Upload folder using huggingface_hub

README.md

@@ -0,0 +1,118 @@
+---
+license: other
+base_model: meta-llama/Meta-Llama-3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: C013_llama3-8b-base_pretrain_20240428_005832
+  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. -->
+
+# C013_llama3-8b-base_pretrain_20240428_005832
+
+This model is a fine-tuned version of [/mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base](https://huggingface.co//mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base) on the C013_data dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5943
+
+## 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: 1.5e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: polynomial
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 4.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.7594        | 0.0149 | 1    | 1.7163          |
+| 1.7333        | 0.0746 | 5    | 1.7008          |
+| 1.6854        | 0.1493 | 10   | 1.6825          |
+| 1.6897        | 0.2239 | 15   | 1.6701          |
+| 1.6656        | 0.2985 | 20   | 1.6651          |
+| 1.7254        | 0.3731 | 25   | 1.6679          |
+| 1.7178        | 0.4478 | 30   | 1.6542          |
+| 1.6656        | 0.5224 | 35   | 1.6459          |
+| 1.6647        | 0.5970 | 40   | 1.6308          |
+| 1.6645        | 0.6716 | 45   | 1.6205          |
+| 1.6151        | 0.7463 | 50   | 1.6129          |
+| 1.6359        | 0.8209 | 55   | 1.6052          |
+| 1.5885        | 0.8955 | 60   | 1.5995          |
+| 1.6142        | 0.9701 | 65   | 1.5943          |
+| 1.4875        | 1.0448 | 70   | 1.5963          |
+| 1.3844        | 1.1194 | 75   | 1.6118          |
+| 1.3555        | 1.1940 | 80   | 1.6069          |
+| 1.3597        | 1.2687 | 85   | 1.6040          |
+| 1.3737        | 1.3433 | 90   | 1.6071          |
+| 1.3492        | 1.4179 | 95   | 1.6074          |
+| 1.3826        | 1.4925 | 100  | 1.6055          |
+| 1.3533        | 1.5672 | 105  | 1.6035          |
+| 1.3611        | 1.6418 | 110  | 1.6023          |
+| 1.328         | 1.7164 | 115  | 1.6022          |
+| 1.3443        | 1.7910 | 120  | 1.6026          |
+| 1.3386        | 1.8657 | 125  | 1.6029          |
+| 1.3396        | 1.9403 | 130  | 1.6029          |
+| 1.3573        | 2.0149 | 135  | 1.6029          |
+| 1.3754        | 2.0896 | 140  | 1.6034          |
+| 1.3229        | 2.1642 | 145  | 1.6044          |
+| 1.3194        | 2.2388 | 150  | 1.6055          |
+| 1.3361        | 2.3134 | 155  | 1.6065          |
+| 1.3231        | 2.3881 | 160  | 1.6072          |
+| 1.32          | 2.4627 | 165  | 1.6076          |
+| 1.3406        | 2.5373 | 170  | 1.6078          |
+| 1.3184        | 2.6119 | 175  | 1.6079          |
+| 1.2745        | 2.6866 | 180  | 1.6080          |
+| 1.3024        | 2.7612 | 185  | 1.6079          |
+| 1.3243        | 2.8358 | 190  | 1.6079          |
+| 1.3239        | 2.9104 | 195  | 1.6080          |
+| 1.3349        | 2.9851 | 200  | 1.6081          |
+| 1.337         | 3.0597 | 205  | 1.6079          |
+| 1.3091        | 3.1343 | 210  | 1.6078          |
+| 1.3266        | 3.2090 | 215  | 1.6079          |
+| 1.3014        | 3.2836 | 220  | 1.6083          |
+| 1.3153        | 3.3582 | 225  | 1.6086          |
+| 1.3192        | 3.4328 | 230  | 1.6090          |
+| 1.315         | 3.5075 | 235  | 1.6093          |
+| 1.3047        | 3.5821 | 240  | 1.6093          |
+| 1.3208        | 3.6567 | 245  | 1.6093          |
+| 1.362         | 3.7313 | 250  | 1.6093          |
+| 1.3255        | 3.8060 | 255  | 1.6091          |
+| 1.2941        | 3.8806 | 260  | 1.6089          |
+| 1.3254        | 3.9552 | 265  | 1.6086          |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.5942710638046265,
+    "eval_runtime": 5.9491,
+    "eval_samples_per_second": 80.012,
+    "eval_steps_per_second": 0.672,
+    "perplexity": 4.924737943686505,
+    "total_flos": 27742804377600.0,
+    "train_loss": 1.416380336925165,
+    "train_runtime": 8905.9803,
+    "train_samples_per_second": 1.923,
+    "train_steps_per_second": 0.03
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/mnt/models-pku/progressalign/shared_storage/downloaded_models/llama3-8b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.5942710638046265,
+    "eval_runtime": 5.9491,
+    "eval_samples_per_second": 80.012,
+    "eval_steps_per_second": 0.672,
+    "perplexity": 4.924737943686505
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "transformers_version": "4.40.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53363316d9924c96e096dd5b63929d7e9d45a9c03c8f3d0970c4badb0aefd36
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71ef2a2c31d2c04b0017c447332b80d5c984458295d0436aebc4ffdf9a42224
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585dc5d3556ff7a55628baf005d3ef97dd34aca9563ea3cba74e0b85971dbf9f
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f159c7551c754124cc544cee77946f4f7e3f5a3f33a2214f122b2f91bc7166bb
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\\n' + content + '\\n\\n### Response:\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end_of_text|>' + '\\n\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end_of_text|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "total_flos": 27742804377600.0,
+    "train_loss": 1.416380336925165,
+    "train_runtime": 8905.9803,
+    "train_samples_per_second": 1.923,
+    "train_steps_per_second": 0.03
+}

trainer_log.jsonl

@@ -0,0 +1,110 @@
+{"current_steps": 1, "total_steps": 268, "loss": 1.7594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 0.014925373134328358, "percentage": 0.37, "elapsed_time": "0:00:22", "remaining_time": "1:40:48"}
+{"current_steps": 1, "total_steps": 268, "loss": null, "eval_loss": 1.7162834405899048, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.014925373134328358, "percentage": 0.37, "elapsed_time": "0:00:22", "remaining_time": "1:40:48"}
+{"current_steps": 5, "total_steps": 268, "loss": 1.7333, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.25e-06, "epoch": 0.07462686567164178, "percentage": 1.87, "elapsed_time": "0:01:38", "remaining_time": "1:26:08"}
+{"current_steps": 5, "total_steps": 268, "loss": null, "eval_loss": 1.7008264064788818, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.07462686567164178, "percentage": 1.87, "elapsed_time": "0:01:38", "remaining_time": "1:26:08"}
+{"current_steps": 10, "total_steps": 268, "loss": 1.6854, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6e-06, "epoch": 0.14925373134328357, "percentage": 3.73, "elapsed_time": "0:04:29", "remaining_time": "1:55:44"}
