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 +1,73 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: reasoning-multilingual-R1-Llama-70B-train
+  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. -->
+
+# reasoning-multilingual-R1-Llama-70B-train
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) on the reasoning-multilingual-R1-Llama-70B-train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6135
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9061        | 0.1089 | 11   | 0.7100          |
+| 0.6565        | 0.2178 | 22   | 0.6685          |
+| 0.601         | 0.3267 | 33   | 0.6480          |
+| 0.7668        | 0.4356 | 44   | 0.6343          |
+| 0.8058        | 0.5446 | 55   | 0.6248          |
+| 0.675         | 0.6535 | 66   | 0.6190          |
+| 0.5383        | 0.7624 | 77   | 0.6156          |
+| 0.5044        | 0.8713 | 88   | 0.6139          |
+| 0.6322        | 0.9802 | 99   | 0.6136          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.6134611368179321,
+    "eval_runtime": 1.6849,
+    "eval_samples_per_second": 5.342,
+    "eval_steps_per_second": 1.187,
+    "total_flos": 1.5438974547499418e+17,
+    "train_loss": 0.6889385657735391,
+    "train_runtime": 730.4137,
+    "train_samples_per_second": 1.101,
+    "train_steps_per_second": 0.138
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "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": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.6134611368179321,
+    "eval_runtime": 1.6849,
+    "eval_samples_per_second": 5.342,
+    "eval_steps_per_second": 1.187
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b631857e204c75616db0bcb42c50d4c295d1f1a32c3af0527741a416f02220
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c9e75c7cdf0cd27aceb0a51a6f1fb610712c6d1ad0e17afd712595c590a58cc
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4347644546f7710d913a36ac83b394dce10454fc3528f29e83c802e831d8bfed
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d437ce163296198a8379b8205e1b2475b8c86c0a59fab9684ce432c8eed19aaa
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02643f00207dfc5ed248992486bde04314c21dca556bf65ce520690962b8db63
+size 11422965

tokenizer_config.json

@@ -0,0 +1,204 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<｜User｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151645": {
+      "content": "<｜Assistant｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151646": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151648": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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
+    },
+    "151665": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.5438974547499418e+17,
+    "train_loss": 0.6889385657735391,
+    "train_runtime": 730.4137,
+    "train_samples_per_second": 1.101,
+    "train_steps_per_second": 0.138
+}

trainer_log.jsonl

@@ -0,0 +1,108 @@
+{"current_steps": 1, "total_steps": 98, "loss": 0.7892, "lr": 1e-05, "epoch": 0.01020408163265306, "percentage": 1.02, "elapsed_time": "0:00:06", "remaining_time": "0:10:52"}
+{"current_steps": 2, "total_steps": 98, "loss": 0.8673, "lr": 9.997377845227577e-06, "epoch": 0.02040816326530612, "percentage": 2.04, "elapsed_time": "0:00:13", "remaining_time": "0:10:37"}
+{"current_steps": 3, "total_steps": 98, "loss": 0.7133, "lr": 9.98951413118856e-06, "epoch": 0.030612244897959183, "percentage": 3.06, "elapsed_time": "0:00:19", "remaining_time": "0:10:26"}
+{"current_steps": 4, "total_steps": 98, "loss": 0.9344, "lr": 9.97641710583307e-06, "epoch": 0.04081632653061224, "percentage": 4.08, "elapsed_time": "0:00:26", "remaining_time": "0:10:19"}
+{"current_steps": 5, "total_steps": 98, "loss": 0.7424, "lr": 9.958100506132127e-06, "epoch": 0.05102040816326531, "percentage": 5.1, "elapsed_time": "0:00:32", "remaining_time": "0:10:13"}
+{"current_steps": 6, "total_steps": 98, "loss": 0.9459, "lr": 9.934583543669454e-06, "epoch": 0.061224489795918366, "percentage": 6.12, "elapsed_time": "0:00:39", "remaining_time": "0:10:06"}
+{"current_steps": 7, "total_steps": 98, "loss": 0.5593, "lr": 9.905890884491196e-06, "epoch": 0.07142857142857142, "percentage": 7.14, "elapsed_time": "0:00:46", "remaining_time": "0:09:58"}
+{"current_steps": 8, "total_steps": 98, "loss": 0.7666, "lr": 9.872052623234632e-06, "epoch": 0.08163265306122448, "percentage": 8.16, "elapsed_time": "0:00:52", "remaining_time": "0:09:52"}
+{"current_steps": 9, "total_steps": 98, "loss": 0.7883, "lr": 9.833104251563058e-06, "epoch": 0.09183673469387756, "percentage": 9.18, "elapsed_time": "0:00:59", "remaining_time": "0:09:44"}
+{"current_steps": 10, "total_steps": 98, "loss": 0.6585, "lr": 9.789086620939936e-06, "epoch": 0.10204081632653061, "percentage": 10.2, "elapsed_time": "0:01:05", "remaining_time": "0:09:38"}
+{"current_steps": 10, "total_steps": 98, "eval_loss": 0.6779686212539673, "epoch": 0.10204081632653061, "percentage": 10.2, "elapsed_time": "0:01:06", "remaining_time": "0:09:45"}
+{"current_steps": 11, "total_steps": 98, "loss": 0.8185, "lr": 9.740045899781353e-06, "epoch": 0.11224489795918367, "percentage": 11.22, "elapsed_time": "0:01:13", "remaining_time": "0:09:38"}
+{"current_steps": 12, "total_steps": 98, "loss": 0.5112, "lr": 9.68603352503172e-06, "epoch": 0.12244897959183673, "percentage": 12.24, "elapsed_time": "0:01:19", "remaining_time": "0:09:31"}
