Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,62 @@
+---
+license: other
+base_model: meta-llama/Meta-Llama-3.1-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the belle_math dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9967
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6272        | 4.4444 | 500  | 0.9967          |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.2.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

.ipynb_checkpoints/eval_results-checkpoint.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.444444444444445,
+    "eval_loss": 0.996656596660614,
+    "eval_runtime": 10.5528,
+    "eval_samples_per_second": 9.476,
+    "eval_steps_per_second": 9.476
+}

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+base_model: meta-llama/Meta-Llama-3.1-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the belle_math dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9967
+
+## 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: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 500
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.6272        | 4.4444 | 500  | 0.9967          |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.2.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 4.444444444444445,
+    "eval_loss": 0.996656596660614,
+    "eval_runtime": 10.5528,
+    "eval_samples_per_second": 9.476,
+    "eval_steps_per_second": 9.476,
+    "total_flos": 2.953325949045965e+16,
+    "train_loss": 0.8754597247838974,
+    "train_runtime": 1354.7094,
+    "train_samples_per_second": 2.953,
+    "train_steps_per_second": 0.369
+}

checkpoint-500/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "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": 131072,
+  "mlp_bias": false,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-500/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.3"
+}

checkpoint-500/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800a442270faa73a437f3b21541c4106bc2d96a11c189fefd00de9380989bd7c
+size 4976698672

checkpoint-500/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2fcc4779577c9438a9e1f7af1efac7398ebd738d6bc88f90c12cc5160b5519
+size 4999802720

checkpoint-500/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e9504dd4e4a146d484c52a97584ec14dac92237c46b064934af67a85e7d383
+size 4915916176

checkpoint-500/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4486f35c040f683f7d790354f66c169c109eb9fa0954a4a35d7c458a108405d
+size 1168138808

checkpoint-500/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"
+  }
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61bbf3124f58a026d5673dfbdd014fe564d3af9e64d8c877e4137814cdbdd8f0
+size 1744904195

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
+size 1064

checkpoint-500/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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-500/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": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "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": "<|eom_id|>",
+      "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": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,3541 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.444444444444445,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 10.75,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4464,
+      "step": 1
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 13.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2646,
+      "step": 2
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 11.3125,
+      "learning_rate": 6e-06,
+      "loss": 1.4738,
+      "step": 3
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 12.875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3848,
+      "step": 4
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 11.0,
+      "learning_rate": 1e-05,
+      "loss": 1.5257,
+      "step": 5
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.2e-05,
+      "loss": 1.4105,
+      "step": 6
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.287,
+      "step": 7
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.2099,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 26.25,
+      "learning_rate": 1.8e-05,
+      "loss": 1.311,
+      "step": 9
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 588.0,
+      "learning_rate": 2e-05,
+      "loss": 2.4975,
+      "step": 10
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 73.5,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.2125,
+      "step": 11
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 9.125,
+      "learning_rate": 2.4e-05,
+      "loss": 1.3688,
+      "step": 12
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 4.96875,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.2372,
+      "step": 13
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 11.1875,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.3227,
+      "step": 14
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 5.15625,
+      "learning_rate": 3e-05,
+      "loss": 1.1693,
+      "step": 15
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.0922,
+      "step": 16
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.0916,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.25,
+      "learning_rate": 3.6e-05,
+      "loss": 1.1219,
+      "step": 18
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 4.875,
+      "learning_rate": 3.8e-05,
+      "loss": 1.2237,
+      "step": 19
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 4.9375,
+      "learning_rate": 4e-05,
+      "loss": 1.0106,
+      "step": 20
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0266,
+      "step": 21
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.9007,
+      "step": 22
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.9784,
+      "step": 23
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 3.671875,
+      "learning_rate": 4.8e-05,
+      "loss": 1.1803,
+      "step": 24
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 4.75,
+      "learning_rate": 5e-05,
+      "loss": 1.2705,
+      "step": 25
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 4.5,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.0653,
+      "step": 26
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.25,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.988,
+      "step": 27
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 13.625,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.138,
+      "step": 28
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 3.015625,
+      "learning_rate": 5.8e-05,
+      "loss": 0.9095,
+      "step": 29
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 4.1875,
+      "learning_rate": 6e-05,
+      "loss": 1.1132,
+      "step": 30
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 4.8125,
+      "learning_rate": 6.2e-05,
+      "loss": 0.9967,
+      "step": 31
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 3.859375,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.9615,
+      "step": 32
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 4.53125,
+      "learning_rate": 6.6e-05,
+      "loss": 1.0561,
+      "step": 33
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 3.546875,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.1543,
+      "step": 34
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 8.125,
+      "learning_rate": 7e-05,
+      "loss": 1.1004,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.21875,
+      "learning_rate": 7.2e-05,
+      "loss": 1.0279,
+      "step": 36
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 3.40625,
+      "learning_rate": 7.4e-05,
+      "loss": 0.9469,
+      "step": 37
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 10.8125,
+      "learning_rate": 7.6e-05,
+      "loss": 1.0991,
+      "step": 38
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 3.96875,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.0668,
+      "step": 39
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 3.359375,
+      "learning_rate": 8e-05,
+      "loss": 0.9899,
+      "step": 40
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 3.296875,
+      "learning_rate": 8.2e-05,
+      "loss": 1.0636,
+      "step": 41
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 2.96875,
+      "learning_rate": 8.4e-05,
+      "loss": 1.0076,
+      "step": 42
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 3.359375,
+      "learning_rate": 8.6e-05,
+      "loss": 0.9301,
+      "step": 43
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 2.90625,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.171,
+      "step": 44
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.671875,
+      "learning_rate": 9e-05,
+      "loss": 0.9985,
+      "step": 45
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 2.40625,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.034,
+      "step": 46
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.4e-05,
+      "loss": 0.9552,
+      "step": 47
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 2.546875,
+      "learning_rate": 9.6e-05,
+      "loss": 1.2027,
+      "step": 48
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.8e-05,
+      "loss": 1.2453,
+      "step": 49
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 7.15625,
+      "learning_rate": 0.0001,
+      "loss": 1.1497,
+      "step": 50
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 12.6875,
+      "learning_rate": 9.999878153526974e-05,
+      "loss": 1.0698,
+      "step": 51
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 7.625,
+      "learning_rate": 9.999512620046522e-05,
+      "loss": 1.093,
+      "step": 52
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 7.46875,
+      "learning_rate": 9.998903417374228e-05,
+      "loss": 1.0031,
+      "step": 53
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.46875,
+      "learning_rate": 9.998050575201771e-05,
+      "loss": 1.2479,
+      "step": 54
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 7.59375,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 1.1337,
+      "step": 55
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 7.96875,
+      "learning_rate": 9.995614150494293e-05,
+      "loss": 1.0747,
+      "step": 56
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 9.0,
+      "learning_rate": 9.99403068670717e-05,
+      "loss": 1.1863,
+      "step": 57
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 5.59375,
+      "learning_rate": 9.992203820909906e-05,
+      "loss": 0.8643,
+      "step": 58
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 6.40625,
+      "learning_rate": 9.990133642141359e-05,
+      "loss": 1.0411,
+      "step": 59
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.25,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.0888,
+      "step": 60
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.985263761134602e-05,
+      "loss": 0.9589,
+      "step": 61
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 5.75,
+      "learning_rate": 9.982464296247522e-05,
+      "loss": 1.0835,
+      "step": 62
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.5625,
+      "learning_rate": 9.979421993079852e-05,
+      "loss": 0.9976,
+      "step": 63
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 5.8125,
+      "learning_rate": 9.976136999909156e-05,
+      "loss": 1.0755,
+      "step": 64
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 7.34375,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 1.0238,
+      "step": 65
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 6.03125,
+      "learning_rate": 9.968839595802982e-05,
+      "loss": 0.9071,
+      "step": 66
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 5.96875,
+      "learning_rate": 9.964827540532685e-05,
+      "loss": 0.9407,
+      "step": 67
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.96057350657239e-05,
+      "loss": 1.1039,
+      "step": 68
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.956077701257709e-05,
+      "loss": 1.0651,
+      "step": 69
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 1.0068,
+      "step": 70
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.946361664814943e-05,
+      "loss": 0.9485,
+      "step": 71
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.75,
+      "learning_rate": 9.941141907232765e-05,
+      "loss": 1.247,
+      "step": 72
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.93568132536494e-05,
+      "loss": 1.0063,
+      "step": 73
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 6.15625,
+      "learning_rate": 9.929980185352526e-05,
+      "loss": 0.9367,
+      "step": 74
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 6.875,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.05,
+      "step": 75
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 9.375,
+      "learning_rate": 9.917857354066931e-05,
+      "loss": 1.1569,
+      "step": 76
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.911436253643445e-05,
+      "loss": 0.8825,
+      "step": 77
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 5.5,
+      "learning_rate": 9.904775776745958e-05,
+      "loss": 0.8632,
+      "step": 78
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.89787624799672e-05,
+      "loss": 0.9715,
+      "step": 79
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 5.59375,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.0032,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.88336139167084e-05,
+      "loss": 1.1563,
+      "step": 81
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 7.09375,
+      "learning_rate": 9.875746771527816e-05,
+      "loss": 1.0159,
+      "step": 82
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 6.03125,
+      "learning_rate": 9.867894514365802e-05,
+      "loss": 1.1233,
+      "step": 83
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.859805002892732e-05,
+      "loss": 1.0673,
+      "step": 84
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 6.8125,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 0.9338,
+      "step": 85
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 6.4375,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 1.0843,
+      "step": 86
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.834116943022298e-05,
+      "loss": 0.9081,
+      "step": 87
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 5.875,
+      "learning_rate": 9.825082472361557e-05,
+      "loss": 0.9989,
+      "step": 88
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 5.78125,
+      "learning_rate": 9.815812833988291e-05,
+      "loss": 0.8834,
+      "step": 89
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.5625,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.9779,
+      "step": 90
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.796569872700288e-05,
+      "loss": 1.0189,
+      "step": 91
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 6.125,
+      "learning_rate": 9.786597487660337e-05,
+      "loss": 1.0696,
+      "step": 92
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 5.6875,
+      "learning_rate": 9.776391810611718e-05,
+      "loss": 1.059,
+      "step": 93
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.765953338964735e-05,
+      "loss": 0.8577,
+      "step": 94
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9671,
+      "step": 95
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 5.875,
+      "learning_rate": 9.744380058222483e-05,
+      "loss": 1.0792,
+      "step": 96
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 7.84375,
+      "learning_rate": 9.733246300578483e-05,
+      "loss": 1.0958,
+      "step": 97
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 6.1875,
+      "learning_rate": 9.721881851187406e-05,
+      "loss": 0.966,
+      "step": 98
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.710287263936484e-05,
+      "loss": 0.8868,
+      "step": 99
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 1.0577,
+      "step": 100
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.686409947459458e-05,
+      "loss": 0.7904,
+      "step": 101
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.674128381980072e-05,
+      "loss": 0.8927,
+      "step": 102
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.661619006077561e-05,
+      "loss": 1.0477,
+      "step": 103
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.648882429441257e-05,
+      "loss": 1.0107,
+      "step": 104
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 1.0277,
+      "step": 105
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 2.34375,
+      "learning_rate": 9.622730168061567e-05,
+      "loss": 0.9528,
+      "step": 106
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.609315757942503e-05,
+      "loss": 0.8783,
+      "step": 107
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.595676696276172e-05,
+      "loss": 0.991,
+      "step": 108
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.581813647811198e-05,
+      "loss": 1.0017,
+      "step": 109
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.0257,
+      "step": 110
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.553418304030886e-05,
+      "loss": 0.9087,
+      "step": 111
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.538887392664544e-05,
+      "loss": 1.002,
+      "step": 112
+    },
+    {
+      "epoch": 1.0044444444444445,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 0.7493,
+      "step": 113
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.50916263202557e-05,
+      "loss": 0.8562,
+      "step": 114
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 0.9812,
+      "step": 115
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.478558801197065e-05,
+      "loss": 0.8069,
+      "step": 116
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.3359375,
+      "learning_rate": 9.462929092260628e-05,
+      "loss": 0.8336,
+      "step": 117
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.447081866456489e-05,
+      "loss": 0.9364,
+      "step": 118
+    },
+    {
+      "epoch": 1.0577777777777777,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.431017896156074e-05,
+      "loss": 0.7365,
+      "step": 119
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 1.0947,
+      "step": 120
+    },
+    {
+      "epoch": 1.0755555555555556,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.398242864333083e-05,
+      "loss": 0.9642,
+      "step": 121
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 1.2578125,
+      "learning_rate": 9.381533400219318e-05,
+      "loss": 0.824,
+      "step": 122
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.364610386349049e-05,
+      "loss": 0.814,
+      "step": 123
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.347474647526095e-05,
+      "loss": 0.7891,
+      "step": 124
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.8481,
+      "step": 125