+{"current_steps": 10, "total_steps": 268, "loss": null, "eval_loss": 1.682459831237793, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.14925373134328357, "percentage": 3.73, "elapsed_time": "0:04:29", "remaining_time": "1:55:44"}
+{"current_steps": 15, "total_steps": 268, "loss": 1.6897, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.75e-06, "epoch": 0.22388059701492538, "percentage": 5.6, "elapsed_time": "0:07:13", "remaining_time": "2:01:47"}
+{"current_steps": 15, "total_steps": 268, "loss": null, "eval_loss": 1.670121192932129, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.22388059701492538, "percentage": 5.6, "elapsed_time": "0:07:13", "remaining_time": "2:01:47"}
+{"current_steps": 20, "total_steps": 268, "loss": 1.6656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3500000000000001e-05, "epoch": 0.29850746268656714, "percentage": 7.46, "elapsed_time": "0:09:58", "remaining_time": "2:03:36"}
+{"current_steps": 20, "total_steps": 268, "loss": null, "eval_loss": 1.6651127338409424, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.29850746268656714, "percentage": 7.46, "elapsed_time": "0:09:58", "remaining_time": "2:03:36"}
+{"current_steps": 25, "total_steps": 268, "loss": 1.7254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3725993373990923e-05, "epoch": 0.373134328358209, "percentage": 9.33, "elapsed_time": "0:12:45", "remaining_time": "2:03:59"}
+{"current_steps": 25, "total_steps": 268, "loss": null, "eval_loss": 1.6679344177246094, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.373134328358209, "percentage": 9.33, "elapsed_time": "0:12:45", "remaining_time": "2:03:59"}
+{"current_steps": 30, "total_steps": 268, "loss": 1.7178, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.096088986215196e-05, "epoch": 0.44776119402985076, "percentage": 11.19, "elapsed_time": "0:15:33", "remaining_time": "2:03:23"}
+{"current_steps": 30, "total_steps": 268, "loss": null, "eval_loss": 1.6541944742202759, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.44776119402985076, "percentage": 11.19, "elapsed_time": "0:15:33", "remaining_time": "2:03:23"}
+{"current_steps": 35, "total_steps": 268, "loss": 1.6656, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.713726547724396e-06, "epoch": 0.5223880597014925, "percentage": 13.06, "elapsed_time": "0:18:22", "remaining_time": "2:02:19"}
+{"current_steps": 35, "total_steps": 268, "loss": null, "eval_loss": 1.6459277868270874, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5223880597014925, "percentage": 13.06, "elapsed_time": "0:18:22", "remaining_time": "2:02:19"}
+{"current_steps": 40, "total_steps": 268, "loss": 1.6647, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.8954890860223175e-06, "epoch": 0.5970149253731343, "percentage": 14.93, "elapsed_time": "0:21:10", "remaining_time": "2:00:42"}
+{"current_steps": 40, "total_steps": 268, "loss": null, "eval_loss": 1.6308344602584839, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.5970149253731343, "percentage": 14.93, "elapsed_time": "0:21:10", "remaining_time": "2:00:42"}
+{"current_steps": 45, "total_steps": 268, "loss": 1.6645, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.431031497828169e-06, "epoch": 0.6716417910447762, "percentage": 16.79, "elapsed_time": "0:23:57", "remaining_time": "1:58:41"}
+{"current_steps": 45, "total_steps": 268, "loss": null, "eval_loss": 1.6204748153686523, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.6716417910447762, "percentage": 16.79, "elapsed_time": "0:23:57", "remaining_time": "1:58:41"}
+{"current_steps": 50, "total_steps": 268, "loss": 1.6151, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.257147264863097e-06, "epoch": 0.746268656716418, "percentage": 18.66, "elapsed_time": "0:26:46", "remaining_time": "1:56:46"}
+{"current_steps": 50, "total_steps": 268, "loss": null, "eval_loss": 1.6129424571990967, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.746268656716418, "percentage": 18.66, "elapsed_time": "0:26:46", "remaining_time": "1:56:46"}
+{"current_steps": 55, "total_steps": 268, "loss": 1.6359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.320875141743125e-06, "epoch": 0.8208955223880597, "percentage": 20.52, "elapsed_time": "0:29:34", "remaining_time": "1:54:30"}
+{"current_steps": 55, "total_steps": 268, "loss": null, "eval_loss": 1.6052401065826416, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8208955223880597, "percentage": 20.52, "elapsed_time": "0:29:34", "remaining_time": "1:54:30"}
+{"current_steps": 60, "total_steps": 268, "loss": 1.5885, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.57801538033309e-06, "epoch": 0.8955223880597015, "percentage": 22.39, "elapsed_time": "0:32:20", "remaining_time": "1:52:07"}
+{"current_steps": 60, "total_steps": 268, "loss": null, "eval_loss": 1.5995320081710815, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.8955223880597015, "percentage": 22.39, "elapsed_time": "0:32:20", "remaining_time": "1:52:07"}
+{"current_steps": 65, "total_steps": 268, "loss": 1.6142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9918341191886553e-06, "epoch": 0.9701492537313433, "percentage": 24.25, "elapsed_time": "0:35:06", "remaining_time": "1:49:37"}
+{"current_steps": 65, "total_steps": 268, "loss": null, "eval_loss": 1.5942710638046265, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.9701492537313433, "percentage": 24.25, "elapsed_time": "0:35:06", "remaining_time": "1:49:37"}
+{"current_steps": 70, "total_steps": 268, "loss": 1.4875, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5319356141270557e-06, "epoch": 1.044776119402985, "percentage": 26.12, "elapsed_time": "0:37:53", "remaining_time": "1:47:10"}
+{"current_steps": 70, "total_steps": 268, "loss": null, "eval_loss": 1.5963352918624878, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.044776119402985, "percentage": 26.12, "elapsed_time": "0:37:53", "remaining_time": "1:47:10"}
+{"current_steps": 75, "total_steps": 268, "loss": 1.3844, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.173283781790582e-06, "epoch": 1.1194029850746268, "percentage": 27.99, "elapsed_time": "0:40:38", "remaining_time": "1:44:35"}
+{"current_steps": 75, "total_steps": 268, "loss": null, "eval_loss": 1.611823558807373, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1194029850746268, "percentage": 27.99, "elapsed_time": "0:40:38", "remaining_time": "1:44:35"}
+{"current_steps": 80, "total_steps": 268, "loss": 1.3555, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.95356202130823e-07, "epoch": 1.1940298507462686, "percentage": 29.85, "elapsed_time": "0:43:24", "remaining_time": "1:42:00"}
