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 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: code_finetune
+  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. -->
+
+# code_finetune
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B) on the open_thoughts_19K dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+
+## 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: 6
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 48
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.3178        | 1.0   | 2986  | nan             |
+| 1.0555        | 2.0   | 5972  | nan             |
+| 0.7954        | 3.0   | 8958  | nan             |
+| 0.5992        | 4.0   | 11944 | nan             |
+| 0.5494        | 5.0   | 14930 | nan             |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_loss": NaN,
+    "eval_runtime": 348.2336,
+    "eval_samples_per_second": 45.728,
+    "eval_steps_per_second": 1.43,
+    "total_flos": 7403300223713280.0,
+    "train_loss": 0.9973710162960596,
+    "train_runtime": 63021.9977,
+    "train_samples_per_second": 11.37,
+    "train_steps_per_second": 0.237
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 48,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 5.0,
+    "eval_loss": NaN,
+    "eval_runtime": 348.2336,
+    "eval_samples_per_second": 45.728,
+    "eval_steps_per_second": 1.43
+}

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": "4.45.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbcea1e6a0ec952df2aba5b0efcf97192435619bdca797713f4eb2d507d1fdd
+size 4986211280

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be6695429c49826c7e8237b13d974cac0c02093cc6603373fd0749e03cf6ff62
+size 4954847344

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aee174d346418ebc436b65cc0209610ac4debbe76c5d8b8121bdd108dde3de1d
+size 4954847392

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c81a377241295de8f68f9b22c23483ad1f1dd2e3c0f36be474d035d4564284c
+size 4954847392

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b65d5bd4fbfc9340125cc74987c841b35d7ce3740ce98b1cb21150c001d70d3
+size 4954847392

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62887914eefc17ce071c28defe9e60395b14855d6eaf7f4688b513e03f420f1c
+size 4734533160

model.safetensors.index.json

@@ -0,0 +1,586 @@
+{
+  "metadata": {
+    "total_size": 29540067328
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.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｜><think>\\n'}}{% 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": 5.0,
+    "total_flos": 7403300223713280.0,
+    "train_loss": 0.9973710162960596,
+    "train_runtime": 63021.9977,
+    "train_samples_per_second": 11.37,
+    "train_steps_per_second": 0.237
+}

trainer_log.jsonl

@@ -0,0 +1,155 @@
+{"current_steps": 100, "total_steps": 14930, "loss": 11.7393, "lr": 6.697923643670463e-07, "epoch": 0.033489618218352314, "percentage": 0.67, "elapsed_time": "0:06:51", "remaining_time": "16:57:30"}
+{"current_steps": 200, "total_steps": 14930, "loss": 3.297, "lr": 1.3395847287340927e-06, "epoch": 0.06697923643670463, "percentage": 1.34, "elapsed_time": "0:13:36", "remaining_time": "16:42:12"}
+{"current_steps": 300, "total_steps": 14930, "loss": 1.8384, "lr": 2.0093770931011387e-06, "epoch": 0.10046885465505694, "percentage": 2.01, "elapsed_time": "0:20:21", "remaining_time": "16:32:31"}
+{"current_steps": 400, "total_steps": 14930, "loss": 1.6728, "lr": 2.6791694574681854e-06, "epoch": 0.13395847287340926, "percentage": 2.68, "elapsed_time": "0:27:05", "remaining_time": "16:23:50"}
+{"current_steps": 500, "total_steps": 14930, "loss": 1.5883, "lr": 3.3489618218352316e-06, "epoch": 0.16744809109176156, "percentage": 3.35, "elapsed_time": "0:33:48", "remaining_time": "16:15:55"}
+{"current_steps": 600, "total_steps": 14930, "loss": 1.5399, "lr": 4.018754186202277e-06, "epoch": 0.20093770931011387, "percentage": 4.02, "elapsed_time": "0:40:33", "remaining_time": "16:08:31"}
+{"current_steps": 700, "total_steps": 14930, "loss": 1.5214, "lr": 4.688546550569324e-06, "epoch": 0.23442732752846618, "percentage": 4.69, "elapsed_time": "0:47:17", "remaining_time": "16:01:25"}
+{"current_steps": 800, "total_steps": 14930, "loss": 1.4822, "lr": 5.358338914936371e-06, "epoch": 0.2679169457468185, "percentage": 5.36, "elapsed_time": "0:54:01", "remaining_time": "15:54:17"}
+{"current_steps": 900, "total_steps": 14930, "loss": 1.4623, "lr": 6.028131279303416e-06, "epoch": 0.3014065639651708, "percentage": 6.03, "elapsed_time": "1:00:45", "remaining_time": "15:47:12"}
+{"current_steps": 1000, "total_steps": 14930, "loss": 1.4408, "lr": 6.697923643670463e-06, "epoch": 0.33489618218352313, "percentage": 6.7, "elapsed_time": "1:07:29", "remaining_time": "15:40:09"}
+{"current_steps": 1100, "total_steps": 14930, "loss": 1.4378, "lr": 7.3677160080375086e-06, "epoch": 0.3683858004018754, "percentage": 7.37, "elapsed_time": "1:15:46", "remaining_time": "15:52:37"}
+{"current_steps": 1200, "total_steps": 14930, "loss": 1.4189, "lr": 8.037508372404555e-06, "epoch": 0.40187541862022774, "percentage": 8.04, "elapsed_time": "1:22:29", "remaining_time": "15:43:56"}
+{"current_steps": 1300, "total_steps": 14930, "loss": 1.4098, "lr": 8.707300736771601e-06, "epoch": 0.43536503683858, "percentage": 8.71, "elapsed_time": "1:29:14", "remaining_time": "15:35:38"}
+{"current_steps": 1400, "total_steps": 14930, "loss": 1.4011, "lr": 9.377093101138647e-06, "epoch": 0.46885465505693236, "percentage": 9.38, "elapsed_time": "1:35:58", "remaining_time": "15:27:33"}
+{"current_steps": 1500, "total_steps": 14930, "loss": 1.3933, "lr": 9.999993303758581e-06, "epoch": 0.5023442732752846, "percentage": 10.05, "elapsed_time": "1:42:42", "remaining_time": "15:19:35"}
+{"current_steps": 1600, "total_steps": 14930, "loss": 1.3828, "lr": 9.998435483941776e-06, "epoch": 0.535833891493637, "percentage": 10.72, "elapsed_time": "1:49:26", "remaining_time": "15:11:49"}
+{"current_steps": 1700, "total_steps": 14930, "loss": 1.3772, "lr": 9.994145483428403e-06, "epoch": 0.5693235097119893, "percentage": 11.39, "elapsed_time": "1:56:11", "remaining_time": "15:04:11"}
+{"current_steps": 1800, "total_steps": 14930, "loss": 1.3674, "lr": 9.987125647163527e-06, "epoch": 0.6028131279303416, "percentage": 12.06, "elapsed_time": "2:02:54", "remaining_time": "14:56:35"}
+{"current_steps": 1900, "total_steps": 14930, "loss": 1.3538, "lr": 9.977379812240013e-06, "epoch": 0.6363027461486939, "percentage": 12.73, "elapsed_time": "2:09:40", "remaining_time": "14:49:14"}
+{"current_steps": 2000, "total_steps": 14930, "loss": 1.3566, "lr": 9.964913305801151e-06, "epoch": 0.6697923643670463, "percentage": 13.4, "elapsed_time": "2:16:24", "remaining_time": "14:41:50"}
+{"current_steps": 2100, "total_steps": 14930, "loss": 1.3473, "lr": 9.9497329421288e-06, "epoch": 0.7032819825853985, "percentage": 14.07, "elapsed_time": "2:24:07", "remaining_time": "14:40:30"}
+{"current_steps": 2200, "total_steps": 14930, "loss": 1.35, "lr": 9.931847018918654e-06, "epoch": 0.7367716008037508, "percentage": 14.74, "elapsed_time": "2:30:52", "remaining_time": "14:32:59"}
+{"current_steps": 2300, "total_steps": 14930, "loss": 1.3381, "lr": 9.911265312744663e-06, "epoch": 0.7702612190221031, "percentage": 15.41, "elapsed_time": "2:37:37", "remaining_time": "14:25:31"}
+{"current_steps": 2400, "total_steps": 14930, "loss": 1.3409, "lr": 9.887999073715083e-06, "epoch": 0.8037508372404555, "percentage": 16.08, "elapsed_time": "2:44:21", "remaining_time": "14:18:05"}
+{"current_steps": 2500, "total_steps": 14930, "loss": 1.333, "lr": 9.86206101932309e-06, "epoch": 0.8372404554588078, "percentage": 16.74, "elapsed_time": "2:51:05", "remaining_time": "14:10:41"}