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.312568346036288e-05,
+      "loss": 0.7348,
+      "step": 126
+    },
+    {
+      "epoch": 1.1288888888888888,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.294799484653323e-05,
+      "loss": 1.1175,
+      "step": 127
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.276821300802534e-05,
+      "loss": 1.1577,
+      "step": 128
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.258634670715238e-05,
+      "loss": 0.8026,
+      "step": 129
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 1.875,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.8051,
+      "step": 130
+    },
+    {
+      "epoch": 1.1644444444444444,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.221639627510076e-05,
+      "loss": 1.0332,
+      "step": 131
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.202833017478422e-05,
+      "loss": 0.9912,
+      "step": 132
+    },
+    {
+      "epoch": 1.1822222222222223,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.183821567294809e-05,
+      "loss": 0.7942,
+      "step": 133
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.164606203550497e-05,
+      "loss": 0.8423,
+      "step": 134
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.7237,
+      "step": 135
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.125567491391476e-05,
+      "loss": 0.8881,
+      "step": 136
+    },
+    {
+      "epoch": 1.2177777777777778,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.105746045668521e-05,
+      "loss": 0.8953,
+      "step": 137
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.085724491675642e-05,
+      "loss": 1.0433,
+      "step": 138
+    },
+    {
+      "epoch": 1.2355555555555555,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.065503805235138e-05,
+      "loss": 0.9354,
+      "step": 139
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.9633,
+      "step": 140
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.02446898677957e-05,
+      "loss": 1.0975,
+      "step": 141
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.003656854743667e-05,
+      "loss": 0.8621,
+      "step": 142
+    },
+    {
+      "epoch": 1.271111111111111,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.982649590120982e-05,
+      "loss": 0.8958,
+      "step": 143
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.375,
+      "learning_rate": 8.961448216775954e-05,
+      "loss": 0.9975,
+      "step": 144
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.9486,
+      "step": 145
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.9184672866292e-05,
+      "loss": 0.876,
+      "step": 146
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.896689824657372e-05,
+      "loss": 0.8772,
+      "step": 147
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 1.2421875,
+      "learning_rate": 8.874722443520899e-05,
+      "loss": 0.8023,
+      "step": 148
+    },
+    {
+      "epoch": 1.3244444444444445,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.852566213878947e-05,
+      "loss": 1.0432,
+      "step": 149
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.921875,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.9147,
+      "step": 150
+    },
+    {
+      "epoch": 1.3422222222222222,
+      "grad_norm": 2.3125,
+      "learning_rate": 8.807691537683685e-05,
+      "loss": 0.9798,
+      "step": 151
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.784975278258783e-05,
+      "loss": 0.8849,
+      "step": 152
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.578125,
+      "learning_rate": 8.762074544478623e-05,
+      "loss": 0.9281,
+      "step": 153
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 1.375,
+      "learning_rate": 8.73899045249266e-05,
+      "loss": 1.0482,
+      "step": 154
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 1.6484375,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.0076,
+      "step": 155
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 1.203125,
+      "learning_rate": 8.692276703129421e-05,
+      "loss": 0.817,
+      "step": 156
+    },
+    {
+      "epoch": 1.3955555555555557,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.668649322514382e-05,
+      "loss": 1.0906,
+      "step": 157
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 0.9078,
+      "step": 158
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.620859307187339e-05,
+      "loss": 0.9268,
+      "step": 159
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.8873,
+      "step": 160
+    },
+    {
+      "epoch": 1.431111111111111,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.572363398164017e-05,
+      "loss": 0.8488,
+      "step": 161
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.375,
+      "learning_rate": 8.547853682682604e-05,
+      "loss": 1.001,
+      "step": 162
+    },
+    {
+      "epoch": 1.448888888888889,
+      "grad_norm": 1.7265625,
+      "learning_rate": 8.523171049817974e-05,
+      "loss": 1.0562,
+      "step": 163
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.498316702566828e-05,
+      "loss": 0.845,
+      "step": 164
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.7172,
+      "step": 165
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 1.1953125,
+      "learning_rate": 8.44809771867835e-05,
+      "loss": 0.9064,
+      "step": 166
+    },
+    {
+      "epoch": 1.4844444444444445,
+      "grad_norm": 2.390625,
+      "learning_rate": 8.422735529643444e-05,
+      "loss": 0.888,
+      "step": 167
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.397206521307584e-05,
+      "loss": 0.8158,
+      "step": 168
+    },
+    {
+      "epoch": 1.5022222222222221,
+      "grad_norm": 1.1875,
+      "learning_rate": 8.371511937918616e-05,
+      "loss": 0.8498,
+      "step": 169
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.93,
+      "step": 170
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.109375,
+      "learning_rate": 8.319631063261209e-05,
+      "loss": 1.2189,
+      "step": 171
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.293447300593402e-05,
+      "loss": 1.0049,
+      "step": 172
+    },
+    {
+      "epoch": 1.537777777777778,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.267103019950529e-05,
+      "loss": 0.9254,
+      "step": 173
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.240599505315655e-05,
+      "loss": 0.8603,
+      "step": 174
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.9305,
+      "step": 175
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 1.828125,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.0136,
+      "step": 176
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 1.9609375,
+      "learning_rate": 8.160146513324254e-05,
+      "loss": 1.0119,
+      "step": 177
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.133019056822304e-05,
+      "loss": 0.8887,
+      "step": 178
+    },
+    {
+      "epoch": 1.5911111111111111,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.105738901391552e-05,
+      "loss": 1.0235,
+      "step": 179
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.078125,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.8074,
+      "step": 180
+    },
+    {
+      "epoch": 1.608888888888889,
+      "grad_norm": 0.90625,
+      "learning_rate": 8.05072581950634e-05,
+      "loss": 0.861,
+      "step": 181
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.022995574311876e-05,
+      "loss": 0.9879,
+      "step": 182
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.99511799257793e-05,
+      "loss": 0.7969,
+      "step": 183
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 1.140625,
+      "learning_rate": 7.967094433018508e-05,
+      "loss": 0.85,
+      "step": 184
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 1.078125,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.765,
+      "step": 185
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.910614850786448e-05,
+      "loss": 1.0234,
+      "step": 186
+    },
+    {
+      "epoch": 1.6622222222222223,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.882161580848967e-05,
+      "loss": 0.9385,
+      "step": 187
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.85356783842216e-05,
+      "loss": 0.8661,
+      "step": 188
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.82483501712469e-05,
+      "loss": 1.1284,
+      "step": 189
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.9681,
+      "step": 190
+    },
+    {
+      "epoch": 1.6977777777777778,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.766957746216721e-05,
+      "loss": 0.8778,
+      "step": 191
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.5703125,
+      "learning_rate": 7.737816117462752e-05,
+      "loss": 0.9828,
+      "step": 192
+    },
+    {
+      "epoch": 1.7155555555555555,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.7085410514137e-05,
+      "loss": 0.9298,
+      "step": 193
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 1.2578125,
+      "learning_rate": 7.679133974894983e-05,
+      "loss": 0.9032,
+      "step": 194
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.0169,
+      "step": 195
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.619929529850397e-05,
+      "loss": 0.8967,
+      "step": 196
+    },
+    {
+      "epoch": 1.751111111111111,
+      "grad_norm": 1.75,
+      "learning_rate": 7.590135046865651e-05,
+      "loss": 0.926,
+      "step": 197
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.560214324352858e-05,
+      "loss": 1.0398,
+      "step": 198
+    },
+    {
+      "epoch": 1.7688888888888887,
+      "grad_norm": 0.9765625,
+      "learning_rate": 7.530168820605818e-05,
+      "loss": 0.9307,
+      "step": 199
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.7421875,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8868,
+      "step": 200
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 2.1875,
+      "learning_rate": 7.469709332921155e-05,
+      "loss": 0.8817,
+      "step": 201
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 2.96875,
+      "learning_rate": 7.439298295693665e-05,
+      "loss": 1.1957,
+      "step": 202
+    },
+    {
+      "epoch": 1.8044444444444445,
+      "grad_norm": 1.9765625,
+      "learning_rate": 7.408768370508576e-05,
+      "loss": 1.087,
+      "step": 203
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 1.5,
+      "learning_rate": 7.378121045351378e-05,
+      "loss": 0.9296,
+      "step": 204
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.6484375,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.0053,
+      "step": 205
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.316480175599309e-05,
+      "loss": 0.8588,
+      "step": 206
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.285489635293472e-05,
+      "loss": 0.8839,
+      "step": 207
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 1.640625,
+      "learning_rate": 7.254387703447154e-05,
+      "loss": 0.9149,
+      "step": 208
+    },
+    {
+      "epoch": 1.8577777777777778,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.223175895924638e-05,
+      "loss": 0.8972,
+      "step": 209
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.0323,
+      "step": 210
+    },
+    {
+      "epoch": 1.8755555555555556,
+      "grad_norm": 1.6171875,
+      "learning_rate": 7.160428744009912e-05,
+      "loss": 1.0817,
+      "step": 211
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 1.71875,
+      "learning_rate": 7.128896457825364e-05,
+      "loss": 1.0261,
+      "step": 212
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.097260412230886e-05,
+      "loss": 0.9723,
+      "step": 213
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.06552214912271e-05,
+      "loss": 1.1117,
+      "step": 214
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.8511,
+      "step": 215
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.1640625,
+      "learning_rate": 7.001745162784477e-05,
+      "loss": 0.9363,
+      "step": 216
+    },
+    {
+      "epoch": 1.9288888888888889,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.969709547954756e-05,
+      "loss": 0.9447,
+      "step": 217
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 1.25,
+      "learning_rate": 6.937577932260515e-05,
+      "loss": 0.7898,
+      "step": 218
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.905351881751372e-05,
+      "loss": 0.8289,
+      "step": 219
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.125,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.8569,
+      "step": 220
+    },
+    {
+      "epoch": 1.9644444444444444,
+      "grad_norm": 1.2734375,
+      "learning_rate": 6.840622763423391e-05,
+      "loss": 0.8994,
+      "step": 221
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 1.4375,
+      "learning_rate": 6.808122850410461e-05,
+      "loss": 0.8751,
+      "step": 222
+    },
+    {
+      "epoch": 1.982222222222222,
+      "grad_norm": 1.5703125,
+      "learning_rate": 6.775534812040685e-05,
+      "loss": 1.0663,
+      "step": 223
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 1.6328125,
+      "learning_rate": 6.742860236609077e-05,
+      "loss": 1.1425,
+      "step": 224
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.9115,
+      "step": 225
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 1.1953125,
+      "learning_rate": 6.677257848751277e-05,
+      "loss": 0.9296,
+      "step": 226
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.644333233692916e-05,
+      "loss": 1.0117,
+      "step": 227
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 1.765625,
+      "learning_rate": 6.611328476152557e-05,
+      "loss": 0.9275,
+      "step": 228
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 1.140625,
+      "learning_rate": 6.578245184735513e-05,
+      "loss": 0.9839,
+      "step": 229
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.1015625,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.6496,
+      "step": 230
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 1.1640625,
+      "learning_rate": 6.511849453752223e-05,
+      "loss": 0.903,
+      "step": 231
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 1.1015625,
+      "learning_rate": 6.478540250220234e-05,
+      "loss": 0.9134,
+      "step": 232
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.445158984722358e-05,
+      "loss": 0.7132,
+      "step": 233
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.411707284214384e-05,
+      "loss": 0.7823,
+      "step": 234
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.8642,
+      "step": 235
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 1.40625,
+      "learning_rate": 6.344599103076329e-05,
+      "loss": 0.8489,
+      "step": 236
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 1.4296875,
+      "learning_rate": 6.310945893204324e-05,
+      "loss": 0.8013,
+      "step": 237
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 1.3125,
+      "learning_rate": 6.277228789678953e-05,
+      "loss": 0.8753,
+      "step": 238
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 1.1875,
+      "learning_rate": 6.243449435824276e-05,
+      "loss": 0.8545,
+      "step": 239
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.7864,
+      "step": 240
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.17571056551295e-05,
+      "loss": 0.9452,
+      "step": 241
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.141754350553279e-05,
+      "loss": 0.8245,
+      "step": 242
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.107742488097338e-05,
+      "loss": 0.8336,
+      "step": 243
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 1.046875,
+      "learning_rate": 6.073676635835317e-05,
+      "loss": 0.729,
+      "step": 244
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 1.0546875,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.7696,
+      "step": 245
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 0.89453125,
+      "learning_rate": 6.005389605729824e-05,
+      "loss": 0.754,
+      "step": 246
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 1.109375,
+      "learning_rate": 5.97117175609986e-05,
+      "loss": 0.8451,
+      "step": 247
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 1.28125,
+      "learning_rate": 5.9369065729286245e-05,
+      "loss": 0.9647,
+      "step": 248
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 1.296875,
+      "learning_rate": 5.902595726252801e-05,
+      "loss": 0.9317,
+      "step": 249
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.0,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.1104,
+      "step": 250
+    },
+    {
+      "epoch": 2.2311111111111113,
+      "grad_norm": 1.8203125,
+      "learning_rate": 5.833843733580512e-05,
+      "loss": 0.8364,
+      "step": 251
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.140625,
+      "learning_rate": 5.799405938459175e-05,
+      "loss": 0.9288,
+      "step": 252
+    },
+    {
+      "epoch": 2.2488888888888887,
+      "grad_norm": 1.3359375,
+      "learning_rate": 5.764929181420191e-05,
+      "loss": 0.7471,
+      "step": 253
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.5703125,
+      "learning_rate": 5.730415142812059e-05,
+      "loss": 0.826,
+      "step": 254
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 2.25,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.9825,
+      "step": 255
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 1.5,
+      "learning_rate": 5.661281951285613e-05,
+      "loss": 0.8868,
+      "step": 256
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 1.4921875,
+      "learning_rate": 5.6266661678215216e-05,
+      "loss": 0.8671,
+      "step": 257
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 1.53125,
+      "learning_rate": 5.5920198415325064e-05,
+      "loss": 0.6903,
+      "step": 258
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 1.359375,
+      "learning_rate": 5.557344661031627e-05,
+      "loss": 0.7786,
+      "step": 259
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5703125,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.0231,
+      "step": 260
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.3359375,
+      "learning_rate": 5.487914498795747e-05,
+      "loss": 0.7585,
+      "step": 261
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 1.6640625,
+      "learning_rate": 5.453162900988902e-05,
+      "loss": 0.9553,
+      "step": 262
+    },
+    {
+      "epoch": 2.3377777777777777,
+      "grad_norm": 1.3203125,
+      "learning_rate": 5.418389216661579e-05,
+      "loss": 0.7379,
+      "step": 263
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.383595140634093e-05,
+      "loss": 0.7197,
+      "step": 264
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.9332,
+      "step": 265
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 1.21875,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.8006,