+{"current_steps": 80, "total_steps": 268, "loss": null, "eval_loss": 1.6069068908691406, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.1940298507462686, "percentage": 29.85, "elapsed_time": "0:43:24", "remaining_time": "1:42:00"}
+{"current_steps": 85, "total_steps": 268, "loss": 1.3597, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.814152836799623e-07, "epoch": 1.2686567164179103, "percentage": 31.72, "elapsed_time": "0:46:11", "remaining_time": "1:39:25"}
+{"current_steps": 85, "total_steps": 268, "loss": null, "eval_loss": 1.6040061712265015, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.2686567164179103, "percentage": 31.72, "elapsed_time": "0:46:11", "remaining_time": "1:39:25"}
+{"current_steps": 90, "total_steps": 268, "loss": 1.3737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.178827427887253e-07, "epoch": 1.3432835820895521, "percentage": 33.58, "elapsed_time": "0:48:56", "remaining_time": "1:36:48"}
+{"current_steps": 90, "total_steps": 268, "loss": null, "eval_loss": 1.607108235359192, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.3432835820895521, "percentage": 33.58, "elapsed_time": "0:48:56", "remaining_time": "1:36:48"}
+{"current_steps": 95, "total_steps": 268, "loss": 1.3492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.938048900654646e-07, "epoch": 1.417910447761194, "percentage": 35.45, "elapsed_time": "0:51:42", "remaining_time": "1:34:09"}
+{"current_steps": 95, "total_steps": 268, "loss": null, "eval_loss": 1.607422113418579, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.417910447761194, "percentage": 35.45, "elapsed_time": "0:51:42", "remaining_time": "1:34:09"}
+{"current_steps": 100, "total_steps": 268, "loss": 1.3826, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0039745928104856e-07, "epoch": 1.4925373134328357, "percentage": 37.31, "elapsed_time": "0:54:28", "remaining_time": "1:31:31"}
+{"current_steps": 100, "total_steps": 268, "loss": null, "eval_loss": 1.6055359840393066, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.4925373134328357, "percentage": 37.31, "elapsed_time": "0:54:28", "remaining_time": "1:31:31"}
+{"current_steps": 105, "total_steps": 268, "loss": 1.3533, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3065986110942366e-07, "epoch": 1.5671641791044775, "percentage": 39.18, "elapsed_time": "0:57:14", "remaining_time": "1:28:51"}
+{"current_steps": 105, "total_steps": 268, "loss": null, "eval_loss": 1.6034619808197021, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.5671641791044775, "percentage": 39.18, "elapsed_time": "0:57:14", "remaining_time": "1:28:51"}
+{"current_steps": 110, "total_steps": 268, "loss": 1.3611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.790498012203728e-07, "epoch": 1.6417910447761193, "percentage": 41.04, "elapsed_time": "1:00:00", "remaining_time": "1:26:11"}
+{"current_steps": 110, "total_steps": 268, "loss": null, "eval_loss": 1.6023228168487549, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.6417910447761193, "percentage": 41.04, "elapsed_time": "1:00:00", "remaining_time": "1:26:11"}
+{"current_steps": 115, "total_steps": 268, "loss": 1.328, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.412101742620585e-07, "epoch": 1.716417910447761, "percentage": 42.91, "elapsed_time": "1:02:47", "remaining_time": "1:23:32"}
+{"current_steps": 115, "total_steps": 268, "loss": null, "eval_loss": 1.602164387702942, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.716417910447761, "percentage": 42.91, "elapsed_time": "1:02:47", "remaining_time": "1:23:32"}
+{"current_steps": 120, "total_steps": 268, "loss": 1.3443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1374103686567517e-07, "epoch": 1.7910447761194028, "percentage": 44.78, "elapsed_time": "1:05:35", "remaining_time": "1:20:53"}
+{"current_steps": 120, "total_steps": 268, "loss": null, "eval_loss": 1.602574348449707, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.7910447761194028, "percentage": 44.78, "elapsed_time": "1:05:35", "remaining_time": "1:20:53"}
+{"current_steps": 125, "total_steps": 268, "loss": 1.3386, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.401027853897119e-08, "epoch": 1.8656716417910446, "percentage": 46.64, "elapsed_time": "1:08:22", "remaining_time": "1:18:13"}
+{"current_steps": 125, "total_steps": 268, "loss": null, "eval_loss": 1.602864146232605, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.8656716417910446, "percentage": 46.64, "elapsed_time": "1:08:22", "remaining_time": "1:18:13"}
+{"current_steps": 130, "total_steps": 268, "loss": 1.3396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.999735362178058e-08, "epoch": 1.9402985074626866, "percentage": 48.51, "elapsed_time": "1:11:10", "remaining_time": "1:15:33"}
+{"current_steps": 130, "total_steps": 268, "loss": null, "eval_loss": 1.6029260158538818, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.9402985074626866, "percentage": 48.51, "elapsed_time": "1:11:10", "remaining_time": "1:15:33"}
+{"current_steps": 135, "total_steps": 268, "loss": 1.3573, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.016511465398424e-08, "epoch": 2.014925373134328, "percentage": 50.37, "elapsed_time": "1:13:57", "remaining_time": "1:12:51"}
+{"current_steps": 135, "total_steps": 268, "loss": null, "eval_loss": 1.6028627157211304, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.014925373134328, "percentage": 50.37, "elapsed_time": "1:13:57", "remaining_time": "1:12:51"}
+{"current_steps": 140, "total_steps": 268, "loss": 1.3754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.335540171983123e-08, "epoch": 2.08955223880597, "percentage": 52.24, "elapsed_time": "1:16:43", "remaining_time": "1:10:09"}
+{"current_steps": 140, "total_steps": 268, "loss": null, "eval_loss": 1.6034482717514038, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.08955223880597, "percentage": 52.24, "elapsed_time": "1:16:43", "remaining_time": "1:10:09"}
+{"current_steps": 145, "total_steps": 268, "loss": 1.3229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.870459761414777e-08, "epoch": 2.1641791044776117, "percentage": 54.1, "elapsed_time": "1:19:28", "remaining_time": "1:07:25"}
+{"current_steps": 145, "total_steps": 268, "loss": null, "eval_loss": 1.6044023036956787, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.1641791044776117, "percentage": 54.1, "elapsed_time": "1:19:28", "remaining_time": "1:07:25"}
+{"current_steps": 150, "total_steps": 268, "loss": 1.3194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.5575858924021805e-08, "epoch": 2.2388059701492535, "percentage": 55.97, "elapsed_time": "1:22:14", "remaining_time": "1:04:41"}