+{"current_steps": 13, "total_steps": 98, "loss": 0.8276, "lr": 9.627106148213521e-06, "epoch": 0.1326530612244898, "percentage": 13.27, "elapsed_time": "0:01:26", "remaining_time": "0:09:23"}
+{"current_steps": 14, "total_steps": 98, "loss": 0.871, "lr": 9.563325576007702e-06, "epoch": 0.14285714285714285, "percentage": 14.29, "elapsed_time": "0:01:32", "remaining_time": "0:09:15"}
+{"current_steps": 15, "total_steps": 98, "loss": 0.6533, "lr": 9.494758705426978e-06, "epoch": 0.15306122448979592, "percentage": 15.31, "elapsed_time": "0:01:39", "remaining_time": "0:09:08"}
+{"current_steps": 16, "total_steps": 98, "loss": 0.8991, "lr": 9.421477453650118e-06, "epoch": 0.16326530612244897, "percentage": 16.33, "elapsed_time": "0:01:45", "remaining_time": "0:09:01"}
+{"current_steps": 17, "total_steps": 98, "loss": 0.9211, "lr": 9.343558682590757e-06, "epoch": 0.17346938775510204, "percentage": 17.35, "elapsed_time": "0:01:52", "remaining_time": "0:08:54"}
+{"current_steps": 18, "total_steps": 98, "loss": 1.0597, "lr": 9.261084118279846e-06, "epoch": 0.1836734693877551, "percentage": 18.37, "elapsed_time": "0:01:58", "remaining_time": "0:08:47"}
+{"current_steps": 19, "total_steps": 98, "loss": 0.851, "lr": 9.174140265146356e-06, "epoch": 0.19387755102040816, "percentage": 19.39, "elapsed_time": "0:02:05", "remaining_time": "0:08:40"}
+{"current_steps": 20, "total_steps": 98, "loss": 0.6259, "lr": 9.082818315286054e-06, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:02:11", "remaining_time": "0:08:33"}
+{"current_steps": 20, "total_steps": 98, "eval_loss": 0.6493471264839172, "epoch": 0.20408163265306123, "percentage": 20.41, "elapsed_time": "0:02:12", "remaining_time": "0:08:36"}
+{"current_steps": 21, "total_steps": 98, "loss": 0.666, "lr": 8.987214052813605e-06, "epoch": 0.21428571428571427, "percentage": 21.43, "elapsed_time": "0:02:19", "remaining_time": "0:08:30"}
+{"current_steps": 22, "total_steps": 98, "loss": 0.8241, "lr": 8.887427753398249e-06, "epoch": 0.22448979591836735, "percentage": 22.45, "elapsed_time": "0:02:25", "remaining_time": "0:08:23"}
+{"current_steps": 23, "total_steps": 98, "loss": 0.6583, "lr": 8.783564079088478e-06, "epoch": 0.23469387755102042, "percentage": 23.47, "elapsed_time": "0:02:32", "remaining_time": "0:08:16"}
+{"current_steps": 24, "total_steps": 98, "loss": 0.5784, "lr": 8.675731968536004e-06, "epoch": 0.24489795918367346, "percentage": 24.49, "elapsed_time": "0:02:38", "remaining_time": "0:08:09"}
+{"current_steps": 25, "total_steps": 98, "loss": 0.7402, "lr": 8.564044522734147e-06, "epoch": 0.25510204081632654, "percentage": 25.51, "elapsed_time": "0:02:45", "remaining_time": "0:08:02"}
+{"current_steps": 26, "total_steps": 98, "loss": 0.6183, "lr": 8.448618886390523e-06, "epoch": 0.2653061224489796, "percentage": 26.53, "elapsed_time": "0:02:51", "remaining_time": "0:07:56"}
+{"current_steps": 27, "total_steps": 98, "loss": 0.715, "lr": 8.329576125058406e-06, "epoch": 0.2755102040816326, "percentage": 27.55, "elapsed_time": "0:02:58", "remaining_time": "0:07:49"}
+{"current_steps": 28, "total_steps": 98, "loss": 0.8192, "lr": 8.207041098155701e-06, "epoch": 0.2857142857142857, "percentage": 28.57, "elapsed_time": "0:03:04", "remaining_time": "0:07:42"}
+{"current_steps": 29, "total_steps": 98, "loss": 0.8079, "lr": 8.081142328004638e-06, "epoch": 0.29591836734693877, "percentage": 29.59, "elapsed_time": "0:03:11", "remaining_time": "0:07:35"}
+{"current_steps": 30, "total_steps": 98, "loss": 0.6613, "lr": 7.952011865029614e-06, "epoch": 0.30612244897959184, "percentage": 30.61, "elapsed_time": "0:03:18", "remaining_time": "0:07:29"}
+{"current_steps": 30, "total_steps": 98, "eval_loss": 0.6358546614646912, "epoch": 0.30612244897959184, "percentage": 30.61, "elapsed_time": "0:03:18", "remaining_time": "0:07:30"}
+{"current_steps": 31, "total_steps": 98, "loss": 0.5806, "lr": 7.819785149254534e-06, "epoch": 0.3163265306122449, "percentage": 31.63, "elapsed_time": "0:03:25", "remaining_time": "0:07:23"}
+{"current_steps": 32, "total_steps": 98, "loss": 0.6589, "lr": 7.68460086824492e-06, "epoch": 0.32653061224489793, "percentage": 32.65, "elapsed_time": "0:03:31", "remaining_time": "0:07:17"}
+{"current_steps": 33, "total_steps": 98, "loss": 0.6457, "lr": 7.546600811643816e-06, "epoch": 0.336734693877551, "percentage": 33.67, "elapsed_time": "0:03:38", "remaining_time": "0:07:10"}
+{"current_steps": 34, "total_steps": 98, "loss": 0.7869, "lr": 7.405929722454026e-06, "epoch": 0.3469387755102041, "percentage": 34.69, "elapsed_time": "0:03:44", "remaining_time": "0:07:03"}
+{"current_steps": 35, "total_steps": 98, "loss": 0.6141, "lr": 7.262735145222696e-06, "epoch": 0.35714285714285715, "percentage": 35.71, "elapsed_time": "0:03:51", "remaining_time": "0:06:56"}
+{"current_steps": 36, "total_steps": 98, "loss": 0.6092, "lr": 7.117167271287453e-06, "epoch": 0.3673469387755102, "percentage": 36.73, "elapsed_time": "0:03:58", "remaining_time": "0:06:49"}
+{"current_steps": 37, "total_steps": 98, "loss": 0.6149, "lr": 6.969378781246436e-06, "epoch": 0.37755102040816324, "percentage": 37.76, "elapsed_time": "0:04:04", "remaining_time": "0:06:43"}
+{"current_steps": 38, "total_steps": 98, "loss": 0.6212, "lr": 6.819524684817439e-06, "epoch": 0.3877551020408163, "percentage": 38.78, "elapsed_time": "0:04:11", "remaining_time": "0:06:36"}
+{"current_steps": 39, "total_steps": 98, "loss": 0.7555, "lr": 6.667762158254104e-06, "epoch": 0.3979591836734694, "percentage": 39.8, "elapsed_time": "0:04:17", "remaining_time": "0:06:29"}
