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 +1,81 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-32B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: Qwen2.5-32B-Base
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Qwen2.5-32B-Base
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-32B](https://huggingface.co/Qwen/Qwen2.5-32B) on the QA_train_data dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9999
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9373        | 0.1778 | 100  | 0.9672          |
+| 0.9671        | 0.3556 | 200  | 0.9639          |
+| 0.9584        | 0.5333 | 300  | 0.9629          |
+| 0.957         | 0.7111 | 400  | 0.9597          |
+| 0.9477        | 0.8889 | 500  | 0.9587          |
+| 0.8552        | 1.0667 | 600  | 0.9710          |
+| 0.7944        | 1.2444 | 700  | 0.9722          |
+| 0.7359        | 1.4222 | 800  | 0.9709          |
+| 0.8494        | 1.6    | 900  | 0.9662          |
+| 0.8163        | 1.7778 | 1000 | 0.9663          |
+| 0.8041        | 1.9556 | 1100 | 0.9639          |
+| 0.6291        | 2.1333 | 1200 | 0.9990          |
+| 0.6122        | 2.3111 | 1300 | 1.0004          |
+| 0.6718        | 2.4889 | 1400 | 1.0003          |
+| 0.6712        | 2.6667 | 1500 | 1.0002          |
+| 0.6397        | 2.8444 | 1600 | 0.9996          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.20.3

added_tokens.json

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

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.997333333333333,
+    "eval_loss": 0.9999473690986633,
+    "eval_runtime": 67.4925,
+    "eval_samples_per_second": 29.633,
+    "eval_steps_per_second": 1.852,
+    "total_flos": 297597215473664.0,
+    "train_loss": 0.7989534891938541,
+    "train_runtime": 8333.3074,
+    "train_samples_per_second": 6.48,
+    "train_steps_per_second": 0.202
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-32B",
+  "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": 27648,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 64,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "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": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.997333333333333,
+    "eval_loss": 0.9999473690986633,
+    "eval_runtime": 67.4925,
+    "eval_samples_per_second": 29.633,
+    "eval_steps_per_second": 1.852
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8f3fc838fa2cc8e4e18bb9e4bff58453db6e7b3a35f9d5456d6da7170636de
+size 4891730992

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce4b27d2bcc747451e717646b7115e94dedf984aedadcec20dfaed93b4aee98
+size 4876059352

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a36d34ffcd7bb0619ac02565031abbaf18de66effeb816e8be4993dc701c14
+size 4876059384

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f570c10d7fe1a73d7362f0acb38c7be37639a9c60205e45070f2f06ae66b67c
+size 4876059416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b6ca01c24590f188630ab33c9376bff5da4cbc0f481f6c3d2d0bc215802455
+size 4876059416

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1151a1548683255a03140de6c0c5d8827f91f7306fe41a0b6b80b9c100f32942
+size 4876059416

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bf6ba48b9b22f2ae29e06de39732a5be1faa8ab1a9f8b56ab6dd00b1b46e80
+size 4876059416

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a5b8f22704766b95042ee2fab1f77710250eb1d3890f15a83715d71dfc4c28
+size 4876059416

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9870cd80a9175c827ef8a9c96f8353ab7cc18b29d7bfe4454de9d910f51b1146
+size 4876059416

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef2e801263b7f886a4981c37f1cce53b404809122084b20dfc10ebb27d0b9cd
+size 4876059416

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ba1f1b0973b790e76b53b13aa12ac5eb1b7f2ef8a7be5828b3840447b2ddf8
+size 4876059416

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aad45de9f5b9ca3736693f5f05ef00a772b8c13ad2f22c3a8e72fe84aac94638
+size 4876059416

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f807cf5d2c9c986124fb054c48238f32b2ffd74811db915a788b498ae83365b
+size 4876059416

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c178f2eaa397911f576aed4e4ca950219caf040842351fad77f2daae1125d4c2
+size 2123397800

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+  "metadata": {
+    "total_size": 65527752704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.997333333333333,
+    "total_flos": 297597215473664.0,
+    "train_loss": 0.7989534891938541,
+    "train_runtime": 8333.3074,
+    "train_samples_per_second": 6.48,
+    "train_steps_per_second": 0.202
+}