+{"current_steps": 150, "total_steps": 268, "loss": null, "eval_loss": 1.60551917552948, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.2388059701492535, "percentage": 55.97, "elapsed_time": "1:22:14", "remaining_time": "1:04:41"}
+{"current_steps": 155, "total_steps": 268, "loss": 1.3361, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.3505182098899865e-08, "epoch": 2.3134328358208958, "percentage": 57.84, "elapsed_time": "1:24:59", "remaining_time": "1:01:57"}
+{"current_steps": 155, "total_steps": 268, "loss": null, "eval_loss": 1.6064879894256592, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.3134328358208958, "percentage": 57.84, "elapsed_time": "1:24:59", "remaining_time": "1:01:57"}
+{"current_steps": 160, "total_steps": 268, "loss": 1.3231, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.2158864924030916e-08, "epoch": 2.388059701492537, "percentage": 59.7, "elapsed_time": "1:27:46", "remaining_time": "0:59:14"}
+{"current_steps": 160, "total_steps": 268, "loss": null, "eval_loss": 1.60716712474823, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.388059701492537, "percentage": 59.7, "elapsed_time": "1:27:46", "remaining_time": "0:59:14"}
+{"current_steps": 165, "total_steps": 268, "loss": 1.32, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.130028101466846e-08, "epoch": 2.4626865671641793, "percentage": 61.57, "elapsed_time": "1:30:32", "remaining_time": "0:56:31"}
+{"current_steps": 165, "total_steps": 268, "loss": null, "eval_loss": 1.6076022386550903, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.4626865671641793, "percentage": 61.57, "elapsed_time": "1:30:32", "remaining_time": "0:56:31"}
+{"current_steps": 170, "total_steps": 268, "loss": 1.3406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.076420137573488e-08, "epoch": 2.5373134328358207, "percentage": 63.43, "elapsed_time": "1:33:18", "remaining_time": "0:53:47"}
+{"current_steps": 170, "total_steps": 268, "loss": null, "eval_loss": 1.6078119277954102, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5373134328358207, "percentage": 63.43, "elapsed_time": "1:33:18", "remaining_time": "0:53:47"}
+{"current_steps": 175, "total_steps": 268, "loss": 1.3184, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0437175954586924e-08, "epoch": 2.611940298507463, "percentage": 65.3, "elapsed_time": "1:36:04", "remaining_time": "0:51:03"}
+{"current_steps": 175, "total_steps": 268, "loss": null, "eval_loss": 1.6078969240188599, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.611940298507463, "percentage": 65.3, "elapsed_time": "1:36:04", "remaining_time": "0:51:03"}
+{"current_steps": 180, "total_steps": 268, "loss": 1.2745, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.024273255042209e-08, "epoch": 2.6865671641791042, "percentage": 67.16, "elapsed_time": "1:38:51", "remaining_time": "0:48:19"}
+{"current_steps": 180, "total_steps": 268, "loss": null, "eval_loss": 1.607950210571289, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.6865671641791042, "percentage": 67.16, "elapsed_time": "1:38:51", "remaining_time": "0:48:19"}
+{"current_steps": 185, "total_steps": 268, "loss": 1.3024, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.013036339654868e-08, "epoch": 2.7611940298507465, "percentage": 69.03, "elapsed_time": "1:41:37", "remaining_time": "0:45:35"}
+{"current_steps": 185, "total_steps": 268, "loss": null, "eval_loss": 1.607932448387146, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.7611940298507465, "percentage": 69.03, "elapsed_time": "1:41:37", "remaining_time": "0:45:35"}
+{"current_steps": 190, "total_steps": 268, "loss": 1.3243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.006745403152126e-08, "epoch": 2.835820895522388, "percentage": 70.9, "elapsed_time": "1:44:24", "remaining_time": "0:42:51"}
+{"current_steps": 190, "total_steps": 268, "loss": null, "eval_loss": 1.6079127788543701, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.835820895522388, "percentage": 70.9, "elapsed_time": "1:44:24", "remaining_time": "0:42:51"}
+{"current_steps": 195, "total_steps": 268, "loss": 1.3239, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0033467418823265e-08, "epoch": 2.91044776119403, "percentage": 72.76, "elapsed_time": "1:47:10", "remaining_time": "0:40:07"}
+{"current_steps": 195, "total_steps": 268, "loss": null, "eval_loss": 1.6080163717269897, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.91044776119403, "percentage": 72.76, "elapsed_time": "1:47:10", "remaining_time": "0:40:07"}
+{"current_steps": 200, "total_steps": 268, "loss": 1.3349, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.001583122566221e-08, "epoch": 2.9850746268656714, "percentage": 74.63, "elapsed_time": "1:49:56", "remaining_time": "0:37:22"}
+{"current_steps": 200, "total_steps": 268, "loss": null, "eval_loss": 1.6080641746520996, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.9850746268656714, "percentage": 74.63, "elapsed_time": "1:49:56", "remaining_time": "0:37:22"}
+{"current_steps": 205, "total_steps": 268, "loss": 1.337, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0007090159326376e-08, "epoch": 3.0597014925373136, "percentage": 76.49, "elapsed_time": "1:52:42", "remaining_time": "0:34:38"}
+{"current_steps": 205, "total_steps": 268, "loss": null, "eval_loss": 1.6079014539718628, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0597014925373136, "percentage": 76.49, "elapsed_time": "1:52:42", "remaining_time": "0:34:38"}
+{"current_steps": 210, "total_steps": 268, "loss": 1.3091, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000298058072559e-08, "epoch": 3.1343283582089554, "percentage": 78.36, "elapsed_time": "1:55:27", "remaining_time": "0:31:53"}
+{"current_steps": 210, "total_steps": 268, "loss": null, "eval_loss": 1.6077641248703003, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.1343283582089554, "percentage": 78.36, "elapsed_time": "1:55:27", "remaining_time": "0:31:53"}
+{"current_steps": 215, "total_steps": 268, "loss": 1.3266, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0001163431988796e-08, "epoch": 3.208955223880597, "percentage": 80.22, "elapsed_time": "1:58:13", "remaining_time": "0:29:08"}
+{"current_steps": 215, "total_steps": 268, "loss": null, "eval_loss": 1.60787832736969, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.208955223880597, "percentage": 80.22, "elapsed_time": "1:58:13", "remaining_time": "0:29:08"}
+{"current_steps": 220, "total_steps": 268, "loss": 1.3014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000415857597904e-08, "epoch": 3.283582089552239, "percentage": 82.09, "elapsed_time": "2:00:57", "remaining_time": "0:26:23"}