+{"current_steps": 2600, "total_steps": 14930, "loss": 1.3195, "lr": 9.833465327495307e-06, "epoch": 0.87073007367716, "percentage": 17.41, "elapsed_time": "2:57:52", "remaining_time": "14:03:30"}
+{"current_steps": 2700, "total_steps": 14930, "loss": 1.3183, "lr": 9.802227628842045e-06, "epoch": 0.9042196918955124, "percentage": 18.08, "elapsed_time": "3:04:36", "remaining_time": "13:56:10"}
+{"current_steps": 2800, "total_steps": 14930, "loss": 1.3145, "lr": 9.7683649981135e-06, "epoch": 0.9377093101138647, "percentage": 18.75, "elapsed_time": "3:11:20", "remaining_time": "13:48:54"}
+{"current_steps": 2900, "total_steps": 14930, "loss": 1.3178, "lr": 9.731895944866576e-06, "epoch": 0.971198928332217, "percentage": 19.42, "elapsed_time": "3:18:04", "remaining_time": "13:41:41"}
+{"current_steps": 2986, "total_steps": 14930, "eval_loss": NaN, "epoch": 1.0, "percentage": 20.0, "elapsed_time": "3:29:40", "remaining_time": "13:58:41"}
+{"current_steps": 3000, "total_steps": 14930, "loss": 1.3204, "lr": 9.69284040334742e-06, "epoch": 1.0046885465505693, "percentage": 20.09, "elapsed_time": "3:30:37", "remaining_time": "13:57:33"}
+{"current_steps": 3100, "total_steps": 14930, "loss": 1.31, "lr": 9.651219721595235e-06, "epoch": 1.0381781647689217, "percentage": 20.76, "elapsed_time": "3:38:21", "remaining_time": "13:53:17"}
+{"current_steps": 3200, "total_steps": 14930, "loss": 1.2948, "lr": 9.607056649773266e-06, "epoch": 1.0716677829872738, "percentage": 21.43, "elapsed_time": "3:45:05", "remaining_time": "13:45:07"}
+{"current_steps": 3300, "total_steps": 14930, "loss": 1.2819, "lr": 9.56037532773342e-06, "epoch": 1.1051574012056262, "percentage": 22.1, "elapsed_time": "3:51:50", "remaining_time": "13:37:03"}
+{"current_steps": 3400, "total_steps": 14930, "loss": 1.2655, "lr": 9.511201271821235e-06, "epoch": 1.1386470194239786, "percentage": 22.77, "elapsed_time": "3:58:34", "remaining_time": "13:29:01"}
+{"current_steps": 3500, "total_steps": 14930, "loss": 1.2451, "lr": 9.459561360928472e-06, "epoch": 1.1721366376423308, "percentage": 23.44, "elapsed_time": "4:05:17", "remaining_time": "13:21:03"}
+{"current_steps": 3600, "total_steps": 14930, "loss": 1.2355, "lr": 9.405483821800912e-06, "epoch": 1.2056262558606832, "percentage": 24.11, "elapsed_time": "4:12:01", "remaining_time": "13:13:12"}
+{"current_steps": 3700, "total_steps": 14930, "loss": 1.2295, "lr": 9.348998213609416e-06, "epoch": 1.2391158740790356, "percentage": 24.78, "elapsed_time": "4:18:46", "remaining_time": "13:05:23"}
+{"current_steps": 3800, "total_steps": 14930, "loss": 1.2011, "lr": 9.29013541179268e-06, "epoch": 1.2726054922973877, "percentage": 25.45, "elapsed_time": "4:25:29", "remaining_time": "12:57:37"}
+{"current_steps": 3900, "total_steps": 14930, "loss": 1.1906, "lr": 9.228927591180484e-06, "epoch": 1.3060951105157401, "percentage": 26.12, "elapsed_time": "4:32:13", "remaining_time": "12:49:55"}
+{"current_steps": 4000, "total_steps": 14930, "loss": 1.1715, "lr": 9.165408208406703e-06, "epoch": 1.3395847287340925, "percentage": 26.79, "elapsed_time": "4:38:57", "remaining_time": "12:42:15"}
+{"current_steps": 4100, "total_steps": 14930, "loss": 1.1605, "lr": 9.099611983621684e-06, "epoch": 1.3730743469524447, "percentage": 27.46, "elapsed_time": "4:46:42", "remaining_time": "12:37:20"}
+{"current_steps": 4200, "total_steps": 14930, "loss": 1.1425, "lr": 9.03157488151394e-06, "epoch": 1.406563965170797, "percentage": 28.13, "elapsed_time": "4:53:26", "remaining_time": "12:29:40"}
+{"current_steps": 4300, "total_steps": 14930, "loss": 1.1233, "lr": 8.961334091651618e-06, "epoch": 1.4400535833891492, "percentage": 28.8, "elapsed_time": "5:00:10", "remaining_time": "12:22:04"}
+{"current_steps": 4400, "total_steps": 14930, "loss": 1.1193, "lr": 8.888928008154393e-06, "epoch": 1.4735432016075016, "percentage": 29.47, "elapsed_time": "5:06:55", "remaining_time": "12:14:31"}
+{"current_steps": 4500, "total_steps": 14930, "loss": 1.0943, "lr": 8.81439620870698e-06, "epoch": 1.507032819825854, "percentage": 30.14, "elapsed_time": "5:13:39", "remaining_time": "12:06:58"}
+{"current_steps": 4600, "total_steps": 14930, "loss": 1.0895, "lr": 8.737779432925682e-06, "epoch": 1.5405224380442064, "percentage": 30.81, "elapsed_time": "5:20:23", "remaining_time": "11:59:29"}
+{"current_steps": 4700, "total_steps": 14930, "loss": 1.0894, "lr": 8.659119560089822e-06, "epoch": 1.5740120562625586, "percentage": 31.48, "elapsed_time": "5:27:07", "remaining_time": "11:52:01"}
+{"current_steps": 4800, "total_steps": 14930, "loss": 1.0715, "lr": 8.578459586250235e-06, "epoch": 1.607501674480911, "percentage": 32.15, "elapsed_time": "5:33:51", "remaining_time": "11:44:34"}
+{"current_steps": 4900, "total_steps": 14930, "loss": 1.0717, "lr": 8.495843600727313e-06, "epoch": 1.6409912926992631, "percentage": 32.82, "elapsed_time": "5:40:36", "remaining_time": "11:37:11"}
+{"current_steps": 5000, "total_steps": 14930, "loss": 1.0706, "lr": 8.411316762011469e-06, "epoch": 1.6744809109176155, "percentage": 33.49, "elapsed_time": "5:47:20", "remaining_time": "11:29:48"}
+{"current_steps": 5100, "total_steps": 14930, "loss": 1.0665, "lr": 8.324925273079176e-06, "epoch": 1.707970529135968, "percentage": 34.16, "elapsed_time": "5:55:06", "remaining_time": "11:24:27"}
+{"current_steps": 5200, "total_steps": 14930, "loss": 1.0661, "lr": 8.236716356138098e-06, "epoch": 1.7414601473543203, "percentage": 34.83, "elapsed_time": "6:01:50", "remaining_time": "11:17:03"}
+{"current_steps": 5300, "total_steps": 14930, "loss": 1.0636, "lr": 8.146738226815088e-06, "epoch": 1.7749497655726725, "percentage": 35.5, "elapsed_time": "6:08:34", "remaining_time": "11:09:42"}
+{"current_steps": 5400, "total_steps": 14930, "loss": 1.0676, "lr": 8.055040067801172e-06, "epoch": 1.8084393837910246, "percentage": 36.17, "elapsed_time": "6:15:19", "remaining_time": "11:02:22"}
+{"current_steps": 5500, "total_steps": 14930, "loss": 1.0612, "lr": 7.961672001967954e-06, "epoch": 1.841929002009377, "percentage": 36.84, "elapsed_time": "6:22:02", "remaining_time": "10:55:02"}
+{"current_steps": 5600, "total_steps": 14930, "loss": 1.0561, "lr": 7.866685064970086e-06, "epoch": 1.8754186202277294, "percentage": 37.51, "elapsed_time": "6:28:46", "remaining_time": "10:47:43"}
+{"current_steps": 5700, "total_steps": 14930, "loss": 1.0597, "lr": 7.770131177348806e-06, "epoch": 1.9089082384460818, "percentage": 38.18, "elapsed_time": "6:35:30", "remaining_time": "10:40:26"}
+{"current_steps": 5800, "total_steps": 14930, "loss": 1.0603, "lr": 7.672063116151811e-06, "epoch": 1.942397856664434, "percentage": 38.85, "elapsed_time": "6:42:14", "remaining_time": "10:33:10"}
+{"current_steps": 5900, "total_steps": 14930, "loss": 1.0555, "lr": 7.572534486084937e-06, "epoch": 1.9758874748827864, "percentage": 39.52, "elapsed_time": "6:48:58", "remaining_time": "10:25:56"}
+{"current_steps": 5972, "total_steps": 14930, "eval_loss": NaN, "epoch": 2.0, "percentage": 40.0, "elapsed_time": "6:59:36", "remaining_time": "10:29:25"}
+{"current_steps": 6000, "total_steps": 14930, "loss": 1.0571, "lr": 7.47159969021144e-06, "epoch": 2.0093770931011385, "percentage": 40.19, "elapsed_time": "7:01:29", "remaining_time": "10:27:19"}
+{"current_steps": 6100, "total_steps": 14930, "loss": 1.0526, "lr": 7.369313900214897e-06, "epoch": 2.042866711319491, "percentage": 40.86, "elapsed_time": "7:09:12", "remaining_time": "10:21:17"}
+{"current_steps": 6200, "total_steps": 14930, "loss": 1.0395, "lr": 7.265733026241967e-06, "epoch": 2.0763563295378433, "percentage": 41.53, "elapsed_time": "7:15:56", "remaining_time": "10:13:50"}