trainer_log.jsonl

@@ -0,0 +1,185 @@
+{"current_steps": 10, "total_steps": 1686, "loss": 1.0313, "lr": 2.958579881656805e-07, "epoch": 0.017777777777777778, "percentage": 0.59, "elapsed_time": "0:00:46", "remaining_time": "2:11:13"}
+{"current_steps": 20, "total_steps": 1686, "loss": 1.0088, "lr": 5.91715976331361e-07, "epoch": 0.035555555555555556, "percentage": 1.19, "elapsed_time": "0:01:28", "remaining_time": "2:02:10"}
+{"current_steps": 30, "total_steps": 1686, "loss": 1.0074, "lr": 8.875739644970415e-07, "epoch": 0.05333333333333334, "percentage": 1.78, "elapsed_time": "0:02:06", "remaining_time": "1:56:27"}
+{"current_steps": 40, "total_steps": 1686, "loss": 0.9623, "lr": 1.183431952662722e-06, "epoch": 0.07111111111111111, "percentage": 2.37, "elapsed_time": "0:02:43", "remaining_time": "1:52:24"}
+{"current_steps": 50, "total_steps": 1686, "loss": 0.9638, "lr": 1.4792899408284026e-06, "epoch": 0.08888888888888889, "percentage": 2.97, "elapsed_time": "0:03:20", "remaining_time": "1:49:21"}
+{"current_steps": 60, "total_steps": 1686, "loss": 1.0104, "lr": 1.775147928994083e-06, "epoch": 0.10666666666666667, "percentage": 3.56, "elapsed_time": "0:03:56", "remaining_time": "1:47:02"}
+{"current_steps": 70, "total_steps": 1686, "loss": 1.0002, "lr": 2.0710059171597635e-06, "epoch": 0.12444444444444444, "percentage": 4.15, "elapsed_time": "0:04:32", "remaining_time": "1:44:44"}
+{"current_steps": 80, "total_steps": 1686, "loss": 1.0223, "lr": 2.366863905325444e-06, "epoch": 0.14222222222222222, "percentage": 4.74, "elapsed_time": "0:05:09", "remaining_time": "1:43:38"}
+{"current_steps": 90, "total_steps": 1686, "loss": 0.9855, "lr": 2.6627218934911246e-06, "epoch": 0.16, "percentage": 5.34, "elapsed_time": "0:05:44", "remaining_time": "1:41:48"}
+{"current_steps": 100, "total_steps": 1686, "loss": 0.9373, "lr": 2.958579881656805e-06, "epoch": 0.17777777777777778, "percentage": 5.93, "elapsed_time": "0:06:27", "remaining_time": "1:42:22"}
+{"current_steps": 100, "total_steps": 1686, "eval_loss": 0.9671729803085327, "epoch": 0.17777777777777778, "percentage": 5.93, "elapsed_time": "0:07:35", "remaining_time": "2:00:31"}
+{"current_steps": 110, "total_steps": 1686, "loss": 0.9625, "lr": 3.2544378698224853e-06, "epoch": 0.19555555555555557, "percentage": 6.52, "elapsed_time": "0:08:16", "remaining_time": "1:58:28"}
+{"current_steps": 120, "total_steps": 1686, "loss": 0.9634, "lr": 3.550295857988166e-06, "epoch": 0.21333333333333335, "percentage": 7.12, "elapsed_time": "0:08:53", "remaining_time": "1:56:00"}
+{"current_steps": 130, "total_steps": 1686, "loss": 0.933, "lr": 3.846153846153847e-06, "epoch": 0.2311111111111111, "percentage": 7.71, "elapsed_time": "0:09:30", "remaining_time": "1:53:49"}
+{"current_steps": 140, "total_steps": 1686, "loss": 0.951, "lr": 4.142011834319527e-06, "epoch": 0.24888888888888888, "percentage": 8.3, "elapsed_time": "0:10:10", "remaining_time": "1:52:20"}
+{"current_steps": 150, "total_steps": 1686, "loss": 0.9375, "lr": 4.437869822485207e-06, "epoch": 0.26666666666666666, "percentage": 8.9, "elapsed_time": "0:10:49", "remaining_time": "1:50:47"}
+{"current_steps": 160, "total_steps": 1686, "loss": 0.9533, "lr": 4.733727810650888e-06, "epoch": 0.28444444444444444, "percentage": 9.49, "elapsed_time": "0:11:33", "remaining_time": "1:50:09"}
+{"current_steps": 170, "total_steps": 1686, "loss": 0.9641, "lr": 4.999994639090922e-06, "epoch": 0.3022222222222222, "percentage": 10.08, "elapsed_time": "0:12:09", "remaining_time": "1:48:28"}
+{"current_steps": 180, "total_steps": 1686, "loss": 0.958, "lr": 4.999351357820732e-06, "epoch": 0.32, "percentage": 10.68, "elapsed_time": "0:12:51", "remaining_time": "1:47:34"}
+{"current_steps": 190, "total_steps": 1686, "loss": 0.9524, "lr": 4.99763621084537e-06, "epoch": 0.3377777777777778, "percentage": 11.27, "elapsed_time": "0:13:40", "remaining_time": "1:47:38"}
+{"current_steps": 200, "total_steps": 1686, "loss": 0.9671, "lr": 4.994849933718568e-06, "epoch": 0.35555555555555557, "percentage": 11.86, "elapsed_time": "0:14:21", "remaining_time": "1:46:38"}
+{"current_steps": 200, "total_steps": 1686, "eval_loss": 0.9638746380805969, "epoch": 0.35555555555555557, "percentage": 11.86, "elapsed_time": "0:15:28", "remaining_time": "1:55:01"}
+{"current_steps": 210, "total_steps": 1686, "loss": 0.9697, "lr": 4.990993721356317e-06, "epoch": 0.37333333333333335, "percentage": 12.46, "elapsed_time": "0:16:10", "remaining_time": "1:53:41"}
+{"current_steps": 220, "total_steps": 1686, "loss": 1.0093, "lr": 4.986069227524407e-06, "epoch": 0.39111111111111113, "percentage": 13.05, "elapsed_time": "0:16:59", "remaining_time": "1:53:14"}
+{"current_steps": 230, "total_steps": 1686, "loss": 0.9411, "lr": 4.980078564129211e-06, "epoch": 0.4088888888888889, "percentage": 13.64, "elapsed_time": "0:17:41", "remaining_time": "1:52:02"}
+{"current_steps": 240, "total_steps": 1686, "loss": 1.0076, "lr": 4.973024300311968e-06, "epoch": 0.4266666666666667, "percentage": 14.23, "elapsed_time": "0:18:17", "remaining_time": "1:50:10"}
+{"current_steps": 250, "total_steps": 1686, "loss": 0.9674, "lr": 4.9649094613469904e-06, "epoch": 0.4444444444444444, "percentage": 14.83, "elapsed_time": "0:18:56", "remaining_time": "1:48:49"}
+{"current_steps": 260, "total_steps": 1686, "loss": 0.9507, "lr": 4.955737527344251e-06, "epoch": 0.4622222222222222, "percentage": 15.42, "elapsed_time": "0:19:38", "remaining_time": "1:47:45"}
+{"current_steps": 270, "total_steps": 1686, "loss": 0.9783, "lr": 4.945512431756916e-06, "epoch": 0.48, "percentage": 16.01, "elapsed_time": "0:20:22", "remaining_time": "1:46:50"}
+{"current_steps": 280, "total_steps": 1686, "loss": 0.9694, "lr": 4.934238559694448e-06, "epoch": 0.49777777777777776, "percentage": 16.61, "elapsed_time": "0:21:07", "remaining_time": "1:46:06"}
+{"current_steps": 290, "total_steps": 1686, "loss": 0.9724, "lr": 4.921920746042023e-06, "epoch": 0.5155555555555555, "percentage": 17.2, "elapsed_time": "0:21:51", "remaining_time": "1:45:14"}
+{"current_steps": 300, "total_steps": 1686, "loss": 0.9584, "lr": 4.908564273387051e-06, "epoch": 0.5333333333333333, "percentage": 17.79, "elapsed_time": "0:22:30", "remaining_time": "1:43:57"}
+{"current_steps": 300, "total_steps": 1686, "eval_loss": 0.9628667235374451, "epoch": 0.5333333333333333, "percentage": 17.79, "elapsed_time": "0:23:37", "remaining_time": "1:49:10"}
+{"current_steps": 310, "total_steps": 1686, "loss": 0.9468, "lr": 4.894174869753701e-06, "epoch": 0.5511111111111111, "percentage": 18.39, "elapsed_time": "0:24:13", "remaining_time": "1:47:33"}
+{"current_steps": 320, "total_steps": 1686, "loss": 0.9523, "lr": 4.878758706146389e-06, "epoch": 0.5688888888888889, "percentage": 18.98, "elapsed_time": "0:24:55", "remaining_time": "1:46:22"}
+{"current_steps": 330, "total_steps": 1686, "loss": 0.9527, "lr": 4.862322393903305e-06, "epoch": 0.5866666666666667, "percentage": 19.57, "elapsed_time": "0:25:33", "remaining_time": "1:44:59"}
+{"current_steps": 340, "total_steps": 1686, "loss": 0.9544, "lr": 4.84487298186108e-06, "epoch": 0.6044444444444445, "percentage": 20.17, "elapsed_time": "0:26:17", "remaining_time": "1:44:04"}
+{"current_steps": 350, "total_steps": 1686, "loss": 0.903, "lr": 4.8264179533318526e-06, "epoch": 0.6222222222222222, "percentage": 20.76, "elapsed_time": "0:26:55", "remaining_time": "1:42:46"}
+{"current_steps": 360, "total_steps": 1686, "loss": 0.935, "lr": 4.806965222893979e-06, "epoch": 0.64, "percentage": 21.35, "elapsed_time": "0:27:35", "remaining_time": "1:41:39"}
+{"current_steps": 370, "total_steps": 1686, "loss": 0.9859, "lr": 4.786523132997817e-06, "epoch": 0.6577777777777778, "percentage": 21.95, "elapsed_time": "0:28:23", "remaining_time": "1:40:57"}
+{"current_steps": 380, "total_steps": 1686, "loss": 1.0107, "lr": 4.765100450387999e-06, "epoch": 0.6755555555555556, "percentage": 22.54, "elapsed_time": "0:29:14", "remaining_time": "1:40:30"}
+{"current_steps": 390, "total_steps": 1686, "loss": 0.9379, "lr": 4.74270636234375e-06, "epoch": 0.6933333333333334, "percentage": 23.13, "elapsed_time": "0:29:56", "remaining_time": "1:39:30"}
+{"current_steps": 400, "total_steps": 1686, "loss": 0.957, "lr": 4.719350472738849e-06, "epoch": 0.7111111111111111, "percentage": 23.72, "elapsed_time": "0:30:38", "remaining_time": "1:38:29"}
+{"current_steps": 400, "total_steps": 1686, "eval_loss": 0.9597401022911072, "epoch": 0.7111111111111111, "percentage": 23.72, "elapsed_time": "0:31:45", "remaining_time": "1:42:06"}
+{"current_steps": 410, "total_steps": 1686, "loss": 0.9736, "lr": 4.69504279792294e-06, "epoch": 0.7288888888888889, "percentage": 24.32, "elapsed_time": "0:32:26", "remaining_time": "1:40:57"}
+{"current_steps": 420, "total_steps": 1686, "loss": 0.9402, "lr": 4.669793762425942e-06, "epoch": 0.7466666666666667, "percentage": 24.91, "elapsed_time": "0:33:04", "remaining_time": "1:39:43"}
+{"current_steps": 430, "total_steps": 1686, "loss": 1.0085, "lr": 4.643614194487411e-06, "epoch": 0.7644444444444445, "percentage": 25.5, "elapsed_time": "0:33:45", "remaining_time": "1:38:37"}
+{"current_steps": 440, "total_steps": 1686, "loss": 0.9195, "lr": 4.616515321412769e-06, "epoch": 0.7822222222222223, "percentage": 26.1, "elapsed_time": "0:34:27", "remaining_time": "1:37:34"}
+{"current_steps": 450, "total_steps": 1686, "loss": 0.9976, "lr": 4.588508764758386e-06, "epoch": 0.8, "percentage": 26.69, "elapsed_time": "0:35:06", "remaining_time": "1:36:27"}
+{"current_steps": 460, "total_steps": 1686, "loss": 0.9269, "lr": 4.559606535347594e-06, "epoch": 0.8177777777777778, "percentage": 27.28, "elapsed_time": "0:35:42", "remaining_time": "1:35:10"}