+{"current_steps": 40, "total_steps": 98, "loss": 0.7435, "lr": 6.514250379489754e-06, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:04:24", "remaining_time": "0:06:23"}
+{"current_steps": 40, "total_steps": 98, "eval_loss": 0.6259888410568237, "epoch": 0.40816326530612246, "percentage": 40.82, "elapsed_time": "0:04:25", "remaining_time": "0:06:24"}
+{"current_steps": 41, "total_steps": 98, "loss": 0.5895, "lr": 6.3591503611817155e-06, "epoch": 0.41836734693877553, "percentage": 41.84, "elapsed_time": "0:04:31", "remaining_time": "0:06:17"}
+{"current_steps": 42, "total_steps": 98, "loss": 0.7163, "lr": 6.202624781831269e-06, "epoch": 0.42857142857142855, "percentage": 42.86, "elapsed_time": "0:04:37", "remaining_time": "0:06:10"}
+{"current_steps": 43, "total_steps": 98, "loss": 0.5732, "lr": 6.044837815156377e-06, "epoch": 0.4387755102040816, "percentage": 43.88, "elapsed_time": "0:04:44", "remaining_time": "0:06:03"}
+{"current_steps": 44, "total_steps": 98, "loss": 0.6766, "lr": 5.885954957896115e-06, "epoch": 0.4489795918367347, "percentage": 44.9, "elapsed_time": "0:04:51", "remaining_time": "0:05:57"}
+{"current_steps": 45, "total_steps": 98, "loss": 0.7598, "lr": 5.726142856227453e-06, "epoch": 0.45918367346938777, "percentage": 45.92, "elapsed_time": "0:04:57", "remaining_time": "0:05:50"}
+{"current_steps": 46, "total_steps": 98, "loss": 0.6605, "lr": 5.5655691309764225e-06, "epoch": 0.46938775510204084, "percentage": 46.94, "elapsed_time": "0:05:04", "remaining_time": "0:05:43"}
+{"current_steps": 47, "total_steps": 98, "loss": 0.7614, "lr": 5.404402201807022e-06, "epoch": 0.47959183673469385, "percentage": 47.96, "elapsed_time": "0:05:10", "remaining_time": "0:05:37"}
+{"current_steps": 48, "total_steps": 98, "loss": 0.5739, "lr": 5.242811110572243e-06, "epoch": 0.4897959183673469, "percentage": 48.98, "elapsed_time": "0:05:17", "remaining_time": "0:05:30"}
+{"current_steps": 49, "total_steps": 98, "loss": 0.6136, "lr": 5.080965344012509e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:05:23", "remaining_time": "0:05:23"}
+{"current_steps": 50, "total_steps": 98, "loss": 0.6416, "lr": 4.919034655987493e-06, "epoch": 0.5102040816326531, "percentage": 51.02, "elapsed_time": "0:05:30", "remaining_time": "0:05:17"}
+{"current_steps": 50, "total_steps": 98, "eval_loss": 0.6182550191879272, "epoch": 0.5102040816326531, "percentage": 51.02, "elapsed_time": "0:05:31", "remaining_time": "0:05:17"}
+{"current_steps": 51, "total_steps": 98, "loss": 0.6626, "lr": 4.757188889427761e-06, "epoch": 0.5204081632653061, "percentage": 52.04, "elapsed_time": "0:05:37", "remaining_time": "0:05:11"}
+{"current_steps": 52, "total_steps": 98, "loss": 0.6619, "lr": 4.59559779819298e-06, "epoch": 0.5306122448979592, "percentage": 53.06, "elapsed_time": "0:05:44", "remaining_time": "0:05:04"}
+{"current_steps": 53, "total_steps": 98, "loss": 0.6588, "lr": 4.434430869023579e-06, "epoch": 0.5408163265306123, "percentage": 54.08, "elapsed_time": "0:05:50", "remaining_time": "0:04:57"}
+{"current_steps": 54, "total_steps": 98, "loss": 0.5158, "lr": 4.27385714377255e-06, "epoch": 0.5510204081632653, "percentage": 55.1, "elapsed_time": "0:05:57", "remaining_time": "0:04:51"}
+{"current_steps": 55, "total_steps": 98, "loss": 0.5739, "lr": 4.1140450421038865e-06, "epoch": 0.5612244897959183, "percentage": 56.12, "elapsed_time": "0:06:03", "remaining_time": "0:04:44"}
+{"current_steps": 56, "total_steps": 98, "loss": 0.6139, "lr": 3.955162184843625e-06, "epoch": 0.5714285714285714, "percentage": 57.14, "elapsed_time": "0:06:10", "remaining_time": "0:04:37"}
+{"current_steps": 57, "total_steps": 98, "loss": 0.726, "lr": 3.7973752181687336e-06, "epoch": 0.5816326530612245, "percentage": 58.16, "elapsed_time": "0:06:16", "remaining_time": "0:04:31"}
+{"current_steps": 58, "total_steps": 98, "loss": 0.5639, "lr": 3.6408496388182857e-06, "epoch": 0.5918367346938775, "percentage": 59.18, "elapsed_time": "0:06:23", "remaining_time": "0:04:24"}
+{"current_steps": 59, "total_steps": 98, "loss": 0.7702, "lr": 3.4857496205102475e-06, "epoch": 0.6020408163265306, "percentage": 60.2, "elapsed_time": "0:06:29", "remaining_time": "0:04:17"}
+{"current_steps": 60, "total_steps": 98, "loss": 0.584, "lr": 3.3322378417458985e-06, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:06:36", "remaining_time": "0:04:11"}
+{"current_steps": 60, "total_steps": 98, "eval_loss": 0.6135112643241882, "epoch": 0.6122448979591837, "percentage": 61.22, "elapsed_time": "0:06:37", "remaining_time": "0:04:11"}
+{"current_steps": 61, "total_steps": 98, "loss": 0.7829, "lr": 3.180475315182563e-06, "epoch": 0.6224489795918368, "percentage": 62.24, "elapsed_time": "0:06:43", "remaining_time": "0:04:04"}
+{"current_steps": 62, "total_steps": 98, "loss": 0.6104, "lr": 3.0306212187535653e-06, "epoch": 0.6326530612244898, "percentage": 63.27, "elapsed_time": "0:06:50", "remaining_time": "0:03:58"}
+{"current_steps": 63, "total_steps": 98, "loss": 0.5196, "lr": 2.882832728712551e-06, "epoch": 0.6428571428571429, "percentage": 64.29, "elapsed_time": "0:06:56", "remaining_time": "0:03:51"}
+{"current_steps": 64, "total_steps": 98, "loss": 0.6801, "lr": 2.7372648547773063e-06, "epoch": 0.6530612244897959, "percentage": 65.31, "elapsed_time": "0:07:03", "remaining_time": "0:03:44"}