+{"current_steps": 6300, "total_steps": 14930, "loss": 1.0189, "lr": 7.160913686341495e-06, "epoch": 2.1098459477561957, "percentage": 42.2, "elapsed_time": "7:22:41", "remaining_time": "10:06:24"}
+{"current_steps": 6400, "total_steps": 14930, "loss": 1.0034, "lr": 7.054913175516698e-06, "epoch": 2.1433355659745477, "percentage": 42.87, "elapsed_time": "7:29:25", "remaining_time": "9:58:59"}
+{"current_steps": 6500, "total_steps": 14930, "loss": 0.9789, "lr": 6.947789434407284e-06, "epoch": 2.1768251841929, "percentage": 43.54, "elapsed_time": "7:36:09", "remaining_time": "9:51:35"}
+{"current_steps": 6600, "total_steps": 14930, "loss": 0.9673, "lr": 6.839601017618699e-06, "epoch": 2.2103148024112524, "percentage": 44.21, "elapsed_time": "7:42:53", "remaining_time": "9:44:13"}
+{"current_steps": 6700, "total_steps": 14930, "loss": 0.9564, "lr": 6.730407061715752e-06, "epoch": 2.243804420629605, "percentage": 44.88, "elapsed_time": "7:49:37", "remaining_time": "9:36:52"}
+{"current_steps": 6800, "total_steps": 14930, "loss": 0.9251, "lr": 6.620267252898148e-06, "epoch": 2.2772940388479572, "percentage": 45.55, "elapsed_time": "7:56:21", "remaining_time": "9:29:32"}
+{"current_steps": 6900, "total_steps": 14930, "loss": 0.9125, "lr": 6.509241794375577e-06, "epoch": 2.3107836570663096, "percentage": 46.22, "elapsed_time": "8:03:05", "remaining_time": "9:22:12"}
+{"current_steps": 7000, "total_steps": 14930, "loss": 0.8919, "lr": 6.3973913734602174e-06, "epoch": 2.3442732752846616, "percentage": 46.89, "elapsed_time": "8:09:48", "remaining_time": "9:14:53"}
+{"current_steps": 7100, "total_steps": 14930, "loss": 0.879, "lr": 6.284777128394603e-06, "epoch": 2.377762893503014, "percentage": 47.56, "elapsed_time": "8:17:32", "remaining_time": "9:08:42"}
+{"current_steps": 7200, "total_steps": 14930, "loss": 0.8625, "lr": 6.171460614933038e-06, "epoch": 2.4112525117213663, "percentage": 48.23, "elapsed_time": "8:24:16", "remaining_time": "9:01:24"}
+{"current_steps": 7300, "total_steps": 14930, "loss": 0.8374, "lr": 6.057503772694761e-06, "epoch": 2.4447421299397187, "percentage": 48.89, "elapsed_time": "8:31:01", "remaining_time": "8:54:07"}
+{"current_steps": 7400, "total_steps": 14930, "loss": 0.8394, "lr": 5.942968891307317e-06, "epoch": 2.478231748158071, "percentage": 49.56, "elapsed_time": "8:37:45", "remaining_time": "8:46:51"}
+{"current_steps": 7500, "total_steps": 14930, "loss": 0.8131, "lr": 5.8279185763585975e-06, "epoch": 2.511721366376423, "percentage": 50.23, "elapsed_time": "8:44:29", "remaining_time": "8:39:36"}
+{"current_steps": 7600, "total_steps": 14930, "loss": 0.805, "lr": 5.7124157151761795e-06, "epoch": 2.5452109845947755, "percentage": 50.9, "elapsed_time": "8:51:14", "remaining_time": "8:32:22"}
+{"current_steps": 7700, "total_steps": 14930, "loss": 0.8083, "lr": 5.596523442452652e-06, "epoch": 2.578700602813128, "percentage": 51.57, "elapsed_time": "8:57:58", "remaining_time": "8:25:08"}
+{"current_steps": 7800, "total_steps": 14930, "loss": 0.7845, "lr": 5.480305105735749e-06, "epoch": 2.6121902210314802, "percentage": 52.24, "elapsed_time": "9:04:42", "remaining_time": "8:17:55"}
+{"current_steps": 7900, "total_steps": 14930, "loss": 0.7909, "lr": 5.363824230802127e-06, "epoch": 2.6456798392498326, "percentage": 52.91, "elapsed_time": "9:11:27", "remaining_time": "8:10:44"}
+{"current_steps": 8000, "total_steps": 14930, "loss": 0.7963, "lr": 5.247144486933706e-06, "epoch": 2.679169457468185, "percentage": 53.58, "elapsed_time": "9:18:12", "remaining_time": "8:03:32"}
+{"current_steps": 8100, "total_steps": 14930, "loss": 0.7835, "lr": 5.130329652115603e-06, "epoch": 2.7126590756865374, "percentage": 54.25, "elapsed_time": "9:25:55", "remaining_time": "7:57:11"}
+{"current_steps": 8200, "total_steps": 14930, "loss": 0.7899, "lr": 5.013443578174608e-06, "epoch": 2.7461486939048894, "percentage": 54.92, "elapsed_time": "9:32:39", "remaining_time": "7:49:59"}
+{"current_steps": 8300, "total_steps": 14930, "loss": 0.788, "lr": 4.8965501558773326e-06, "epoch": 2.7796383121232418, "percentage": 55.59, "elapsed_time": "9:39:23", "remaining_time": "7:42:49"}
+{"current_steps": 8400, "total_steps": 14930, "loss": 0.7979, "lr": 4.779713280007051e-06, "epoch": 2.813127930341594, "percentage": 56.26, "elapsed_time": "9:46:08", "remaining_time": "7:35:38"}
+{"current_steps": 8500, "total_steps": 14930, "loss": 0.7839, "lr": 4.6629968144383545e-06, "epoch": 2.8466175485599465, "percentage": 56.93, "elapsed_time": "9:52:51", "remaining_time": "7:28:28"}
+{"current_steps": 8600, "total_steps": 14930, "loss": 0.7899, "lr": 4.546464557228699e-06, "epoch": 2.8801071667782985, "percentage": 57.6, "elapsed_time": "9:59:36", "remaining_time": "7:21:20"}
+{"current_steps": 8700, "total_steps": 14930, "loss": 0.7959, "lr": 4.430180205745932e-06, "epoch": 2.913596784996651, "percentage": 58.27, "elapsed_time": "10:06:20", "remaining_time": "7:14:11"}
+{"current_steps": 8800, "total_steps": 14930, "loss": 0.7956, "lr": 4.314207321850849e-06, "epoch": 2.9470864032150033, "percentage": 58.94, "elapsed_time": "10:13:05", "remaining_time": "7:07:04"}
+{"current_steps": 8900, "total_steps": 14930, "loss": 0.7954, "lr": 4.198609297153831e-06, "epoch": 2.9805760214333556, "percentage": 59.61, "elapsed_time": "10:19:49", "remaining_time": "6:59:56"}
+{"current_steps": 8958, "total_steps": 14930, "eval_loss": NaN, "epoch": 3.0, "percentage": 60.0, "elapsed_time": "10:29:31", "remaining_time": "6:59:41"}
+{"current_steps": 9000, "total_steps": 14930, "loss": 0.7853, "lr": 4.083449318364527e-06, "epoch": 3.014065639651708, "percentage": 60.28, "elapsed_time": "10:32:21", "remaining_time": "6:56:39"}
+{"current_steps": 9100, "total_steps": 14930, "loss": 0.7987, "lr": 3.968790332753555e-06, "epoch": 3.0475552578700604, "percentage": 60.95, "elapsed_time": "10:40:05", "remaining_time": "6:50:04"}
+{"current_steps": 9200, "total_steps": 14930, "loss": 0.7732, "lr": 3.8546950137450656e-06, "epoch": 3.081044876088413, "percentage": 61.62, "elapsed_time": "10:46:49", "remaining_time": "6:42:51"}
+{"current_steps": 9300, "total_steps": 14930, "loss": 0.7563, "lr": 3.7412257266590007e-06, "epoch": 3.1145344943067648, "percentage": 62.29, "elapsed_time": "10:53:34", "remaining_time": "6:35:39"}
+{"current_steps": 9400, "total_steps": 14930, "loss": 0.739, "lr": 3.62844449462176e-06, "epoch": 3.148024112525117, "percentage": 62.96, "elapsed_time": "11:00:18", "remaining_time": "6:28:27"}
+{"current_steps": 9500, "total_steps": 14930, "loss": 0.7228, "lr": 3.5164129646639204e-06, "epoch": 3.1815137307434695, "percentage": 63.63, "elapsed_time": "11:07:02", "remaining_time": "6:21:16"}
+{"current_steps": 9600, "total_steps": 14930, "loss": 0.7088, "lr": 3.4051923740235205e-06, "epoch": 3.215003348961822, "percentage": 64.3, "elapsed_time": "11:13:46", "remaining_time": "6:14:05"}
+{"current_steps": 9700, "total_steps": 14930, "loss": 0.6959, "lr": 3.2948435166733506e-06, "epoch": 3.2484929671801743, "percentage": 64.97, "elapsed_time": "11:20:30", "remaining_time": "6:06:54"}
+{"current_steps": 9800, "total_steps": 14930, "loss": 0.6686, "lr": 3.1854267100905344e-06, "epoch": 3.2819825853985263, "percentage": 65.64, "elapsed_time": "11:27:14", "remaining_time": "5:59:45"}
+{"current_steps": 9900, "total_steps": 14930, "loss": 0.6606, "lr": 3.0770017622865523e-06, "epoch": 3.3154722036168787, "percentage": 66.31, "elapsed_time": "11:33:58", "remaining_time": "5:52:35"}
+{"current_steps": 10000, "total_steps": 14930, "loss": 0.6448, "lr": 2.9696279391157663e-06, "epoch": 3.348961821835231, "percentage": 66.98, "elapsed_time": "11:40:42", "remaining_time": "5:45:27"}
+{"current_steps": 10100, "total_steps": 14930, "loss": 0.6331, "lr": 2.8633639318802685e-06, "epoch": 3.3824514400535834, "percentage": 67.65, "elapsed_time": "11:48:25", "remaining_time": "5:38:46"}