+{"current_steps": 470, "total_steps": 1686, "loss": 0.9837, "lr": 4.5298210281197474e-06, "epoch": 0.8355555555555556, "percentage": 27.88, "elapsed_time": "0:36:16", "remaining_time": "1:33:51"}
+{"current_steps": 480, "total_steps": 1686, "loss": 0.9712, "lr": 4.499165016814564e-06, "epoch": 0.8533333333333334, "percentage": 28.47, "elapsed_time": "0:36:57", "remaining_time": "1:32:52"}
+{"current_steps": 490, "total_steps": 1686, "loss": 1.0075, "lr": 4.46765164849401e-06, "epoch": 0.8711111111111111, "percentage": 29.06, "elapsed_time": "0:37:35", "remaining_time": "1:31:44"}
+{"current_steps": 500, "total_steps": 1686, "loss": 0.9477, "lr": 4.435294437904082e-06, "epoch": 0.8888888888888888, "percentage": 29.66, "elapsed_time": "0:38:12", "remaining_time": "1:30:37"}
+{"current_steps": 500, "total_steps": 1686, "eval_loss": 0.9587395787239075, "epoch": 0.8888888888888888, "percentage": 29.66, "elapsed_time": "0:39:19", "remaining_time": "1:33:17"}
+{"current_steps": 510, "total_steps": 1686, "loss": 1.002, "lr": 4.402107261678908e-06, "epoch": 0.9066666666666666, "percentage": 30.25, "elapsed_time": "0:39:58", "remaining_time": "1:32:11"}
+{"current_steps": 520, "total_steps": 1686, "loss": 0.9613, "lr": 4.368104352389641e-06, "epoch": 0.9244444444444444, "percentage": 30.84, "elapsed_time": "0:40:37", "remaining_time": "1:31:06"}
+{"current_steps": 530, "total_steps": 1686, "loss": 0.9345, "lr": 4.333300292440728e-06, "epoch": 0.9422222222222222, "percentage": 31.44, "elapsed_time": "0:41:15", "remaining_time": "1:29:58"}
+{"current_steps": 540, "total_steps": 1686, "loss": 0.9644, "lr": 4.2977100078161196e-06, "epoch": 0.96, "percentage": 32.03, "elapsed_time": "0:41:57", "remaining_time": "1:29:02"}
+{"current_steps": 550, "total_steps": 1686, "loss": 0.9952, "lr": 4.2613487616781595e-06, "epoch": 0.9777777777777777, "percentage": 32.62, "elapsed_time": "0:42:37", "remaining_time": "1:28:01"}
+{"current_steps": 560, "total_steps": 1686, "loss": 1.0213, "lr": 4.224232147821858e-06, "epoch": 0.9955555555555555, "percentage": 33.21, "elapsed_time": "0:43:17", "remaining_time": "1:27:03"}
+{"current_steps": 570, "total_steps": 1686, "loss": 0.8555, "lr": 4.186376083987376e-06, "epoch": 1.0133333333333334, "percentage": 33.81, "elapsed_time": "0:46:35", "remaining_time": "1:31:14"}
+{"current_steps": 580, "total_steps": 1686, "loss": 0.8231, "lr": 4.147796805033583e-06, "epoch": 1.031111111111111, "percentage": 34.4, "elapsed_time": "0:47:11", "remaining_time": "1:30:00"}
+{"current_steps": 590, "total_steps": 1686, "loss": 0.7805, "lr": 4.108510855975611e-06, "epoch": 1.048888888888889, "percentage": 34.99, "elapsed_time": "0:47:47", "remaining_time": "1:28:46"}
+{"current_steps": 600, "total_steps": 1686, "loss": 0.8552, "lr": 4.0685350848894065e-06, "epoch": 1.0666666666666667, "percentage": 35.59, "elapsed_time": "0:48:23", "remaining_time": "1:27:34"}
+{"current_steps": 600, "total_steps": 1686, "eval_loss": 0.9710310101509094, "epoch": 1.0666666666666667, "percentage": 35.59, "elapsed_time": "0:49:30", "remaining_time": "1:29:36"}
+{"current_steps": 610, "total_steps": 1686, "loss": 0.8172, "lr": 4.027886635686301e-06, "epoch": 1.0844444444444445, "percentage": 36.18, "elapsed_time": "0:50:09", "remaining_time": "1:28:27"}
+{"current_steps": 620, "total_steps": 1686, "loss": 0.7653, "lr": 3.986582940760717e-06, "epoch": 1.1022222222222222, "percentage": 36.77, "elapsed_time": "0:50:47", "remaining_time": "1:27:19"}
+{"current_steps": 630, "total_steps": 1686, "loss": 0.8175, "lr": 3.9446417135141536e-06, "epoch": 1.12, "percentage": 37.37, "elapsed_time": "0:51:25", "remaining_time": "1:26:11"}
+{"current_steps": 640, "total_steps": 1686, "loss": 0.7756, "lr": 3.902080940758658e-06, "epoch": 1.1377777777777778, "percentage": 37.96, "elapsed_time": "0:52:01", "remaining_time": "1:25:01"}
+{"current_steps": 650, "total_steps": 1686, "loss": 0.752, "lr": 3.858918875003053e-06, "epoch": 1.1555555555555554, "percentage": 38.55, "elapsed_time": "0:52:41", "remaining_time": "1:23:58"}
+{"current_steps": 660, "total_steps": 1686, "loss": 0.7721, "lr": 3.815174026625202e-06, "epoch": 1.1733333333333333, "percentage": 39.15, "elapsed_time": "0:53:20", "remaining_time": "1:22:56"}
+{"current_steps": 670, "total_steps": 1686, "loss": 0.7816, "lr": 3.770865155933694e-06, "epoch": 1.1911111111111112, "percentage": 39.74, "elapsed_time": "0:54:06", "remaining_time": "1:22:03"}
+{"current_steps": 680, "total_steps": 1686, "loss": 0.7897, "lr": 3.7260112651223553e-06, "epoch": 1.208888888888889, "percentage": 40.33, "elapsed_time": "0:54:48", "remaining_time": "1:21:05"}
+{"current_steps": 690, "total_steps": 1686, "loss": 0.8024, "lr": 3.6806315901209987e-06, "epoch": 1.2266666666666666, "percentage": 40.93, "elapsed_time": "0:55:25", "remaining_time": "1:20:00"}
+{"current_steps": 700, "total_steps": 1686, "loss": 0.7944, "lr": 3.6347455923459616e-06, "epoch": 1.2444444444444445, "percentage": 41.52, "elapsed_time": "0:56:05", "remaining_time": "1:19:00"}
+{"current_steps": 700, "total_steps": 1686, "eval_loss": 0.9722110629081726, "epoch": 1.2444444444444445, "percentage": 41.52, "elapsed_time": "0:57:12", "remaining_time": "1:20:35"}
+{"current_steps": 710, "total_steps": 1686, "loss": 0.8198, "lr": 3.5883729503539265e-06, "epoch": 1.2622222222222224, "percentage": 42.11, "elapsed_time": "0:57:52", "remaining_time": "1:19:33"}
+{"current_steps": 720, "total_steps": 1686, "loss": 0.7903, "lr": 3.541533551402621e-06, "epoch": 1.28, "percentage": 42.7, "elapsed_time": "0:58:32", "remaining_time": "1:18:32"}
+{"current_steps": 730, "total_steps": 1686, "loss": 0.8095, "lr": 3.494247482922024e-06, "epoch": 1.2977777777777777, "percentage": 43.3, "elapsed_time": "0:59:08", "remaining_time": "1:17:26"}
+{"current_steps": 740, "total_steps": 1686, "loss": 0.8326, "lr": 3.4465350238997112e-06, "epoch": 1.3155555555555556, "percentage": 43.89, "elapsed_time": "0:59:45", "remaining_time": "1:16:23"}
+{"current_steps": 750, "total_steps": 1686, "loss": 0.7833, "lr": 3.3984166361840646e-06, "epoch": 1.3333333333333333, "percentage": 44.48, "elapsed_time": "1:00:32", "remaining_time": "1:15:32"}
+{"current_steps": 760, "total_steps": 1686, "loss": 0.8171, "lr": 3.3499129557090517e-06, "epoch": 1.3511111111111112, "percentage": 45.08, "elapsed_time": "1:01:16", "remaining_time": "1:14:39"}
+{"current_steps": 770, "total_steps": 1686, "loss": 0.7968, "lr": 3.301044783644348e-06, "epoch": 1.3688888888888888, "percentage": 45.67, "elapsed_time": "1:01:56", "remaining_time": "1:13:41"}
+{"current_steps": 780, "total_steps": 1686, "loss": 0.7689, "lr": 3.2518330774746014e-06, "epoch": 1.3866666666666667, "percentage": 46.26, "elapsed_time": "1:02:35", "remaining_time": "1:12:41"}
+{"current_steps": 790, "total_steps": 1686, "loss": 0.776, "lr": 3.2022989420116556e-06, "epoch": 1.4044444444444444, "percentage": 46.86, "elapsed_time": "1:03:16", "remaining_time": "1:11:45"}
+{"current_steps": 800, "total_steps": 1686, "loss": 0.7359, "lr": 3.152463620343591e-06, "epoch": 1.4222222222222223, "percentage": 47.45, "elapsed_time": "1:03:52", "remaining_time": "1:10:44"}
+{"current_steps": 800, "total_steps": 1686, "eval_loss": 0.9709274768829346, "epoch": 1.4222222222222223, "percentage": 47.45, "elapsed_time": "1:05:00", "remaining_time": "1:12:00"}
+{"current_steps": 810, "total_steps": 1686, "loss": 0.8143, "lr": 3.102348484724467e-06, "epoch": 1.44, "percentage": 48.04, "elapsed_time": "1:05:38", "remaining_time": "1:10:59"}
+{"current_steps": 820, "total_steps": 1686, "loss": 0.8282, "lr": 3.0519750274086675e-06, "epoch": 1.4577777777777778, "percentage": 48.64, "elapsed_time": "1:06:20", "remaining_time": "1:10:04"}
+{"current_steps": 830, "total_steps": 1686, "loss": 0.7994, "lr": 3.001364851433789e-06, "epoch": 1.4755555555555555, "percentage": 49.23, "elapsed_time": "1:07:04", "remaining_time": "1:09:10"}
+{"current_steps": 840, "total_steps": 1686, "loss": 0.7533, "lr": 2.950539661356011e-06, "epoch": 1.4933333333333334, "percentage": 49.82, "elapsed_time": "1:07:40", "remaining_time": "1:08:09"}
+{"current_steps": 850, "total_steps": 1686, "loss": 0.8492, "lr": 2.899521253941937e-06, "epoch": 1.511111111111111, "percentage": 50.42, "elapsed_time": "1:08:23", "remaining_time": "1:07:15"}
+{"current_steps": 860, "total_steps": 1686, "loss": 0.7805, "lr": 2.8483315088208828e-06, "epoch": 1.528888888888889, "percentage": 51.01, "elapsed_time": "1:09:13", "remaining_time": "1:06:29"}
+{"current_steps": 870, "total_steps": 1686, "loss": 0.8412, "lr": 2.7969923791016334e-06, "epoch": 1.5466666666666666, "percentage": 51.6, "elapsed_time": "1:09:48", "remaining_time": "1:05:28"}
+{"current_steps": 880, "total_steps": 1686, "loss": 0.8048, "lr": 2.7455258819576876e-06, "epoch": 1.5644444444444443, "percentage": 52.19, "elapsed_time": "1:10:28", "remaining_time": "1:04:32"}
+{"current_steps": 890, "total_steps": 1686, "loss": 0.7951, "lr": 2.6939540891850265e-06, "epoch": 1.5822222222222222, "percentage": 52.79, "elapsed_time": "1:11:09", "remaining_time": "1:03:38"}
+{"current_steps": 900, "total_steps": 1686, "loss": 0.8494, "lr": 2.642299117736456e-06, "epoch": 1.6, "percentage": 53.38, "elapsed_time": "1:11:52", "remaining_time": "1:02:46"}
+{"current_steps": 900, "total_steps": 1686, "eval_loss": 0.9661916494369507, "epoch": 1.6, "percentage": 53.38, "elapsed_time": "1:13:00", "remaining_time": "1:03:45"}