+{"current_steps": 65, "total_steps": 98, "loss": 0.6176, "lr": 2.594070277545975e-06, "epoch": 0.6632653061224489, "percentage": 66.33, "elapsed_time": "0:07:09", "remaining_time": "0:03:38"}
+{"current_steps": 66, "total_steps": 98, "loss": 0.5881, "lr": 2.4533991883561868e-06, "epoch": 0.673469387755102, "percentage": 67.35, "elapsed_time": "0:07:16", "remaining_time": "0:03:31"}
+{"current_steps": 67, "total_steps": 98, "loss": 0.6984, "lr": 2.315399131755081e-06, "epoch": 0.6836734693877551, "percentage": 68.37, "elapsed_time": "0:07:23", "remaining_time": "0:03:24"}
+{"current_steps": 68, "total_steps": 98, "loss": 0.5849, "lr": 2.1802148507454675e-06, "epoch": 0.6938775510204082, "percentage": 69.39, "elapsed_time": "0:07:29", "remaining_time": "0:03:18"}
+{"current_steps": 69, "total_steps": 98, "loss": 0.5754, "lr": 2.0479881349703885e-06, "epoch": 0.7040816326530612, "percentage": 70.41, "elapsed_time": "0:07:36", "remaining_time": "0:03:11"}
+{"current_steps": 70, "total_steps": 98, "loss": 0.5412, "lr": 1.9188576719953635e-06, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:07:42", "remaining_time": "0:03:05"}
+{"current_steps": 70, "total_steps": 98, "eval_loss": 0.6104864478111267, "epoch": 0.7142857142857143, "percentage": 71.43, "elapsed_time": "0:07:43", "remaining_time": "0:03:05"}
+{"current_steps": 71, "total_steps": 98, "loss": 0.7436, "lr": 1.7929589018443016e-06, "epoch": 0.7244897959183674, "percentage": 72.45, "elapsed_time": "0:07:49", "remaining_time": "0:02:58"}
+{"current_steps": 72, "total_steps": 98, "loss": 0.6451, "lr": 1.6704238749415958e-06, "epoch": 0.7346938775510204, "percentage": 73.47, "elapsed_time": "0:07:56", "remaining_time": "0:02:52"}
+{"current_steps": 73, "total_steps": 98, "loss": 0.5105, "lr": 1.5513811136094786e-06, "epoch": 0.7448979591836735, "percentage": 74.49, "elapsed_time": "0:08:02", "remaining_time": "0:02:45"}
+{"current_steps": 74, "total_steps": 98, "loss": 0.6226, "lr": 1.4359554772658551e-06, "epoch": 0.7551020408163265, "percentage": 75.51, "elapsed_time": "0:08:09", "remaining_time": "0:02:38"}
+{"current_steps": 75, "total_steps": 98, "loss": 0.6833, "lr": 1.3242680314639995e-06, "epoch": 0.7653061224489796, "percentage": 76.53, "elapsed_time": "0:08:16", "remaining_time": "0:02:32"}
+{"current_steps": 76, "total_steps": 98, "loss": 0.7391, "lr": 1.2164359209115235e-06, "epoch": 0.7755102040816326, "percentage": 77.55, "elapsed_time": "0:08:22", "remaining_time": "0:02:25"}
+{"current_steps": 77, "total_steps": 98, "loss": 0.6871, "lr": 1.1125722466017547e-06, "epoch": 0.7857142857142857, "percentage": 78.57, "elapsed_time": "0:08:29", "remaining_time": "0:02:18"}
+{"current_steps": 78, "total_steps": 98, "loss": 0.5721, "lr": 1.012785947186397e-06, "epoch": 0.7959183673469388, "percentage": 79.59, "elapsed_time": "0:08:35", "remaining_time": "0:02:12"}
+{"current_steps": 79, "total_steps": 98, "loss": 0.7103, "lr": 9.171816847139447e-07, "epoch": 0.8061224489795918, "percentage": 80.61, "elapsed_time": "0:08:42", "remaining_time": "0:02:05"}
+{"current_steps": 80, "total_steps": 98, "loss": 0.799, "lr": 8.258597348536452e-07, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:08:48", "remaining_time": "0:01:58"}
+{"current_steps": 80, "total_steps": 98, "eval_loss": 0.6090193390846252, "epoch": 0.8163265306122449, "percentage": 81.63, "elapsed_time": "0:08:49", "remaining_time": "0:01:59"}
+{"current_steps": 81, "total_steps": 98, "loss": 0.8626, "lr": 7.389158817201541e-07, "epoch": 0.826530612244898, "percentage": 82.65, "elapsed_time": "0:08:56", "remaining_time": "0:01:52"}
+{"current_steps": 82, "total_steps": 98, "loss": 0.6516, "lr": 6.564413174092443e-07, "epoch": 0.8367346938775511, "percentage": 83.67, "elapsed_time": "0:09:02", "remaining_time": "0:01:45"}
+{"current_steps": 83, "total_steps": 98, "loss": 0.6813, "lr": 5.785225463498828e-07, "epoch": 0.8469387755102041, "percentage": 84.69, "elapsed_time": "0:09:09", "remaining_time": "0:01:39"}
+{"current_steps": 84, "total_steps": 98, "loss": 0.7443, "lr": 5.05241294573024e-07, "epoch": 0.8571428571428571, "percentage": 85.71, "elapsed_time": "0:09:15", "remaining_time": "0:01:32"}
+{"current_steps": 85, "total_steps": 98, "loss": 0.5733, "lr": 4.3667442399229985e-07, "epoch": 0.8673469387755102, "percentage": 86.73, "elapsed_time": "0:09:22", "remaining_time": "0:01:26"}
+{"current_steps": 86, "total_steps": 98, "loss": 0.7788, "lr": 3.728938517864794e-07, "epoch": 0.8775510204081632, "percentage": 87.76, "elapsed_time": "0:09:28", "remaining_time": "0:01:19"}
+{"current_steps": 87, "total_steps": 98, "loss": 0.697, "lr": 3.1396647496828245e-07, "epoch": 0.8877551020408163, "percentage": 88.78, "elapsed_time": "0:09:35", "remaining_time": "0:01:12"}
+{"current_steps": 88, "total_steps": 98, "loss": 0.6064, "lr": 2.599541002186479e-07, "epoch": 0.8979591836734694, "percentage": 89.8, "elapsed_time": "0:09:41", "remaining_time": "0:01:06"}
+{"current_steps": 89, "total_steps": 98, "loss": 0.6339, "lr": 2.109133790600648e-07, "epoch": 0.9081632653061225, "percentage": 90.82, "elapsed_time": "0:09:48", "remaining_time": "0:00:59"}
+{"current_steps": 90, "total_steps": 98, "loss": 0.8355, "lr": 1.6689574843694433e-07, "epoch": 0.9183673469387755, "percentage": 91.84, "elapsed_time": "0:09:55", "remaining_time": "0:00:52"}
+{"current_steps": 90, "total_steps": 98, "eval_loss": 0.6084674000740051, "epoch": 0.9183673469387755, "percentage": 91.84, "elapsed_time": "0:09:55", "remaining_time": "0:00:52"}