+{"current_steps": 220, "total_steps": 268, "loss": null, "eval_loss": 1.6083022356033325, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.283582089552239, "percentage": 82.09, "elapsed_time": "2:00:57", "remaining_time": "0:26:23"}
+{"current_steps": 225, "total_steps": 268, "loss": 1.3153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000133662276014e-08, "epoch": 3.3582089552238807, "percentage": 83.96, "elapsed_time": "2:03:41", "remaining_time": "0:23:38"}
+{"current_steps": 225, "total_steps": 268, "loss": null, "eval_loss": 1.608628273010254, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.3582089552238807, "percentage": 83.96, "elapsed_time": "2:03:41", "remaining_time": "0:23:38"}
+{"current_steps": 230, "total_steps": 268, "loss": 1.3192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000037695987735e-08, "epoch": 3.4328358208955225, "percentage": 85.82, "elapsed_time": "2:06:25", "remaining_time": "0:20:53"}
+{"current_steps": 230, "total_steps": 268, "loss": null, "eval_loss": 1.6089787483215332, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.4328358208955225, "percentage": 85.82, "elapsed_time": "2:06:25", "remaining_time": "0:20:53"}
+{"current_steps": 235, "total_steps": 268, "loss": 1.315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000009015715774e-08, "epoch": 3.5074626865671643, "percentage": 87.69, "elapsed_time": "2:09:10", "remaining_time": "0:18:08"}
+{"current_steps": 235, "total_steps": 268, "loss": null, "eval_loss": 1.6092561483383179, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.5074626865671643, "percentage": 87.69, "elapsed_time": "2:09:10", "remaining_time": "0:18:08"}
+{"current_steps": 240, "total_steps": 268, "loss": 1.3047, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000001740409057e-08, "epoch": 3.582089552238806, "percentage": 89.55, "elapsed_time": "2:11:55", "remaining_time": "0:15:23"}
+{"current_steps": 240, "total_steps": 268, "loss": null, "eval_loss": 1.6093214750289917, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.582089552238806, "percentage": 89.55, "elapsed_time": "2:11:55", "remaining_time": "0:15:23"}
+{"current_steps": 245, "total_steps": 268, "loss": 1.3208, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000025140825e-08, "epoch": 3.656716417910448, "percentage": 91.42, "elapsed_time": "2:14:40", "remaining_time": "0:12:38"}
+{"current_steps": 245, "total_steps": 268, "loss": null, "eval_loss": 1.609329342842102, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.656716417910448, "percentage": 91.42, "elapsed_time": "2:14:40", "remaining_time": "0:12:38"}
+{"current_steps": 250, "total_steps": 268, "loss": 1.362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000002399302e-08, "epoch": 3.7313432835820897, "percentage": 93.28, "elapsed_time": "2:17:26", "remaining_time": "0:09:53"}
+{"current_steps": 250, "total_steps": 268, "loss": null, "eval_loss": 1.609269380569458, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.7313432835820897, "percentage": 93.28, "elapsed_time": "2:17:26", "remaining_time": "0:09:53"}
+{"current_steps": 255, "total_steps": 268, "loss": 1.3255, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000001205015e-08, "epoch": 3.8059701492537314, "percentage": 95.15, "elapsed_time": "2:20:11", "remaining_time": "0:07:08"}
+{"current_steps": 255, "total_steps": 268, "loss": null, "eval_loss": 1.609143853187561, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8059701492537314, "percentage": 95.15, "elapsed_time": "2:20:11", "remaining_time": "0:07:08"}
+{"current_steps": 260, "total_steps": 268, "loss": 1.2941, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.000000000001954e-08, "epoch": 3.8805970149253732, "percentage": 97.01, "elapsed_time": "2:22:56", "remaining_time": "0:04:23"}
+{"current_steps": 260, "total_steps": 268, "loss": null, "eval_loss": 1.608902096748352, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.8805970149253732, "percentage": 97.01, "elapsed_time": "2:22:56", "remaining_time": "0:04:23"}
+{"current_steps": 265, "total_steps": 268, "loss": 1.3254, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.0000000000000024e-08, "epoch": 3.955223880597015, "percentage": 98.88, "elapsed_time": "2:25:42", "remaining_time": "0:01:38"}
+{"current_steps": 265, "total_steps": 268, "loss": null, "eval_loss": 1.6086210012435913, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.955223880597015, "percentage": 98.88, "elapsed_time": "2:25:42", "remaining_time": "0:01:38"}
+{"current_steps": 268, "total_steps": 268, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:27:58", "remaining_time": "0:00:00"}
+{"current_steps": 4, "total_steps": 4, "loss": null, "eval_loss": 1.5942710638046265, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "2:28:53", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,840 @@
+{
+  "best_metric": 1.5942710638046265,
+  "best_model_checkpoint": "./output/training_results/C013_llama3-8b-base_pretrain_20240428_005832/checkpoint-65",
+  "epoch": 4.0,
+  "eval_steps": 5,
+  "global_step": 268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014925373134328358,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0,
+      "loss": 1.7594,
+      "step": 1
+    },
+    {
+      "epoch": 0.014925373134328358,
+      "eval_loss": 1.7162834405899048,
+      "eval_runtime": 5.9233,
+      "eval_samples_per_second": 80.36,
+      "eval_steps_per_second": 0.675,
+      "step": 1
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "grad_norm": 3.233517003168196,
+      "learning_rate": 2.25e-06,
+      "loss": 1.7333,
+      "step": 5
+    },
+    {
+      "epoch": 0.07462686567164178,
+      "eval_loss": 1.7008264064788818,
+      "eval_runtime": 5.9309,
+      "eval_samples_per_second": 80.257,
+      "eval_steps_per_second": 0.674,
+      "step": 5
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 3.423591914627149,
+      "learning_rate": 6e-06,
+      "loss": 1.6854,
+      "step": 10
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "eval_loss": 1.682459831237793,
+      "eval_runtime": 5.9184,
+      "eval_samples_per_second": 80.427,
+      "eval_steps_per_second": 0.676,
+      "step": 10
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "grad_norm": 2.75139227215463,
+      "learning_rate": 9.75e-06,
+      "loss": 1.6897,
+      "step": 15
+    },
+    {
+      "epoch": 0.22388059701492538,
+      "eval_loss": 1.670121192932129,
+      "eval_runtime": 5.9473,
+      "eval_samples_per_second": 80.036,
+      "eval_steps_per_second": 0.673,
+      "step": 15
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "grad_norm": 2.55059243594346,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 1.6656,