+{"current_steps": 910, "total_steps": 1686, "loss": 0.7601, "lr": 2.5905831202365856e-06, "epoch": 1.6177777777777778, "percentage": 53.97, "elapsed_time": "1:13:40", "remaining_time": "1:02:49"}
+{"current_steps": 920, "total_steps": 1686, "loss": 0.7561, "lr": 2.538828275481509e-06, "epoch": 1.6355555555555554, "percentage": 54.57, "elapsed_time": "1:14:19", "remaining_time": "1:01:52"}
+{"current_steps": 930, "total_steps": 1686, "loss": 0.7645, "lr": 2.4870567789272563e-06, "epoch": 1.6533333333333333, "percentage": 55.16, "elapsed_time": "1:14:56", "remaining_time": "1:00:55"}
+{"current_steps": 940, "total_steps": 1686, "loss": 0.7935, "lr": 2.435290833171109e-06, "epoch": 1.6711111111111112, "percentage": 55.75, "elapsed_time": "1:15:38", "remaining_time": "1:00:01"}
+{"current_steps": 950, "total_steps": 1686, "loss": 0.7813, "lr": 2.3835526384298475e-06, "epoch": 1.6888888888888889, "percentage": 56.35, "elapsed_time": "1:16:17", "remaining_time": "0:59:06"}
+{"current_steps": 960, "total_steps": 1686, "loss": 0.752, "lr": 2.3318643830190186e-06, "epoch": 1.7066666666666666, "percentage": 56.94, "elapsed_time": "1:16:53", "remaining_time": "0:58:08"}
+{"current_steps": 970, "total_steps": 1686, "loss": 0.78, "lr": 2.2802482338373096e-06, "epoch": 1.7244444444444444, "percentage": 57.53, "elapsed_time": "1:17:30", "remaining_time": "0:57:12"}
+{"current_steps": 980, "total_steps": 1686, "loss": 0.7736, "lr": 2.228726326860109e-06, "epoch": 1.7422222222222223, "percentage": 58.13, "elapsed_time": "1:18:11", "remaining_time": "0:56:19"}
+{"current_steps": 990, "total_steps": 1686, "loss": 0.799, "lr": 2.1773207576463227e-06, "epoch": 1.76, "percentage": 58.72, "elapsed_time": "1:18:51", "remaining_time": "0:55:26"}
+{"current_steps": 1000, "total_steps": 1686, "loss": 0.8163, "lr": 2.1260535718625274e-06, "epoch": 1.7777777777777777, "percentage": 59.31, "elapsed_time": "1:19:34", "remaining_time": "0:54:35"}
+{"current_steps": 1000, "total_steps": 1686, "eval_loss": 0.9663456082344055, "epoch": 1.7777777777777777, "percentage": 59.31, "elapsed_time": "1:20:41", "remaining_time": "0:55:21"}
+{"current_steps": 1010, "total_steps": 1686, "loss": 0.7882, "lr": 2.0749467558285224e-06, "epoch": 1.7955555555555556, "percentage": 59.91, "elapsed_time": "1:21:24", "remaining_time": "0:54:29"}
+{"current_steps": 1020, "total_steps": 1686, "loss": 0.8198, "lr": 2.024022227088329e-06, "epoch": 1.8133333333333335, "percentage": 60.5, "elapsed_time": "1:22:02", "remaining_time": "0:53:34"}
+{"current_steps": 1030, "total_steps": 1686, "loss": 0.8141, "lr": 1.973301825010685e-06, "epoch": 1.8311111111111111, "percentage": 61.09, "elapsed_time": "1:22:41", "remaining_time": "0:52:40"}
+{"current_steps": 1040, "total_steps": 1686, "loss": 0.7297, "lr": 1.922807301423065e-06, "epoch": 1.8488888888888888, "percentage": 61.68, "elapsed_time": "1:23:18", "remaining_time": "0:51:45"}
+{"current_steps": 1050, "total_steps": 1686, "loss": 0.7754, "lr": 1.8725603112832518e-06, "epoch": 1.8666666666666667, "percentage": 62.28, "elapsed_time": "1:23:59", "remaining_time": "0:50:52"}
+{"current_steps": 1060, "total_steps": 1686, "loss": 0.8001, "lr": 1.8225824033924377e-06, "epoch": 1.8844444444444446, "percentage": 62.87, "elapsed_time": "1:24:40", "remaining_time": "0:50:00"}
+{"current_steps": 1070, "total_steps": 1686, "loss": 0.7828, "lr": 1.7728950111538585e-06, "epoch": 1.9022222222222223, "percentage": 63.46, "elapsed_time": "1:25:25", "remaining_time": "0:49:10"}
+{"current_steps": 1080, "total_steps": 1686, "loss": 0.7754, "lr": 1.7235194433809215e-06, "epoch": 1.92, "percentage": 64.06, "elapsed_time": "1:26:02", "remaining_time": "0:48:16"}
+{"current_steps": 1090, "total_steps": 1686, "loss": 0.7963, "lr": 1.674476875158756e-06, "epoch": 1.9377777777777778, "percentage": 64.65, "elapsed_time": "1:26:45", "remaining_time": "0:47:26"}
+{"current_steps": 1100, "total_steps": 1686, "loss": 0.8041, "lr": 1.6257883387631178e-06, "epoch": 1.9555555555555557, "percentage": 65.24, "elapsed_time": "1:27:23", "remaining_time": "0:46:33"}
+{"current_steps": 1100, "total_steps": 1686, "eval_loss": 0.9638973474502563, "epoch": 1.9555555555555557, "percentage": 65.24, "elapsed_time": "1:28:31", "remaining_time": "0:47:09"}
+{"current_steps": 1110, "total_steps": 1686, "loss": 0.8067, "lr": 1.5774747146405423e-06, "epoch": 1.9733333333333334, "percentage": 65.84, "elapsed_time": "1:29:16", "remaining_time": "0:46:19"}
+{"current_steps": 1120, "total_steps": 1686, "loss": 0.7654, "lr": 1.5295567224536023e-06, "epoch": 1.991111111111111, "percentage": 66.43, "elapsed_time": "1:30:03", "remaining_time": "0:45:30"}
+{"current_steps": 1130, "total_steps": 1686, "loss": 0.7469, "lr": 1.4820549121951321e-06, "epoch": 2.008888888888889, "percentage": 67.02, "elapsed_time": "1:33:23", "remaining_time": "0:45:56"}
+{"current_steps": 1140, "total_steps": 1686, "loss": 0.6237, "lr": 1.434989655375197e-06, "epoch": 2.026666666666667, "percentage": 67.62, "elapsed_time": "1:34:02", "remaining_time": "0:45:02"}
+{"current_steps": 1150, "total_steps": 1686, "loss": 0.6339, "lr": 1.3883811362846275e-06, "epoch": 2.0444444444444443, "percentage": 68.21, "elapsed_time": "1:34:43", "remaining_time": "0:44:09"}
+{"current_steps": 1160, "total_steps": 1686, "loss": 0.6055, "lr": 1.342249343338829e-06, "epoch": 2.062222222222222, "percentage": 68.8, "elapsed_time": "1:35:21", "remaining_time": "0:43:14"}
+{"current_steps": 1170, "total_steps": 1686, "loss": 0.6589, "lr": 1.296614060505596e-06, "epoch": 2.08, "percentage": 69.4, "elapsed_time": "1:35:56", "remaining_time": "0:42:18"}
+{"current_steps": 1180, "total_steps": 1686, "loss": 0.6441, "lr": 1.251494858820615e-06, "epoch": 2.097777777777778, "percentage": 69.99, "elapsed_time": "1:36:41", "remaining_time": "0:41:27"}
+{"current_steps": 1190, "total_steps": 1686, "loss": 0.6571, "lr": 1.2069110879942758e-06, "epoch": 2.1155555555555554, "percentage": 70.58, "elapsed_time": "1:37:20", "remaining_time": "0:40:34"}
+{"current_steps": 1200, "total_steps": 1686, "loss": 0.6291, "lr": 1.1628818681133965e-06, "epoch": 2.1333333333333333, "percentage": 71.17, "elapsed_time": "1:37:57", "remaining_time": "0:39:40"}
+{"current_steps": 1200, "total_steps": 1686, "eval_loss": 0.9990262985229492, "epoch": 2.1333333333333333, "percentage": 71.17, "elapsed_time": "1:39:05", "remaining_time": "0:40:07"}
+{"current_steps": 1210, "total_steps": 1686, "loss": 0.6581, "lr": 1.119426081441437e-06, "epoch": 2.151111111111111, "percentage": 71.77, "elapsed_time": "1:39:43", "remaining_time": "0:39:13"}
+{"current_steps": 1220, "total_steps": 1686, "loss": 0.6067, "lr": 1.0765623643206946e-06, "epoch": 2.168888888888889, "percentage": 72.36, "elapsed_time": "1:40:26", "remaining_time": "0:38:21"}
+{"current_steps": 1230, "total_steps": 1686, "loss": 0.6324, "lr": 1.0343090991799677e-06, "epoch": 2.1866666666666665, "percentage": 72.95, "elapsed_time": "1:41:06", "remaining_time": "0:37:28"}
+{"current_steps": 1240, "total_steps": 1686, "loss": 0.6631, "lr": 9.926844066511132e-07, "epoch": 2.2044444444444444, "percentage": 73.55, "elapsed_time": "1:41:46", "remaining_time": "0:36:36"}
+{"current_steps": 1250, "total_steps": 1686, "loss": 0.6162, "lr": 9.517061377978762e-07, "epoch": 2.2222222222222223, "percentage": 74.14, "elapsed_time": "1:42:24", "remaining_time": "0:35:43"}
+{"current_steps": 1260, "total_steps": 1686, "loss": 0.7062, "lr": 9.113918664603277e-07, "epoch": 2.24, "percentage": 74.73, "elapsed_time": "1:43:09", "remaining_time": "0:34:52"}
+{"current_steps": 1270, "total_steps": 1686, "loss": 0.6165, "lr": 8.717588817181868e-07, "epoch": 2.2577777777777777, "percentage": 75.33, "elapsed_time": "1:44:00", "remaining_time": "0:34:04"}
+{"current_steps": 1280, "total_steps": 1686, "loss": 0.6159, "lr": 8.328241804762737e-07, "epoch": 2.2755555555555556, "percentage": 75.92, "elapsed_time": "1:44:40", "remaining_time": "0:33:12"}
+{"current_steps": 1290, "total_steps": 1686, "loss": 0.6516, "lr": 7.946044601752539e-07, "epoch": 2.2933333333333334, "percentage": 76.51, "elapsed_time": "1:45:22", "remaining_time": "0:32:20"}
+{"current_steps": 1300, "total_steps": 1686, "loss": 0.6122, "lr": 7.571161116308206e-07, "epoch": 2.311111111111111, "percentage": 77.11, "elapsed_time": "1:45:59", "remaining_time": "0:31:28"}
+{"current_steps": 1300, "total_steps": 1686, "eval_loss": 1.0003914833068848, "epoch": 2.311111111111111, "percentage": 77.11, "elapsed_time": "1:47:06", "remaining_time": "0:31:48"}
+{"current_steps": 1310, "total_steps": 1686, "loss": 0.618, "lr": 7.203752120043608e-07, "epoch": 2.328888888888889, "percentage": 77.7, "elapsed_time": "1:47:43", "remaining_time": "0:30:55"}
+{"current_steps": 1320, "total_steps": 1686, "loss": 0.6663, "lr": 6.843975179081513e-07, "epoch": 2.3466666666666667, "percentage": 78.29, "elapsed_time": "1:48:18", "remaining_time": "0:30:01"}
+{"current_steps": 1330, "total_steps": 1686, "loss": 0.6055, "lr": 6.491984586480132e-07, "epoch": 2.3644444444444446, "percentage": 78.88, "elapsed_time": "1:48:54", "remaining_time": "0:29:08"}
+{"current_steps": 1340, "total_steps": 1686, "loss": 0.6199, "lr": 6.147931296063353e-07, "epoch": 2.3822222222222225, "percentage": 79.48, "elapsed_time": "1:49:33", "remaining_time": "0:28:17"}
+{"current_steps": 1350, "total_steps": 1686, "loss": 0.6617, "lr": 5.811962857683124e-07, "epoch": 2.4, "percentage": 80.07, "elapsed_time": "1:50:17", "remaining_time": "0:27:26"}
+{"current_steps": 1360, "total_steps": 1686, "loss": 0.6497, "lr": 5.484223353941506e-07, "epoch": 2.417777777777778, "percentage": 80.66, "elapsed_time": "1:50:57", "remaining_time": "0:26:35"}
