e-09, "epoch": 2.941970310391363, "percentage": 98.2, "elapsed_time": "0:49:46", "remaining_time": "0:00:54"}
+{"current_steps": 1095, "total_steps": 1110, "loss": 0.1109, "accuracy": 0.9750000238418579, "learning_rate": 2.7808705265053305e-09, "epoch": 2.9554655870445345, "percentage": 98.65, "elapsed_time": "0:49:57", "remaining_time": "0:00:41"}
+{"current_steps": 1100, "total_steps": 1110, "loss": 0.118, "accuracy": 0.9750000238418579, "learning_rate": 1.2360697859462035e-09, "epoch": 2.968960863697706, "percentage": 99.1, "elapsed_time": "0:50:09", "remaining_time": "0:00:27"}
+{"current_steps": 1105, "total_steps": 1110, "loss": 0.1793, "accuracy": 0.9750000238418579, "learning_rate": 3.090365472041557e-10, "epoch": 2.982456140350877, "percentage": 99.55, "elapsed_time": "0:50:54", "remaining_time": "0:00:13"}
+{"current_steps": 1110, "total_steps": 1110, "loss": 0.0661, "accuracy": 1.0, "learning_rate": 0.0, "epoch": 2.9959514170040484, "percentage": 100.0, "elapsed_time": "0:51:06", "remaining_time": "0:00:00"}
+{"current_steps": 1110, "total_steps": 1110, "epoch": 2.9959514170040484, "percentage": 100.0, "elapsed_time": "0:51:41", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc442c3d32be2bbc2d811b67fd7c92e7801cf862c05b6b1929828c997ece013e
+size 5432