+      "step": 266
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.279107524965819e-05,
+      "loss": 0.8995,
+      "step": 267
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.244248848978067e-05,
+      "loss": 1.009,
+      "step": 268
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 1.4140625,
+      "learning_rate": 5.209378268645998e-05,
+      "loss": 1.0106,
+      "step": 269
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8872,
+      "step": 270
+    },
+    {
+      "epoch": 2.408888888888889,
+      "grad_norm": 1.40625,
+      "learning_rate": 5.139608193617845e-05,
+      "loss": 0.7844,
+      "step": 271
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 1.65625,
+      "learning_rate": 5.104712099416785e-05,
+      "loss": 0.9682,
+      "step": 272
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 1.296875,
+      "learning_rate": 5.0698109016957274e-05,
+      "loss": 0.7677,
+      "step": 273
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 1.3125,
+      "learning_rate": 5.034906301489808e-05,
+      "loss": 0.807,
+      "step": 274
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.6171875,
+      "learning_rate": 5e-05,
+      "loss": 0.8616,
+      "step": 275
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.965093698510193e-05,
+      "loss": 0.8555,
+      "step": 276
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 1.2734375,
+      "learning_rate": 4.9301890983042744e-05,
+      "loss": 0.9175,
+      "step": 277
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 1.25,
+      "learning_rate": 4.895287900583216e-05,
+      "loss": 0.8347,
+      "step": 278
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.1875,
+      "learning_rate": 4.860391806382157e-05,
+      "loss": 0.6997,
+      "step": 279
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.5546875,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7535,
+      "step": 280
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 1.75,
+      "learning_rate": 4.790621731354003e-05,
+      "loss": 0.6498,
+      "step": 281
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 1.59375,
+      "learning_rate": 4.755751151021934e-05,
+      "loss": 0.8289,
+      "step": 282
+    },
+    {
+      "epoch": 2.5155555555555553,
+      "grad_norm": 1.1796875,
+      "learning_rate": 4.720892475034181e-05,
+      "loss": 0.7781,
+      "step": 283
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 1.3359375,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 0.887,
+      "step": 284
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.9711,
+      "step": 285
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 1.03125,
+      "learning_rate": 4.616404859365907e-05,
+      "loss": 0.7761,
+      "step": 286
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 1.203125,
+      "learning_rate": 4.5816107833384234e-05,
+      "loss": 0.8821,
+      "step": 287
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.0859375,
+      "learning_rate": 4.5468370990111006e-05,
+      "loss": 0.9093,
+      "step": 288
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 1.296875,
+      "learning_rate": 4.512085501204253e-05,
+      "loss": 0.8367,
+      "step": 289
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 1.2265625,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8892,
+      "step": 290
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 1.234375,
+      "learning_rate": 4.442655338968373e-05,
+      "loss": 0.8095,
+      "step": 291
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 1.2421875,
+      "learning_rate": 4.407980158467495e-05,
+      "loss": 0.6999,
+      "step": 292
+    },
+    {
+      "epoch": 2.6044444444444443,
+      "grad_norm": 1.375,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 0.9533,
+      "step": 293
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 1.1484375,
+      "learning_rate": 4.3387180487143876e-05,
+      "loss": 1.0029,
+      "step": 294
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 1.140625,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.8176,
+      "step": 295
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 1.140625,
+      "learning_rate": 4.269584857187943e-05,
+      "loss": 0.7422,
+      "step": 296
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.6484375,
+      "learning_rate": 4.23507081857981e-05,
+      "loss": 0.9981,
+      "step": 297
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 1.4921875,
+      "learning_rate": 4.2005940615408264e-05,
+      "loss": 0.7285,
+      "step": 298
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 1.1484375,
+      "learning_rate": 4.166156266419489e-05,
+      "loss": 0.7904,
+      "step": 299
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.7890625,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8762,
+      "step": 300
+    },
+    {
+      "epoch": 2.6755555555555555,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.0974042737472006e-05,
+      "loss": 0.7147,
+      "step": 301
+    },
+    {
+      "epoch": 2.6844444444444444,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.063093427071376e-05,
+      "loss": 0.8428,
+      "step": 302
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 1.9765625,
+      "learning_rate": 4.028828243900141e-05,
+      "loss": 0.9927,
+      "step": 303
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 2.25,
+      "learning_rate": 3.9946103942701777e-05,
+      "loss": 0.882,
+      "step": 304
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 2.3125,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.9207,
+      "step": 305
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.5390625,
+      "learning_rate": 3.926323364164684e-05,
+      "loss": 0.9289,
+      "step": 306
+    },
+    {
+      "epoch": 2.728888888888889,
+      "grad_norm": 1.8671875,
+      "learning_rate": 3.892257511902664e-05,
+      "loss": 0.972,
+      "step": 307
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 1.8515625,
+      "learning_rate": 3.858245649446721e-05,
+      "loss": 0.8648,
+      "step": 308
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 1.734375,
+      "learning_rate": 3.82428943448705e-05,
+      "loss": 0.7915,
+      "step": 309
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.703125,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.9658,
+      "step": 310
+    },
+    {
+      "epoch": 2.7644444444444445,
+      "grad_norm": 1.7734375,
+      "learning_rate": 3.756550564175727e-05,
+      "loss": 0.9002,
+      "step": 311
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 1.25,
+      "learning_rate": 3.7227712103210486e-05,
+      "loss": 0.671,
+      "step": 312
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 1.4375,
+      "learning_rate": 3.6890541067956776e-05,
+      "loss": 0.8574,
+      "step": 313
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.655400896923672e-05,
+      "loss": 1.0365,
+      "step": 314
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.359375,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.8598,
+      "step": 315
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 1.3125,
+      "learning_rate": 3.588292715785617e-05,
+      "loss": 0.8167,
+      "step": 316
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "grad_norm": 1.4921875,
+      "learning_rate": 3.554841015277641e-05,
+      "loss": 0.8554,
+      "step": 317
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 1.4140625,
+      "learning_rate": 3.5214597497797684e-05,
+      "loss": 0.9625,
+      "step": 318
+    },
+    {
+      "epoch": 2.8355555555555556,
+      "grad_norm": 1.6875,
+      "learning_rate": 3.488150546247778e-05,
+      "loss": 0.9035,
+      "step": 319
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.671875,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.85,
+      "step": 320
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 1.4296875,
+      "learning_rate": 3.4217548152644885e-05,
+      "loss": 1.1274,
+      "step": 321
+    },
+    {
+      "epoch": 2.862222222222222,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.388671523847445e-05,
+      "loss": 0.7901,
+      "step": 322
+    },
+    {
+      "epoch": 2.871111111111111,
+      "grad_norm": 1.234375,
+      "learning_rate": 3.355666766307084e-05,
+      "loss": 0.9324,
+      "step": 323
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.109375,
+      "learning_rate": 3.322742151248725e-05,
+      "loss": 0.8024,
+      "step": 324
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 2.4375,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.9827,
+      "step": 325
+    },
+    {
+      "epoch": 2.897777777777778,
+      "grad_norm": 1.1875,
+      "learning_rate": 3.257139763390925e-05,
+      "loss": 0.8115,
+      "step": 326
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.224465187959316e-05,
+      "loss": 0.8628,
+      "step": 327
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 1.125,
+      "learning_rate": 3.1918771495895396e-05,
+      "loss": 0.8138,
+      "step": 328
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 1.34375,
+      "learning_rate": 3.1593772365766105e-05,
+      "loss": 0.7686,
+      "step": 329
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.171875,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.861,
+      "step": 330
+    },
+    {
+      "epoch": 2.942222222222222,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.09464811824863e-05,
+      "loss": 0.7815,
+      "step": 331
+    },
+    {
+      "epoch": 2.951111111111111,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.062422067739485e-05,
+      "loss": 0.8253,
+      "step": 332
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.2890625,
+      "learning_rate": 3.0302904520452447e-05,
+      "loss": 0.8101,
+      "step": 333
+    },
+    {
+      "epoch": 2.968888888888889,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.9982548372155263e-05,
+      "loss": 0.828,
+      "step": 334
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 1.6953125,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.7968,
+      "step": 335
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 1.640625,
+      "learning_rate": 2.934477850877292e-05,
+      "loss": 1.0188,
+      "step": 336
+    },
+    {
+      "epoch": 2.9955555555555557,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.9027395877691144e-05,
+      "loss": 0.8255,
+      "step": 337
+    },
+    {
+      "epoch": 3.0044444444444443,
+      "grad_norm": 1.109375,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.6085,
+      "step": 338
+    },
+    {
+      "epoch": 3.013333333333333,
+      "grad_norm": 0.99609375,
+      "learning_rate": 2.8395712559900877e-05,
+      "loss": 0.7823,
+      "step": 339
+    },
+    {
+      "epoch": 3.022222222222222,
+      "grad_norm": 1.2265625,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.8947,
+      "step": 340
+    },
+    {
+      "epoch": 3.031111111111111,
+      "grad_norm": 1.140625,
+      "learning_rate": 2.776824104075364e-05,
+      "loss": 0.8595,
+      "step": 341
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 1.265625,
+      "learning_rate": 2.7456122965528475e-05,
+      "loss": 0.829,
+      "step": 342
+    },
+    {
+      "epoch": 3.048888888888889,
+      "grad_norm": 0.94921875,
+      "learning_rate": 2.7145103647065308e-05,
+      "loss": 0.5761,
+      "step": 343
+    },
+    {
+      "epoch": 3.057777777777778,
+      "grad_norm": 1.1328125,
+      "learning_rate": 2.6835198244006927e-05,
+      "loss": 0.7939,
+      "step": 344
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 1.0703125,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.6288,
+      "step": 345
+    },
+    {
+      "epoch": 3.0755555555555554,
+      "grad_norm": 1.15625,
+      "learning_rate": 2.6218789546486234e-05,
+      "loss": 0.7359,
+      "step": 346
+    },
+    {
+      "epoch": 3.0844444444444443,
+      "grad_norm": 1.3359375,
+      "learning_rate": 2.591231629491423e-05,
+      "loss": 0.7755,
+      "step": 347
+    },
+    {
+      "epoch": 3.0933333333333333,
+      "grad_norm": 1.2734375,
+      "learning_rate": 2.560701704306336e-05,
+      "loss": 0.6429,
+      "step": 348
+    },
+    {
+      "epoch": 3.102222222222222,
+      "grad_norm": 1.28125,
+      "learning_rate": 2.5302906670788462e-05,
+      "loss": 0.7758,
+      "step": 349
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 2.109375,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6468,
+      "step": 350
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 2.0,
+      "learning_rate": 2.469831179394182e-05,
+      "loss": 0.6939,
+      "step": 351
+    },
+    {
+      "epoch": 3.128888888888889,
+      "grad_norm": 2.109375,
+      "learning_rate": 2.4397856756471432e-05,
+      "loss": 0.8737,
+      "step": 352
+    },
+    {
+      "epoch": 3.137777777777778,
+      "grad_norm": 2.0,
+      "learning_rate": 2.4098649531343497e-05,
+      "loss": 0.6743,
+      "step": 353
+    },
+    {
+      "epoch": 3.1466666666666665,
+      "grad_norm": 2.03125,
+      "learning_rate": 2.3800704701496053e-05,
+      "loss": 0.7847,
+      "step": 354
+    },
+    {
+      "epoch": 3.1555555555555554,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.8001,
+      "step": 355
+    },
+    {
+      "epoch": 3.1644444444444444,
+      "grad_norm": 1.578125,
+      "learning_rate": 2.3208660251050158e-05,
+      "loss": 0.7351,
+      "step": 356
+    },
+    {
+      "epoch": 3.1733333333333333,
+      "grad_norm": 1.9296875,
+      "learning_rate": 2.2914589485863014e-05,
+      "loss": 0.7505,
+      "step": 357
+    },
+    {
+      "epoch": 3.1822222222222223,
+      "grad_norm": 2.609375,
+      "learning_rate": 2.2621838825372493e-05,
+      "loss": 0.8125,
+      "step": 358
+    },
+    {
+      "epoch": 3.1911111111111112,
+      "grad_norm": 1.8046875,
+      "learning_rate": 2.23304225378328e-05,
+      "loss": 0.8101,
+      "step": 359
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.6484375,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.8313,
+      "step": 360
+    },
+    {
+      "epoch": 3.2088888888888887,
+      "grad_norm": 1.390625,
+      "learning_rate": 2.1751649828753106e-05,
+      "loss": 0.6678,
+      "step": 361
+    },
+    {
+      "epoch": 3.2177777777777776,
+      "grad_norm": 1.59375,
+      "learning_rate": 2.1464321615778422e-05,
+      "loss": 0.7392,
+      "step": 362
+    },
+    {
+      "epoch": 3.2266666666666666,
+      "grad_norm": 1.484375,
+      "learning_rate": 2.117838419151034e-05,
+      "loss": 0.6166,
+      "step": 363
+    },
+    {
+      "epoch": 3.2355555555555555,
+      "grad_norm": 1.3515625,
+      "learning_rate": 2.0893851492135537e-05,
+      "loss": 0.5738,
+      "step": 364
+    },
+    {
+      "epoch": 3.2444444444444445,
+      "grad_norm": 1.453125,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6822,
+      "step": 365
+    },
+    {
+      "epoch": 3.2533333333333334,
+      "grad_norm": 1.625,
+      "learning_rate": 2.0329055669814934e-05,
+      "loss": 0.9337,
+      "step": 366
+    },
+    {
+      "epoch": 3.2622222222222224,
+      "grad_norm": 1.828125,
+      "learning_rate": 2.0048820074220715e-05,
+      "loss": 0.8167,
+      "step": 367
+    },
+    {
+      "epoch": 3.2711111111111113,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.977004425688126e-05,
+      "loss": 0.7508,
+      "step": 368
+    },
+    {
+      "epoch": 3.2800000000000002,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.9492741804936622e-05,
+      "loss": 0.745,
+      "step": 369
+    },
+    {
+      "epoch": 3.2888888888888888,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.8252,
+      "step": 370
+    },
+    {
+      "epoch": 3.2977777777777777,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.8942610986084486e-05,
+      "loss": 0.6201,
+      "step": 371
+    },
+    {
+      "epoch": 3.3066666666666666,
+      "grad_norm": 1.5,
+      "learning_rate": 1.866980943177699e-05,
+      "loss": 0.6965,
+      "step": 372
+    },
+    {
+      "epoch": 3.3155555555555556,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.8398534866757454e-05,
+      "loss": 0.7522,
+      "step": 373
+    },
+    {
+      "epoch": 3.3244444444444445,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.8128800512565513e-05,
+      "loss": 0.7584,
+      "step": 374
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.6047,
+      "step": 375
+    },
+    {
+      "epoch": 3.3422222222222224,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.7594004946843456e-05,
+      "loss": 0.77,
+      "step": 376
+    },
+    {
+      "epoch": 3.351111111111111,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.7328969800494726e-05,
+      "loss": 0.7815,
+      "step": 377
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7065526994065973e-05,
+      "loss": 0.7838,
+      "step": 378
+    },
+    {
+      "epoch": 3.368888888888889,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.680368936738792e-05,
+      "loss": 0.7368,
+      "step": 379
+    },
+    {
+      "epoch": 3.3777777777777778,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8079,
+      "step": 380
+    },
+    {
+      "epoch": 3.3866666666666667,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.6284880620813848e-05,
+      "loss": 0.9025,
+      "step": 381
+    },
+    {
+      "epoch": 3.3955555555555557,
+      "grad_norm": 1.5,
+      "learning_rate": 1.602793478692419e-05,
+      "loss": 0.8089,
+      "step": 382
+    },
+    {
+      "epoch": 3.4044444444444446,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.5772644703565565e-05,
+      "loss": 0.6786,
+      "step": 383
+    },
+    {
+      "epoch": 3.413333333333333,
+      "grad_norm": 1.5,
+      "learning_rate": 1.551902281321651e-05,
+      "loss": 0.6152,
+      "step": 384
+    },
+    {
+      "epoch": 3.422222222222222,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.5888,
+      "step": 385
+    },
+    {
+      "epoch": 3.431111111111111,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.5016832974331724e-05,
+      "loss": 0.8046,
+      "step": 386
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.4768289501820265e-05,
+      "loss": 0.7949,
+      "step": 387
+    },
+    {
+      "epoch": 3.448888888888889,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.4521463173173965e-05,
+      "loss": 0.6952,
+      "step": 388
+    },
+    {
+      "epoch": 3.457777777777778,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.4276366018359844e-05,
+      "loss": 0.7142,
+      "step": 389
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.8104,
+      "step": 390
+    },
+    {
+      "epoch": 3.4755555555555557,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.3791406928126638e-05,
+      "loss": 0.8418,
+      "step": 391
+    },
+    {
+      "epoch": 3.4844444444444447,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 0.6546,