+{"current_steps": 1370, "total_steps": 1686, "loss": 0.5923, "lr": 5.164853338399795e-07, "epoch": 2.4355555555555557, "percentage": 81.26, "elapsed_time": "1:51:35", "remaining_time": "0:25:44"}
+{"current_steps": 1380, "total_steps": 1686, "loss": 0.6634, "lr": 4.853989775301074e-07, "epoch": 2.453333333333333, "percentage": 81.85, "elapsed_time": "1:52:14", "remaining_time": "0:24:53"}
+{"current_steps": 1390, "total_steps": 1686, "loss": 0.6338, "lr": 4.55176598083206e-07, "epoch": 2.471111111111111, "percentage": 82.44, "elapsed_time": "1:52:51", "remaining_time": "0:24:02"}
+{"current_steps": 1400, "total_steps": 1686, "loss": 0.6718, "lr": 4.2583115659494356e-07, "epoch": 2.488888888888889, "percentage": 83.04, "elapsed_time": "1:53:29", "remaining_time": "0:23:11"}
+{"current_steps": 1400, "total_steps": 1686, "eval_loss": 1.0003468990325928, "epoch": 2.488888888888889, "percentage": 83.04, "elapsed_time": "1:54:37", "remaining_time": "0:23:24"}
+{"current_steps": 1410, "total_steps": 1686, "loss": 0.5828, "lr": 3.9737523807952206e-07, "epoch": 2.506666666666667, "percentage": 83.63, "elapsed_time": "1:55:19", "remaining_time": "0:22:34"}
+{"current_steps": 1420, "total_steps": 1686, "loss": 0.6212, "lr": 3.698210460724991e-07, "epoch": 2.5244444444444447, "percentage": 84.22, "elapsed_time": "1:56:09", "remaining_time": "0:21:45"}
+{"current_steps": 1430, "total_steps": 1686, "loss": 0.5807, "lr": 3.4318039739720974e-07, "epoch": 2.542222222222222, "percentage": 84.82, "elapsed_time": "1:56:47", "remaining_time": "0:20:54"}
+{"current_steps": 1440, "total_steps": 1686, "loss": 0.6545, "lr": 3.1746471709702963e-07, "epoch": 2.56, "percentage": 85.41, "elapsed_time": "1:57:30", "remaining_time": "0:20:04"}
+{"current_steps": 1450, "total_steps": 1686, "loss": 0.6209, "lr": 2.9268503353566484e-07, "epoch": 2.5777777777777775, "percentage": 86.0, "elapsed_time": "1:58:19", "remaining_time": "0:19:15"}
+{"current_steps": 1460, "total_steps": 1686, "loss": 0.6429, "lr": 2.6885197366754935e-07, "epoch": 2.5955555555555554, "percentage": 86.6, "elapsed_time": "1:59:00", "remaining_time": "0:18:25"}
+{"current_steps": 1470, "total_steps": 1686, "loss": 0.6184, "lr": 2.459757584803965e-07, "epoch": 2.6133333333333333, "percentage": 87.19, "elapsed_time": "1:59:35", "remaining_time": "0:17:34"}
+{"current_steps": 1480, "total_steps": 1686, "loss": 0.6387, "lr": 2.2406619861185363e-07, "epoch": 2.631111111111111, "percentage": 87.78, "elapsed_time": "2:00:15", "remaining_time": "0:16:44"}
+{"current_steps": 1490, "total_steps": 1686, "loss": 0.6321, "lr": 2.0313269014213378e-07, "epoch": 2.648888888888889, "percentage": 88.37, "elapsed_time": "2:00:51", "remaining_time": "0:15:53"}
+{"current_steps": 1500, "total_steps": 1686, "loss": 0.6712, "lr": 1.8318421056443576e-07, "epoch": 2.6666666666666665, "percentage": 88.97, "elapsed_time": "2:01:32", "remaining_time": "0:15:04"}
+{"current_steps": 1500, "total_steps": 1686, "eval_loss": 1.0002143383026123, "epoch": 2.6666666666666665, "percentage": 88.97, "elapsed_time": "2:02:40", "remaining_time": "0:15:12"}
+{"current_steps": 1510, "total_steps": 1686, "loss": 0.64, "lr": 1.6422931493488004e-07, "epoch": 2.6844444444444444, "percentage": 89.56, "elapsed_time": "2:03:18", "remaining_time": "0:14:22"}
+{"current_steps": 1520, "total_steps": 1686, "loss": 0.6328, "lr": 1.4627613220360632e-07, "epoch": 2.7022222222222223, "percentage": 90.15, "elapsed_time": "2:03:56", "remaining_time": "0:13:32"}
+{"current_steps": 1530, "total_steps": 1686, "loss": 0.6195, "lr": 1.2933236172861435e-07, "epoch": 2.7199999999999998, "percentage": 90.75, "elapsed_time": "2:04:32", "remaining_time": "0:12:41"}
+{"current_steps": 1540, "total_steps": 1686, "loss": 0.6437, "lr": 1.1340526997383194e-07, "epoch": 2.7377777777777776, "percentage": 91.34, "elapsed_time": "2:05:16", "remaining_time": "0:11:52"}
+{"current_steps": 1550, "total_steps": 1686, "loss": 0.6516, "lr": 9.850168739284183e-08, "epoch": 2.7555555555555555, "percentage": 91.93, "elapsed_time": "2:05:52", "remaining_time": "0:11:02"}
+{"current_steps": 1560, "total_steps": 1686, "loss": 0.6293, "lr": 8.462800549958793e-08, "epoch": 2.7733333333333334, "percentage": 92.53, "elapsed_time": "2:06:31", "remaining_time": "0:10:13"}
+{"current_steps": 1570, "total_steps": 1686, "loss": 0.6241, "lr": 7.179017412732581e-08, "epoch": 2.7911111111111113, "percentage": 93.12, "elapsed_time": "2:07:10", "remaining_time": "0:09:23"}
+{"current_steps": 1580, "total_steps": 1686, "loss": 0.6547, "lr": 5.999369887699113e-08, "epoch": 2.8088888888888888, "percentage": 93.71, "elapsed_time": "2:07:48", "remaining_time": "0:08:34"}
+{"current_steps": 1590, "total_steps": 1686, "loss": 0.6381, "lr": 4.924363875608379e-08, "epoch": 2.8266666666666667, "percentage": 94.31, "elapsed_time": "2:08:32", "remaining_time": "0:07:45"}
+{"current_steps": 1600, "total_steps": 1686, "loss": 0.6397, "lr": 3.9544604009072173e-08, "epoch": 2.8444444444444446, "percentage": 94.9, "elapsed_time": "2:09:07", "remaining_time": "0:06:56"}
+{"current_steps": 1600, "total_steps": 1686, "eval_loss": 0.9996402859687805, "epoch": 2.8444444444444446, "percentage": 94.9, "elapsed_time": "2:10:15", "remaining_time": "0:07:00"}
+{"current_steps": 1610, "total_steps": 1686, "loss": 0.6399, "lr": 3.090075414025562e-08, "epoch": 2.862222222222222, "percentage": 95.49, "elapsed_time": "2:10:54", "remaining_time": "0:06:10"}
+{"current_steps": 1620, "total_steps": 1686, "loss": 0.6356, "lr": 2.331579612993018e-08, "epoch": 2.88, "percentage": 96.09, "elapsed_time": "2:11:38", "remaining_time": "0:05:21"}
+{"current_steps": 1630, "total_steps": 1686, "loss": 0.6473, "lr": 1.679298284462033e-08, "epoch": 2.897777777777778, "percentage": 96.68, "elapsed_time": "2:12:16", "remaining_time": "0:04:32"}
+{"current_steps": 1640, "total_steps": 1686, "loss": 0.639, "lr": 1.1335111642064855e-08, "epoch": 2.9155555555555557, "percentage": 97.27, "elapsed_time": "2:12:58", "remaining_time": "0:03:43"}
+{"current_steps": 1650, "total_steps": 1686, "loss": 0.6115, "lr": 6.944523171547313e-09, "epoch": 2.9333333333333336, "percentage": 97.86, "elapsed_time": "2:13:39", "remaining_time": "0:02:54"}
+{"current_steps": 1660, "total_steps": 1686, "loss": 0.6142, "lr": 3.623100370091226e-09, "epoch": 2.951111111111111, "percentage": 98.46, "elapsed_time": "2:14:17", "remaining_time": "0:02:06"}
+{"current_steps": 1670, "total_steps": 1686, "loss": 0.6238, "lr": 1.3722676549493553e-09, "epoch": 2.968888888888889, "percentage": 99.05, "elapsed_time": "2:14:55", "remaining_time": "0:01:17"}
+{"current_steps": 1680, "total_steps": 1686, "loss": 0.6662, "lr": 1.9299031272956846e-10, "epoch": 2.986666666666667, "percentage": 99.64, "elapsed_time": "2:15:39", "remaining_time": "0:00:29"}
+{"current_steps": 1686, "total_steps": 1686, "epoch": 2.997333333333333, "percentage": 100.0, "elapsed_time": "2:18:51", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1346 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.997333333333333,
+  "eval_steps": 100,
+  "global_step": 1686,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 3.064221071757039,
+      "learning_rate": 2.958579881656805e-07,
+      "loss": 1.0313,
+      "step": 10
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 2.311668702631407,
+      "learning_rate": 5.91715976331361e-07,
+      "loss": 1.0088,
+      "step": 20
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.7042990791798596,
+      "learning_rate": 8.875739644970415e-07,
+      "loss": 1.0074,
+      "step": 30
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 1.4979922190245858,
+      "learning_rate": 1.183431952662722e-06,
+      "loss": 0.9623,
+      "step": 40
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 1.62270031557648,
+      "learning_rate": 1.4792899408284026e-06,
+      "loss": 0.9638,
+      "step": 50
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 2.3961447512268093,
+      "learning_rate": 1.775147928994083e-06,
+      "loss": 1.0104,
+      "step": 60
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 1.4915238179077648,
+      "learning_rate": 2.0710059171597635e-06,
+      "loss": 1.0002,
+      "step": 70
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 2.2772628135300255,
+      "learning_rate": 2.366863905325444e-06,
+      "loss": 1.0223,
+      "step": 80
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 1.8457773806820135,
+      "learning_rate": 2.6627218934911246e-06,
+      "loss": 0.9855,
+      "step": 90
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.0682523156202766,
+      "learning_rate": 2.958579881656805e-06,
+      "loss": 0.9373,
+      "step": 100
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "eval_loss": 0.9671729803085327,
+      "eval_runtime": 68.6602,
+      "eval_samples_per_second": 29.129,
+      "eval_steps_per_second": 1.821,
+      "step": 100
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 1.4598489133901087,
+      "learning_rate": 3.2544378698224853e-06,
+      "loss": 0.9625,
+      "step": 110
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.180267593823412,
+      "learning_rate": 3.550295857988166e-06,
+      "loss": 0.9634,
+      "step": 120
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 1.2931186615642782,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 0.933,
+      "step": 130
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 1.512746752342751,
+      "learning_rate": 4.142011834319527e-06,