+{"current_steps": 91, "total_steps": 98, "loss": 0.6868, "lr": 1.2794737676536993e-07, "epoch": 0.9285714285714286, "percentage": 92.86, "elapsed_time": "0:10:02", "remaining_time": "0:00:46"}
+{"current_steps": 92, "total_steps": 98, "loss": 0.6827, "lr": 9.410911550880474e-08, "epoch": 0.9387755102040817, "percentage": 93.88, "elapsed_time": "0:10:08", "remaining_time": "0:00:39"}
+{"current_steps": 93, "total_steps": 98, "loss": 0.5356, "lr": 6.54164563305465e-08, "epoch": 0.9489795918367347, "percentage": 94.9, "elapsed_time": "0:10:15", "remaining_time": "0:00:33"}
+{"current_steps": 94, "total_steps": 98, "loss": 0.6793, "lr": 4.189949386787462e-08, "epoch": 0.9591836734693877, "percentage": 95.92, "elapsed_time": "0:10:21", "remaining_time": "0:00:26"}
+{"current_steps": 95, "total_steps": 98, "loss": 0.7195, "lr": 2.358289416693027e-08, "epoch": 0.9693877551020408, "percentage": 96.94, "elapsed_time": "0:10:28", "remaining_time": "0:00:19"}
+{"current_steps": 96, "total_steps": 98, "loss": 0.5873, "lr": 1.0485868811441757e-08, "epoch": 0.9795918367346939, "percentage": 97.96, "elapsed_time": "0:10:34", "remaining_time": "0:00:13"}
+{"current_steps": 97, "total_steps": 98, "loss": 0.6365, "lr": 2.6221547724253337e-09, "epoch": 0.9897959183673469, "percentage": 98.98, "elapsed_time": "0:10:41", "remaining_time": "0:00:06"}
+{"current_steps": 98, "total_steps": 98, "loss": 0.5644, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:10:48", "remaining_time": "0:00:00"}
+{"current_steps": 98, "total_steps": 98, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:11:39", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,821 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 11,
+  "global_step": 101,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009900990099009901,
+      "grad_norm": 1.9865820407867432,
+      "learning_rate": 5e-06,
+      "loss": 0.8807,
+      "step": 1
+    },
+    {
+      "epoch": 0.019801980198019802,
+      "grad_norm": 1.6995460987091064,
+      "learning_rate": 1e-05,
+      "loss": 0.7298,
+      "step": 2
+    },
+    {
+      "epoch": 0.0297029702970297,
+      "grad_norm": 1.870273232460022,
+      "learning_rate": 9.997482711915926e-06,
+      "loss": 0.8256,
+      "step": 3
+    },
+    {
+      "epoch": 0.039603960396039604,
+      "grad_norm": 2.035698175430298,
+      "learning_rate": 9.989933382359423e-06,
+      "loss": 0.8423,
+      "step": 4
+    },
+    {
+      "epoch": 0.04950495049504951,
+      "grad_norm": 1.5802401304244995,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 1.0321,
+      "step": 5
+    },
+    {
+      "epoch": 0.0594059405940594,
+      "grad_norm": 1.3238128423690796,
+      "learning_rate": 9.959774064153977e-06,
+      "loss": 0.7894,
+      "step": 6
+    },
+    {
+      "epoch": 0.06930693069306931,
+      "grad_norm": 1.3449586629867554,
+      "learning_rate": 9.937194443381972e-06,
+      "loss": 0.69,
+      "step": 7
+    },
+    {
+      "epoch": 0.07920792079207921,
+      "grad_norm": 1.215697169303894,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 0.8263,
+      "step": 8
+    },
+    {
+      "epoch": 0.0891089108910891,
+      "grad_norm": 1.4947011470794678,
+      "learning_rate": 9.877148934427037e-06,
+      "loss": 0.7706,
+      "step": 9
+    },
+    {
+      "epoch": 0.09900990099009901,
+      "grad_norm": 0.9939355850219727,
+      "learning_rate": 9.839743506981783e-06,
+      "loss": 0.6854,
+      "step": 10
+    },
+    {
+      "epoch": 0.10891089108910891,
+      "grad_norm": 1.3050940036773682,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 0.9061,
+      "step": 11
+    },
+    {
+      "epoch": 0.10891089108910891,
+      "eval_loss": 0.7099791765213013,
+      "eval_runtime": 1.6876,
+      "eval_samples_per_second": 5.333,
+      "eval_steps_per_second": 1.185,
+      "step": 11
+    },
+    {
+      "epoch": 0.1188118811881188,
+      "grad_norm": 1.0027287006378174,
+      "learning_rate": 9.750355588704728e-06,
+      "loss": 0.7043,
+      "step": 12
+    },
+    {
+      "epoch": 0.12871287128712872,
+      "grad_norm": 0.9371753334999084,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.6727,
+      "step": 13
+    },
+    {
+      "epoch": 0.13861386138613863,
+      "grad_norm": 0.9471062421798706,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 0.6772,
+      "step": 14
+    },
+    {
+      "epoch": 0.1485148514851485,
+      "grad_norm": 1.1542134284973145,
+      "learning_rate": 9.580542287160348e-06,
+      "loss": 0.7956,
+      "step": 15
+    },
+    {
+      "epoch": 0.15841584158415842,
+      "grad_norm": 1.1275238990783691,
+      "learning_rate": 9.514632691433108e-06,
+      "loss": 0.7486,
+      "step": 16
+    },
+    {
+      "epoch": 0.16831683168316833,
+      "grad_norm": 1.0453617572784424,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 0.659,
+      "step": 17
+    },
+    {
+      "epoch": 0.1782178217821782,
+      "grad_norm": 1.0331149101257324,
+      "learning_rate": 9.369246885348926e-06,
+      "loss": 0.7471,
+      "step": 18
+    },
+    {
+      "epoch": 0.18811881188118812,
+      "grad_norm": 0.8706634044647217,
+      "learning_rate": 9.289917066174887e-06,
+      "loss": 0.5547,
+      "step": 19
+    },
+    {
+      "epoch": 0.19801980198019803,
+      "grad_norm": 1.1781532764434814,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.6239,