+      "step": 392
+    },
+    {
+      "epoch": 3.493333333333333,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.3313506774856177e-05,
+      "loss": 0.8296,
+      "step": 393
+    },
+    {
+      "epoch": 3.502222222222222,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.3077232968705805e-05,
+      "loss": 0.7203,
+      "step": 394
+    },
+    {
+      "epoch": 3.511111111111111,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6301,
+      "step": 395
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.2610095475073414e-05,
+      "loss": 0.7751,
+      "step": 396
+    },
+    {
+      "epoch": 3.528888888888889,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.2379254555213788e-05,
+      "loss": 0.7448,
+      "step": 397
+    },
+    {
+      "epoch": 3.537777777777778,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.2150247217412186e-05,
+      "loss": 0.6768,
+      "step": 398
+    },
+    {
+      "epoch": 3.546666666666667,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.1923084623163172e-05,
+      "loss": 0.7193,
+      "step": 399
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6328,
+      "step": 400
+    },
+    {
+      "epoch": 3.5644444444444443,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.1474337861210543e-05,
+      "loss": 0.727,
+      "step": 401
+    },
+    {
+      "epoch": 3.5733333333333333,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.1252775564791024e-05,
+      "loss": 0.7467,
+      "step": 402
+    },
+    {
+      "epoch": 3.582222222222222,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.1033101753426283e-05,
+      "loss": 0.7672,
+      "step": 403
+    },
+    {
+      "epoch": 3.591111111111111,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.0815327133708015e-05,
+      "loss": 0.7215,
+      "step": 404
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6078,
+      "step": 405
+    },
+    {
+      "epoch": 3.608888888888889,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.0385517832240471e-05,
+      "loss": 0.7894,
+      "step": 406
+    },
+    {
+      "epoch": 3.6177777777777775,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.0173504098790187e-05,
+      "loss": 0.7391,
+      "step": 407
+    },
+    {
+      "epoch": 3.626666666666667,
+      "grad_norm": 2.296875,
+      "learning_rate": 9.963431452563332e-06,
+      "loss": 0.6962,
+      "step": 408
+    },
+    {
+      "epoch": 3.6355555555555554,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.755310132204298e-06,
+      "loss": 0.8193,
+      "step": 409
+    },
+    {
+      "epoch": 3.6444444444444444,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7433,
+      "step": 410
+    },
+    {
+      "epoch": 3.6533333333333333,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.344961947648623e-06,
+      "loss": 0.5545,
+      "step": 411
+    },
+    {
+      "epoch": 3.6622222222222223,
+      "grad_norm": 2.546875,
+      "learning_rate": 9.142755083243576e-06,
+      "loss": 0.938,
+      "step": 412
+    },
+    {
+      "epoch": 3.671111111111111,
+      "grad_norm": 2.203125,
+      "learning_rate": 8.9425395433148e-06,
+      "loss": 0.8629,
+      "step": 413
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 2.15625,
+      "learning_rate": 8.744325086085248e-06,
+      "loss": 0.8981,
+      "step": 414
+    },
+    {
+      "epoch": 3.688888888888889,
+      "grad_norm": 2.0,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.7164,
+      "step": 415
+    },
+    {
+      "epoch": 3.6977777777777776,
+      "grad_norm": 1.7421875,
+      "learning_rate": 8.353937964495029e-06,
+      "loss": 0.7385,
+      "step": 416
+    },
+    {
+      "epoch": 3.7066666666666666,
+      "grad_norm": 1.921875,
+      "learning_rate": 8.16178432705192e-06,
+      "loss": 0.6595,
+      "step": 417
+    },
+    {
+      "epoch": 3.7155555555555555,
+      "grad_norm": 1.8203125,
+      "learning_rate": 7.971669825215788e-06,
+      "loss": 0.7062,
+      "step": 418
+    },
+    {
+      "epoch": 3.7244444444444444,
+      "grad_norm": 2.34375,
+      "learning_rate": 7.783603724899257e-06,
+      "loss": 0.8843,
+      "step": 419
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 1.734375,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6351,
+      "step": 420
+    },
+    {
+      "epoch": 3.7422222222222223,
+      "grad_norm": 2.03125,
+      "learning_rate": 7.413653292847617e-06,
+      "loss": 0.7729,
+      "step": 421
+    },
+    {
+      "epoch": 3.7511111111111113,
+      "grad_norm": 2.140625,
+      "learning_rate": 7.2317869919746705e-06,
+      "loss": 0.8741,
+      "step": 422
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.052005153466779e-06,
+      "loss": 0.7252,
+      "step": 423
+    },
+    {
+      "epoch": 3.7688888888888887,
+      "grad_norm": 1.90625,
+      "learning_rate": 6.874316539637127e-06,
+      "loss": 0.6773,
+      "step": 424
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 2.28125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6376,
+      "step": 425
+    },
+    {
+      "epoch": 3.7866666666666666,
+      "grad_norm": 1.7421875,
+      "learning_rate": 6.52525352473905e-06,
+      "loss": 0.7645,
+      "step": 426
+    },
+    {
+      "epoch": 3.7955555555555556,
+      "grad_norm": 2.0625,
+      "learning_rate": 6.353896136509524e-06,
+      "loss": 0.797,
+      "step": 427
+    },
+    {
+      "epoch": 3.8044444444444445,
+      "grad_norm": 1.6796875,
+      "learning_rate": 6.184665997806832e-06,
+      "loss": 0.7175,
+      "step": 428
+    },
+    {
+      "epoch": 3.8133333333333335,
+      "grad_norm": 1.9921875,
+      "learning_rate": 6.017571356669183e-06,
+      "loss": 0.8561,
+      "step": 429
+    },
+    {
+      "epoch": 3.822222222222222,
+      "grad_norm": 1.8359375,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.5715,
+      "step": 430
+    },
+    {
+      "epoch": 3.8311111111111114,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.689821038439263e-06,
+      "loss": 0.68,
+      "step": 431
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.125,
+      "learning_rate": 5.529181335435124e-06,
+      "loss": 0.7089,
+      "step": 432
+    },
+    {
+      "epoch": 3.848888888888889,
+      "grad_norm": 1.734375,
+      "learning_rate": 5.370709077393721e-06,
+      "loss": 0.7589,
+      "step": 433
+    },
+    {
+      "epoch": 3.8577777777777778,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.214411988029355e-06,
+      "loss": 0.7617,
+      "step": 434
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 1.78125,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.9029,
+      "step": 435
+    },
+    {
+      "epoch": 3.8755555555555556,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.908373679744316e-06,
+      "loss": 0.6779,
+      "step": 436
+    },
+    {
+      "epoch": 3.8844444444444446,
+      "grad_norm": 2.0,
+      "learning_rate": 4.758647376699032e-06,
+      "loss": 0.8606,
+      "step": 437
+    },
+    {
+      "epoch": 3.8933333333333335,
+      "grad_norm": 2.109375,
+      "learning_rate": 4.611126073354571e-06,
+      "loss": 0.7648,
+      "step": 438
+    },
+    {
+      "epoch": 3.902222222222222,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.465816959691149e-06,
+      "loss": 0.6418,
+      "step": 439
+    },
+    {
+      "epoch": 3.911111111111111,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.7436,
+      "step": 440
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 1.71875,
+      "learning_rate": 4.181863521888019e-06,
+      "loss": 0.7485,
+      "step": 441
+    },
+    {
+      "epoch": 3.928888888888889,
+      "grad_norm": 2.015625,
+      "learning_rate": 4.043233037238281e-06,
+      "loss": 0.7783,
+      "step": 442
+    },
+    {
+      "epoch": 3.937777777777778,
+      "grad_norm": 1.6640625,
+      "learning_rate": 3.90684242057498e-06,
+      "loss": 0.5753,
+      "step": 443
+    },
+    {
+      "epoch": 3.9466666666666668,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.772698319384349e-06,
+      "loss": 0.6734,
+      "step": 444
+    },
+    {
+      "epoch": 3.9555555555555557,
+      "grad_norm": 1.6953125,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.7748,
+      "step": 445
+    },
+    {
+      "epoch": 3.964444444444444,
+      "grad_norm": 1.765625,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.7126,
+      "step": 446
+    },
+    {
+      "epoch": 3.9733333333333336,
+      "grad_norm": 1.875,
+      "learning_rate": 3.3838099392243916e-06,
+      "loss": 0.7099,
+      "step": 447
+    },
+    {
+      "epoch": 3.982222222222222,
+      "grad_norm": 2.296875,
+      "learning_rate": 3.258716180199278e-06,
+      "loss": 0.9139,
+      "step": 448
+    },
+    {
+      "epoch": 3.991111111111111,
+      "grad_norm": 2.34375,
+      "learning_rate": 3.1359005254054273e-06,
+      "loss": 0.7272,
+      "step": 449
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.875,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8561,
+      "step": 450
+    },
+    {
+      "epoch": 4.0088888888888885,
+      "grad_norm": 1.8515625,
+      "learning_rate": 2.8971273606351658e-06,
+      "loss": 0.7015,
+      "step": 451
+    },
+    {
+      "epoch": 4.017777777777778,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.7811814881259503e-06,
+      "loss": 0.6025,
+      "step": 452
+    },
+    {
+      "epoch": 4.026666666666666,
+      "grad_norm": 2.125,
+      "learning_rate": 2.667536994215186e-06,
+      "loss": 0.7018,
+      "step": 453
+    },
+    {
+      "epoch": 4.035555555555556,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.5561994177751737e-06,
+      "loss": 0.6452,
+      "step": 454
+    },
+    {
+      "epoch": 4.044444444444444,
+      "grad_norm": 2.140625,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.573,
+      "step": 455
+    },
+    {
+      "epoch": 4.053333333333334,
+      "grad_norm": 2.34375,
+      "learning_rate": 2.340466610352654e-06,
+      "loss": 0.6177,
+      "step": 456
+    },
+    {
+      "epoch": 4.062222222222222,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.2360818938828187e-06,
+      "loss": 0.6479,
+      "step": 457
+    },
+    {
+      "epoch": 4.071111111111111,
+      "grad_norm": 1.7578125,
+      "learning_rate": 2.134025123396638e-06,
+      "loss": 0.6464,
+      "step": 458
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 2.140625,
+      "learning_rate": 2.0343012729971243e-06,
+      "loss": 0.6545,
+      "step": 459
+    },
+    {
+      "epoch": 4.088888888888889,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6401,
+      "step": 460
+    },
+    {
+      "epoch": 4.097777777777778,
+      "grad_norm": 1.75,
+      "learning_rate": 1.841871660117095e-06,
+      "loss": 0.5654,
+      "step": 461
+    },
+    {
+      "epoch": 4.1066666666666665,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.7491752763844293e-06,
+      "loss": 0.6355,
+      "step": 462
+    },
+    {
+      "epoch": 4.115555555555556,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.6588305697770313e-06,
+      "loss": 0.8252,
+      "step": 463
+    },
+    {
+      "epoch": 4.124444444444444,
+      "grad_norm": 2.078125,
+      "learning_rate": 1.5708419435684462e-06,
+      "loss": 0.573,
+      "step": 464
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.6218,
+      "step": 465
+    },
+    {
+      "epoch": 4.142222222222222,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.4019499710726913e-06,
+      "loss": 0.5241,
+      "step": 466
+    },
+    {
+      "epoch": 4.151111111111111,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.3210548563419856e-06,
+      "loss": 0.6395,
+      "step": 467
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.2425322847218368e-06,
+      "loss": 0.7088,
+      "step": 468
+    },
+    {
+      "epoch": 4.168888888888889,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.166386083291604e-06,
+      "loss": 0.7894,
+      "step": 469
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6565,
+      "step": 470
+    },
+    {
+      "epoch": 4.1866666666666665,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.0212375200327973e-06,
+      "loss": 0.5306,
+      "step": 471
+    },
+    {
+      "epoch": 4.195555555555556,
+      "grad_norm": 1.8125,
+      "learning_rate": 9.522422325404235e-07,
+      "loss": 0.6762,
+      "step": 472
+    },
+    {
+      "epoch": 4.204444444444444,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 0.5428,
+      "step": 473
+    },
+    {
+      "epoch": 4.213333333333333,
+      "grad_norm": 1.9375,
+      "learning_rate": 8.214264593307098e-07,
+      "loss": 0.6506,
+      "step": 474
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5546,
+      "step": 475
+    },
+    {
+      "epoch": 4.231111111111111,
+      "grad_norm": 1.7578125,
+      "learning_rate": 7.001981464747565e-07,
+      "loss": 0.6947,
+      "step": 476
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 2.046875,
+      "learning_rate": 6.431867463506048e-07,
+      "loss": 0.8005,
+      "step": 477
+    },
+    {
+      "epoch": 4.248888888888889,
+      "grad_norm": 2.03125,
+      "learning_rate": 5.885809276723608e-07,
+      "loss": 0.7249,
+      "step": 478
+    },
+    {
+      "epoch": 4.257777777777778,
+      "grad_norm": 2.171875,
+      "learning_rate": 5.363833518505834e-07,
+      "loss": 0.7854,
+      "step": 479
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 2.484375,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.762,
+      "step": 480
+    },
+    {
+      "epoch": 4.275555555555556,
+      "grad_norm": 1.9609375,
+      "learning_rate": 4.392229874229159e-07,
+      "loss": 0.7091,
+      "step": 481
+    },
+    {
+      "epoch": 4.2844444444444445,
+      "grad_norm": 1.8671875,
+      "learning_rate": 3.9426493427611177e-07,
+      "loss": 0.6231,
+      "step": 482
+    },
+    {
+      "epoch": 4.293333333333333,
+      "grad_norm": 2.203125,
+      "learning_rate": 3.517245946731529e-07,
+      "loss": 0.7348,
+      "step": 483
+    },
+    {
+      "epoch": 4.302222222222222,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.1160404197018154e-07,
+      "loss": 0.531,
+      "step": 484
+    },
+    {
+      "epoch": 4.311111111111111,
+      "grad_norm": 2.015625,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5834,
+      "step": 485
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 1.875,
+      "learning_rate": 2.386300009084408e-07,
+      "loss": 0.5736,
+      "step": 486
+    },
+    {
+      "epoch": 4.328888888888889,
+      "grad_norm": 1.8828125,
+      "learning_rate": 2.057800692014833e-07,
+      "loss": 0.4758,
+      "step": 487
+    },
+    {
+      "epoch": 4.337777777777778,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.753570375247815e-07,
+      "loss": 0.4747,
+      "step": 488
+    },
+    {
+      "epoch": 4.346666666666667,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.4736238865398765e-07,
+      "loss": 0.6023,
+      "step": 489
+    },
+    {
+      "epoch": 4.355555555555555,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6376,
+      "step": 490
+    },
+    {
+      "epoch": 4.364444444444445,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.866357858642205e-08,
+      "loss": 0.5588,
+      "step": 491
+    },
+    {
+      "epoch": 4.373333333333333,
+      "grad_norm": 2.0,
+      "learning_rate": 7.796179090094891e-08,
+      "loss": 0.6635,
+      "step": 492
+    },
+    {
+      "epoch": 4.3822222222222225,
+      "grad_norm": 2.109375,
+      "learning_rate": 5.969313292830125e-08,
+      "loss": 0.5795,
+      "step": 493
+    },
+    {
+      "epoch": 4.391111111111111,
+      "grad_norm": 1.7734375,
+      "learning_rate": 4.385849505708084e-08,
+      "loss": 0.5087,
+      "step": 494
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5711,
+      "step": 495
+    },
+    {
+      "epoch": 4.408888888888889,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.949424798228239e-08,
+      "loss": 0.6284,
+      "step": 496
+    },
+    {
+      "epoch": 4.417777777777777,
+      "grad_norm": 2.5,
+      "learning_rate": 1.096582625772502e-08,
+      "loss": 0.7002,
+      "step": 497
+    },
+    {
+      "epoch": 4.426666666666667,
+      "grad_norm": 2.046875,
+      "learning_rate": 4.873799534788059e-09,
+      "loss": 0.5831,
+      "step": 498
+    },
+    {
+      "epoch": 4.435555555555555,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.2184647302626583e-09,
+      "loss": 0.5923,
+      "step": 499
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.0,
+      "loss": 0.6272,
+      "step": 500
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_loss": 0.996656596660614,
+      "eval_runtime": 10.8023,
+      "eval_samples_per_second": 9.257,
+      "eval_steps_per_second": 9.257,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.953325949045965e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0696888f178dbdc84cc2260ca4ff69e7fb438f163ee3391251597831c8cc404
+size 5368

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B",
+  "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": 131072,
+  "mlp_bias": false,
+  "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": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.3",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.444444444444445,
+    "eval_loss": 0.996656596660614,
+    "eval_runtime": 10.5528,
+    "eval_samples_per_second": 9.476,
+    "eval_steps_per_second": 9.476
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:800a442270faa73a437f3b21541c4106bc2d96a11c189fefd00de9380989bd7c
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b2fcc4779577c9438a9e1f7af1efac7398ebd738d6bc88f90c12cc5160b5519
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e9504dd4e4a146d484c52a97584ec14dac92237c46b064934af67a85e7d383
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4486f35c040f683f7d790354f66c169c109eb9fa0954a4a35d7c458a108405d
+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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

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": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "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": "<|eom_id|>",
+      "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": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.444444444444445,
+    "total_flos": 2.953325949045965e+16,
+    "train_loss": 0.8754597247838974,
+    "train_runtime": 1354.7094,
+    "train_samples_per_second": 2.953,
+    "train_steps_per_second": 0.369
+}

trainer_state.json

@@ -0,0 +1,3550 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.444444444444445,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008888888888888889,
+      "grad_norm": 10.75,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4464,
+      "step": 1
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 13.0,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2646,