+{"current_steps": 10200, "total_steps": 14930, "loss": 0.6145, "lr": 2.758267825248798e-06, "epoch": 3.415941058271936, "percentage": 68.32, "elapsed_time": "11:55:10", "remaining_time": "5:31:38"}
+{"current_steps": 10300, "total_steps": 14930, "loss": 0.6065, "lr": 2.6543970655072514e-06, "epoch": 3.4494306764902882, "percentage": 68.99, "elapsed_time": "12:01:55", "remaining_time": "5:24:30"}
+{"current_steps": 10400, "total_steps": 14930, "loss": 0.6009, "lr": 2.5518084291581163e-06, "epoch": 3.48292029470864, "percentage": 69.66, "elapsed_time": "12:08:41", "remaining_time": "5:17:23"}
+{"current_steps": 10500, "total_steps": 14930, "loss": 0.5847, "lr": 2.450557991886039e-06, "epoch": 3.5164099129269926, "percentage": 70.33, "elapsed_time": "12:15:25", "remaining_time": "5:10:16"}
+{"current_steps": 10600, "total_steps": 14930, "loss": 0.578, "lr": 2.350701097906447e-06, "epoch": 3.549899531145345, "percentage": 71.0, "elapsed_time": "12:22:09", "remaining_time": "5:03:10"}
+{"current_steps": 10700, "total_steps": 14930, "loss": 0.5838, "lr": 2.252292329714012e-06, "epoch": 3.5833891493636973, "percentage": 71.67, "elapsed_time": "12:28:53", "remaining_time": "4:56:03"}
+{"current_steps": 10800, "total_steps": 14930, "loss": 0.5653, "lr": 2.155385478247455e-06, "epoch": 3.6168787675820493, "percentage": 72.34, "elapsed_time": "12:35:37", "remaining_time": "4:48:57"}
+{"current_steps": 10900, "total_steps": 14930, "loss": 0.5723, "lr": 2.0600335134870415e-06, "epoch": 3.6503683858004017, "percentage": 73.01, "elapsed_time": "12:42:22", "remaining_time": "4:41:52"}
+{"current_steps": 11000, "total_steps": 14930, "loss": 0.5762, "lr": 1.9662885555008055e-06, "epoch": 3.683858004018754, "percentage": 73.68, "elapsed_time": "12:49:06", "remaining_time": "4:34:46"}
+{"current_steps": 11100, "total_steps": 14930, "loss": 0.5715, "lr": 1.8742018459553551e-06, "epoch": 3.7173476222371065, "percentage": 74.35, "elapsed_time": "12:56:50", "remaining_time": "4:28:02"}
+{"current_steps": 11200, "total_steps": 14930, "loss": 0.577, "lr": 1.7838237201067976e-06, "epoch": 3.750837240455459, "percentage": 75.02, "elapsed_time": "13:03:34", "remaining_time": "4:20:57"}
+{"current_steps": 11300, "total_steps": 14930, "loss": 0.5825, "lr": 1.695203579287134e-06, "epoch": 3.7843268586738112, "percentage": 75.69, "elapsed_time": "13:10:18", "remaining_time": "4:13:52"}
+{"current_steps": 11400, "total_steps": 14930, "loss": 0.5871, "lr": 1.6083898639011402e-06, "epoch": 3.8178164768921636, "percentage": 76.36, "elapsed_time": "13:17:03", "remaining_time": "4:06:48"}
+{"current_steps": 11500, "total_steps": 14930, "loss": 0.5805, "lr": 1.5234300269484848e-06, "epoch": 3.8513060951105156, "percentage": 77.03, "elapsed_time": "13:23:47", "remaining_time": "3:59:44"}
+{"current_steps": 11600, "total_steps": 14930, "loss": 0.5859, "lr": 1.440370508085589e-06, "epoch": 3.884795713328868, "percentage": 77.7, "elapsed_time": "13:30:31", "remaining_time": "3:52:40"}
+{"current_steps": 11700, "total_steps": 14930, "loss": 0.5961, "lr": 1.3592567082413683e-06, "epoch": 3.9182853315472204, "percentage": 78.37, "elapsed_time": "13:37:15", "remaining_time": "3:45:37"}
+{"current_steps": 11800, "total_steps": 14930, "loss": 0.6098, "lr": 1.2801329648007648e-06, "epoch": 3.9517749497655728, "percentage": 79.04, "elapsed_time": "13:44:00", "remaining_time": "3:38:34"}
+{"current_steps": 11900, "total_steps": 14930, "loss": 0.5992, "lr": 1.203042527369611e-06, "epoch": 3.985264567983925, "percentage": 79.71, "elapsed_time": "13:50:43", "remaining_time": "3:31:31"}
+{"current_steps": 11944, "total_steps": 14930, "eval_loss": NaN, "epoch": 4.0, "percentage": 80.0, "elapsed_time": "13:59:30", "remaining_time": "3:29:52"}
+{"current_steps": 12000, "total_steps": 14930, "loss": 0.5984, "lr": 1.1280275341340919e-06, "epoch": 4.018754186202277, "percentage": 80.38, "elapsed_time": "14:03:15", "remaining_time": "3:25:53"}
+{"current_steps": 12100, "total_steps": 14930, "loss": 0.6147, "lr": 1.0551289888277e-06, "epoch": 4.0522438044206295, "percentage": 81.04, "elapsed_time": "14:10:59", "remaining_time": "3:19:01"}
+{"current_steps": 12200, "total_steps": 14930, "loss": 0.5882, "lr": 9.843867383183065e-07, "epoch": 4.085733422638982, "percentage": 81.71, "elapsed_time": "14:17:43", "remaining_time": "3:11:55"}
+{"current_steps": 12300, "total_steps": 14930, "loss": 0.5785, "lr": 9.158394508275764e-07, "epoch": 4.119223040857334, "percentage": 82.38, "elapsed_time": "14:24:27", "remaining_time": "3:04:50"}
+{"current_steps": 12400, "total_steps": 14930, "loss": 0.568, "lr": 8.495245947946428e-07, "epoch": 4.152712659075687, "percentage": 83.05, "elapsed_time": "14:31:10", "remaining_time": "2:57:44"}
+{"current_steps": 12500, "total_steps": 14930, "loss": 0.5548, "lr": 7.85478418395586e-07, "epoch": 4.186202277294039, "percentage": 83.72, "elapsed_time": "14:37:54", "remaining_time": "2:50:39"}
+{"current_steps": 12600, "total_steps": 14930, "loss": 0.5491, "lr": 7.237359297299213e-07, "epoch": 4.219691895512391, "percentage": 84.39, "elapsed_time": "14:44:38", "remaining_time": "2:43:35"}
+{"current_steps": 12700, "total_steps": 14930, "loss": 0.5344, "lr": 6.643308776849211e-07, "epoch": 4.253181513730744, "percentage": 85.06, "elapsed_time": "14:51:23", "remaining_time": "2:36:31"}
+{"current_steps": 12800, "total_steps": 14930, "loss": 0.5205, "lr": 6.07295733488234e-07, "epoch": 4.286671131949095, "percentage": 85.73, "elapsed_time": "14:58:06", "remaining_time": "2:29:27"}
+{"current_steps": 12900, "total_steps": 14930, "loss": 0.5143, "lr": 5.526616729588719e-07, "epoch": 4.320160750167448, "percentage": 86.4, "elapsed_time": "15:04:50", "remaining_time": "2:22:23"}
+{"current_steps": 13000, "total_steps": 14930, "loss": 0.5027, "lr": 5.00458559466292e-07, "epoch": 4.3536503683858, "percentage": 87.07, "elapsed_time": "15:11:34", "remaining_time": "2:15:20"}
+{"current_steps": 13100, "total_steps": 14930, "loss": 0.498, "lr": 4.507149276068562e-07, "epoch": 4.3871399866041525, "percentage": 87.74, "elapsed_time": "15:19:17", "remaining_time": "2:08:25"}
+{"current_steps": 13200, "total_steps": 14930, "loss": 0.4925, "lr": 4.0345796760662247e-07, "epoch": 4.420629604822505, "percentage": 88.41, "elapsed_time": "15:26:01", "remaining_time": "2:01:21"}
+{"current_steps": 13300, "total_steps": 14930, "loss": 0.4893, "lr": 3.587135104589706e-07, "epoch": 4.454119223040857, "percentage": 89.08, "elapsed_time": "15:32:46", "remaining_time": "1:54:19"}
+{"current_steps": 13400, "total_steps": 14930, "loss": 0.4844, "lr": 3.16506013805194e-07, "epoch": 4.48760884125921, "percentage": 89.75, "elapsed_time": "15:39:30", "remaining_time": "1:47:16"}
+{"current_steps": 13500, "total_steps": 14930, "loss": 0.472, "lr": 2.7685854856577934e-07, "epoch": 4.521098459477562, "percentage": 90.42, "elapsed_time": "15:46:14", "remaining_time": "1:40:13"}
+{"current_steps": 13600, "total_steps": 14930, "loss": 0.4774, "lr": 2.3979278632967507e-07, "epoch": 4.5545880776959144, "percentage": 91.09, "elapsed_time": "15:52:59", "remaining_time": "1:33:11"}
+{"current_steps": 13700, "total_steps": 14930, "loss": 0.4786, "lr": 2.0532898750844633e-07, "epoch": 4.588077695914267, "percentage": 91.76, "elapsed_time": "15:59:43", "remaining_time": "1:26:09"}
+{"current_steps": 13800, "total_steps": 14930, "loss": 0.4786, "lr": 1.734859902617886e-07, "epoch": 4.621567314132619, "percentage": 92.43, "elapsed_time": "16:06:28", "remaining_time": "1:19:08"}
+{"current_steps": 13900, "total_steps": 14930, "loss": 0.4882, "lr": 1.4428120020045122e-07, "epoch": 4.655056932350972, "percentage": 93.1, "elapsed_time": "16:13:12", "remaining_time": "1:12:06"}