+      "loss": 0.951,
+      "step": 140
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.8895957215192007,
+      "learning_rate": 4.437869822485207e-06,
+      "loss": 0.9375,
+      "step": 150
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 2.562051614464793,
+      "learning_rate": 4.733727810650888e-06,
+      "loss": 0.9533,
+      "step": 160
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 1.7071555116041661,
+      "learning_rate": 4.999994639090922e-06,
+      "loss": 0.9641,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.4808539506312526,
+      "learning_rate": 4.999351357820732e-06,
+      "loss": 0.958,
+      "step": 180
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 3.108282359705838,
+      "learning_rate": 4.99763621084537e-06,
+      "loss": 0.9524,
+      "step": 190
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.6209678934544214,
+      "learning_rate": 4.994849933718568e-06,
+      "loss": 0.9671,
+      "step": 200
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "eval_loss": 0.9638746380805969,
+      "eval_runtime": 67.7576,
+      "eval_samples_per_second": 29.517,
+      "eval_steps_per_second": 1.845,
+      "step": 200
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 2.011525806742045,
+      "learning_rate": 4.990993721356317e-06,
+      "loss": 0.9697,
+      "step": 210
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 1.3952496927844644,
+      "learning_rate": 4.986069227524407e-06,
+      "loss": 1.0093,
+      "step": 220
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 1.1889866128952742,
+      "learning_rate": 4.980078564129211e-06,
+      "loss": 0.9411,
+      "step": 230
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 1.5732743711804986,
+      "learning_rate": 4.973024300311968e-06,
+      "loss": 1.0076,
+      "step": 240
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.6111844423415858,
+      "learning_rate": 4.9649094613469904e-06,
+      "loss": 0.9674,
+      "step": 250
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 1.3411297288659159,
+      "learning_rate": 4.955737527344251e-06,
+      "loss": 0.9507,
+      "step": 260
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 1.8162663201702451,
+      "learning_rate": 4.945512431756916e-06,
+      "loss": 0.9783,
+      "step": 270
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 1.373822283926042,
+      "learning_rate": 4.934238559694448e-06,
+      "loss": 0.9694,
+      "step": 280
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 1.4026814878661258,
+      "learning_rate": 4.921920746042023e-06,
+      "loss": 0.9724,
+      "step": 290
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.4388462413249878,
+      "learning_rate": 4.908564273387051e-06,
+      "loss": 0.9584,
+      "step": 300
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "eval_loss": 0.9628667235374451,
+      "eval_runtime": 67.724,
+      "eval_samples_per_second": 29.532,
+      "eval_steps_per_second": 1.846,
+      "step": 300
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 1.1700333111323251,
+      "learning_rate": 4.894174869753701e-06,
+      "loss": 0.9468,
+      "step": 310
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 1.4725090311768079,
+      "learning_rate": 4.878758706146389e-06,
+      "loss": 0.9523,
+      "step": 320
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.2704505454904513,
+      "learning_rate": 4.862322393903305e-06,
+      "loss": 0.9527,
+      "step": 330
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 2.3493531077217336,
+      "learning_rate": 4.84487298186108e-06,
+      "loss": 0.9544,
+      "step": 340
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.3584514135832693,
+      "learning_rate": 4.8264179533318526e-06,
+      "loss": 0.903,
+      "step": 350
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.3344268399358867,
+      "learning_rate": 4.806965222893979e-06,
+      "loss": 0.935,
+      "step": 360
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 1.626354968285715,
+      "learning_rate": 4.786523132997817e-06,
+      "loss": 0.9859,
+      "step": 370
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 1.3370406996157487,
+      "learning_rate": 4.765100450387999e-06,
+      "loss": 1.0107,
+      "step": 380
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 2.4117986108589893,
+      "learning_rate": 4.74270636234375e-06,
+      "loss": 0.9379,
+      "step": 390
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 3.6777984705003957,
+      "learning_rate": 4.719350472738849e-06,
+      "loss": 0.957,
+      "step": 400
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "eval_loss": 0.9597401022911072,
+      "eval_runtime": 67.6639,
+      "eval_samples_per_second": 29.558,
+      "eval_steps_per_second": 1.847,
+      "step": 400
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 2.9005913172464544,
+      "learning_rate": 4.69504279792294e-06,
+      "loss": 0.9736,
+      "step": 410
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.4861556222479484,
+      "learning_rate": 4.669793762425942e-06,
+      "loss": 0.9402,
+      "step": 420
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 1.404332314308356,
+      "learning_rate": 4.643614194487411e-06,
+      "loss": 1.0085,
+      "step": 430
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 1.2973467924712199,
+      "learning_rate": 4.616515321412769e-06,
+      "loss": 0.9195,
+      "step": 440
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.8400721698335023,
+      "learning_rate": 4.588508764758386e-06,
+      "loss": 0.9976,
+      "step": 450
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 1.34389013645689,
+      "learning_rate": 4.559606535347594e-06,
+      "loss": 0.9269,
+      "step": 460
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 1.4781191494614154,
+      "learning_rate": 4.5298210281197474e-06,
+      "loss": 0.9837,
+      "step": 470
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 1.2822503245441141,
+      "learning_rate": 4.499165016814564e-06,
+      "loss": 0.9712,
+      "step": 480
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 1.7262576201495767,
+      "learning_rate": 4.46765164849401e-06,
+      "loss": 1.0075,
+      "step": 490
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.848736473377725,
+      "learning_rate": 4.435294437904082e-06,
+      "loss": 0.9477,
+      "step": 500
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "eval_loss": 0.9587395787239075,
+      "eval_runtime": 67.6284,
+      "eval_samples_per_second": 29.573,
+      "eval_steps_per_second": 1.848,
+      "step": 500
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.7174287518034348,
+      "learning_rate": 4.402107261678908e-06,
+      "loss": 1.002,
+      "step": 510
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 1.4683365527516716,
+      "learning_rate": 4.368104352389641e-06,
+      "loss": 0.9613,
+      "step": 520
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 1.4656973277718064,
+      "learning_rate": 4.333300292440728e-06,
+      "loss": 0.9345,
+      "step": 530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.3740078632601003,
+      "learning_rate": 4.2977100078161196e-06,
+      "loss": 0.9644,
+      "step": 540
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.4355083298426001,
+      "learning_rate": 4.2613487616781595e-06,
+      "loss": 0.9952,
+      "step": 550
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.8504347531710936,
+      "learning_rate": 4.224232147821858e-06,
+      "loss": 1.0213,
+      "step": 560
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.1787812976568717,
+      "learning_rate": 4.186376083987376e-06,
+      "loss": 0.8555,
+      "step": 570
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 1.6020289309675289,
+      "learning_rate": 4.147796805033583e-06,
+      "loss": 0.8231,
+      "step": 580
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 1.5772724854646063,
+      "learning_rate": 4.108510855975611e-06,
+      "loss": 0.7805,
+      "step": 590
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.5423541893936756,
+      "learning_rate": 4.0685350848894065e-06,
+      "loss": 0.8552,
+      "step": 600
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "eval_loss": 0.9710310101509094,
+      "eval_runtime": 67.5663,
+      "eval_samples_per_second": 29.601,
+      "eval_steps_per_second": 1.85,
+      "step": 600
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 2.0459202464567303,
+      "learning_rate": 4.027886635686301e-06,
+      "loss": 0.8172,
+      "step": 610
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 1.1330519416716263,
+      "learning_rate": 3.986582940760717e-06,
+      "loss": 0.7653,
+      "step": 620
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.291984175159882,
+      "learning_rate": 3.9446417135141536e-06,
+      "loss": 0.8175,
+      "step": 630
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 1.9370076066794117,
+      "learning_rate": 3.902080940758658e-06,
+      "loss": 0.7756,
+      "step": 640
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 1.1866194794808598,
+      "learning_rate": 3.858918875003053e-06,
+      "loss": 0.752,
+      "step": 650
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 1.2727193771706111,
+      "learning_rate": 3.815174026625202e-06,
+      "loss": 0.7721,
+      "step": 660
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 1.545919656220833,