+      "step": 2
+    },
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 11.3125,
+      "learning_rate": 6e-06,
+      "loss": 1.4738,
+      "step": 3
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 12.875,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.3848,
+      "step": 4
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 11.0,
+      "learning_rate": 1e-05,
+      "loss": 1.5257,
+      "step": 5
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 11.8125,
+      "learning_rate": 1.2e-05,
+      "loss": 1.4105,
+      "step": 6
+    },
+    {
+      "epoch": 0.06222222222222222,
+      "grad_norm": 8.0625,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 1.287,
+      "step": 7
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 9.4375,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.2099,
+      "step": 8
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 26.25,
+      "learning_rate": 1.8e-05,
+      "loss": 1.311,
+      "step": 9
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 588.0,
+      "learning_rate": 2e-05,
+      "loss": 2.4975,
+      "step": 10
+    },
+    {
+      "epoch": 0.09777777777777778,
+      "grad_norm": 73.5,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 1.2125,
+      "step": 11
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 9.125,
+      "learning_rate": 2.4e-05,
+      "loss": 1.3688,
+      "step": 12
+    },
+    {
+      "epoch": 0.11555555555555555,
+      "grad_norm": 4.96875,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 1.2372,
+      "step": 13
+    },
+    {
+      "epoch": 0.12444444444444444,
+      "grad_norm": 11.1875,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 1.3227,
+      "step": 14
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 5.15625,
+      "learning_rate": 3e-05,
+      "loss": 1.1693,
+      "step": 15
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 1.0922,
+      "step": 16
+    },
+    {
+      "epoch": 0.1511111111111111,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.0916,
+      "step": 17
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.25,
+      "learning_rate": 3.6e-05,
+      "loss": 1.1219,
+      "step": 18
+    },
+    {
+      "epoch": 0.1688888888888889,
+      "grad_norm": 4.875,
+      "learning_rate": 3.8e-05,
+      "loss": 1.2237,
+      "step": 19
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 4.9375,
+      "learning_rate": 4e-05,
+      "loss": 1.0106,
+      "step": 20
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.2e-05,
+      "loss": 1.0266,
+      "step": 21
+    },
+    {
+      "epoch": 0.19555555555555557,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.9007,
+      "step": 22
+    },
+    {
+      "epoch": 0.20444444444444446,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.9784,
+      "step": 23
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 3.671875,
+      "learning_rate": 4.8e-05,
+      "loss": 1.1803,
+      "step": 24
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 4.75,
+      "learning_rate": 5e-05,
+      "loss": 1.2705,
+      "step": 25
+    },
+    {
+      "epoch": 0.2311111111111111,
+      "grad_norm": 4.5,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 1.0653,
+      "step": 26
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.25,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.988,
+      "step": 27
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 13.625,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.138,
+      "step": 28
+    },
+    {
+      "epoch": 0.2577777777777778,
+      "grad_norm": 3.015625,
+      "learning_rate": 5.8e-05,
+      "loss": 0.9095,
+      "step": 29
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 4.1875,
+      "learning_rate": 6e-05,
+      "loss": 1.1132,
+      "step": 30
+    },
+    {
+      "epoch": 0.27555555555555555,
+      "grad_norm": 4.8125,
+      "learning_rate": 6.2e-05,
+      "loss": 0.9967,
+      "step": 31
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 3.859375,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.9615,
+      "step": 32
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 4.53125,
+      "learning_rate": 6.6e-05,
+      "loss": 1.0561,
+      "step": 33
+    },
+    {
+      "epoch": 0.3022222222222222,
+      "grad_norm": 3.546875,
+      "learning_rate": 6.800000000000001e-05,
+      "loss": 1.1543,
+      "step": 34
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 8.125,
+      "learning_rate": 7e-05,
+      "loss": 1.1004,
+      "step": 35
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.21875,
+      "learning_rate": 7.2e-05,
+      "loss": 1.0279,
+      "step": 36
+    },
+    {
+      "epoch": 0.3288888888888889,
+      "grad_norm": 3.40625,
+      "learning_rate": 7.4e-05,
+      "loss": 0.9469,
+      "step": 37
+    },
+    {
+      "epoch": 0.3377777777777778,
+      "grad_norm": 10.8125,
+      "learning_rate": 7.6e-05,
+      "loss": 1.0991,
+      "step": 38
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 3.96875,
+      "learning_rate": 7.800000000000001e-05,
+      "loss": 1.0668,
+      "step": 39
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 3.359375,
+      "learning_rate": 8e-05,
+      "loss": 0.9899,
+      "step": 40
+    },
+    {
+      "epoch": 0.36444444444444446,
+      "grad_norm": 3.296875,
+      "learning_rate": 8.2e-05,
+      "loss": 1.0636,
+      "step": 41
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 2.96875,
+      "learning_rate": 8.4e-05,
+      "loss": 1.0076,
+      "step": 42
+    },
+    {
+      "epoch": 0.38222222222222224,
+      "grad_norm": 3.359375,
+      "learning_rate": 8.6e-05,
+      "loss": 0.9301,
+      "step": 43
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 2.90625,
+      "learning_rate": 8.800000000000001e-05,
+      "loss": 1.171,
+      "step": 44
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.671875,
+      "learning_rate": 9e-05,
+      "loss": 0.9985,
+      "step": 45
+    },
+    {
+      "epoch": 0.4088888888888889,
+      "grad_norm": 2.40625,
+      "learning_rate": 9.200000000000001e-05,
+      "loss": 1.034,
+      "step": 46
+    },
+    {
+      "epoch": 0.4177777777777778,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.4e-05,
+      "loss": 0.9552,
+      "step": 47
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 2.546875,
+      "learning_rate": 9.6e-05,
+      "loss": 1.2027,
+      "step": 48
+    },
+    {
+      "epoch": 0.43555555555555553,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.8e-05,
+      "loss": 1.2453,
+      "step": 49
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 7.15625,
+      "learning_rate": 0.0001,
+      "loss": 1.1497,
+      "step": 50
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 12.6875,
+      "learning_rate": 9.999878153526974e-05,
+      "loss": 1.0698,
+      "step": 51
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 7.625,
+      "learning_rate": 9.999512620046522e-05,
+      "loss": 1.093,
+      "step": 52
+    },
+    {
+      "epoch": 0.4711111111111111,
+      "grad_norm": 7.46875,
+      "learning_rate": 9.998903417374228e-05,
+      "loss": 1.0031,
+      "step": 53
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 7.46875,
+      "learning_rate": 9.998050575201771e-05,
+      "loss": 1.2479,
+      "step": 54
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 7.59375,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 1.1337,
+      "step": 55
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 7.96875,
+      "learning_rate": 9.995614150494293e-05,
+      "loss": 1.0747,
+      "step": 56
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 9.0,
+      "learning_rate": 9.99403068670717e-05,
+      "loss": 1.1863,
+      "step": 57
+    },
+    {
+      "epoch": 0.5155555555555555,
+      "grad_norm": 5.59375,
+      "learning_rate": 9.992203820909906e-05,
+      "loss": 0.8643,
+      "step": 58
+    },
+    {
+      "epoch": 0.5244444444444445,
+      "grad_norm": 6.40625,
+      "learning_rate": 9.990133642141359e-05,
+      "loss": 1.0411,
+      "step": 59
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 5.25,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.0888,
+      "step": 60
+    },
+    {
+      "epoch": 0.5422222222222223,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.985263761134602e-05,
+      "loss": 0.9589,
+      "step": 61
+    },
+    {
+      "epoch": 0.5511111111111111,
+      "grad_norm": 5.75,
+      "learning_rate": 9.982464296247522e-05,
+      "loss": 1.0835,
+      "step": 62
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.5625,
+      "learning_rate": 9.979421993079852e-05,
+      "loss": 0.9976,
+      "step": 63
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 5.8125,
+      "learning_rate": 9.976136999909156e-05,
+      "loss": 1.0755,
+      "step": 64
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 7.34375,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 1.0238,
+      "step": 65
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 6.03125,
+      "learning_rate": 9.968839595802982e-05,
+      "loss": 0.9071,
+      "step": 66
+    },
+    {
+      "epoch": 0.5955555555555555,
+      "grad_norm": 5.96875,
+      "learning_rate": 9.964827540532685e-05,
+      "loss": 0.9407,
+      "step": 67
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.96057350657239e-05,
+      "loss": 1.1039,
+      "step": 68
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.956077701257709e-05,
+      "loss": 1.0651,
+      "step": 69
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 1.0068,
+      "step": 70
+    },
+    {
+      "epoch": 0.6311111111111111,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.946361664814943e-05,
+      "loss": 0.9485,
+      "step": 71
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.75,
+      "learning_rate": 9.941141907232765e-05,
+      "loss": 1.247,
+      "step": 72
+    },
+    {
+      "epoch": 0.6488888888888888,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.93568132536494e-05,
+      "loss": 1.0063,
+      "step": 73
+    },
+    {
+      "epoch": 0.6577777777777778,
+      "grad_norm": 6.15625,
+      "learning_rate": 9.929980185352526e-05,
+      "loss": 0.9367,
+      "step": 74
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 6.875,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 1.05,
+      "step": 75
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 9.375,
+      "learning_rate": 9.917857354066931e-05,
+      "loss": 1.1569,
+      "step": 76
+    },
+    {
+      "epoch": 0.6844444444444444,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.911436253643445e-05,
+      "loss": 0.8825,
+      "step": 77
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 5.5,
+      "learning_rate": 9.904775776745958e-05,
+      "loss": 0.8632,
+      "step": 78
+    },
+    {
+      "epoch": 0.7022222222222222,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.89787624799672e-05,
+      "loss": 0.9715,
+      "step": 79
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 5.59375,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.0032,
+      "step": 80
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.88336139167084e-05,
+      "loss": 1.1563,
+      "step": 81
+    },
+    {
+      "epoch": 0.7288888888888889,
+      "grad_norm": 7.09375,
+      "learning_rate": 9.875746771527816e-05,
+      "loss": 1.0159,
+      "step": 82
+    },
+    {
+      "epoch": 0.7377777777777778,
+      "grad_norm": 6.03125,
+      "learning_rate": 9.867894514365802e-05,
+      "loss": 1.1233,
+      "step": 83
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.859805002892732e-05,
+      "loss": 1.0673,
+      "step": 84
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 6.8125,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 0.9338,
+      "step": 85
+    },
+    {
+      "epoch": 0.7644444444444445,
+      "grad_norm": 6.4375,
+      "learning_rate": 9.842915805643155e-05,
+      "loss": 1.0843,
+      "step": 86
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.834116943022298e-05,
+      "loss": 0.9081,
+      "step": 87
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 5.875,
+      "learning_rate": 9.825082472361557e-05,
+      "loss": 0.9989,
+      "step": 88
+    },
+    {
+      "epoch": 0.7911111111111111,
+      "grad_norm": 5.78125,
+      "learning_rate": 9.815812833988291e-05,
+      "loss": 0.8834,
+      "step": 89
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.5625,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.9779,
+      "step": 90
+    },
+    {
+      "epoch": 0.8088888888888889,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.796569872700288e-05,
+      "loss": 1.0189,
+      "step": 91
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 6.125,
+      "learning_rate": 9.786597487660337e-05,
+      "loss": 1.0696,
+      "step": 92
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 5.6875,
+      "learning_rate": 9.776391810611718e-05,
+      "loss": 1.059,
+      "step": 93
+    },
+    {
+      "epoch": 0.8355555555555556,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.765953338964735e-05,
+      "loss": 0.8577,
+      "step": 94
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9671,
+      "step": 95
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 5.875,
+      "learning_rate": 9.744380058222483e-05,
+      "loss": 1.0792,
+      "step": 96
+    },
+    {
+      "epoch": 0.8622222222222222,
+      "grad_norm": 7.84375,
+      "learning_rate": 9.733246300578483e-05,
+      "loss": 1.0958,
+      "step": 97
+    },
+    {
+      "epoch": 0.8711111111111111,
+      "grad_norm": 6.1875,
+      "learning_rate": 9.721881851187406e-05,
+      "loss": 0.966,
+      "step": 98
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.710287263936484e-05,
+      "loss": 0.8868,
+      "step": 99
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.5703125,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 1.0577,
+      "step": 100
+    },
+    {
+      "epoch": 0.8977777777777778,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.686409947459458e-05,
+      "loss": 0.7904,
+      "step": 101
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.674128381980072e-05,
+      "loss": 0.8927,
+      "step": 102
+    },
+    {
+      "epoch": 0.9155555555555556,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.661619006077561e-05,
+      "loss": 1.0477,
+      "step": 103
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.648882429441257e-05,
+      "loss": 1.0107,
+      "step": 104
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 1.0277,
+      "step": 105
+    },
+    {
+      "epoch": 0.9422222222222222,
+      "grad_norm": 2.34375,
+      "learning_rate": 9.622730168061567e-05,
+      "loss": 0.9528,
+      "step": 106
+    },
+    {
+      "epoch": 0.9511111111111111,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.609315757942503e-05,
+      "loss": 0.8783,
+      "step": 107
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.0625,
+      "learning_rate": 9.595676696276172e-05,
+      "loss": 0.991,
+      "step": 108
+    },
+    {
+      "epoch": 0.9688888888888889,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.581813647811198e-05,
+      "loss": 1.0017,
+      "step": 109
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 1.4765625,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.0257,
+      "step": 110
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.553418304030886e-05,
+      "loss": 0.9087,
+      "step": 111
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.538887392664544e-05,
+      "loss": 1.002,
+      "step": 112
+    },
+    {
+      "epoch": 1.0044444444444445,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.524135262330098e-05,
+      "loss": 0.7493,
+      "step": 113
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 1.34375,
+      "learning_rate": 9.50916263202557e-05,
+      "loss": 0.8562,
+      "step": 114
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 0.9812,
+      "step": 115
+    },
+    {
+      "epoch": 1.031111111111111,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.478558801197065e-05,
+      "loss": 0.8069,
+      "step": 116
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.3359375,
+      "learning_rate": 9.462929092260628e-05,
+      "loss": 0.8336,
+      "step": 117
+    },
+    {
+      "epoch": 1.048888888888889,
+      "grad_norm": 1.6484375,
+      "learning_rate": 9.447081866456489e-05,
+      "loss": 0.9364,
+      "step": 118
+    },
+    {
+      "epoch": 1.0577777777777777,
+      "grad_norm": 1.3984375,
+      "learning_rate": 9.431017896156074e-05,
+      "loss": 0.7365,
+      "step": 119
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 1.0947,
+      "step": 120
+    },
+    {
+      "epoch": 1.0755555555555556,
+      "grad_norm": 1.421875,
+      "learning_rate": 9.398242864333083e-05,
+      "loss": 0.9642,
+      "step": 121
+    },
+    {
+      "epoch": 1.0844444444444445,
+      "grad_norm": 1.2578125,
+      "learning_rate": 9.381533400219318e-05,
+      "loss": 0.824,
+      "step": 122
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 1.015625,
+      "learning_rate": 9.364610386349049e-05,
+      "loss": 0.814,
+      "step": 123
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 1.359375,
+      "learning_rate": 9.347474647526095e-05,
+      "loss": 0.7891,
+      "step": 124
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.8481,
+      "step": 125
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.109375,
+      "learning_rate": 9.312568346036288e-05,
+      "loss": 0.7348,
+      "step": 126
+    },
+    {
+      "epoch": 1.1288888888888888,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.294799484653323e-05,
+      "loss": 1.1175,
+      "step": 127
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 1.1953125,
+      "learning_rate": 9.276821300802534e-05,
+      "loss": 1.1577,
+      "step": 128
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.258634670715238e-05,
+      "loss": 0.8026,
+      "step": 129
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 1.875,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.8051,
+      "step": 130
+    },
+    {
+      "epoch": 1.1644444444444444,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.221639627510076e-05,
+      "loss": 1.0332,
+      "step": 131
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 1.2890625,
+      "learning_rate": 9.202833017478422e-05,
+      "loss": 0.9912,
+      "step": 132
+    },
+    {
+      "epoch": 1.1822222222222223,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.183821567294809e-05,
+      "loss": 0.7942,
+      "step": 133
+    },
+    {
+      "epoch": 1.1911111111111112,
+      "grad_norm": 1.328125,
+      "learning_rate": 9.164606203550497e-05,
+      "loss": 0.8423,
+      "step": 134
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.98828125,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.7237,