+{"current_steps": 14000, "total_steps": 14930, "loss": 0.4816, "lr": 1.1773058087221068e-07, "epoch": 4.688546550569323, "percentage": 93.77, "elapsed_time": "16:19:56", "remaining_time": "1:05:05"}
+{"current_steps": 14100, "total_steps": 14930, "loss": 0.482, "lr": 9.384864503607871e-08, "epoch": 4.7220361687876755, "percentage": 94.44, "elapsed_time": "16:27:40", "remaining_time": "0:58:08"}
+{"current_steps": 14200, "total_steps": 14930, "loss": 0.4989, "lr": 7.264844672952299e-08, "epoch": 4.755525787006028, "percentage": 95.11, "elapsed_time": "16:34:24", "remaining_time": "0:51:07"}
+{"current_steps": 14300, "total_steps": 14930, "loss": 0.5135, "lr": 5.4141574133037555e-08, "epoch": 4.78901540522438, "percentage": 95.78, "elapsed_time": "16:41:08", "remaining_time": "0:44:06"}
+{"current_steps": 14400, "total_steps": 14930, "loss": 0.5077, "lr": 3.8338143235959746e-08, "epoch": 4.822505023442733, "percentage": 96.45, "elapsed_time": "16:47:53", "remaining_time": "0:37:05"}
+{"current_steps": 14500, "total_steps": 14930, "loss": 0.5146, "lr": 2.5246792306999334e-08, "epoch": 4.855994641661085, "percentage": 97.12, "elapsed_time": "16:54:37", "remaining_time": "0:30:05"}
+{"current_steps": 14600, "total_steps": 14930, "loss": 0.5236, "lr": 1.4874677172497243e-08, "epoch": 4.8894842598794375, "percentage": 97.79, "elapsed_time": "17:01:21", "remaining_time": "0:23:05"}
+{"current_steps": 14700, "total_steps": 14930, "loss": 0.5404, "lr": 7.2274673050010124e-09, "epoch": 4.92297387809779, "percentage": 98.46, "elapsed_time": "17:08:05", "remaining_time": "0:16:05"}
+{"current_steps": 14800, "total_steps": 14930, "loss": 0.5488, "lr": 2.309342724287622e-09, "epoch": 4.956463496316142, "percentage": 99.13, "elapsed_time": "17:14:50", "remaining_time": "0:09:05"}
+{"current_steps": 14900, "total_steps": 14930, "loss": 0.5494, "lr": 1.229917125389335e-10, "epoch": 4.989953114534495, "percentage": 99.8, "elapsed_time": "17:21:34", "remaining_time": "0:02:05"}
+{"current_steps": 14930, "total_steps": 14930, "eval_loss": NaN, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "17:29:23", "remaining_time": "0:00:00"}
+{"current_steps": 14930, "total_steps": 14930, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "17:30:21", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1125 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 2986,
+  "global_step": 14930,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.033489618218352314,
+      "grad_norm": 27.663120029291747,
+      "learning_rate": 6.697923643670463e-07,
+      "loss": 11.7393,
+      "step": 100
+    },
+    {
+      "epoch": 0.06697923643670463,
+      "grad_norm": 1.7320339885689573,
+      "learning_rate": 1.3395847287340927e-06,
+      "loss": 3.297,
+      "step": 200
+    },
+    {
+      "epoch": 0.10046885465505694,
+      "grad_norm": 1.2696699900839306,
+      "learning_rate": 2.0093770931011387e-06,
+      "loss": 1.8384,
+      "step": 300
+    },
+    {
+      "epoch": 0.13395847287340926,
+      "grad_norm": 1.1644334409082224,
+      "learning_rate": 2.6791694574681854e-06,
+      "loss": 1.6728,
+      "step": 400
+    },
+    {
+      "epoch": 0.16744809109176156,
+      "grad_norm": 1.272695149119617,
+      "learning_rate": 3.3489618218352316e-06,
+      "loss": 1.5883,
+      "step": 500
+    },
+    {
+      "epoch": 0.20093770931011387,
+      "grad_norm": 1.2497604240608484,
+      "learning_rate": 4.018754186202277e-06,
+      "loss": 1.5399,
+      "step": 600
+    },
+    {
+      "epoch": 0.23442732752846618,
+      "grad_norm": 1.1521160041280882,
+      "learning_rate": 4.688546550569324e-06,
+      "loss": 1.5214,
+      "step": 700
+    },
+    {
+      "epoch": 0.2679169457468185,
+      "grad_norm": 1.0610261246972188,
+      "learning_rate": 5.358338914936371e-06,
+      "loss": 1.4822,
+      "step": 800
+    },
+    {
+      "epoch": 0.3014065639651708,
+      "grad_norm": 1.1385854301492127,
+      "learning_rate": 6.028131279303416e-06,
+      "loss": 1.4623,
+      "step": 900
+    },
+    {
+      "epoch": 0.33489618218352313,
+      "grad_norm": 1.04201570658625,
+      "learning_rate": 6.697923643670463e-06,
+      "loss": 1.4408,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3683858004018754,
+      "grad_norm": 1.0568444189378532,
+      "learning_rate": 7.3677160080375086e-06,
+      "loss": 1.4378,
+      "step": 1100
+    },
+    {
+      "epoch": 0.40187541862022774,
+      "grad_norm": 1.088346568816493,
+      "learning_rate": 8.037508372404555e-06,
+      "loss": 1.4189,
+      "step": 1200
+    },
+    {
+      "epoch": 0.43536503683858,
+      "grad_norm": 1.0714826983472352,
+      "learning_rate": 8.707300736771601e-06,
+      "loss": 1.4098,
+      "step": 1300
+    },
+    {
+      "epoch": 0.46885465505693236,
+      "grad_norm": 1.0415739456028938,
+      "learning_rate": 9.377093101138647e-06,
+      "loss": 1.4011,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5023442732752846,
+      "grad_norm": 1.0789186294154542,
+      "learning_rate": 9.999993303758581e-06,
+      "loss": 1.3933,
+      "step": 1500
+    },
+    {
+      "epoch": 0.535833891493637,
+      "grad_norm": 1.0509262824198378,
+      "learning_rate": 9.998435483941776e-06,
+      "loss": 1.3828,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5693235097119893,
+      "grad_norm": 1.0764796757312198,
+      "learning_rate": 9.994145483428403e-06,
+      "loss": 1.3772,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6028131279303416,
+      "grad_norm": 1.047153842290928,
+      "learning_rate": 9.987125647163527e-06,
+      "loss": 1.3674,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6363027461486939,
+      "grad_norm": 0.9188670491033151,
+      "learning_rate": 9.977379812240013e-06,
+      "loss": 1.3538,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6697923643670463,
+      "grad_norm": 1.004701344911835,
+      "learning_rate": 9.964913305801151e-06,
+      "loss": 1.3566,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7032819825853985,
+      "grad_norm": 1.1760354727564355,
+      "learning_rate": 9.9497329421288e-06,
+      "loss": 1.3473,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7367716008037508,
+      "grad_norm": 0.9440290166066829,
+      "learning_rate": 9.931847018918654e-06,
+      "loss": 1.35,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7702612190221031,
+      "grad_norm": 0.8730032484094693,
+      "learning_rate": 9.911265312744663e-06,
+      "loss": 1.3381,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8037508372404555,
+      "grad_norm": 1.0757201534073755,
+      "learning_rate": 9.887999073715083e-06,
+      "loss": 1.3409,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8372404554588078,
+      "grad_norm": 0.8841599798410706,
+      "learning_rate": 9.86206101932309e-06,
+      "loss": 1.333,
+      "step": 2500
+    },
+    {
+      "epoch": 0.87073007367716,
+      "grad_norm": 0.9378532515897725,
+      "learning_rate": 9.833465327495307e-06,
+      "loss": 1.3195,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9042196918955124,
+      "grad_norm": 1.2091982749118577,
+      "learning_rate": 9.802227628842045e-06,
+      "loss": 1.3183,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9377093101138647,
+      "grad_norm": 1.0171797419584845,
+      "learning_rate": 9.7683649981135e-06,
+      "loss": 1.3145,
+      "step": 2800
+    },
+    {
+      "epoch": 0.971198928332217,
+      "grad_norm": 0.9664734856676821,
+      "learning_rate": 9.731895944866576e-06,
+      "loss": 1.3178,
+      "step": 2900