+      "learning_rate": 3.770865155933694e-06,
+      "loss": 0.7816,
+      "step": 670
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 1.9266494592917187,
+      "learning_rate": 3.7260112651223553e-06,
+      "loss": 0.7897,
+      "step": 680
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 2.057825893443874,
+      "learning_rate": 3.6806315901209987e-06,
+      "loss": 0.8024,
+      "step": 690
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 1.2392576716268238,
+      "learning_rate": 3.6347455923459616e-06,
+      "loss": 0.7944,
+      "step": 700
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "eval_loss": 0.9722110629081726,
+      "eval_runtime": 67.6028,
+      "eval_samples_per_second": 29.585,
+      "eval_steps_per_second": 1.849,
+      "step": 700
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 1.7969055853329803,
+      "learning_rate": 3.5883729503539265e-06,
+      "loss": 0.8198,
+      "step": 710
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.3886692866173258,
+      "learning_rate": 3.541533551402621e-06,
+      "loss": 0.7903,
+      "step": 720
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 1.2294305356221513,
+      "learning_rate": 3.494247482922024e-06,
+      "loss": 0.8095,
+      "step": 730
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 1.558667712302195,
+      "learning_rate": 3.4465350238997112e-06,
+      "loss": 0.8326,
+      "step": 740
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.1479609335353171,
+      "learning_rate": 3.3984166361840646e-06,
+      "loss": 0.7833,
+      "step": 750
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 1.2159354644232423,
+      "learning_rate": 3.3499129557090517e-06,
+      "loss": 0.8171,
+      "step": 760
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 1.4385597949788431,
+      "learning_rate": 3.301044783644348e-06,
+      "loss": 0.7968,
+      "step": 770
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 1.4756414075732949,
+      "learning_rate": 3.2518330774746014e-06,
+      "loss": 0.7689,
+      "step": 780
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 1.5209105713654745,
+      "learning_rate": 3.2022989420116556e-06,
+      "loss": 0.776,
+      "step": 790
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.7391061143058137,
+      "learning_rate": 3.152463620343591e-06,
+      "loss": 0.7359,
+      "step": 800
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "eval_loss": 0.9709274768829346,
+      "eval_runtime": 67.9642,
+      "eval_samples_per_second": 29.427,
+      "eval_steps_per_second": 1.839,
+      "step": 800
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.023232810277016,
+      "learning_rate": 3.102348484724467e-06,
+      "loss": 0.8143,
+      "step": 810
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 1.4087143597081888,
+      "learning_rate": 3.0519750274086675e-06,
+      "loss": 0.8282,
+      "step": 820
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 2.379499508964777,
+      "learning_rate": 3.001364851433789e-06,
+      "loss": 0.7994,
+      "step": 830
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.4148971570091637,
+      "learning_rate": 2.950539661356011e-06,
+      "loss": 0.7533,
+      "step": 840
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.3823213189741146,
+      "learning_rate": 2.899521253941937e-06,
+      "loss": 0.8492,
+      "step": 850
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 1.1488970638328968,
+      "learning_rate": 2.8483315088208828e-06,
+      "loss": 0.7805,
+      "step": 860
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.5267987965557517,
+      "learning_rate": 2.7969923791016334e-06,
+      "loss": 0.8412,
+      "step": 870
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 1.393454391992812,
+      "learning_rate": 2.7455258819576876e-06,
+      "loss": 0.8048,
+      "step": 880
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 1.8181282810366222,
+      "learning_rate": 2.6939540891850265e-06,
+      "loss": 0.7951,
+      "step": 890
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2842315283042123,
+      "learning_rate": 2.642299117736456e-06,
+      "loss": 0.8494,
+      "step": 900
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.9661916494369507,
+      "eval_runtime": 67.5902,
+      "eval_samples_per_second": 29.59,
+      "eval_steps_per_second": 1.849,
+      "step": 900
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 1.3592948657037425,
+      "learning_rate": 2.5905831202365856e-06,
+      "loss": 0.7601,
+      "step": 910
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 1.811137037940328,
+      "learning_rate": 2.538828275481509e-06,
+      "loss": 0.7561,
+      "step": 920
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 1.2508052091761472,
+      "learning_rate": 2.4870567789272563e-06,
+      "loss": 0.7645,
+      "step": 930
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 1.6434568587878196,
+      "learning_rate": 2.435290833171109e-06,
+      "loss": 0.7935,
+      "step": 940
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.635983339764013,
+      "learning_rate": 2.3835526384298475e-06,
+      "loss": 0.7813,
+      "step": 950
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.3393891297643545,
+      "learning_rate": 2.3318643830190186e-06,
+      "loss": 0.752,
+      "step": 960
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 1.468531788770485,
+      "learning_rate": 2.2802482338373096e-06,
+      "loss": 0.78,
+      "step": 970
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 1.4403918441032775,
+      "learning_rate": 2.228726326860109e-06,
+      "loss": 0.7736,
+      "step": 980
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.5016888280136909,
+      "learning_rate": 2.1773207576463227e-06,
+      "loss": 0.799,
+      "step": 990
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.4232106086043248,
+      "learning_rate": 2.1260535718625274e-06,
+      "loss": 0.8163,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "eval_loss": 0.9663456082344055,
+      "eval_runtime": 67.7852,
+      "eval_samples_per_second": 29.505,
+      "eval_steps_per_second": 1.844,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 2.021142501636729,
+      "learning_rate": 2.0749467558285224e-06,
+      "loss": 0.7882,
+      "step": 1010
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 1.4389492235517993,
+      "learning_rate": 2.024022227088329e-06,
+      "loss": 0.8198,
+      "step": 1020
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 1.8381964707129699,
+      "learning_rate": 1.973301825010685e-06,
+      "loss": 0.8141,
+      "step": 1030
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 1.1150366712372968,
+      "learning_rate": 1.922807301423065e-06,
+      "loss": 0.7297,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.1816318425909016,
+      "learning_rate": 1.8725603112832518e-06,
+      "loss": 0.7754,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 2.3505796457878154,
+      "learning_rate": 1.8225824033924377e-06,
+      "loss": 0.8001,
+      "step": 1060
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 1.4164977558439569,
+      "learning_rate": 1.7728950111538585e-06,
+      "loss": 0.7828,
+      "step": 1070
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.0614294585251351,
+      "learning_rate": 1.7235194433809215e-06,
+      "loss": 0.7754,
+      "step": 1080
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 1.2695304411022084,
+      "learning_rate": 1.674476875158756e-06,
+      "loss": 0.7963,
+      "step": 1090
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.7878889758415848,
+      "learning_rate": 1.6257883387631178e-06,
+      "loss": 0.8041,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "eval_loss": 0.9638973474502563,
+      "eval_runtime": 67.6938,
+      "eval_samples_per_second": 29.545,
+      "eval_steps_per_second": 1.847,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 1.2393550606660526,
+      "learning_rate": 1.5774747146405423e-06,
+      "loss": 0.8067,
+      "step": 1110
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 1.3321869776875785,
+      "learning_rate": 1.5295567224536023e-06,
+      "loss": 0.7654,
+      "step": 1120
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 1.352880244351638,
+      "learning_rate": 1.4820549121951321e-06,
+      "loss": 0.7469,
+      "step": 1130
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 1.4679043094200657,
+      "learning_rate": 1.434989655375197e-06,
+      "loss": 0.6237,
+      "step": 1140
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.308896485866915,
+      "learning_rate": 1.3883811362846275e-06,
+      "loss": 0.6339,
+      "step": 1150
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 1.1573190903084591,
+      "learning_rate": 1.342249343338829e-06,
+      "loss": 0.6055,
+      "step": 1160
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.4670238225692112,
+      "learning_rate": 1.296614060505596e-06,
+      "loss": 0.6589,
+      "step": 1170
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 1.1016096251472431,
+      "learning_rate": 1.251494858820615e-06,
+      "loss": 0.6441,
+      "step": 1180
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 1.4722885203046696,
+      "learning_rate": 1.2069110879942758e-06,
+      "loss": 0.6571,
+      "step": 1190
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.8212881071516174,
+      "learning_rate": 1.1628818681133965e-06,