+      "step": 135
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 1.140625,
+      "learning_rate": 9.125567491391476e-05,
+      "loss": 0.8881,
+      "step": 136
+    },
+    {
+      "epoch": 1.2177777777777778,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.105746045668521e-05,
+      "loss": 0.8953,
+      "step": 137
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.085724491675642e-05,
+      "loss": 1.0433,
+      "step": 138
+    },
+    {
+      "epoch": 1.2355555555555555,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.065503805235138e-05,
+      "loss": 0.9354,
+      "step": 139
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.9633,
+      "step": 140
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 1.6171875,
+      "learning_rate": 9.02446898677957e-05,
+      "loss": 1.0975,
+      "step": 141
+    },
+    {
+      "epoch": 1.2622222222222224,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.003656854743667e-05,
+      "loss": 0.8621,
+      "step": 142
+    },
+    {
+      "epoch": 1.271111111111111,
+      "grad_norm": 1.3125,
+      "learning_rate": 8.982649590120982e-05,
+      "loss": 0.8958,
+      "step": 143
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.375,
+      "learning_rate": 8.961448216775954e-05,
+      "loss": 0.9975,
+      "step": 144
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.9486,
+      "step": 145
+    },
+    {
+      "epoch": 1.2977777777777777,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.9184672866292e-05,
+      "loss": 0.876,
+      "step": 146
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.896689824657372e-05,
+      "loss": 0.8772,
+      "step": 147
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 1.2421875,
+      "learning_rate": 8.874722443520899e-05,
+      "loss": 0.8023,
+      "step": 148
+    },
+    {
+      "epoch": 1.3244444444444445,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.852566213878947e-05,
+      "loss": 1.0432,
+      "step": 149
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.921875,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.9147,
+      "step": 150
+    },
+    {
+      "epoch": 1.3422222222222222,
+      "grad_norm": 2.3125,
+      "learning_rate": 8.807691537683685e-05,
+      "loss": 0.9798,
+      "step": 151
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.784975278258783e-05,
+      "loss": 0.8849,
+      "step": 152
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.578125,
+      "learning_rate": 8.762074544478623e-05,
+      "loss": 0.9281,
+      "step": 153
+    },
+    {
+      "epoch": 1.3688888888888888,
+      "grad_norm": 1.375,
+      "learning_rate": 8.73899045249266e-05,
+      "loss": 1.0482,
+      "step": 154
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 1.6484375,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.0076,
+      "step": 155
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 1.203125,
+      "learning_rate": 8.692276703129421e-05,
+      "loss": 0.817,
+      "step": 156
+    },
+    {
+      "epoch": 1.3955555555555557,
+      "grad_norm": 1.4765625,
+      "learning_rate": 8.668649322514382e-05,
+      "loss": 1.0906,
+      "step": 157
+    },
+    {
+      "epoch": 1.4044444444444444,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.644843137107059e-05,
+      "loss": 0.9078,
+      "step": 158
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.620859307187339e-05,
+      "loss": 0.9268,
+      "step": 159
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 1.40625,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.8873,
+      "step": 160
+    },
+    {
+      "epoch": 1.431111111111111,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.572363398164017e-05,
+      "loss": 0.8488,
+      "step": 161
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.375,
+      "learning_rate": 8.547853682682604e-05,
+      "loss": 1.001,
+      "step": 162
+    },
+    {
+      "epoch": 1.448888888888889,
+      "grad_norm": 1.7265625,
+      "learning_rate": 8.523171049817974e-05,
+      "loss": 1.0562,
+      "step": 163
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 1.3984375,
+      "learning_rate": 8.498316702566828e-05,
+      "loss": 0.845,
+      "step": 164
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.7172,
+      "step": 165
+    },
+    {
+      "epoch": 1.4755555555555555,
+      "grad_norm": 1.1953125,
+      "learning_rate": 8.44809771867835e-05,
+      "loss": 0.9064,
+      "step": 166
+    },
+    {
+      "epoch": 1.4844444444444445,
+      "grad_norm": 2.390625,
+      "learning_rate": 8.422735529643444e-05,
+      "loss": 0.888,
+      "step": 167
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.397206521307584e-05,
+      "loss": 0.8158,
+      "step": 168
+    },
+    {
+      "epoch": 1.5022222222222221,
+      "grad_norm": 1.1875,
+      "learning_rate": 8.371511937918616e-05,
+      "loss": 0.8498,
+      "step": 169
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.5546875,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.93,
+      "step": 170
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 2.109375,
+      "learning_rate": 8.319631063261209e-05,
+      "loss": 1.2189,
+      "step": 171
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.293447300593402e-05,
+      "loss": 1.0049,
+      "step": 172
+    },
+    {
+      "epoch": 1.537777777777778,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.267103019950529e-05,
+      "loss": 0.9254,
+      "step": 173
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.4921875,
+      "learning_rate": 8.240599505315655e-05,
+      "loss": 0.8603,
+      "step": 174
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 1.5859375,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.9305,
+      "step": 175
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 1.828125,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.0136,
+      "step": 176
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 1.9609375,
+      "learning_rate": 8.160146513324254e-05,
+      "loss": 1.0119,
+      "step": 177
+    },
+    {
+      "epoch": 1.5822222222222222,
+      "grad_norm": 1.53125,
+      "learning_rate": 8.133019056822304e-05,
+      "loss": 0.8887,
+      "step": 178
+    },
+    {
+      "epoch": 1.5911111111111111,
+      "grad_norm": 1.421875,
+      "learning_rate": 8.105738901391552e-05,
+      "loss": 1.0235,
+      "step": 179
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.078125,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.8074,
+      "step": 180
+    },
+    {
+      "epoch": 1.608888888888889,
+      "grad_norm": 0.90625,
+      "learning_rate": 8.05072581950634e-05,
+      "loss": 0.861,
+      "step": 181
+    },
+    {
+      "epoch": 1.6177777777777778,
+      "grad_norm": 1.5234375,
+      "learning_rate": 8.022995574311876e-05,
+      "loss": 0.9879,
+      "step": 182
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.99511799257793e-05,
+      "loss": 0.7969,
+      "step": 183
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 1.140625,
+      "learning_rate": 7.967094433018508e-05,
+      "loss": 0.85,
+      "step": 184
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 1.078125,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.765,
+      "step": 185
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 1.390625,
+      "learning_rate": 7.910614850786448e-05,
+      "loss": 1.0234,
+      "step": 186
+    },
+    {
+      "epoch": 1.6622222222222223,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.882161580848967e-05,
+      "loss": 0.9385,
+      "step": 187
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.85356783842216e-05,
+      "loss": 0.8661,
+      "step": 188
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.82483501712469e-05,
+      "loss": 1.1284,
+      "step": 189
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.9681,
+      "step": 190
+    },
+    {
+      "epoch": 1.6977777777777778,
+      "grad_norm": 1.3671875,
+      "learning_rate": 7.766957746216721e-05,
+      "loss": 0.8778,
+      "step": 191
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.5703125,
+      "learning_rate": 7.737816117462752e-05,
+      "loss": 0.9828,
+      "step": 192
+    },
+    {
+      "epoch": 1.7155555555555555,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.7085410514137e-05,
+      "loss": 0.9298,
+      "step": 193
+    },
+    {
+      "epoch": 1.7244444444444444,
+      "grad_norm": 1.2578125,
+      "learning_rate": 7.679133974894983e-05,
+      "loss": 0.9032,
+      "step": 194
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.4375,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 1.0169,
+      "step": 195
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 1.484375,
+      "learning_rate": 7.619929529850397e-05,
+      "loss": 0.8967,
+      "step": 196
+    },
+    {
+      "epoch": 1.751111111111111,
+      "grad_norm": 1.75,
+      "learning_rate": 7.590135046865651e-05,
+      "loss": 0.926,
+      "step": 197
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.34375,
+      "learning_rate": 7.560214324352858e-05,
+      "loss": 1.0398,
+      "step": 198
+    },
+    {
+      "epoch": 1.7688888888888887,
+      "grad_norm": 0.9765625,
+      "learning_rate": 7.530168820605818e-05,
+      "loss": 0.9307,
+      "step": 199
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 1.7421875,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.8868,
+      "step": 200
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 2.1875,
+      "learning_rate": 7.469709332921155e-05,
+      "loss": 0.8817,
+      "step": 201
+    },
+    {
+      "epoch": 1.7955555555555556,
+      "grad_norm": 2.96875,
+      "learning_rate": 7.439298295693665e-05,
+      "loss": 1.1957,
+      "step": 202
+    },
+    {
+      "epoch": 1.8044444444444445,
+      "grad_norm": 1.9765625,
+      "learning_rate": 7.408768370508576e-05,
+      "loss": 1.087,
+      "step": 203
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 1.5,
+      "learning_rate": 7.378121045351378e-05,
+      "loss": 0.9296,
+      "step": 204
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.6484375,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.0053,
+      "step": 205
+    },
+    {
+      "epoch": 1.8311111111111111,
+      "grad_norm": 1.59375,
+      "learning_rate": 7.316480175599309e-05,
+      "loss": 0.8588,
+      "step": 206
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 1.609375,
+      "learning_rate": 7.285489635293472e-05,
+      "loss": 0.8839,
+      "step": 207
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 1.640625,
+      "learning_rate": 7.254387703447154e-05,
+      "loss": 0.9149,
+      "step": 208
+    },
+    {
+      "epoch": 1.8577777777777778,
+      "grad_norm": 1.53125,
+      "learning_rate": 7.223175895924638e-05,
+      "loss": 0.8972,
+      "step": 209
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.703125,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 1.0323,
+      "step": 210
+    },
+    {
+      "epoch": 1.8755555555555556,
+      "grad_norm": 1.6171875,
+      "learning_rate": 7.160428744009912e-05,
+      "loss": 1.0817,
+      "step": 211
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 1.71875,
+      "learning_rate": 7.128896457825364e-05,
+      "loss": 1.0261,
+      "step": 212
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 1.5390625,
+      "learning_rate": 7.097260412230886e-05,
+      "loss": 0.9723,
+      "step": 213
+    },
+    {
+      "epoch": 1.9022222222222223,
+      "grad_norm": 1.453125,
+      "learning_rate": 7.06552214912271e-05,
+      "loss": 1.1117,
+      "step": 214
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 1.328125,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.8511,
+      "step": 215
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.1640625,
+      "learning_rate": 7.001745162784477e-05,
+      "loss": 0.9363,
+      "step": 216
+    },
+    {
+      "epoch": 1.9288888888888889,
+      "grad_norm": 1.4765625,
+      "learning_rate": 6.969709547954756e-05,
+      "loss": 0.9447,
+      "step": 217
+    },
+    {
+      "epoch": 1.9377777777777778,
+      "grad_norm": 1.25,
+      "learning_rate": 6.937577932260515e-05,
+      "loss": 0.7898,
+      "step": 218
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.905351881751372e-05,
+      "loss": 0.8289,
+      "step": 219
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 1.125,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.8569,
+      "step": 220
+    },
+    {
+      "epoch": 1.9644444444444444,
+      "grad_norm": 1.2734375,
+      "learning_rate": 6.840622763423391e-05,
+      "loss": 0.8994,
+      "step": 221
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 1.4375,
+      "learning_rate": 6.808122850410461e-05,
+      "loss": 0.8751,
+      "step": 222
+    },
+    {
+      "epoch": 1.982222222222222,
+      "grad_norm": 1.5703125,
+      "learning_rate": 6.775534812040685e-05,
+      "loss": 1.0663,
+      "step": 223
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 1.6328125,
+      "learning_rate": 6.742860236609077e-05,
+      "loss": 1.1425,
+      "step": 224
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.9115,
+      "step": 225
+    },
+    {
+      "epoch": 2.008888888888889,
+      "grad_norm": 1.1953125,
+      "learning_rate": 6.677257848751277e-05,
+      "loss": 0.9296,
+      "step": 226
+    },
+    {
+      "epoch": 2.017777777777778,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.644333233692916e-05,
+      "loss": 1.0117,
+      "step": 227
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 1.765625,
+      "learning_rate": 6.611328476152557e-05,
+      "loss": 0.9275,
+      "step": 228
+    },
+    {
+      "epoch": 2.0355555555555553,
+      "grad_norm": 1.140625,
+      "learning_rate": 6.578245184735513e-05,
+      "loss": 0.9839,
+      "step": 229
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.1015625,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.6496,
+      "step": 230
+    },
+    {
+      "epoch": 2.0533333333333332,
+      "grad_norm": 1.1640625,
+      "learning_rate": 6.511849453752223e-05,
+      "loss": 0.903,
+      "step": 231
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 1.1015625,
+      "learning_rate": 6.478540250220234e-05,
+      "loss": 0.9134,
+      "step": 232
+    },
+    {
+      "epoch": 2.071111111111111,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.445158984722358e-05,
+      "loss": 0.7132,
+      "step": 233
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.3828125,
+      "learning_rate": 6.411707284214384e-05,
+      "loss": 0.7823,
+      "step": 234
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.8642,
+      "step": 235
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 1.40625,
+      "learning_rate": 6.344599103076329e-05,
+      "loss": 0.8489,
+      "step": 236
+    },
+    {
+      "epoch": 2.1066666666666665,
+      "grad_norm": 1.4296875,
+      "learning_rate": 6.310945893204324e-05,
+      "loss": 0.8013,
+      "step": 237
+    },
+    {
+      "epoch": 2.1155555555555554,
+      "grad_norm": 1.3125,
+      "learning_rate": 6.277228789678953e-05,
+      "loss": 0.8753,
+      "step": 238
+    },
+    {
+      "epoch": 2.1244444444444444,
+      "grad_norm": 1.1875,
+      "learning_rate": 6.243449435824276e-05,
+      "loss": 0.8545,
+      "step": 239
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.4140625,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.7864,
+      "step": 240
+    },
+    {
+      "epoch": 2.1422222222222222,
+      "grad_norm": 1.453125,
+      "learning_rate": 6.17571056551295e-05,
+      "loss": 0.9452,
+      "step": 241
+    },
+    {
+      "epoch": 2.151111111111111,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.141754350553279e-05,
+      "loss": 0.8245,
+      "step": 242
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.107742488097338e-05,
+      "loss": 0.8336,
+      "step": 243
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 1.046875,
+      "learning_rate": 6.073676635835317e-05,
+      "loss": 0.729,
+      "step": 244
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 1.0546875,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.7696,
+      "step": 245
+    },
+    {
+      "epoch": 2.1866666666666665,
+      "grad_norm": 0.89453125,
+      "learning_rate": 6.005389605729824e-05,
+      "loss": 0.754,
+      "step": 246
+    },
+    {
+      "epoch": 2.1955555555555555,
+      "grad_norm": 1.109375,
+      "learning_rate": 5.97117175609986e-05,
+      "loss": 0.8451,
+      "step": 247
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 1.28125,
+      "learning_rate": 5.9369065729286245e-05,
+      "loss": 0.9647,
+      "step": 248
+    },
+    {
+      "epoch": 2.2133333333333334,
+      "grad_norm": 1.296875,
+      "learning_rate": 5.902595726252801e-05,
+      "loss": 0.9317,
+      "step": 249
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 2.0,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.1104,
+      "step": 250
+    },
+    {
+      "epoch": 2.2311111111111113,
+      "grad_norm": 1.8203125,
+      "learning_rate": 5.833843733580512e-05,
+      "loss": 0.8364,
+      "step": 251
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 2.140625,
+      "learning_rate": 5.799405938459175e-05,
+      "loss": 0.9288,
+      "step": 252
+    },
+    {
+      "epoch": 2.2488888888888887,
+      "grad_norm": 1.3359375,
+      "learning_rate": 5.764929181420191e-05,
+      "loss": 0.7471,
+      "step": 253
+    },
+    {
+      "epoch": 2.2577777777777777,
+      "grad_norm": 1.5703125,
+      "learning_rate": 5.730415142812059e-05,
+      "loss": 0.826,
+      "step": 254
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 2.25,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.9825,
+      "step": 255
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 1.5,
+      "learning_rate": 5.661281951285613e-05,
+      "loss": 0.8868,
+      "step": 256
+    },
+    {
+      "epoch": 2.2844444444444445,
+      "grad_norm": 1.4921875,
+      "learning_rate": 5.6266661678215216e-05,
+      "loss": 0.8671,
+      "step": 257
+    },
+    {
+      "epoch": 2.2933333333333334,
+      "grad_norm": 1.53125,
+      "learning_rate": 5.5920198415325064e-05,
+      "loss": 0.6903,
+      "step": 258
+    },
+    {
+      "epoch": 2.3022222222222224,
+      "grad_norm": 1.359375,
+      "learning_rate": 5.557344661031627e-05,
+      "loss": 0.7786,
+      "step": 259
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.5703125,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.0231,
+      "step": 260
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 1.3359375,
+      "learning_rate": 5.487914498795747e-05,
+      "loss": 0.7585,
+      "step": 261
+    },
+    {
+      "epoch": 2.328888888888889,
+      "grad_norm": 1.6640625,
+      "learning_rate": 5.453162900988902e-05,
+      "loss": 0.9553,
+      "step": 262