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": NaN,
+      "eval_runtime": 348.649,
+      "eval_samples_per_second": 45.673,
+      "eval_steps_per_second": 1.428,
+      "step": 2986
+    },
+    {
+      "epoch": 1.0046885465505693,
+      "grad_norm": 1.0415846298834508,
+      "learning_rate": 9.69284040334742e-06,
+      "loss": 1.3204,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0381781647689217,
+      "grad_norm": 0.8757930482053028,
+      "learning_rate": 9.651219721595235e-06,
+      "loss": 1.31,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0716677829872738,
+      "grad_norm": 0.9287401756438767,
+      "learning_rate": 9.607056649773266e-06,
+      "loss": 1.2948,
+      "step": 3200
+    },
+    {
+      "epoch": 1.1051574012056262,
+      "grad_norm": 0.966772568640745,
+      "learning_rate": 9.56037532773342e-06,
+      "loss": 1.2819,
+      "step": 3300
+    },
+    {
+      "epoch": 1.1386470194239786,
+      "grad_norm": 0.9981440658348595,
+      "learning_rate": 9.511201271821235e-06,
+      "loss": 1.2655,
+      "step": 3400
+    },
+    {
+      "epoch": 1.1721366376423308,
+      "grad_norm": 1.0546997584325322,
+      "learning_rate": 9.459561360928472e-06,
+      "loss": 1.2451,
+      "step": 3500
+    },
+    {
+      "epoch": 1.2056262558606832,
+      "grad_norm": 0.8994951932737885,
+      "learning_rate": 9.405483821800912e-06,
+      "loss": 1.2355,
+      "step": 3600
+    },
+    {
+      "epoch": 1.2391158740790356,
+      "grad_norm": 1.1226364755523701,
+      "learning_rate": 9.348998213609416e-06,
+      "loss": 1.2295,
+      "step": 3700
+    },
+    {
+      "epoch": 1.2726054922973877,
+      "grad_norm": 1.0157346646837568,
+      "learning_rate": 9.29013541179268e-06,
+      "loss": 1.2011,
+      "step": 3800
+    },
+    {
+      "epoch": 1.3060951105157401,
+      "grad_norm": 1.0670758632556911,
+      "learning_rate": 9.228927591180484e-06,
+      "loss": 1.1906,
+      "step": 3900
+    },
+    {
+      "epoch": 1.3395847287340925,
+      "grad_norm": 0.9528782862122593,
+      "learning_rate": 9.165408208406703e-06,
+      "loss": 1.1715,
+      "step": 4000
+    },
+    {
+      "epoch": 1.3730743469524447,
+      "grad_norm": 0.9576902845349418,
+      "learning_rate": 9.099611983621684e-06,
+      "loss": 1.1605,
+      "step": 4100
+    },
+    {
+      "epoch": 1.406563965170797,
+      "grad_norm": 1.271234164945301,
+      "learning_rate": 9.03157488151394e-06,
+      "loss": 1.1425,
+      "step": 4200
+    },
+    {
+      "epoch": 1.4400535833891492,
+      "grad_norm": 1.1036926365187665,
+      "learning_rate": 8.961334091651618e-06,
+      "loss": 1.1233,
+      "step": 4300
+    },
+    {
+      "epoch": 1.4735432016075016,
+      "grad_norm": 0.9973365902952639,
+      "learning_rate": 8.888928008154393e-06,
+      "loss": 1.1193,
+      "step": 4400
+    },
+    {
+      "epoch": 1.507032819825854,
+      "grad_norm": 1.0008322426572456,
+      "learning_rate": 8.81439620870698e-06,
+      "loss": 1.0943,
+      "step": 4500
+    },
+    {
+      "epoch": 1.5405224380442064,
+      "grad_norm": 1.035859311044444,
+      "learning_rate": 8.737779432925682e-06,
+      "loss": 1.0895,
+      "step": 4600
+    },
+    {
+      "epoch": 1.5740120562625586,
+      "grad_norm": 1.00625654318314,
+      "learning_rate": 8.659119560089822e-06,
+      "loss": 1.0894,
+      "step": 4700
+    },
+    {
+      "epoch": 1.607501674480911,
+      "grad_norm": 1.0315606204038301,
+      "learning_rate": 8.578459586250235e-06,
+      "loss": 1.0715,
+      "step": 4800
+    },
+    {
+      "epoch": 1.6409912926992631,
+      "grad_norm": 1.0926346917432537,
+      "learning_rate": 8.495843600727313e-06,
+      "loss": 1.0717,
+      "step": 4900
+    },
+    {
+      "epoch": 1.6744809109176155,
+      "grad_norm": 1.0612821467128837,
+      "learning_rate": 8.411316762011469e-06,
+      "loss": 1.0706,
+      "step": 5000
+    },
+    {
+      "epoch": 1.707970529135968,
+      "grad_norm": 1.016164489585248,
+      "learning_rate": 8.324925273079176e-06,
+      "loss": 1.0665,
+      "step": 5100
+    },
+    {
+      "epoch": 1.7414601473543203,
+      "grad_norm": 1.0371020643635414,
+      "learning_rate": 8.236716356138098e-06,
+      "loss": 1.0661,
+      "step": 5200
+    },
+    {
+      "epoch": 1.7749497655726725,
+      "grad_norm": 1.0416961084839862,
+      "learning_rate": 8.146738226815088e-06,
+      "loss": 1.0636,
+      "step": 5300
+    },
+    {
+      "epoch": 1.8084393837910246,
+      "grad_norm": 0.9790282258830432,
+      "learning_rate": 8.055040067801172e-06,
+      "loss": 1.0676,
+      "step": 5400
+    },
+    {
+      "epoch": 1.841929002009377,
+      "grad_norm": 1.0172124964539753,
+      "learning_rate": 7.961672001967954e-06,
+      "loss": 1.0612,
+      "step": 5500
+    },
+    {
+      "epoch": 1.8754186202277294,
+      "grad_norm": 1.1307997119049311,
+      "learning_rate": 7.866685064970086e-06,
+      "loss": 1.0561,
+      "step": 5600
+    },
+    {
+      "epoch": 1.9089082384460818,
+      "grad_norm": 1.0443307684727732,
+      "learning_rate": 7.770131177348806e-06,
+      "loss": 1.0597,
+      "step": 5700
+    },
+    {
+      "epoch": 1.942397856664434,
+      "grad_norm": 1.0764967903414877,
+      "learning_rate": 7.672063116151811e-06,
+      "loss": 1.0603,
+      "step": 5800
+    },
+    {
+      "epoch": 1.9758874748827864,
+      "grad_norm": 1.1410122429288658,
+      "learning_rate": 7.572534486084937e-06,
+      "loss": 1.0555,
+      "step": 5900
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": NaN,
+      "eval_runtime": 348.1208,
+      "eval_samples_per_second": 45.743,
+      "eval_steps_per_second": 1.431,
+      "step": 5972
+    },
+    {
+      "epoch": 2.0093770931011385,
+      "grad_norm": 1.0764883927956457,
+      "learning_rate": 7.47159969021144e-06,
+      "loss": 1.0571,
+      "step": 6000
+    },
+    {
+      "epoch": 2.042866711319491,
+      "grad_norm": 1.1019967079045427,
+      "learning_rate": 7.369313900214897e-06,
+      "loss": 1.0526,
+      "step": 6100
+    },
+    {
+      "epoch": 2.0763563295378433,
+      "grad_norm": 1.09355151149325,
+      "learning_rate": 7.265733026241967e-06,
+      "loss": 1.0395,
+      "step": 6200
+    },
+    {
+      "epoch": 2.1098459477561957,
+      "grad_norm": 1.0207706582548508,
+      "learning_rate": 7.160913686341495e-06,
+      "loss": 1.0189,
+      "step": 6300
+    },
+    {
+      "epoch": 2.1433355659745477,
+      "grad_norm": 1.2991784934719508,
+      "learning_rate": 7.054913175516698e-06,
+      "loss": 1.0034,
+      "step": 6400
+    },
+    {
+      "epoch": 2.1768251841929,
+      "grad_norm": 1.1127907199675022,
+      "learning_rate": 6.947789434407284e-06,
+      "loss": 0.9789,
+      "step": 6500
+    },
+    {
+      "epoch": 2.2103148024112524,
+      "grad_norm": 1.0987386576171831,
+      "learning_rate": 6.839601017618699e-06,
+      "loss": 0.9673,
+      "step": 6600
+    },
+    {
+      "epoch": 2.243804420629605,
+      "grad_norm": 1.1749268268222908,
+      "learning_rate": 6.730407061715752e-06,
+      "loss": 0.9564,
+      "step": 6700
+    },
+    {
+      "epoch": 2.2772940388479572,
+      "grad_norm": 1.2656062020023109,
+      "learning_rate": 6.620267252898148e-06,
+      "loss": 0.9251,
+      "step": 6800
+    },
+    {
+      "epoch": 2.3107836570663096,
+      "grad_norm": 1.2775085805331419,
+      "learning_rate": 6.509241794375577e-06,
+      "loss": 0.9125,
+      "step": 6900
+    },
+    {
+      "epoch": 2.3442732752846616,
+      "grad_norm": 1.3173880822264534,
+      "learning_rate": 6.3973913734602174e-06,