+      "step": 20
+    },
+    {
+      "epoch": 0.29850746268656714,
+      "eval_loss": 1.6651127338409424,
+      "eval_runtime": 5.942,
+      "eval_samples_per_second": 80.108,
+      "eval_steps_per_second": 0.673,
+      "step": 20
+    },
+    {
+      "epoch": 0.373134328358209,
+      "grad_norm": 2.7488276843880652,
+      "learning_rate": 1.3725993373990923e-05,
+      "loss": 1.7254,
+      "step": 25
+    },
+    {
+      "epoch": 0.373134328358209,
+      "eval_loss": 1.6679344177246094,
+      "eval_runtime": 5.9726,
+      "eval_samples_per_second": 79.697,
+      "eval_steps_per_second": 0.67,
+      "step": 25
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 3.497477848836299,
+      "learning_rate": 1.096088986215196e-05,
+      "loss": 1.7178,
+      "step": 30
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "eval_loss": 1.6541944742202759,
+      "eval_runtime": 5.953,
+      "eval_samples_per_second": 79.96,
+      "eval_steps_per_second": 0.672,
+      "step": 30
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 2.7958991196951666,
+      "learning_rate": 8.713726547724396e-06,
+      "loss": 1.6656,
+      "step": 35
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "eval_loss": 1.6459277868270874,
+      "eval_runtime": 5.9488,
+      "eval_samples_per_second": 80.016,
+      "eval_steps_per_second": 0.672,
+      "step": 35
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 2.2395806127723907,
+      "learning_rate": 6.8954890860223175e-06,
+      "loss": 1.6647,
+      "step": 40
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "eval_loss": 1.6308344602584839,
+      "eval_runtime": 5.9441,
+      "eval_samples_per_second": 80.08,
+      "eval_steps_per_second": 0.673,
+      "step": 40
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 2.542267170825853,
+      "learning_rate": 5.431031497828169e-06,
+      "loss": 1.6645,
+      "step": 45
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "eval_loss": 1.6204748153686523,
+      "eval_runtime": 5.9555,
+      "eval_samples_per_second": 79.927,
+      "eval_steps_per_second": 0.672,
+      "step": 45
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.796577480411167,
+      "learning_rate": 4.257147264863097e-06,
+      "loss": 1.6151,
+      "step": 50
+    },
+    {
+      "epoch": 0.746268656716418,
+      "eval_loss": 1.6129424571990967,
+      "eval_runtime": 5.9792,
+      "eval_samples_per_second": 79.609,
+      "eval_steps_per_second": 0.669,
+      "step": 50
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "grad_norm": 2.8952316281119757,
+      "learning_rate": 3.320875141743125e-06,
+      "loss": 1.6359,
+      "step": 55
+    },
+    {
+      "epoch": 0.8208955223880597,
+      "eval_loss": 1.6052401065826416,
+      "eval_runtime": 5.9501,
+      "eval_samples_per_second": 79.998,
+      "eval_steps_per_second": 0.672,
+      "step": 55
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "grad_norm": 2.455450911279608,
+      "learning_rate": 2.57801538033309e-06,
+      "loss": 1.5885,
+      "step": 60
+    },
+    {
+      "epoch": 0.8955223880597015,
+      "eval_loss": 1.5995320081710815,
+      "eval_runtime": 5.9574,
+      "eval_samples_per_second": 79.9,
+      "eval_steps_per_second": 0.671,
+      "step": 60
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "grad_norm": 1.8236330059926131,
+      "learning_rate": 1.9918341191886553e-06,
+      "loss": 1.6142,
+      "step": 65
+    },
+    {
+      "epoch": 0.9701492537313433,
+      "eval_loss": 1.5942710638046265,
+      "eval_runtime": 5.9491,
+      "eval_samples_per_second": 80.013,
+      "eval_steps_per_second": 0.672,
+      "step": 65
+    },
+    {
+      "epoch": 1.044776119402985,
+      "grad_norm": 2.5122250154998893,
+      "learning_rate": 1.5319356141270557e-06,
+      "loss": 1.4875,
+      "step": 70
+    },
+    {
+      "epoch": 1.044776119402985,
+      "eval_loss": 1.5963352918624878,
+      "eval_runtime": 5.9465,
+      "eval_samples_per_second": 80.047,
+      "eval_steps_per_second": 0.673,
+      "step": 70
+    },
+    {
+      "epoch": 1.1194029850746268,
+      "grad_norm": 2.2374216929111017,
+      "learning_rate": 1.173283781790582e-06,
+      "loss": 1.3844,
+      "step": 75
+    },
+    {
+      "epoch": 1.1194029850746268,
+      "eval_loss": 1.611823558807373,
+      "eval_runtime": 5.9845,
+      "eval_samples_per_second": 79.538,
+      "eval_steps_per_second": 0.668,
+      "step": 75
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 2.061088772790073,
+      "learning_rate": 8.95356202130823e-07,
+      "loss": 1.3555,
+      "step": 80
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "eval_loss": 1.6069068908691406,
+      "eval_runtime": 5.9508,
+      "eval_samples_per_second": 79.99,
+      "eval_steps_per_second": 0.672,
+      "step": 80
+    },
+    {
+      "epoch": 1.2686567164179103,
+      "grad_norm": 2.0165800449063878,
+      "learning_rate": 6.814152836799623e-07,
+      "loss": 1.3597,
+      "step": 85
+    },
+    {
+      "epoch": 1.2686567164179103,
+      "eval_loss": 1.6040061712265015,
+      "eval_runtime": 5.9381,
+      "eval_samples_per_second": 80.161,
+      "eval_steps_per_second": 0.674,
+      "step": 85
+    },
+    {
+      "epoch": 1.3432835820895521,
+      "grad_norm": 2.0046777857294593,
+      "learning_rate": 5.178827427887253e-07,
+      "loss": 1.3737,
+      "step": 90
+    },
+    {
+      "epoch": 1.3432835820895521,
+      "eval_loss": 1.607108235359192,
+      "eval_runtime": 5.938,
+      "eval_samples_per_second": 80.161,
+      "eval_steps_per_second": 0.674,
+      "step": 90
+    },
+    {
+      "epoch": 1.417910447761194,
+      "grad_norm": 1.9599395887640554,
+      "learning_rate": 3.938048900654646e-07,
+      "loss": 1.3492,
+      "step": 95
+    },
+    {
+      "epoch": 1.417910447761194,
+      "eval_loss": 1.607422113418579,
+      "eval_runtime": 5.9586,
+      "eval_samples_per_second": 79.884,
+      "eval_steps_per_second": 0.671,
+      "step": 95
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "grad_norm": 2.090141489085601,
+      "learning_rate": 3.0039745928104856e-07,
+      "loss": 1.3826,
+      "step": 100
+    },
+    {
+      "epoch": 1.4925373134328357,
+      "eval_loss": 1.6055359840393066,
+      "eval_runtime": 5.9265,
+      "eval_samples_per_second": 80.317,
+      "eval_steps_per_second": 0.675,
+      "step": 100
+    },
+    {
+      "epoch": 1.5671641791044775,
+      "grad_norm": 1.9332970593875183,
+      "learning_rate": 2.3065986110942366e-07,
+      "loss": 1.3533,
+      "step": 105
+    },
+    {