+      "step": 20
+    },
+    {
+      "epoch": 0.2079207920792079,
+      "grad_norm": 1.2011443376541138,
+      "learning_rate": 9.118382907149164e-06,
+      "loss": 0.7847,
+      "step": 21
+    },
+    {
+      "epoch": 0.21782178217821782,
+      "grad_norm": 1.028536319732666,
+      "learning_rate": 9.026351287655294e-06,
+      "loss": 0.6565,
+      "step": 22
+    },
+    {
+      "epoch": 0.21782178217821782,
+      "eval_loss": 0.6684643030166626,
+      "eval_runtime": 1.6848,
+      "eval_samples_per_second": 5.342,
+      "eval_steps_per_second": 1.187,
+      "step": 22
+    },
+    {
+      "epoch": 0.22772277227722773,
+      "grad_norm": 0.9103761315345764,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.6495,
+      "step": 23
+    },
+    {
+      "epoch": 0.2376237623762376,
+      "grad_norm": 1.0075730085372925,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.7109,
+      "step": 24
+    },
+    {
+      "epoch": 0.24752475247524752,
+      "grad_norm": 0.9617104530334473,
+      "learning_rate": 8.726322248378775e-06,
+      "loss": 0.6993,
+      "step": 25
+    },
+    {
+      "epoch": 0.25742574257425743,
+      "grad_norm": 1.072245717048645,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.8897,
+      "step": 26
+    },
+    {
+      "epoch": 0.26732673267326734,
+      "grad_norm": 1.0244859457015991,
+      "learning_rate": 8.507374438531606e-06,
+      "loss": 0.8158,
+      "step": 27
+    },
+    {
+      "epoch": 0.27722772277227725,
+      "grad_norm": 1.0862797498703003,
+      "learning_rate": 8.392547057785662e-06,
+      "loss": 0.7539,
+      "step": 28
+    },
+    {
+      "epoch": 0.2871287128712871,
+      "grad_norm": 0.9954370260238647,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.718,
+      "step": 29
+    },
+    {
+      "epoch": 0.297029702970297,
+      "grad_norm": 1.0018794536590576,
+      "learning_rate": 8.152763335422612e-06,
+      "loss": 0.7518,
+      "step": 30
+    },
+    {
+      "epoch": 0.3069306930693069,
+      "grad_norm": 0.9397566318511963,
+      "learning_rate": 8.028048435688333e-06,
+      "loss": 0.663,
+      "step": 31
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 0.8733705878257751,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.6565,
+      "step": 32
+    },
+    {
+      "epoch": 0.32673267326732675,
+      "grad_norm": 0.938222348690033,
+      "learning_rate": 7.769600319330553e-06,
+      "loss": 0.601,
+      "step": 33
+    },
+    {
+      "epoch": 0.32673267326732675,
+      "eval_loss": 0.648015022277832,
+      "eval_runtime": 1.6839,
+      "eval_samples_per_second": 5.345,
+      "eval_steps_per_second": 1.188,
+      "step": 33
+    },
+    {
+      "epoch": 0.33663366336633666,
+      "grad_norm": 0.9610555768013,
+      "learning_rate": 7.636127338052513e-06,
+      "loss": 0.7488,
+      "step": 34
+    },
+    {
+      "epoch": 0.3465346534653465,
+      "grad_norm": 1.0051265954971313,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.7929,
+      "step": 35
+    },
+    {
+      "epoch": 0.3564356435643564,
+      "grad_norm": 0.8689800500869751,
+      "learning_rate": 7.361355373863415e-06,
+      "loss": 0.57,
+      "step": 36
+    },
+    {
+      "epoch": 0.36633663366336633,
+      "grad_norm": 1.0085370540618896,
+      "learning_rate": 7.2203330630288714e-06,
+      "loss": 0.672,
+      "step": 37
+    },
+    {
+      "epoch": 0.37623762376237624,
+      "grad_norm": 0.8325203061103821,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.6143,
+      "step": 38
+    },
+    {
+      "epoch": 0.38613861386138615,
+      "grad_norm": 0.9245986342430115,
+      "learning_rate": 6.931725628465643e-06,
+      "loss": 0.7288,
+      "step": 39
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 1.1846799850463867,
+      "learning_rate": 6.78443110795936e-06,
+      "loss": 0.8207,
+      "step": 40
+    },
+    {
+      "epoch": 0.40594059405940597,
+      "grad_norm": 0.8949479460716248,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.6476,
+      "step": 41
+    },
+    {
+      "epoch": 0.4158415841584158,
+      "grad_norm": 0.9853402376174927,
+      "learning_rate": 6.484601876641375e-06,
+      "loss": 0.7146,
+      "step": 42
+    },
+    {
+      "epoch": 0.42574257425742573,
+      "grad_norm": 0.9564022421836853,
+      "learning_rate": 6.332369068450175e-06,
+      "loss": 0.7382,
+      "step": 43
+    },
+    {
+      "epoch": 0.43564356435643564,
+      "grad_norm": 1.0044441223144531,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.7668,
+      "step": 44
+    },
+    {
+      "epoch": 0.43564356435643564,
+      "eval_loss": 0.6342881917953491,
+      "eval_runtime": 1.6847,
+      "eval_samples_per_second": 5.342,
+      "eval_steps_per_second": 1.187,
+      "step": 44
+    },
+    {
+      "epoch": 0.44554455445544555,
+      "grad_norm": 0.8848042488098145,
+      "learning_rate": 6.024033340325954e-06,
+      "loss": 0.6532,
+      "step": 45
+    },
+    {
+      "epoch": 0.45544554455445546,
+      "grad_norm": 0.8762900233268738,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.674,
+      "step": 46
+    },
+    {
+      "epoch": 0.46534653465346537,
+      "grad_norm": 0.8674903512001038,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.6138,
+      "step": 47
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.9267687201499939,