+    },
+    {
+      "epoch": 2.3377777777777777,
+      "grad_norm": 1.3203125,
+      "learning_rate": 5.418389216661579e-05,
+      "loss": 0.7379,
+      "step": 263
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 1.2578125,
+      "learning_rate": 5.383595140634093e-05,
+      "loss": 0.7197,
+      "step": 264
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 1.4765625,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.9332,
+      "step": 265
+    },
+    {
+      "epoch": 2.3644444444444446,
+      "grad_norm": 1.21875,
+      "learning_rate": 5.313952597646568e-05,
+      "loss": 0.8006,
+      "step": 266
+    },
+    {
+      "epoch": 2.3733333333333335,
+      "grad_norm": 1.4609375,
+      "learning_rate": 5.279107524965819e-05,
+      "loss": 0.8995,
+      "step": 267
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.244248848978067e-05,
+      "loss": 1.009,
+      "step": 268
+    },
+    {
+      "epoch": 2.391111111111111,
+      "grad_norm": 1.4140625,
+      "learning_rate": 5.209378268645998e-05,
+      "loss": 1.0106,
+      "step": 269
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8872,
+      "step": 270
+    },
+    {
+      "epoch": 2.408888888888889,
+      "grad_norm": 1.40625,
+      "learning_rate": 5.139608193617845e-05,
+      "loss": 0.7844,
+      "step": 271
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 1.65625,
+      "learning_rate": 5.104712099416785e-05,
+      "loss": 0.9682,
+      "step": 272
+    },
+    {
+      "epoch": 2.4266666666666667,
+      "grad_norm": 1.296875,
+      "learning_rate": 5.0698109016957274e-05,
+      "loss": 0.7677,
+      "step": 273
+    },
+    {
+      "epoch": 2.4355555555555557,
+      "grad_norm": 1.3125,
+      "learning_rate": 5.034906301489808e-05,
+      "loss": 0.807,
+      "step": 274
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.6171875,
+      "learning_rate": 5e-05,
+      "loss": 0.8616,
+      "step": 275
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.965093698510193e-05,
+      "loss": 0.8555,
+      "step": 276
+    },
+    {
+      "epoch": 2.462222222222222,
+      "grad_norm": 1.2734375,
+      "learning_rate": 4.9301890983042744e-05,
+      "loss": 0.9175,
+      "step": 277
+    },
+    {
+      "epoch": 2.471111111111111,
+      "grad_norm": 1.25,
+      "learning_rate": 4.895287900583216e-05,
+      "loss": 0.8347,
+      "step": 278
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.1875,
+      "learning_rate": 4.860391806382157e-05,
+      "loss": 0.6997,
+      "step": 279
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 1.5546875,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7535,
+      "step": 280
+    },
+    {
+      "epoch": 2.497777777777778,
+      "grad_norm": 1.75,
+      "learning_rate": 4.790621731354003e-05,
+      "loss": 0.6498,
+      "step": 281
+    },
+    {
+      "epoch": 2.506666666666667,
+      "grad_norm": 1.59375,
+      "learning_rate": 4.755751151021934e-05,
+      "loss": 0.8289,
+      "step": 282
+    },
+    {
+      "epoch": 2.5155555555555553,
+      "grad_norm": 1.1796875,
+      "learning_rate": 4.720892475034181e-05,
+      "loss": 0.7781,
+      "step": 283
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 1.3359375,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 0.887,
+      "step": 284
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 1.546875,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.9711,
+      "step": 285
+    },
+    {
+      "epoch": 2.542222222222222,
+      "grad_norm": 1.03125,
+      "learning_rate": 4.616404859365907e-05,
+      "loss": 0.7761,
+      "step": 286
+    },
+    {
+      "epoch": 2.551111111111111,
+      "grad_norm": 1.203125,
+      "learning_rate": 4.5816107833384234e-05,
+      "loss": 0.8821,
+      "step": 287
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.0859375,
+      "learning_rate": 4.5468370990111006e-05,
+      "loss": 0.9093,
+      "step": 288
+    },
+    {
+      "epoch": 2.568888888888889,
+      "grad_norm": 1.296875,
+      "learning_rate": 4.512085501204253e-05,
+      "loss": 0.8367,
+      "step": 289
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 1.2265625,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8892,
+      "step": 290
+    },
+    {
+      "epoch": 2.586666666666667,
+      "grad_norm": 1.234375,
+      "learning_rate": 4.442655338968373e-05,
+      "loss": 0.8095,
+      "step": 291
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 1.2421875,
+      "learning_rate": 4.407980158467495e-05,
+      "loss": 0.6999,
+      "step": 292
+    },
+    {
+      "epoch": 2.6044444444444443,
+      "grad_norm": 1.375,
+      "learning_rate": 4.373333832178478e-05,
+      "loss": 0.9533,
+      "step": 293
+    },
+    {
+      "epoch": 2.6133333333333333,
+      "grad_norm": 1.1484375,
+      "learning_rate": 4.3387180487143876e-05,
+      "loss": 1.0029,
+      "step": 294
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 1.140625,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.8176,
+      "step": 295
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 1.140625,
+      "learning_rate": 4.269584857187943e-05,
+      "loss": 0.7422,
+      "step": 296
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 1.6484375,
+      "learning_rate": 4.23507081857981e-05,
+      "loss": 0.9981,
+      "step": 297
+    },
+    {
+      "epoch": 2.648888888888889,
+      "grad_norm": 1.4921875,
+      "learning_rate": 4.2005940615408264e-05,
+      "loss": 0.7285,
+      "step": 298
+    },
+    {
+      "epoch": 2.6577777777777776,
+      "grad_norm": 1.1484375,
+      "learning_rate": 4.166156266419489e-05,
+      "loss": 0.7904,
+      "step": 299
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.7890625,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8762,
+      "step": 300
+    },
+    {
+      "epoch": 2.6755555555555555,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.0974042737472006e-05,
+      "loss": 0.7147,
+      "step": 301
+    },
+    {
+      "epoch": 2.6844444444444444,
+      "grad_norm": 1.8671875,
+      "learning_rate": 4.063093427071376e-05,
+      "loss": 0.8428,
+      "step": 302
+    },
+    {
+      "epoch": 2.6933333333333334,
+      "grad_norm": 1.9765625,
+      "learning_rate": 4.028828243900141e-05,
+      "loss": 0.9927,
+      "step": 303
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 2.25,
+      "learning_rate": 3.9946103942701777e-05,
+      "loss": 0.882,
+      "step": 304
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 2.3125,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.9207,
+      "step": 305
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 1.5390625,
+      "learning_rate": 3.926323364164684e-05,
+      "loss": 0.9289,
+      "step": 306
+    },
+    {
+      "epoch": 2.728888888888889,
+      "grad_norm": 1.8671875,
+      "learning_rate": 3.892257511902664e-05,
+      "loss": 0.972,
+      "step": 307
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 1.8515625,
+      "learning_rate": 3.858245649446721e-05,
+      "loss": 0.8648,
+      "step": 308
+    },
+    {
+      "epoch": 2.7466666666666666,
+      "grad_norm": 1.734375,
+      "learning_rate": 3.82428943448705e-05,
+      "loss": 0.7915,
+      "step": 309
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 1.703125,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.9658,
+      "step": 310
+    },
+    {
+      "epoch": 2.7644444444444445,
+      "grad_norm": 1.7734375,
+      "learning_rate": 3.756550564175727e-05,
+      "loss": 0.9002,
+      "step": 311
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 1.25,
+      "learning_rate": 3.7227712103210486e-05,
+      "loss": 0.671,
+      "step": 312
+    },
+    {
+      "epoch": 2.7822222222222224,
+      "grad_norm": 1.4375,
+      "learning_rate": 3.6890541067956776e-05,
+      "loss": 0.8574,
+      "step": 313
+    },
+    {
+      "epoch": 2.7911111111111113,
+      "grad_norm": 1.84375,
+      "learning_rate": 3.655400896923672e-05,
+      "loss": 1.0365,
+      "step": 314
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.359375,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.8598,
+      "step": 315
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 1.3125,
+      "learning_rate": 3.588292715785617e-05,
+      "loss": 0.8167,
+      "step": 316
+    },
+    {
+      "epoch": 2.8177777777777777,
+      "grad_norm": 1.4921875,
+      "learning_rate": 3.554841015277641e-05,
+      "loss": 0.8554,
+      "step": 317
+    },
+    {
+      "epoch": 2.8266666666666667,
+      "grad_norm": 1.4140625,
+      "learning_rate": 3.5214597497797684e-05,
+      "loss": 0.9625,
+      "step": 318
+    },
+    {
+      "epoch": 2.8355555555555556,
+      "grad_norm": 1.6875,
+      "learning_rate": 3.488150546247778e-05,
+      "loss": 0.9035,
+      "step": 319
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.671875,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.85,
+      "step": 320
+    },
+    {
+      "epoch": 2.8533333333333335,
+      "grad_norm": 1.4296875,
+      "learning_rate": 3.4217548152644885e-05,
+      "loss": 1.1274,
+      "step": 321
+    },
+    {
+      "epoch": 2.862222222222222,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.388671523847445e-05,
+      "loss": 0.7901,
+      "step": 322
+    },
+    {
+      "epoch": 2.871111111111111,
+      "grad_norm": 1.234375,
+      "learning_rate": 3.355666766307084e-05,
+      "loss": 0.9324,
+      "step": 323
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.109375,
+      "learning_rate": 3.322742151248725e-05,
+      "loss": 0.8024,
+      "step": 324
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 2.4375,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.9827,
+      "step": 325
+    },
+    {
+      "epoch": 2.897777777777778,
+      "grad_norm": 1.1875,
+      "learning_rate": 3.257139763390925e-05,
+      "loss": 0.8115,
+      "step": 326
+    },
+    {
+      "epoch": 2.9066666666666667,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.224465187959316e-05,
+      "loss": 0.8628,
+      "step": 327
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 1.125,
+      "learning_rate": 3.1918771495895396e-05,
+      "loss": 0.8138,
+      "step": 328
+    },
+    {
+      "epoch": 2.924444444444444,
+      "grad_norm": 1.34375,
+      "learning_rate": 3.1593772365766105e-05,
+      "loss": 0.7686,
+      "step": 329
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 1.171875,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.861,
+      "step": 330
+    },
+    {
+      "epoch": 2.942222222222222,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.09464811824863e-05,
+      "loss": 0.7815,
+      "step": 331
+    },
+    {
+      "epoch": 2.951111111111111,
+      "grad_norm": 1.296875,
+      "learning_rate": 3.062422067739485e-05,
+      "loss": 0.8253,
+      "step": 332
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 1.2890625,
+      "learning_rate": 3.0302904520452447e-05,
+      "loss": 0.8101,
+      "step": 333
+    },
+    {
+      "epoch": 2.968888888888889,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.9982548372155263e-05,
+      "loss": 0.828,
+      "step": 334
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 1.6953125,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.7968,
+      "step": 335
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 1.640625,
+      "learning_rate": 2.934477850877292e-05,
+      "loss": 1.0188,
+      "step": 336
+    },
+    {
+      "epoch": 2.9955555555555557,
+      "grad_norm": 1.421875,
+      "learning_rate": 2.9027395877691144e-05,
+      "loss": 0.8255,
+      "step": 337
+    },
+    {
+      "epoch": 3.0044444444444443,
+      "grad_norm": 1.109375,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 0.6085,
+      "step": 338
+    },
+    {
+      "epoch": 3.013333333333333,
+      "grad_norm": 0.99609375,
+      "learning_rate": 2.8395712559900877e-05,
+      "loss": 0.7823,
+      "step": 339
+    },
+    {
+      "epoch": 3.022222222222222,
+      "grad_norm": 1.2265625,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.8947,
+      "step": 340
+    },
+    {
+      "epoch": 3.031111111111111,
+      "grad_norm": 1.140625,
+      "learning_rate": 2.776824104075364e-05,
+      "loss": 0.8595,
+      "step": 341
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 1.265625,
+      "learning_rate": 2.7456122965528475e-05,
+      "loss": 0.829,
+      "step": 342
+    },
+    {
+      "epoch": 3.048888888888889,
+      "grad_norm": 0.94921875,
+      "learning_rate": 2.7145103647065308e-05,
+      "loss": 0.5761,
+      "step": 343
+    },
+    {
+      "epoch": 3.057777777777778,
+      "grad_norm": 1.1328125,
+      "learning_rate": 2.6835198244006927e-05,
+      "loss": 0.7939,
+      "step": 344
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 1.0703125,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.6288,
+      "step": 345
+    },
+    {
+      "epoch": 3.0755555555555554,
+      "grad_norm": 1.15625,
+      "learning_rate": 2.6218789546486234e-05,
+      "loss": 0.7359,
+      "step": 346
+    },
+    {
+      "epoch": 3.0844444444444443,
+      "grad_norm": 1.3359375,
+      "learning_rate": 2.591231629491423e-05,
+      "loss": 0.7755,
+      "step": 347
+    },
+    {
+      "epoch": 3.0933333333333333,
+      "grad_norm": 1.2734375,
+      "learning_rate": 2.560701704306336e-05,
+      "loss": 0.6429,
+      "step": 348
+    },
+    {
+      "epoch": 3.102222222222222,
+      "grad_norm": 1.28125,
+      "learning_rate": 2.5302906670788462e-05,
+      "loss": 0.7758,
+      "step": 349
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 2.109375,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6468,
+      "step": 350
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 2.0,
+      "learning_rate": 2.469831179394182e-05,
+      "loss": 0.6939,
+      "step": 351
+    },
+    {
+      "epoch": 3.128888888888889,
+      "grad_norm": 2.109375,
+      "learning_rate": 2.4397856756471432e-05,
+      "loss": 0.8737,
+      "step": 352
+    },
+    {
+      "epoch": 3.137777777777778,
+      "grad_norm": 2.0,
+      "learning_rate": 2.4098649531343497e-05,
+      "loss": 0.6743,
+      "step": 353
+    },
+    {
+      "epoch": 3.1466666666666665,
+      "grad_norm": 2.03125,
+      "learning_rate": 2.3800704701496053e-05,
+      "loss": 0.7847,
+      "step": 354
+    },
+    {
+      "epoch": 3.1555555555555554,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.8001,
+      "step": 355
+    },
+    {
+      "epoch": 3.1644444444444444,
+      "grad_norm": 1.578125,
+      "learning_rate": 2.3208660251050158e-05,
+      "loss": 0.7351,
+      "step": 356
+    },
+    {
+      "epoch": 3.1733333333333333,
+      "grad_norm": 1.9296875,
+      "learning_rate": 2.2914589485863014e-05,
+      "loss": 0.7505,
+      "step": 357
+    },
+    {
+      "epoch": 3.1822222222222223,
+      "grad_norm": 2.609375,
+      "learning_rate": 2.2621838825372493e-05,
+      "loss": 0.8125,
+      "step": 358
+    },
+    {
+      "epoch": 3.1911111111111112,
+      "grad_norm": 1.8046875,
+      "learning_rate": 2.23304225378328e-05,
+      "loss": 0.8101,
+      "step": 359
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.6484375,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.8313,
+      "step": 360
+    },
+    {
+      "epoch": 3.2088888888888887,
+      "grad_norm": 1.390625,
+      "learning_rate": 2.1751649828753106e-05,
+      "loss": 0.6678,
+      "step": 361
+    },
+    {
+      "epoch": 3.2177777777777776,
+      "grad_norm": 1.59375,
+      "learning_rate": 2.1464321615778422e-05,
+      "loss": 0.7392,
+      "step": 362
+    },
+    {
+      "epoch": 3.2266666666666666,
+      "grad_norm": 1.484375,
+      "learning_rate": 2.117838419151034e-05,
+      "loss": 0.6166,
+      "step": 363
+    },
+    {
+      "epoch": 3.2355555555555555,
+      "grad_norm": 1.3515625,
+      "learning_rate": 2.0893851492135537e-05,
+      "loss": 0.5738,
+      "step": 364
+    },
+    {
+      "epoch": 3.2444444444444445,
+      "grad_norm": 1.453125,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6822,
+      "step": 365
+    },
+    {
+      "epoch": 3.2533333333333334,
+      "grad_norm": 1.625,
+      "learning_rate": 2.0329055669814934e-05,
+      "loss": 0.9337,
+      "step": 366
+    },
+    {
+      "epoch": 3.2622222222222224,
+      "grad_norm": 1.828125,
+      "learning_rate": 2.0048820074220715e-05,
+      "loss": 0.8167,
+      "step": 367
+    },
+    {
+      "epoch": 3.2711111111111113,
+      "grad_norm": 1.515625,
+      "learning_rate": 1.977004425688126e-05,
+      "loss": 0.7508,
+      "step": 368
+    },
+    {
+      "epoch": 3.2800000000000002,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.9492741804936622e-05,
+      "loss": 0.745,
+      "step": 369
+    },
+    {
+      "epoch": 3.2888888888888888,
+      "grad_norm": 1.671875,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.8252,
+      "step": 370
+    },
+    {
+      "epoch": 3.2977777777777777,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.8942610986084486e-05,
+      "loss": 0.6201,
+      "step": 371
+    },
+    {
+      "epoch": 3.3066666666666666,
+      "grad_norm": 1.5,
+      "learning_rate": 1.866980943177699e-05,
+      "loss": 0.6965,
+      "step": 372
+    },
+    {
+      "epoch": 3.3155555555555556,
+      "grad_norm": 1.765625,
+      "learning_rate": 1.8398534866757454e-05,
+      "loss": 0.7522,
+      "step": 373
+    },
+    {
+      "epoch": 3.3244444444444445,
+      "grad_norm": 1.9296875,
+      "learning_rate": 1.8128800512565513e-05,
+      "loss": 0.7584,
+      "step": 374
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.6047,
+      "step": 375
+    },
+    {
+      "epoch": 3.3422222222222224,
+      "grad_norm": 2.0625,
+      "learning_rate": 1.7594004946843456e-05,
+      "loss": 0.77,
+      "step": 376
+    },
+    {
+      "epoch": 3.351111111111111,
+      "grad_norm": 1.984375,
+      "learning_rate": 1.7328969800494726e-05,
+      "loss": 0.7815,
+      "step": 377
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.7065526994065973e-05,
+      "loss": 0.7838,
+      "step": 378
+    },
+    {
+      "epoch": 3.368888888888889,
+      "grad_norm": 1.7265625,
+      "learning_rate": 1.680368936738792e-05,
+      "loss": 0.7368,
+      "step": 379
+    },
+    {
+      "epoch": 3.3777777777777778,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.8079,
+      "step": 380
+    },
+    {
+      "epoch": 3.3866666666666667,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.6284880620813848e-05,
+      "loss": 0.9025,
+      "step": 381
+    },
+    {
+      "epoch": 3.3955555555555557,
+      "grad_norm": 1.5,
+      "learning_rate": 1.602793478692419e-05,
+      "loss": 0.8089,
+      "step": 382
+    },
+    {
+      "epoch": 3.4044444444444446,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.5772644703565565e-05,
+      "loss": 0.6786,
+      "step": 383
+    },