+      "epoch": 1.5671641791044775,
+      "eval_loss": 1.6034619808197021,
+      "eval_runtime": 5.9297,
+      "eval_samples_per_second": 80.273,
+      "eval_steps_per_second": 0.675,
+      "step": 105
+    },
+    {
+      "epoch": 1.6417910447761193,
+      "grad_norm": 1.942043821463108,
+      "learning_rate": 1.790498012203728e-07,
+      "loss": 1.3611,
+      "step": 110
+    },
+    {
+      "epoch": 1.6417910447761193,
+      "eval_loss": 1.6023228168487549,
+      "eval_runtime": 5.9407,
+      "eval_samples_per_second": 80.126,
+      "eval_steps_per_second": 0.673,
+      "step": 110
+    },
+    {
+      "epoch": 1.716417910447761,
+      "grad_norm": 1.9221561505361804,
+      "learning_rate": 1.412101742620585e-07,
+      "loss": 1.328,
+      "step": 115
+    },
+    {
+      "epoch": 1.716417910447761,
+      "eval_loss": 1.602164387702942,
+      "eval_runtime": 5.9392,
+      "eval_samples_per_second": 80.145,
+      "eval_steps_per_second": 0.673,
+      "step": 115
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 1.8559815029587312,
+      "learning_rate": 1.1374103686567517e-07,
+      "loss": 1.3443,
+      "step": 120
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "eval_loss": 1.602574348449707,
+      "eval_runtime": 5.9713,
+      "eval_samples_per_second": 79.715,
+      "eval_steps_per_second": 0.67,
+      "step": 120
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "grad_norm": 2.031347067054233,
+      "learning_rate": 9.401027853897119e-08,
+      "loss": 1.3386,
+      "step": 125
+    },
+    {
+      "epoch": 1.8656716417910446,
+      "eval_loss": 1.602864146232605,
+      "eval_runtime": 5.956,
+      "eval_samples_per_second": 79.919,
+      "eval_steps_per_second": 0.672,
+      "step": 125
+    },
+    {
+      "epoch": 1.9402985074626866,
+      "grad_norm": 1.9772043505318835,
+      "learning_rate": 7.999735362178058e-08,
+      "loss": 1.3396,
+      "step": 130
+    },
+    {
+      "epoch": 1.9402985074626866,
+      "eval_loss": 1.6029260158538818,
+      "eval_runtime": 5.955,
+      "eval_samples_per_second": 79.933,
+      "eval_steps_per_second": 0.672,
+      "step": 130
+    },
+    {
+      "epoch": 2.014925373134328,
+      "grad_norm": 2.0413931319541203,
+      "learning_rate": 7.016511465398424e-08,
+      "loss": 1.3573,
+      "step": 135
+    },
+    {
+      "epoch": 2.014925373134328,
+      "eval_loss": 1.6028627157211304,
+      "eval_runtime": 5.974,
+      "eval_samples_per_second": 79.679,
+      "eval_steps_per_second": 0.67,
+      "step": 135
+    },
+    {
+      "epoch": 2.08955223880597,
+      "grad_norm": 1.9174789145055136,
+      "learning_rate": 6.335540171983123e-08,
+      "loss": 1.3754,
+      "step": 140
+    },
+    {
+      "epoch": 2.08955223880597,
+      "eval_loss": 1.6034482717514038,
+      "eval_runtime": 5.9455,
+      "eval_samples_per_second": 80.061,
+      "eval_steps_per_second": 0.673,
+      "step": 140
+    },
+    {
+      "epoch": 2.1641791044776117,
+      "grad_norm": 1.8365955877771794,
+      "learning_rate": 5.870459761414777e-08,
+      "loss": 1.3229,
+      "step": 145
+    },
+    {
+      "epoch": 2.1641791044776117,
+      "eval_loss": 1.6044023036956787,
+      "eval_runtime": 5.9418,
+      "eval_samples_per_second": 80.11,
+      "eval_steps_per_second": 0.673,
+      "step": 145
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "grad_norm": 1.957661723231933,
+      "learning_rate": 5.5575858924021805e-08,
+      "loss": 1.3194,
+      "step": 150
+    },
+    {
+      "epoch": 2.2388059701492535,
+      "eval_loss": 1.60551917552948,
+      "eval_runtime": 5.9349,
+      "eval_samples_per_second": 80.204,
+      "eval_steps_per_second": 0.674,
+      "step": 150
+    },
+    {
+      "epoch": 2.3134328358208958,
+      "grad_norm": 1.910367302653755,
+      "learning_rate": 5.3505182098899865e-08,
+      "loss": 1.3361,
+      "step": 155
+    },
+    {
+      "epoch": 2.3134328358208958,
+      "eval_loss": 1.6064879894256592,
+      "eval_runtime": 5.9543,
+      "eval_samples_per_second": 79.942,
+      "eval_steps_per_second": 0.672,
+      "step": 155
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 1.978379692085088,
+      "learning_rate": 5.2158864924030916e-08,
+      "loss": 1.3231,
+      "step": 160
+    },
+    {
+      "epoch": 2.388059701492537,
+      "eval_loss": 1.60716712474823,
+      "eval_runtime": 5.959,
+      "eval_samples_per_second": 79.879,
+      "eval_steps_per_second": 0.671,
+      "step": 160
+    },
+    {
+      "epoch": 2.4626865671641793,
+      "grad_norm": 1.8179876847012644,
+      "learning_rate": 5.130028101466846e-08,
+      "loss": 1.32,
+      "step": 165
+    },
+    {
+      "epoch": 2.4626865671641793,
+      "eval_loss": 1.6076022386550903,
+      "eval_runtime": 5.918,
+      "eval_samples_per_second": 80.433,
+      "eval_steps_per_second": 0.676,
+      "step": 165
+    },
+    {
+      "epoch": 2.5373134328358207,
+      "grad_norm": 1.947999010708536,
+      "learning_rate": 5.076420137573488e-08,
+      "loss": 1.3406,
+      "step": 170
+    },
+    {
+      "epoch": 2.5373134328358207,
+      "eval_loss": 1.6078119277954102,
+      "eval_runtime": 5.9402,
+      "eval_samples_per_second": 80.132,
+      "eval_steps_per_second": 0.673,
+      "step": 170
+    },
+    {
+      "epoch": 2.611940298507463,
+      "grad_norm": 1.9301332893200993,
+      "learning_rate": 5.0437175954586924e-08,
+      "loss": 1.3184,
+      "step": 175
+    },
+    {
+      "epoch": 2.611940298507463,
+      "eval_loss": 1.6078969240188599,
+      "eval_runtime": 5.9794,
+      "eval_samples_per_second": 79.607,
+      "eval_steps_per_second": 0.669,
+      "step": 175
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 1.8025714970137283,
+      "learning_rate": 5.024273255042209e-08,
+      "loss": 1.2745,
+      "step": 180
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "eval_loss": 1.607950210571289,
+      "eval_runtime": 5.9775,
+      "eval_samples_per_second": 79.632,
+      "eval_steps_per_second": 0.669,
+      "step": 180
+    },
+    {
+      "epoch": 2.7611940298507465,
+      "grad_norm": 1.8246857333350315,
+      "learning_rate": 5.013036339654868e-08,
+      "loss": 1.3024,
+      "step": 185
+    },
+    {
+      "epoch": 2.7611940298507465,
+      "eval_loss": 1.607932448387146,
+      "eval_runtime": 5.9386,
+      "eval_samples_per_second": 80.154,
+      "eval_steps_per_second": 0.674,
+      "step": 185
+    },
+    {
+      "epoch": 2.835820895522388,
+      "grad_norm": 1.8544541968240376,
+      "learning_rate": 5.006745403152126e-08,