+      "loss": 0.6291,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "eval_loss": 0.9990262985229492,
+      "eval_runtime": 67.7113,
+      "eval_samples_per_second": 29.537,
+      "eval_steps_per_second": 1.846,
+      "step": 1200
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 1.1599321734840744,
+      "learning_rate": 1.119426081441437e-06,
+      "loss": 0.6581,
+      "step": 1210
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 1.0610363548430464,
+      "learning_rate": 1.0765623643206946e-06,
+      "loss": 0.6067,
+      "step": 1220
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 1.2202345490291358,
+      "learning_rate": 1.0343090991799677e-06,
+      "loss": 0.6324,
+      "step": 1230
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 1.3964391722449683,
+      "learning_rate": 9.926844066511132e-07,
+      "loss": 0.6631,
+      "step": 1240
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.5877635166510526,
+      "learning_rate": 9.517061377978762e-07,
+      "loss": 0.6162,
+      "step": 1250
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.6284099053558183,
+      "learning_rate": 9.113918664603277e-07,
+      "loss": 0.7062,
+      "step": 1260
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.2153325885276287,
+      "learning_rate": 8.717588817181868e-07,
+      "loss": 0.6165,
+      "step": 1270
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 1.9069853339995495,
+      "learning_rate": 8.328241804762737e-07,
+      "loss": 0.6159,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 1.2627676318256413,
+      "learning_rate": 7.946044601752539e-07,
+      "loss": 0.6516,
+      "step": 1290
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5118126208151608,
+      "learning_rate": 7.571161116308206e-07,
+      "loss": 0.6122,
+      "step": 1300
+    },
+    {
+      "epoch": 2.311111111111111,
+      "eval_loss": 1.0003914833068848,
+      "eval_runtime": 67.475,
+      "eval_samples_per_second": 29.641,
+      "eval_steps_per_second": 1.853,
+      "step": 1300
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 1.2227440757674266,
+      "learning_rate": 7.203752120043608e-07,
+      "loss": 0.618,
+      "step": 1310
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 1.5510858354361334,
+      "learning_rate": 6.843975179081513e-07,
+      "loss": 0.6663,
+      "step": 1320
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 1.378250665848821,
+      "learning_rate": 6.491984586480132e-07,
+      "loss": 0.6055,
+      "step": 1330
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 1.1127356981856744,
+      "learning_rate": 6.147931296063353e-07,
+      "loss": 0.6199,
+      "step": 1340
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 2.188826901721088,
+      "learning_rate": 5.811962857683124e-07,
+      "loss": 0.6617,
+      "step": 1350
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 1.3828567284735036,
+      "learning_rate": 5.484223353941506e-07,
+      "loss": 0.6497,
+      "step": 1360
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 1.5823725055737101,
+      "learning_rate": 5.164853338399795e-07,
+      "loss": 0.5923,
+      "step": 1370
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 1.3562682177669632,
+      "learning_rate": 4.853989775301074e-07,
+      "loss": 0.6634,
+      "step": 1380
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 1.2195280460980205,
+      "learning_rate": 4.55176598083206e-07,
+      "loss": 0.6338,
+      "step": 1390
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.2628448199756899,
+      "learning_rate": 4.2583115659494356e-07,
+      "loss": 0.6718,
+      "step": 1400
+    },
+    {
+      "epoch": 2.488888888888889,
+      "eval_loss": 1.0003468990325928,
+      "eval_runtime": 67.5434,
+      "eval_samples_per_second": 29.611,
+      "eval_steps_per_second": 1.851,
+      "step": 1400
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 1.2286413880313467,
+      "learning_rate": 3.9737523807952206e-07,
+      "loss": 0.5828,
+      "step": 1410
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 1.394873151610969,
+      "learning_rate": 3.698210460724991e-07,
+      "loss": 0.6212,
+      "step": 1420
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 1.780676850609808,
+      "learning_rate": 3.4318039739720974e-07,
+      "loss": 0.5807,
+      "step": 1430
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.1085749116496726,
+      "learning_rate": 3.1746471709702963e-07,
+      "loss": 0.6545,
+      "step": 1440
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 1.330319629815968,
+      "learning_rate": 2.9268503353566484e-07,
+      "loss": 0.6209,
+      "step": 1450
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 1.3556403897420495,
+      "learning_rate": 2.6885197366754935e-07,
+      "loss": 0.6429,
+      "step": 1460
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 1.3098137995965915,
+      "learning_rate": 2.459757584803965e-07,
+      "loss": 0.6184,
+      "step": 1470
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 1.402526099054316,
+      "learning_rate": 2.2406619861185363e-07,
+      "loss": 0.6387,
+      "step": 1480
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 1.230774964223306,
+      "learning_rate": 2.0313269014213378e-07,
+      "loss": 0.6321,
+      "step": 1490
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.3122297500292182,
+      "learning_rate": 1.8318421056443576e-07,
+      "loss": 0.6712,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "eval_loss": 1.0002143383026123,
+      "eval_runtime": 67.5875,
+      "eval_samples_per_second": 29.591,
+      "eval_steps_per_second": 1.849,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6844444444444444,
+      "grad_norm": 1.551009662996816,
+      "learning_rate": 1.6422931493488004e-07,
+      "loss": 0.64,
+      "step": 1510
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 1.6211134481898983,
+      "learning_rate": 1.4627613220360632e-07,
+      "loss": 0.6328,
+      "step": 1520
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.4231163217204568,
+      "learning_rate": 1.2933236172861435e-07,
+      "loss": 0.6195,
+      "step": 1530
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 1.3269268827126044,
+      "learning_rate": 1.1340526997383194e-07,
+      "loss": 0.6437,
+      "step": 1540
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.48084418534789,
+      "learning_rate": 9.850168739284183e-08,
+      "loss": 0.6516,
+      "step": 1550
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 1.1708528942719758,
+      "learning_rate": 8.462800549958793e-08,
+      "loss": 0.6293,
+      "step": 1560
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 1.7994599570567928,
+      "learning_rate": 7.179017412732581e-08,
+      "loss": 0.6241,
+      "step": 1570
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 1.3656892730986343,
+      "learning_rate": 5.999369887699113e-08,
+      "loss": 0.6547,
+      "step": 1580
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 1.1251691436587674,
+      "learning_rate": 4.924363875608379e-08,
+      "loss": 0.6381,
+      "step": 1590
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.3837083789874627,
+      "learning_rate": 3.9544604009072173e-08,
+      "loss": 0.6397,
+      "step": 1600
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "eval_loss": 0.9996402859687805,
+      "eval_runtime": 67.5391,
+      "eval_samples_per_second": 29.612,
+      "eval_steps_per_second": 1.851,
+      "step": 1600
+    },
+    {
+      "epoch": 2.862222222222222,
+      "grad_norm": 1.2700069292148142,
+      "learning_rate": 3.090075414025562e-08,
+      "loss": 0.6399,
+      "step": 1610
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.4185347259810261,
+      "learning_rate": 2.331579612993018e-08,
+      "loss": 0.6356,
+      "step": 1620
+    },
+    {
+      "epoch": 2.897777777777778,
+      "grad_norm": 1.72135552899837,
+      "learning_rate": 1.679298284462033e-08,
+      "loss": 0.6473,
+      "step": 1630
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 1.4178555511488433,
+      "learning_rate": 1.1335111642064855e-08,
+      "loss": 0.639,
+      "step": 1640
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.6652000112393874,
+      "learning_rate": 6.944523171547313e-09,
+      "loss": 0.6115,
+      "step": 1650
+    },
+    {
+      "epoch": 2.951111111111111,
+      "grad_norm": 1.3379355246759241,
+      "learning_rate": 3.623100370091226e-09,
+      "loss": 0.6142,
+      "step": 1660
+    },
+    {
+      "epoch": 2.968888888888889,
+      "grad_norm": 1.1616853765979296,
+      "learning_rate": 1.3722676549493553e-09,
+      "loss": 0.6238,
+      "step": 1670
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 1.2081807930869184,
+      "learning_rate": 1.9299031272956846e-10,
+      "loss": 0.6662,
+      "step": 1680
+    },
+    {
+      "epoch": 2.997333333333333,
+      "step": 1686,
+      "total_flos": 297597215473664.0,
+      "train_loss": 0.7989534891938541,
+      "train_runtime": 8333.3074,
+      "train_samples_per_second": 6.48,
+      "train_steps_per_second": 0.202
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1686,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 562,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 297597215473664.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d546eb7dd498845b935fd0668a8645c7c06579214979706fcc1fcdf936843ef2
+size 7160