+      "loss": 0.8919,
+      "step": 7000
+    },
+    {
+      "epoch": 2.377762893503014,
+      "grad_norm": 1.2455502782297214,
+      "learning_rate": 6.284777128394603e-06,
+      "loss": 0.879,
+      "step": 7100
+    },
+    {
+      "epoch": 2.4112525117213663,
+      "grad_norm": 1.332442255586022,
+      "learning_rate": 6.171460614933038e-06,
+      "loss": 0.8625,
+      "step": 7200
+    },
+    {
+      "epoch": 2.4447421299397187,
+      "grad_norm": 1.3507817687995796,
+      "learning_rate": 6.057503772694761e-06,
+      "loss": 0.8374,
+      "step": 7300
+    },
+    {
+      "epoch": 2.478231748158071,
+      "grad_norm": 1.2079298830395293,
+      "learning_rate": 5.942968891307317e-06,
+      "loss": 0.8394,
+      "step": 7400
+    },
+    {
+      "epoch": 2.511721366376423,
+      "grad_norm": 1.2858100084464055,
+      "learning_rate": 5.8279185763585975e-06,
+      "loss": 0.8131,
+      "step": 7500
+    },
+    {
+      "epoch": 2.5452109845947755,
+      "grad_norm": 1.50200071509283,
+      "learning_rate": 5.7124157151761795e-06,
+      "loss": 0.805,
+      "step": 7600
+    },
+    {
+      "epoch": 2.578700602813128,
+      "grad_norm": 1.7131605578882496,
+      "learning_rate": 5.596523442452652e-06,
+      "loss": 0.8083,
+      "step": 7700
+    },
+    {
+      "epoch": 2.6121902210314802,
+      "grad_norm": 1.549866945076186,
+      "learning_rate": 5.480305105735749e-06,
+      "loss": 0.7845,
+      "step": 7800
+    },
+    {
+      "epoch": 2.6456798392498326,
+      "grad_norm": 1.3213984004712975,
+      "learning_rate": 5.363824230802127e-06,
+      "loss": 0.7909,
+      "step": 7900
+    },
+    {
+      "epoch": 2.679169457468185,
+      "grad_norm": 1.4279995035623863,
+      "learning_rate": 5.247144486933706e-06,
+      "loss": 0.7963,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7126590756865374,
+      "grad_norm": 1.8497497934553626,
+      "learning_rate": 5.130329652115603e-06,
+      "loss": 0.7835,
+      "step": 8100
+    },
+    {
+      "epoch": 2.7461486939048894,
+      "grad_norm": 1.4531964604398142,
+      "learning_rate": 5.013443578174608e-06,
+      "loss": 0.7899,
+      "step": 8200
+    },
+    {
+      "epoch": 2.7796383121232418,
+      "grad_norm": 1.5125912635190244,
+      "learning_rate": 4.8965501558773326e-06,
+      "loss": 0.788,
+      "step": 8300
+    },
+    {
+      "epoch": 2.813127930341594,
+      "grad_norm": 1.3974817703691491,
+      "learning_rate": 4.779713280007051e-06,
+      "loss": 0.7979,
+      "step": 8400
+    },
+    {
+      "epoch": 2.8466175485599465,
+      "grad_norm": 1.3666908779315028,
+      "learning_rate": 4.6629968144383545e-06,
+      "loss": 0.7839,
+      "step": 8500
+    },
+    {
+      "epoch": 2.8801071667782985,
+      "grad_norm": 1.3996848474214347,
+      "learning_rate": 4.546464557228699e-06,
+      "loss": 0.7899,
+      "step": 8600
+    },
+    {
+      "epoch": 2.913596784996651,
+      "grad_norm": 1.3649644046851297,
+      "learning_rate": 4.430180205745932e-06,
+      "loss": 0.7959,
+      "step": 8700
+    },
+    {
+      "epoch": 2.9470864032150033,
+      "grad_norm": 1.369973634022689,
+      "learning_rate": 4.314207321850849e-06,
+      "loss": 0.7956,
+      "step": 8800
+    },
+    {
+      "epoch": 2.9805760214333556,
+      "grad_norm": 1.5071401378465865,
+      "learning_rate": 4.198609297153831e-06,
+      "loss": 0.7954,
+      "step": 8900
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": NaN,
+      "eval_runtime": 348.2929,
+      "eval_samples_per_second": 45.72,
+      "eval_steps_per_second": 1.43,
+      "step": 8958
+    },
+    {
+      "epoch": 3.014065639651708,
+      "grad_norm": 1.4428883177319884,
+      "learning_rate": 4.083449318364527e-06,
+      "loss": 0.7853,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0475552578700604,
+      "grad_norm": 1.351580022628522,
+      "learning_rate": 3.968790332753555e-06,
+      "loss": 0.7987,
+      "step": 9100
+    },
+    {
+      "epoch": 3.081044876088413,
+      "grad_norm": 1.3743638112843153,
+      "learning_rate": 3.8546950137450656e-06,
+      "loss": 0.7732,
+      "step": 9200
+    },
+    {
+      "epoch": 3.1145344943067648,
+      "grad_norm": 1.484385543221885,
+      "learning_rate": 3.7412257266590007e-06,
+      "loss": 0.7563,
+      "step": 9300
+    },
+    {
+      "epoch": 3.148024112525117,
+      "grad_norm": 1.5933705790768147,
+      "learning_rate": 3.62844449462176e-06,
+      "loss": 0.739,
+      "step": 9400
+    },
+    {
+      "epoch": 3.1815137307434695,
+      "grad_norm": 1.6870709018629149,
+      "learning_rate": 3.5164129646639204e-06,
+      "loss": 0.7228,
+      "step": 9500
+    },
+    {
+      "epoch": 3.215003348961822,
+      "grad_norm": 1.6481990122285803,
+      "learning_rate": 3.4051923740235205e-06,
+      "loss": 0.7088,
+      "step": 9600
+    },
+    {
+      "epoch": 3.2484929671801743,
+      "grad_norm": 1.5879233480759347,
+      "learning_rate": 3.2948435166733506e-06,
+      "loss": 0.6959,
+      "step": 9700
+    },
+    {
+      "epoch": 3.2819825853985263,
+      "grad_norm": 1.5176278019008493,
+      "learning_rate": 3.1854267100905344e-06,
+      "loss": 0.6686,
+      "step": 9800
+    },
+    {
+      "epoch": 3.3154722036168787,
+      "grad_norm": 1.552541254972543,
+      "learning_rate": 3.0770017622865523e-06,
+      "loss": 0.6606,
+      "step": 9900
+    },
+    {
+      "epoch": 3.348961821835231,
+      "grad_norm": 1.7082594351164857,
+      "learning_rate": 2.9696279391157663e-06,
+      "loss": 0.6448,
+      "step": 10000
+    },
+    {
+      "epoch": 3.3824514400535834,
+      "grad_norm": 3.1211350166343546,
+      "learning_rate": 2.8633639318802685e-06,
+      "loss": 0.6331,
+      "step": 10100
+    },
+    {
+      "epoch": 3.415941058271936,
+      "grad_norm": 1.6469804551491567,
+      "learning_rate": 2.758267825248798e-06,
+      "loss": 0.6145,
+      "step": 10200
+    },
+    {
+      "epoch": 3.4494306764902882,
+      "grad_norm": 1.7146851447701008,
+      "learning_rate": 2.6543970655072514e-06,
+      "loss": 0.6065,
+      "step": 10300
+    },
+    {
+      "epoch": 3.48292029470864,
+      "grad_norm": 2.043969779746548,
+      "learning_rate": 2.5518084291581163e-06,
+      "loss": 0.6009,
+      "step": 10400
+    },
+    {
+      "epoch": 3.5164099129269926,
+      "grad_norm": 1.6446301288443177,
+      "learning_rate": 2.450557991886039e-06,
+      "loss": 0.5847,
+      "step": 10500
+    },
+    {
+      "epoch": 3.549899531145345,
+      "grad_norm": 1.8987310858087982,
+      "learning_rate": 2.350701097906447e-06,
+      "loss": 0.578,
+      "step": 10600
+    },
+    {
+      "epoch": 3.5833891493636973,
+      "grad_norm": 1.5875486081882013,
+      "learning_rate": 2.252292329714012e-06,
+      "loss": 0.5838,
+      "step": 10700
+    },
+    {
+      "epoch": 3.6168787675820493,
+      "grad_norm": 1.5799154770812294,
+      "learning_rate": 2.155385478247455e-06,
+      "loss": 0.5653,
+      "step": 10800
+    },
+    {
+      "epoch": 3.6503683858004017,
+      "grad_norm": 1.9320449012232872,
+      "learning_rate": 2.0600335134870415e-06,
+      "loss": 0.5723,
+      "step": 10900
+    },
+    {
+      "epoch": 3.683858004018754,
+      "grad_norm": 1.9440461986884756,
+      "learning_rate": 1.9662885555008055e-06,
+      "loss": 0.5762,
+      "step": 11000
+    },
+    {
+      "epoch": 3.7173476222371065,
+      "grad_norm": 1.8693480723789162,
+      "learning_rate": 1.8742018459553551e-06,
+      "loss": 0.5715,
+      "step": 11100
+    },
+    {
+      "epoch": 3.750837240455459,