+      "learning_rate": 5.5541909995050554e-06,
+      "loss": 0.6838,
+      "step": 48
+    },
+    {
+      "epoch": 0.48514851485148514,
+      "grad_norm": 0.8423399329185486,
+      "learning_rate": 5.396249784283943e-06,
+      "loss": 0.6081,
+      "step": 49
+    },
+    {
+      "epoch": 0.49504950495049505,
+      "grad_norm": 0.9809019565582275,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.7202,
+      "step": 50
+    },
+    {
+      "epoch": 0.504950495049505,
+      "grad_norm": 0.8688491582870483,
+      "learning_rate": 5.07932981917404e-06,
+      "loss": 0.6236,
+      "step": 51
+    },
+    {
+      "epoch": 0.5148514851485149,
+      "grad_norm": 0.9908064007759094,
+      "learning_rate": 4.9206701808259605e-06,
+      "loss": 0.7449,
+      "step": 52
+    },
+    {
+      "epoch": 0.5247524752475248,
+      "grad_norm": 0.935342013835907,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.6582,
+      "step": 53
+    },
+    {
+      "epoch": 0.5346534653465347,
+      "grad_norm": 1.0338435173034668,
+      "learning_rate": 4.603750215716057e-06,
+      "loss": 0.7808,
+      "step": 54
+    },
+    {
+      "epoch": 0.5445544554455446,
+      "grad_norm": 1.0253307819366455,
+      "learning_rate": 4.445809000494945e-06,
+      "loss": 0.8058,
+      "step": 55
+    },
+    {
+      "epoch": 0.5445544554455446,
+      "eval_loss": 0.6248189210891724,
+      "eval_runtime": 1.6835,
+      "eval_samples_per_second": 5.346,
+      "eval_steps_per_second": 1.188,
+      "step": 55
+    },
+    {
+      "epoch": 0.5544554455445545,
+      "grad_norm": 0.9448875188827515,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.7117,
+      "step": 56
+    },
+    {
+      "epoch": 0.5643564356435643,
+      "grad_norm": 0.8737557530403137,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.5988,
+      "step": 57
+    },
+    {
+      "epoch": 0.5742574257425742,
+      "grad_norm": 0.764798104763031,
+      "learning_rate": 3.975966659674048e-06,
+      "loss": 0.501,
+      "step": 58
+    },
+    {
+      "epoch": 0.5841584158415841,
+      "grad_norm": 0.9195338487625122,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.677,
+      "step": 59
+    },
+    {
+      "epoch": 0.594059405940594,
+      "grad_norm": 0.9102662801742554,
+      "learning_rate": 3.667630931549826e-06,
+      "loss": 0.6363,
+      "step": 60
+    },
+    {
+      "epoch": 0.6039603960396039,
+      "grad_norm": 1.1512144804000854,
+      "learning_rate": 3.5153981233586277e-06,
+      "loss": 0.7082,
+      "step": 61
+    },
+    {
+      "epoch": 0.6138613861386139,
+      "grad_norm": 1.0006070137023926,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.6685,
+      "step": 62
+    },
+    {
+      "epoch": 0.6237623762376238,
+      "grad_norm": 0.9273307919502258,
+      "learning_rate": 3.2155688920406415e-06,
+      "loss": 0.6652,
+      "step": 63
+    },
+    {
+      "epoch": 0.6336633663366337,
+      "grad_norm": 0.9092214703559875,
+      "learning_rate": 3.0682743715343565e-06,
+      "loss": 0.6497,
+      "step": 64
+    },
+    {
+      "epoch": 0.6435643564356436,
+      "grad_norm": 0.8190207481384277,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.5194,
+      "step": 65
+    },
+    {
+      "epoch": 0.6534653465346535,
+      "grad_norm": 0.9039291739463806,
+      "learning_rate": 2.7796669369711294e-06,
+      "loss": 0.675,
+      "step": 66
+    },
+    {
+      "epoch": 0.6534653465346535,
+      "eval_loss": 0.6190232038497925,
+      "eval_runtime": 1.6846,
+      "eval_samples_per_second": 5.342,
+      "eval_steps_per_second": 1.187,
+      "step": 66
+    },
+    {
+      "epoch": 0.6633663366336634,
+      "grad_norm": 1.0311757326126099,
+      "learning_rate": 2.6386446261365874e-06,
+      "loss": 0.8244,
+      "step": 67
+    },
+    {
+      "epoch": 0.6732673267326733,
+      "grad_norm": 0.8113132119178772,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.5488,
+      "step": 68
+    },
+    {
+      "epoch": 0.6831683168316832,
+      "grad_norm": 0.9003159403800964,
+      "learning_rate": 2.363872661947488e-06,
+      "loss": 0.7291,
+      "step": 69
+    },
+    {
+      "epoch": 0.693069306930693,
+      "grad_norm": 1.057133674621582,
+      "learning_rate": 2.230399680669449e-06,
+      "loss": 0.8625,
+      "step": 70
+    },
+    {
+      "epoch": 0.7029702970297029,
+      "grad_norm": 0.9384030699729919,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.6813,
+      "step": 71
+    },
+    {
+      "epoch": 0.7128712871287128,
+      "grad_norm": 0.8832238912582397,
+      "learning_rate": 1.971951564311668e-06,
+      "loss": 0.6099,
+      "step": 72
+    },
+    {
+      "epoch": 0.7227722772277227,
+      "grad_norm": 0.8297242522239685,
+      "learning_rate": 1.8472366645773892e-06,
+      "loss": 0.5465,
+      "step": 73
+    },
+    {
+      "epoch": 0.7326732673267327,
+      "grad_norm": 0.9183589816093445,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.6971,
+      "step": 74
+    },
+    {
+      "epoch": 0.7425742574257426,
+      "grad_norm": 0.8353100419044495,
+      "learning_rate": 1.6074529422143398e-06,
+      "loss": 0.5426,
+      "step": 75
+    },
+    {
+      "epoch": 0.7524752475247525,
+      "grad_norm": 1.051756739616394,
+      "learning_rate": 1.4926255614683931e-06,
+      "loss": 0.7567,
+      "step": 76
+    },
+    {
+      "epoch": 0.7623762376237624,