+    {
+      "epoch": 3.413333333333333,
+      "grad_norm": 1.5,
+      "learning_rate": 1.551902281321651e-05,
+      "loss": 0.6152,
+      "step": 384
+    },
+    {
+      "epoch": 3.422222222222222,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.5888,
+      "step": 385
+    },
+    {
+      "epoch": 3.431111111111111,
+      "grad_norm": 1.8125,
+      "learning_rate": 1.5016832974331724e-05,
+      "loss": 0.8046,
+      "step": 386
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 1.6328125,
+      "learning_rate": 1.4768289501820265e-05,
+      "loss": 0.7949,
+      "step": 387
+    },
+    {
+      "epoch": 3.448888888888889,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.4521463173173965e-05,
+      "loss": 0.6952,
+      "step": 388
+    },
+    {
+      "epoch": 3.457777777777778,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.4276366018359844e-05,
+      "loss": 0.7142,
+      "step": 389
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.8104,
+      "step": 390
+    },
+    {
+      "epoch": 3.4755555555555557,
+      "grad_norm": 2.203125,
+      "learning_rate": 1.3791406928126638e-05,
+      "loss": 0.8418,
+      "step": 391
+    },
+    {
+      "epoch": 3.4844444444444447,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 0.6546,
+      "step": 392
+    },
+    {
+      "epoch": 3.493333333333333,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.3313506774856177e-05,
+      "loss": 0.8296,
+      "step": 393
+    },
+    {
+      "epoch": 3.502222222222222,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.3077232968705805e-05,
+      "loss": 0.7203,
+      "step": 394
+    },
+    {
+      "epoch": 3.511111111111111,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.6301,
+      "step": 395
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.2610095475073414e-05,
+      "loss": 0.7751,
+      "step": 396
+    },
+    {
+      "epoch": 3.528888888888889,
+      "grad_norm": 1.59375,
+      "learning_rate": 1.2379254555213788e-05,
+      "loss": 0.7448,
+      "step": 397
+    },
+    {
+      "epoch": 3.537777777777778,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.2150247217412186e-05,
+      "loss": 0.6768,
+      "step": 398
+    },
+    {
+      "epoch": 3.546666666666667,
+      "grad_norm": 1.4765625,
+      "learning_rate": 1.1923084623163172e-05,
+      "loss": 0.7193,
+      "step": 399
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6328,
+      "step": 400
+    },
+    {
+      "epoch": 3.5644444444444443,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.1474337861210543e-05,
+      "loss": 0.727,
+      "step": 401
+    },
+    {
+      "epoch": 3.5733333333333333,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.1252775564791024e-05,
+      "loss": 0.7467,
+      "step": 402
+    },
+    {
+      "epoch": 3.582222222222222,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.1033101753426283e-05,
+      "loss": 0.7672,
+      "step": 403
+    },
+    {
+      "epoch": 3.591111111111111,
+      "grad_norm": 1.84375,
+      "learning_rate": 1.0815327133708015e-05,
+      "loss": 0.7215,
+      "step": 404
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.6078,
+      "step": 405
+    },
+    {
+      "epoch": 3.608888888888889,
+      "grad_norm": 1.7890625,
+      "learning_rate": 1.0385517832240471e-05,
+      "loss": 0.7894,
+      "step": 406
+    },
+    {
+      "epoch": 3.6177777777777775,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.0173504098790187e-05,
+      "loss": 0.7391,
+      "step": 407
+    },
+    {
+      "epoch": 3.626666666666667,
+      "grad_norm": 2.296875,
+      "learning_rate": 9.963431452563332e-06,
+      "loss": 0.6962,
+      "step": 408
+    },
+    {
+      "epoch": 3.6355555555555554,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.755310132204298e-06,
+      "loss": 0.8193,
+      "step": 409
+    },
+    {
+      "epoch": 3.6444444444444444,
+      "grad_norm": 2.140625,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.7433,
+      "step": 410
+    },
+    {
+      "epoch": 3.6533333333333333,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.344961947648623e-06,
+      "loss": 0.5545,
+      "step": 411
+    },
+    {
+      "epoch": 3.6622222222222223,
+      "grad_norm": 2.546875,
+      "learning_rate": 9.142755083243576e-06,
+      "loss": 0.938,
+      "step": 412
+    },
+    {
+      "epoch": 3.671111111111111,
+      "grad_norm": 2.203125,
+      "learning_rate": 8.9425395433148e-06,
+      "loss": 0.8629,
+      "step": 413
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 2.15625,
+      "learning_rate": 8.744325086085248e-06,
+      "loss": 0.8981,
+      "step": 414
+    },
+    {
+      "epoch": 3.688888888888889,
+      "grad_norm": 2.0,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.7164,
+      "step": 415
+    },
+    {
+      "epoch": 3.6977777777777776,
+      "grad_norm": 1.7421875,
+      "learning_rate": 8.353937964495029e-06,
+      "loss": 0.7385,
+      "step": 416
+    },
+    {
+      "epoch": 3.7066666666666666,
+      "grad_norm": 1.921875,
+      "learning_rate": 8.16178432705192e-06,
+      "loss": 0.6595,
+      "step": 417
+    },
+    {
+      "epoch": 3.7155555555555555,
+      "grad_norm": 1.8203125,
+      "learning_rate": 7.971669825215788e-06,
+      "loss": 0.7062,
+      "step": 418
+    },
+    {
+      "epoch": 3.7244444444444444,
+      "grad_norm": 2.34375,
+      "learning_rate": 7.783603724899257e-06,
+      "loss": 0.8843,
+      "step": 419
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 1.734375,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6351,
+      "step": 420
+    },
+    {
+      "epoch": 3.7422222222222223,
+      "grad_norm": 2.03125,
+      "learning_rate": 7.413653292847617e-06,
+      "loss": 0.7729,
+      "step": 421
+    },
+    {
+      "epoch": 3.7511111111111113,
+      "grad_norm": 2.140625,
+      "learning_rate": 7.2317869919746705e-06,
+      "loss": 0.8741,
+      "step": 422
+    },
+    {
+      "epoch": 3.76,
+      "grad_norm": 1.6953125,
+      "learning_rate": 7.052005153466779e-06,
+      "loss": 0.7252,
+      "step": 423
+    },
+    {
+      "epoch": 3.7688888888888887,
+      "grad_norm": 1.90625,
+      "learning_rate": 6.874316539637127e-06,
+      "loss": 0.6773,
+      "step": 424
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 2.28125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6376,
+      "step": 425
+    },
+    {
+      "epoch": 3.7866666666666666,
+      "grad_norm": 1.7421875,
+      "learning_rate": 6.52525352473905e-06,
+      "loss": 0.7645,
+      "step": 426
+    },
+    {
+      "epoch": 3.7955555555555556,
+      "grad_norm": 2.0625,
+      "learning_rate": 6.353896136509524e-06,
+      "loss": 0.797,
+      "step": 427
+    },
+    {
+      "epoch": 3.8044444444444445,
+      "grad_norm": 1.6796875,
+      "learning_rate": 6.184665997806832e-06,
+      "loss": 0.7175,
+      "step": 428
+    },
+    {
+      "epoch": 3.8133333333333335,
+      "grad_norm": 1.9921875,
+      "learning_rate": 6.017571356669183e-06,
+      "loss": 0.8561,
+      "step": 429
+    },
+    {
+      "epoch": 3.822222222222222,
+      "grad_norm": 1.8359375,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.5715,
+      "step": 430
+    },
+    {
+      "epoch": 3.8311111111111114,
+      "grad_norm": 1.6875,
+      "learning_rate": 5.689821038439263e-06,
+      "loss": 0.68,
+      "step": 431
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 2.125,
+      "learning_rate": 5.529181335435124e-06,
+      "loss": 0.7089,
+      "step": 432
+    },
+    {
+      "epoch": 3.848888888888889,
+      "grad_norm": 1.734375,
+      "learning_rate": 5.370709077393721e-06,
+      "loss": 0.7589,
+      "step": 433
+    },
+    {
+      "epoch": 3.8577777777777778,
+      "grad_norm": 1.71875,
+      "learning_rate": 5.214411988029355e-06,
+      "loss": 0.7617,
+      "step": 434
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 1.78125,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.9029,
+      "step": 435
+    },
+    {
+      "epoch": 3.8755555555555556,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.908373679744316e-06,
+      "loss": 0.6779,
+      "step": 436
+    },
+    {
+      "epoch": 3.8844444444444446,
+      "grad_norm": 2.0,
+      "learning_rate": 4.758647376699032e-06,
+      "loss": 0.8606,
+      "step": 437
+    },
+    {
+      "epoch": 3.8933333333333335,
+      "grad_norm": 2.109375,
+      "learning_rate": 4.611126073354571e-06,
+      "loss": 0.7648,
+      "step": 438
+    },
+    {
+      "epoch": 3.902222222222222,
+      "grad_norm": 1.6328125,
+      "learning_rate": 4.465816959691149e-06,
+      "loss": 0.6418,
+      "step": 439
+    },
+    {
+      "epoch": 3.911111111111111,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.7436,
+      "step": 440
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 1.71875,
+      "learning_rate": 4.181863521888019e-06,
+      "loss": 0.7485,
+      "step": 441
+    },
+    {
+      "epoch": 3.928888888888889,
+      "grad_norm": 2.015625,
+      "learning_rate": 4.043233037238281e-06,
+      "loss": 0.7783,
+      "step": 442
+    },
+    {
+      "epoch": 3.937777777777778,
+      "grad_norm": 1.6640625,
+      "learning_rate": 3.90684242057498e-06,
+      "loss": 0.5753,
+      "step": 443
+    },
+    {
+      "epoch": 3.9466666666666668,
+      "grad_norm": 1.7109375,
+      "learning_rate": 3.772698319384349e-06,
+      "loss": 0.6734,
+      "step": 444
+    },
+    {
+      "epoch": 3.9555555555555557,
+      "grad_norm": 1.6953125,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.7748,
+      "step": 445
+    },
+    {
+      "epoch": 3.964444444444444,
+      "grad_norm": 1.765625,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 0.7126,
+      "step": 446
+    },
+    {
+      "epoch": 3.9733333333333336,
+      "grad_norm": 1.875,
+      "learning_rate": 3.3838099392243916e-06,
+      "loss": 0.7099,
+      "step": 447
+    },
+    {
+      "epoch": 3.982222222222222,
+      "grad_norm": 2.296875,
+      "learning_rate": 3.258716180199278e-06,
+      "loss": 0.9139,
+      "step": 448
+    },
+    {
+      "epoch": 3.991111111111111,
+      "grad_norm": 2.34375,
+      "learning_rate": 3.1359005254054273e-06,
+      "loss": 0.7272,
+      "step": 449
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.875,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8561,
+      "step": 450
+    },
+    {
+      "epoch": 4.0088888888888885,
+      "grad_norm": 1.8515625,
+      "learning_rate": 2.8971273606351658e-06,
+      "loss": 0.7015,
+      "step": 451
+    },
+    {
+      "epoch": 4.017777777777778,
+      "grad_norm": 1.71875,
+      "learning_rate": 2.7811814881259503e-06,
+      "loss": 0.6025,
+      "step": 452
+    },
+    {
+      "epoch": 4.026666666666666,
+      "grad_norm": 2.125,
+      "learning_rate": 2.667536994215186e-06,
+      "loss": 0.7018,
+      "step": 453
+    },
+    {
+      "epoch": 4.035555555555556,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.5561994177751737e-06,
+      "loss": 0.6452,
+      "step": 454
+    },
+    {
+      "epoch": 4.044444444444444,
+      "grad_norm": 2.140625,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.573,
+      "step": 455
+    },
+    {
+      "epoch": 4.053333333333334,
+      "grad_norm": 2.34375,
+      "learning_rate": 2.340466610352654e-06,
+      "loss": 0.6177,
+      "step": 456
+    },
+    {
+      "epoch": 4.062222222222222,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.2360818938828187e-06,
+      "loss": 0.6479,
+      "step": 457
+    },
+    {
+      "epoch": 4.071111111111111,
+      "grad_norm": 1.7578125,
+      "learning_rate": 2.134025123396638e-06,
+      "loss": 0.6464,
+      "step": 458
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 2.140625,
+      "learning_rate": 2.0343012729971243e-06,
+      "loss": 0.6545,
+      "step": 459
+    },
+    {
+      "epoch": 4.088888888888889,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6401,
+      "step": 460
+    },
+    {
+      "epoch": 4.097777777777778,
+      "grad_norm": 1.75,
+      "learning_rate": 1.841871660117095e-06,
+      "loss": 0.5654,
+      "step": 461
+    },
+    {
+      "epoch": 4.1066666666666665,
+      "grad_norm": 1.859375,
+      "learning_rate": 1.7491752763844293e-06,
+      "loss": 0.6355,
+      "step": 462
+    },
+    {
+      "epoch": 4.115555555555556,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.6588305697770313e-06,
+      "loss": 0.8252,
+      "step": 463
+    },
+    {
+      "epoch": 4.124444444444444,
+      "grad_norm": 2.078125,
+      "learning_rate": 1.5708419435684462e-06,
+      "loss": 0.573,
+      "step": 464
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 2.8125,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.6218,
+      "step": 465
+    },
+    {
+      "epoch": 4.142222222222222,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.4019499710726913e-06,
+      "loss": 0.5241,
+      "step": 466
+    },
+    {
+      "epoch": 4.151111111111111,
+      "grad_norm": 1.8671875,
+      "learning_rate": 1.3210548563419856e-06,
+      "loss": 0.6395,
+      "step": 467
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.2425322847218368e-06,
+      "loss": 0.7088,
+      "step": 468
+    },
+    {
+      "epoch": 4.168888888888889,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.166386083291604e-06,
+      "loss": 0.7894,
+      "step": 469
+    },
+    {
+      "epoch": 4.177777777777778,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6565,
+      "step": 470
+    },
+    {
+      "epoch": 4.1866666666666665,
+      "grad_norm": 1.8046875,
+      "learning_rate": 1.0212375200327973e-06,
+      "loss": 0.5306,
+      "step": 471
+    },
+    {
+      "epoch": 4.195555555555556,
+      "grad_norm": 1.8125,
+      "learning_rate": 9.522422325404235e-07,
+      "loss": 0.6762,
+      "step": 472
+    },
+    {
+      "epoch": 4.204444444444444,
+      "grad_norm": 1.6171875,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 0.5428,
+      "step": 473
+    },
+    {
+      "epoch": 4.213333333333333,
+      "grad_norm": 1.9375,
+      "learning_rate": 8.214264593307098e-07,
+      "loss": 0.6506,
+      "step": 474
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 2.046875,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.5546,
+      "step": 475
+    },
+    {
+      "epoch": 4.231111111111111,
+      "grad_norm": 1.7578125,
+      "learning_rate": 7.001981464747565e-07,
+      "loss": 0.6947,
+      "step": 476
+    },
+    {
+      "epoch": 4.24,
+      "grad_norm": 2.046875,
+      "learning_rate": 6.431867463506048e-07,
+      "loss": 0.8005,
+      "step": 477
+    },
+    {
+      "epoch": 4.248888888888889,
+      "grad_norm": 2.03125,
+      "learning_rate": 5.885809276723608e-07,
+      "loss": 0.7249,
+      "step": 478
+    },
+    {
+      "epoch": 4.257777777777778,
+      "grad_norm": 2.171875,
+      "learning_rate": 5.363833518505834e-07,
+      "loss": 0.7854,
+      "step": 479
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 2.484375,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.762,
+      "step": 480
+    },
+    {
+      "epoch": 4.275555555555556,
+      "grad_norm": 1.9609375,
+      "learning_rate": 4.392229874229159e-07,
+      "loss": 0.7091,
+      "step": 481
+    },
+    {
+      "epoch": 4.2844444444444445,
+      "grad_norm": 1.8671875,
+      "learning_rate": 3.9426493427611177e-07,
+      "loss": 0.6231,
+      "step": 482
+    },
+    {
+      "epoch": 4.293333333333333,
+      "grad_norm": 2.203125,
+      "learning_rate": 3.517245946731529e-07,
+      "loss": 0.7348,
+      "step": 483
+    },
+    {
+      "epoch": 4.302222222222222,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.1160404197018154e-07,
+      "loss": 0.531,
+      "step": 484
+    },
+    {
+      "epoch": 4.311111111111111,
+      "grad_norm": 2.015625,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.5834,
+      "step": 485
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 1.875,
+      "learning_rate": 2.386300009084408e-07,
+      "loss": 0.5736,
+      "step": 486
+    },
+    {
+      "epoch": 4.328888888888889,
+      "grad_norm": 1.8828125,
+      "learning_rate": 2.057800692014833e-07,
+      "loss": 0.4758,
+      "step": 487
+    },
+    {
+      "epoch": 4.337777777777778,
+      "grad_norm": 1.890625,
+      "learning_rate": 1.753570375247815e-07,
+      "loss": 0.4747,
+      "step": 488
+    },
+    {
+      "epoch": 4.346666666666667,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.4736238865398765e-07,
+      "loss": 0.6023,
+      "step": 489
+    },
+    {
+      "epoch": 4.355555555555555,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6376,
+      "step": 490
+    },
+    {
+      "epoch": 4.364444444444445,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.866357858642205e-08,
+      "loss": 0.5588,
+      "step": 491
+    },
+    {
+      "epoch": 4.373333333333333,
+      "grad_norm": 2.0,
+      "learning_rate": 7.796179090094891e-08,
+      "loss": 0.6635,
+      "step": 492
+    },
+    {
+      "epoch": 4.3822222222222225,
+      "grad_norm": 2.109375,
+      "learning_rate": 5.969313292830125e-08,
+      "loss": 0.5795,
+      "step": 493
+    },
+    {
+      "epoch": 4.391111111111111,
+      "grad_norm": 1.7734375,
+      "learning_rate": 4.385849505708084e-08,
+      "loss": 0.5087,
+      "step": 494
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5711,
+      "step": 495
+    },
+    {
+      "epoch": 4.408888888888889,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.949424798228239e-08,
+      "loss": 0.6284,
+      "step": 496
+    },
+    {
+      "epoch": 4.417777777777777,
+      "grad_norm": 2.5,
+      "learning_rate": 1.096582625772502e-08,
+      "loss": 0.7002,
+      "step": 497
+    },
+    {
+      "epoch": 4.426666666666667,
+      "grad_norm": 2.046875,
+      "learning_rate": 4.873799534788059e-09,
+      "loss": 0.5831,
+      "step": 498
+    },
+    {
+      "epoch": 4.435555555555555,
+      "grad_norm": 1.9609375,
+      "learning_rate": 1.2184647302626583e-09,
+      "loss": 0.5923,
+      "step": 499
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 2.15625,
+      "learning_rate": 0.0,
+      "loss": 0.6272,
+      "step": 500
+    },
+    {
+      "epoch": 4.444444444444445,
+      "eval_loss": 0.996656596660614,
+      "eval_runtime": 10.8023,
+      "eval_samples_per_second": 9.257,
+      "eval_steps_per_second": 9.257,
+      "step": 500
+    },
+    {
+      "epoch": 4.444444444444445,
+      "step": 500,
+      "total_flos": 2.953325949045965e+16,
+      "train_loss": 0.8754597247838974,
+      "train_runtime": 1354.7094,
+      "train_samples_per_second": 2.953,
+      "train_steps_per_second": 0.369
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.953325949045965e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0696888f178dbdc84cc2260ca4ff69e7fb438f163ee3391251597831c8cc404
+size 5368