+      "grad_norm": 1.6174259181592696,
+      "learning_rate": 1.7838237201067976e-06,
+      "loss": 0.577,
+      "step": 11200
+    },
+    {
+      "epoch": 3.7843268586738112,
+      "grad_norm": 1.7622557353103667,
+      "learning_rate": 1.695203579287134e-06,
+      "loss": 0.5825,
+      "step": 11300
+    },
+    {
+      "epoch": 3.8178164768921636,
+      "grad_norm": 1.6601130738963383,
+      "learning_rate": 1.6083898639011402e-06,
+      "loss": 0.5871,
+      "step": 11400
+    },
+    {
+      "epoch": 3.8513060951105156,
+      "grad_norm": 2.0156698217638445,
+      "learning_rate": 1.5234300269484848e-06,
+      "loss": 0.5805,
+      "step": 11500
+    },
+    {
+      "epoch": 3.884795713328868,
+      "grad_norm": 1.6232268197279267,
+      "learning_rate": 1.440370508085589e-06,
+      "loss": 0.5859,
+      "step": 11600
+    },
+    {
+      "epoch": 3.9182853315472204,
+      "grad_norm": 1.9405869273694487,
+      "learning_rate": 1.3592567082413683e-06,
+      "loss": 0.5961,
+      "step": 11700
+    },
+    {
+      "epoch": 3.9517749497655728,
+      "grad_norm": 1.6205319658414614,
+      "learning_rate": 1.2801329648007648e-06,
+      "loss": 0.6098,
+      "step": 11800
+    },
+    {
+      "epoch": 3.985264567983925,
+      "grad_norm": 2.0422623489549028,
+      "learning_rate": 1.203042527369611e-06,
+      "loss": 0.5992,
+      "step": 11900
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": NaN,
+      "eval_runtime": 348.6255,
+      "eval_samples_per_second": 45.677,
+      "eval_steps_per_second": 1.428,
+      "step": 11944
+    },
+    {
+      "epoch": 4.018754186202277,
+      "grad_norm": 2.042627434325046,
+      "learning_rate": 1.1280275341340919e-06,
+      "loss": 0.5984,
+      "step": 12000
+    },
+    {
+      "epoch": 4.0522438044206295,
+      "grad_norm": 1.6714080325577199,
+      "learning_rate": 1.0551289888277e-06,
+      "loss": 0.6147,
+      "step": 12100
+    },
+    {
+      "epoch": 4.085733422638982,
+      "grad_norm": 1.73673619396585,
+      "learning_rate": 9.843867383183065e-07,
+      "loss": 0.5882,
+      "step": 12200
+    },
+    {
+      "epoch": 4.119223040857334,
+      "grad_norm": 1.7412386584226505,
+      "learning_rate": 9.158394508275764e-07,
+      "loss": 0.5785,
+      "step": 12300
+    },
+    {
+      "epoch": 4.152712659075687,
+      "grad_norm": 1.688382578729062,
+      "learning_rate": 8.495245947946428e-07,
+      "loss": 0.568,
+      "step": 12400
+    },
+    {
+      "epoch": 4.186202277294039,
+      "grad_norm": 1.7570920632165827,
+      "learning_rate": 7.85478418395586e-07,
+      "loss": 0.5548,
+      "step": 12500
+    },
+    {
+      "epoch": 4.219691895512391,
+      "grad_norm": 2.0216120473215775,
+      "learning_rate": 7.237359297299213e-07,
+      "loss": 0.5491,
+      "step": 12600
+    },
+    {
+      "epoch": 4.253181513730744,
+      "grad_norm": 1.7189176283861873,
+      "learning_rate": 6.643308776849211e-07,
+      "loss": 0.5344,
+      "step": 12700
+    },
+    {
+      "epoch": 4.286671131949095,
+      "grad_norm": 1.878389510492855,
+      "learning_rate": 6.07295733488234e-07,
+      "loss": 0.5205,
+      "step": 12800
+    },
+    {
+      "epoch": 4.320160750167448,
+      "grad_norm": 1.8272392601326726,
+      "learning_rate": 5.526616729588719e-07,
+      "loss": 0.5143,
+      "step": 12900
+    },
+    {
+      "epoch": 4.3536503683858,
+      "grad_norm": 1.9885081295428908,
+      "learning_rate": 5.00458559466292e-07,
+      "loss": 0.5027,
+      "step": 13000
+    },
+    {
+      "epoch": 4.3871399866041525,
+      "grad_norm": 1.8856403938879776,
+      "learning_rate": 4.507149276068562e-07,
+      "loss": 0.498,
+      "step": 13100
+    },
+    {
+      "epoch": 4.420629604822505,
+      "grad_norm": 1.9693198350457568,
+      "learning_rate": 4.0345796760662247e-07,
+      "loss": 0.4925,
+      "step": 13200
+    },
+    {
+      "epoch": 4.454119223040857,
+      "grad_norm": 2.1533445061135827,
+      "learning_rate": 3.587135104589706e-07,
+      "loss": 0.4893,
+      "step": 13300
+    },
+    {
+      "epoch": 4.48760884125921,
+      "grad_norm": 1.795431467461819,
+      "learning_rate": 3.16506013805194e-07,
+      "loss": 0.4844,
+      "step": 13400
+    },
+    {
+      "epoch": 4.521098459477562,
+      "grad_norm": 1.8492311436151545,
+      "learning_rate": 2.7685854856577934e-07,
+      "loss": 0.472,
+      "step": 13500
+    },
+    {
+      "epoch": 4.5545880776959144,
+      "grad_norm": 1.9596331843479984,
+      "learning_rate": 2.3979278632967507e-07,
+      "loss": 0.4774,
+      "step": 13600
+    },
+    {
+      "epoch": 4.588077695914267,
+      "grad_norm": 1.9830637420731552,
+      "learning_rate": 2.0532898750844633e-07,
+      "loss": 0.4786,
+      "step": 13700
+    },
+    {
+      "epoch": 4.621567314132619,
+      "grad_norm": 2.0258341442311423,
+      "learning_rate": 1.734859902617886e-07,
+      "loss": 0.4786,
+      "step": 13800
+    },
+    {
+      "epoch": 4.655056932350972,
+      "grad_norm": 1.9180928479733919,
+      "learning_rate": 1.4428120020045122e-07,
+      "loss": 0.4882,
+      "step": 13900
+    },
+    {
+      "epoch": 4.688546550569323,
+      "grad_norm": 1.897536871580035,
+      "learning_rate": 1.1773058087221068e-07,
+      "loss": 0.4816,
+      "step": 14000
+    },
+    {
+      "epoch": 4.7220361687876755,
+      "grad_norm": 1.9655089659832947,
+      "learning_rate": 9.384864503607871e-08,
+      "loss": 0.482,
+      "step": 14100
+    },
+    {
+      "epoch": 4.755525787006028,
+      "grad_norm": 2.1423206586220345,
+      "learning_rate": 7.264844672952299e-08,
+      "loss": 0.4989,
+      "step": 14200
+    },
+    {
+      "epoch": 4.78901540522438,
+      "grad_norm": 1.8698413000910197,
+      "learning_rate": 5.4141574133037555e-08,
+      "loss": 0.5135,
+      "step": 14300
+    },
+    {
+      "epoch": 4.822505023442733,
+      "grad_norm": 1.888414362344593,
+      "learning_rate": 3.8338143235959746e-08,
+      "loss": 0.5077,
+      "step": 14400
+    },
+    {
+      "epoch": 4.855994641661085,
+      "grad_norm": 1.9521761786674516,
+      "learning_rate": 2.5246792306999334e-08,
+      "loss": 0.5146,
+      "step": 14500
+    },
+    {
+      "epoch": 4.8894842598794375,
+      "grad_norm": 1.8440132403394436,
+      "learning_rate": 1.4874677172497243e-08,
+      "loss": 0.5236,
+      "step": 14600
+    },
+    {
+      "epoch": 4.92297387809779,
+      "grad_norm": 1.9744361393291854,
+      "learning_rate": 7.2274673050010124e-09,
+      "loss": 0.5404,
+      "step": 14700
+    },
+    {
+      "epoch": 4.956463496316142,
+      "grad_norm": 1.8076672661575879,
+      "learning_rate": 2.309342724287622e-09,
+      "loss": 0.5488,
+      "step": 14800
+    },
+    {
+      "epoch": 4.989953114534495,
+      "grad_norm": 1.9120835449610545,
+      "learning_rate": 1.229917125389335e-10,
+      "loss": 0.5494,
+      "step": 14900
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": NaN,
+      "eval_runtime": 348.4998,
+      "eval_samples_per_second": 45.693,
+      "eval_steps_per_second": 1.429,
+      "step": 14930
+    },
+    {
+      "epoch": 5.0,
+      "step": 14930,
+      "total_flos": 7403300223713280.0,
+      "train_loss": 0.9973710162960596,
+      "train_runtime": 63021.9977,
+      "train_samples_per_second": 11.37,
+      "train_steps_per_second": 0.237
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 14930,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7403300223713280.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac80307e2d742d85aacb6ec8b4dcdd61f123ee378e7d5b4c2c49d1bafc2aad2
+size 7160