+      "grad_norm": 0.8063908815383911,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.5383,
+      "step": 77
+    },
+    {
+      "epoch": 0.7623762376237624,
+      "eval_loss": 0.6155756711959839,
+      "eval_runtime": 1.6854,
+      "eval_samples_per_second": 5.34,
+      "eval_steps_per_second": 1.187,
+      "step": 77
+    },
+    {
+      "epoch": 0.7722772277227723,
+      "grad_norm": 0.8472511768341064,
+      "learning_rate": 1.2736777516212267e-06,
+      "loss": 0.5792,
+      "step": 78
+    },
+    {
+      "epoch": 0.7821782178217822,
+      "grad_norm": 0.8465410470962524,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.6283,
+      "step": 79
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.7360741496086121,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.4699,
+      "step": 80
+    },
+    {
+      "epoch": 0.801980198019802,
+      "grad_norm": 0.9224135875701904,
+      "learning_rate": 9.73648712344707e-07,
+      "loss": 0.6806,
+      "step": 81
+    },
+    {
+      "epoch": 0.8118811881188119,
+      "grad_norm": 0.871505081653595,
+      "learning_rate": 8.816170928508367e-07,
+      "loss": 0.6824,
+      "step": 82
+    },
+    {
+      "epoch": 0.8217821782178217,
+      "grad_norm": 0.8890396952629089,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.6427,
+      "step": 83
+    },
+    {
+      "epoch": 0.8316831683168316,
+      "grad_norm": 1.091757893562317,
+      "learning_rate": 7.100829338251147e-07,
+      "loss": 0.7535,
+      "step": 84
+    },
+    {
+      "epoch": 0.8415841584158416,
+      "grad_norm": 0.809833824634552,
+      "learning_rate": 6.307531146510754e-07,
+      "loss": 0.5965,
+      "step": 85
+    },
+    {
+      "epoch": 0.8514851485148515,
+      "grad_norm": 0.861588716506958,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.6629,
+      "step": 86
+    },
+    {
+      "epoch": 0.8613861386138614,
+      "grad_norm": 0.7921182513237,
+      "learning_rate": 4.853673085668947e-07,
+      "loss": 0.482,
+      "step": 87
+    },
+    {
+      "epoch": 0.8712871287128713,
+      "grad_norm": 0.7692471742630005,
+      "learning_rate": 4.194577128396521e-07,
+      "loss": 0.5044,
+      "step": 88
+    },
+    {
+      "epoch": 0.8712871287128713,
+      "eval_loss": 0.6139124035835266,
+      "eval_runtime": 1.684,
+      "eval_samples_per_second": 5.344,
+      "eval_steps_per_second": 1.188,
+      "step": 88
+    },
+    {
+      "epoch": 0.8811881188118812,
+      "grad_norm": 0.8603846430778503,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.6439,
+      "step": 89
+    },
+    {
+      "epoch": 0.8910891089108911,
+      "grad_norm": 0.8953405022621155,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.6881,
+      "step": 90
+    },
+    {
+      "epoch": 0.900990099009901,
+      "grad_norm": 0.9108988046646118,
+      "learning_rate": 2.4964441129527337e-07,
+      "loss": 0.7118,
+      "step": 91
+    },
+    {
+      "epoch": 0.9108910891089109,
+      "grad_norm": 0.886647641658783,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.7544,
+      "step": 92
+    },
+    {
+      "epoch": 0.9207920792079208,
+      "grad_norm": 0.943878173828125,
+      "learning_rate": 1.6025649301821877e-07,
+      "loss": 0.7527,
+      "step": 93
+    },
+    {
+      "epoch": 0.9306930693069307,
+      "grad_norm": 0.8354966044425964,
+      "learning_rate": 1.2285106557296479e-07,
+      "loss": 0.6079,
+      "step": 94
+    },
+    {
+      "epoch": 0.9405940594059405,
+      "grad_norm": 0.8121664524078369,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.5891,
+      "step": 95
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 0.9194057583808899,
+      "learning_rate": 6.280555661802857e-08,
+      "loss": 0.6953,
+      "step": 96
+    },
+    {
+      "epoch": 0.9603960396039604,
+      "grad_norm": 0.9447068572044373,
+      "learning_rate": 4.02259358460233e-08,
+      "loss": 0.7401,
+      "step": 97
+    },
+    {
+      "epoch": 0.9702970297029703,
+      "grad_norm": 0.8672422766685486,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.6349,
+      "step": 98
+    },
+    {
+      "epoch": 0.9801980198019802,
+      "grad_norm": 0.904771625995636,
+      "learning_rate": 1.006661764057837e-08,
+      "loss": 0.6322,
+      "step": 99
+    },
+    {
+      "epoch": 0.9801980198019802,
+      "eval_loss": 0.6136024594306946,
+      "eval_runtime": 1.6864,
+      "eval_samples_per_second": 5.337,
+      "eval_steps_per_second": 1.186,
+      "step": 99
+    },
+    {
+      "epoch": 0.9900990099009901,
+      "grad_norm": 0.8689496517181396,
+      "learning_rate": 2.5172880840745873e-09,
+      "loss": 0.6191,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8673611283302307,
+      "learning_rate": 0.0,
+      "loss": 0.5897,
+      "step": 101
+    },
+    {
+      "epoch": 1.0,
+      "step": 101,
+      "total_flos": 1.5438974547499418e+17,
+      "train_loss": 0.6889385657735391,
+      "train_runtime": 730.4137,
+      "train_samples_per_second": 1.101,
+      "train_steps_per_second": 0.138
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 101,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 101,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5438974547499418e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99acf1f883cdae772786ea6621e350833b8e08ae72980b815cd4641d5444798a
+size 7160