+      "loss": 1.3243,
+      "step": 190
+    },
+    {
+      "epoch": 2.835820895522388,
+      "eval_loss": 1.6079127788543701,
+      "eval_runtime": 5.9362,
+      "eval_samples_per_second": 80.186,
+      "eval_steps_per_second": 0.674,
+      "step": 190
+    },
+    {
+      "epoch": 2.91044776119403,
+      "grad_norm": 1.9345137440066773,
+      "learning_rate": 5.0033467418823265e-08,
+      "loss": 1.3239,
+      "step": 195
+    },
+    {
+      "epoch": 2.91044776119403,
+      "eval_loss": 1.6080163717269897,
+      "eval_runtime": 5.9581,
+      "eval_samples_per_second": 79.892,
+      "eval_steps_per_second": 0.671,
+      "step": 195
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 2.033807758057437,
+      "learning_rate": 5.001583122566221e-08,
+      "loss": 1.3349,
+      "step": 200
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_loss": 1.6080641746520996,
+      "eval_runtime": 5.9287,
+      "eval_samples_per_second": 80.287,
+      "eval_steps_per_second": 0.675,
+      "step": 200
+    },
+    {
+      "epoch": 3.0597014925373136,
+      "grad_norm": 1.923714106710108,
+      "learning_rate": 5.0007090159326376e-08,
+      "loss": 1.337,
+      "step": 205
+    },
+    {
+      "epoch": 3.0597014925373136,
+      "eval_loss": 1.6079014539718628,
+      "eval_runtime": 5.9355,
+      "eval_samples_per_second": 80.195,
+      "eval_steps_per_second": 0.674,
+      "step": 205
+    },
+    {
+      "epoch": 3.1343283582089554,
+      "grad_norm": 1.8059505650037335,
+      "learning_rate": 5.000298058072559e-08,
+      "loss": 1.3091,
+      "step": 210
+    },
+    {
+      "epoch": 3.1343283582089554,
+      "eval_loss": 1.6077641248703003,
+      "eval_runtime": 5.9641,
+      "eval_samples_per_second": 79.811,
+      "eval_steps_per_second": 0.671,
+      "step": 210
+    },
+    {
+      "epoch": 3.208955223880597,
+      "grad_norm": 1.894523950936326,
+      "learning_rate": 5.0001163431988796e-08,
+      "loss": 1.3266,
+      "step": 215
+    },
+    {
+      "epoch": 3.208955223880597,
+      "eval_loss": 1.60787832736969,
+      "eval_runtime": 5.9618,
+      "eval_samples_per_second": 79.841,
+      "eval_steps_per_second": 0.671,
+      "step": 215
+    },
+    {
+      "epoch": 3.283582089552239,
+      "grad_norm": 1.8919183390013388,
+      "learning_rate": 5.0000415857597904e-08,
+      "loss": 1.3014,
+      "step": 220
+    },
+    {
+      "epoch": 3.283582089552239,
+      "eval_loss": 1.6083022356033325,
+      "eval_runtime": 5.9802,
+      "eval_samples_per_second": 79.596,
+      "eval_steps_per_second": 0.669,
+      "step": 220
+    },
+    {
+      "epoch": 3.3582089552238807,
+      "grad_norm": 1.8867080087928592,
+      "learning_rate": 5.0000133662276014e-08,
+      "loss": 1.3153,
+      "step": 225
+    },
+    {
+      "epoch": 3.3582089552238807,
+      "eval_loss": 1.608628273010254,
+      "eval_runtime": 5.9587,
+      "eval_samples_per_second": 79.883,
+      "eval_steps_per_second": 0.671,
+      "step": 225
+    },
+    {
+      "epoch": 3.4328358208955225,
+      "grad_norm": 2.000197758434265,
+      "learning_rate": 5.0000037695987735e-08,
+      "loss": 1.3192,
+      "step": 230
+    },
+    {
+      "epoch": 3.4328358208955225,
+      "eval_loss": 1.6089787483215332,
+      "eval_runtime": 5.931,
+      "eval_samples_per_second": 80.256,
+      "eval_steps_per_second": 0.674,
+      "step": 230
+    },
+    {
+      "epoch": 3.5074626865671643,
+      "grad_norm": 1.8236033935396483,
+      "learning_rate": 5.0000009015715774e-08,
+      "loss": 1.315,
+      "step": 235
+    },
+    {
+      "epoch": 3.5074626865671643,
+      "eval_loss": 1.6092561483383179,
+      "eval_runtime": 5.9999,
+      "eval_samples_per_second": 79.335,
+      "eval_steps_per_second": 0.667,
+      "step": 235
+    },
+    {
+      "epoch": 3.582089552238806,
+      "grad_norm": 1.9175089422860454,
+      "learning_rate": 5.0000001740409057e-08,
+      "loss": 1.3047,
+      "step": 240
+    },
+    {
+      "epoch": 3.582089552238806,
+      "eval_loss": 1.6093214750289917,
+      "eval_runtime": 5.9889,
+      "eval_samples_per_second": 79.481,
+      "eval_steps_per_second": 0.668,
+      "step": 240
+    },
+    {
+      "epoch": 3.656716417910448,
+      "grad_norm": 1.8702465201892255,
+      "learning_rate": 5.000000025140825e-08,
+      "loss": 1.3208,
+      "step": 245
+    },
+    {
+      "epoch": 3.656716417910448,
+      "eval_loss": 1.609329342842102,
+      "eval_runtime": 5.9315,
+      "eval_samples_per_second": 80.25,
+      "eval_steps_per_second": 0.674,
+      "step": 245
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "grad_norm": 1.9567098448807434,
+      "learning_rate": 5.000000002399302e-08,
+      "loss": 1.362,
+      "step": 250
+    },
+    {
+      "epoch": 3.7313432835820897,
+      "eval_loss": 1.609269380569458,
+      "eval_runtime": 5.9582,
+      "eval_samples_per_second": 79.89,
+      "eval_steps_per_second": 0.671,
+      "step": 250
+    },
+    {
+      "epoch": 3.8059701492537314,
+      "grad_norm": 1.8742551595721921,
+      "learning_rate": 5.0000000001205015e-08,
+      "loss": 1.3255,
+      "step": 255
+    },
+    {
+      "epoch": 3.8059701492537314,
+      "eval_loss": 1.609143853187561,
+      "eval_runtime": 5.9335,
+      "eval_samples_per_second": 80.223,
+      "eval_steps_per_second": 0.674,
+      "step": 255
+    },
+    {
+      "epoch": 3.8805970149253732,
+      "grad_norm": 1.9100964620707728,
+      "learning_rate": 5.000000000001954e-08,
+      "loss": 1.2941,
+      "step": 260
+    },
+    {
+      "epoch": 3.8805970149253732,
+      "eval_loss": 1.608902096748352,
+      "eval_runtime": 5.9228,
+      "eval_samples_per_second": 80.368,
+      "eval_steps_per_second": 0.675,
+      "step": 260
+    },
+    {
+      "epoch": 3.955223880597015,
+      "grad_norm": 1.959684298255238,
+      "learning_rate": 5.0000000000000024e-08,
+      "loss": 1.3254,
+      "step": 265
+    },
+    {
+      "epoch": 3.955223880597015,
+      "eval_loss": 1.6086210012435913,
+      "eval_runtime": 5.9667,
+      "eval_samples_per_second": 79.776,
+      "eval_steps_per_second": 0.67,
+      "step": 265
+    },
+    {
+      "epoch": 4.0,
+      "step": 268,
+      "total_flos": 27742804377600.0,
+      "train_loss": 1.416380336925165,
+      "train_runtime": 8905.9803,
+      "train_samples_per_second": 1.923,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 5,
+  "total_flos": 27742804377600.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:757df4821b30408e0e76b69d6456366733f2cdee4e35ba6aebacd942ce0f8020
+size 6968