Upload folder using huggingface_hub

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- barc0/transduction_rearc
+model-index:
+- name: barc-llama3.1-8b-instruct-fft-sft-transduction_rearc_lr4e-5_epoch2
+  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. -->
+
+# barc-llama3.1-8b-instruct-fft-sft-transduction_rearc_lr4e-5_epoch2
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the barc0/transduction_rearc dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2794
+
+## 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: 4e-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3971        | 0.9981 | 259  | 0.4259          |
+| 0.2353        | 1.9961 | 518  | 0.2794          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.9961464354527938,
+    "eval_loss": 0.27941030263900757,
+    "eval_runtime": 142.8124,
+    "eval_samples": 1998,
+    "eval_samples_per_second": 13.99,
+    "eval_steps_per_second": 0.441,
+    "total_flos": 2.6836433607911014e+17,
+    "train_loss": 0.7686227933723033,
+    "train_runtime": 16387.3806,
+    "train_samples": 33211,
+    "train_samples_per_second": 4.053,
+    "train_steps_per_second": 0.032
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "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": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9961464354527938,
+    "eval_loss": 0.27941030263900757,
+    "eval_runtime": 142.8124,
+    "eval_samples": 1998,
+    "eval_samples_per_second": 13.99,
+    "eval_steps_per_second": 0.441
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0438baac75bf52a3514097140586cbe8f8e9ae882814c04e91ff3712bbe8015
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695bca69cc86d12d135cc55f4892d3d586202c8450113d0af696255c14751d34
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c828be999d445f8779d3f15a8d3ce639d723692d9d8176cb83226562e689c0
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc2f1897cde8c347d682eac0b65e28acd76fc2ff7f5691edc217f988b64ae1e2
+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 +1,2063 @@
+{
+  "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": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9961464354527938,
+    "total_flos": 2.6836433607911014e+17,
+    "train_loss": 0.7686227933723033,
+    "train_runtime": 16387.3806,
+    "train_samples": 33211,
+    "train_samples_per_second": 4.053,
+    "train_steps_per_second": 0.032
+}

trainer_state.json

@@ -0,0 +1,3684 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9961464354527938,
+  "eval_steps": 500,
+  "global_step": 518,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0038535645472061657,
+      "grad_norm": 1432.749671594044,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 11.5124,
+      "step": 1
+    },
+    {
+      "epoch": 0.007707129094412331,
+      "grad_norm": 1357.8414028391733,
+      "learning_rate": 1.5384615384615387e-06,
+      "loss": 11.4455,
+      "step": 2
+    },
+    {
+      "epoch": 0.011560693641618497,
+      "grad_norm": 1337.1958013405376,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 11.2831,
+      "step": 3
+    },
+    {
+      "epoch": 0.015414258188824663,
+      "grad_norm": 916.8677401776845,
+      "learning_rate": 3.0769230769230774e-06,
+      "loss": 9.6523,
+      "step": 4
+    },
+    {
+      "epoch": 0.019267822736030827,
+      "grad_norm": 668.9521736359394,
+      "learning_rate": 3.846153846153847e-06,
+      "loss": 7.3813,
+      "step": 5
+    },
+    {
+      "epoch": 0.023121387283236993,
+      "grad_norm": 409.96263800148665,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 5.8322,
+      "step": 6
+    },
+    {
+      "epoch": 0.02697495183044316,
+      "grad_norm": 226.39376976378787,
+      "learning_rate": 5.384615384615385e-06,
+      "loss": 4.2464,
+      "step": 7
+    },
+    {
+      "epoch": 0.030828516377649325,
+      "grad_norm": 165.82496194680013,
+      "learning_rate": 6.153846153846155e-06,
+      "loss": 3.7425,
+      "step": 8
+    },
+    {
+      "epoch": 0.03468208092485549,
+      "grad_norm": 173.89210974421533,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 4.0184,
+      "step": 9
+    },
+    {
+      "epoch": 0.038535645472061654,
+      "grad_norm": 168.95311819558103,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 3.7993,
+      "step": 10
+    },
+    {
+      "epoch": 0.04238921001926782,
+      "grad_norm": 76.30995564433688,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 4.4087,
+      "step": 11
+    },
+    {
+      "epoch": 0.046242774566473986,
+      "grad_norm": 74.48219270936819,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 4.141,
+      "step": 12
+    },
+    {
+      "epoch": 0.05009633911368015,
+      "grad_norm": 80.53194275608223,
+      "learning_rate": 1e-05,
+      "loss": 4.1239,
+      "step": 13
+    },
+    {
+      "epoch": 0.05394990366088632,
+      "grad_norm": 33.55587129310653,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 3.6328,
+      "step": 14
+    },
+    {
+      "epoch": 0.057803468208092484,
+      "grad_norm": 63.09531505114449,
+      "learning_rate": 1.1538461538461538e-05,
+      "loss": 3.8233,
+      "step": 15
+    },
+    {
+      "epoch": 0.06165703275529865,
+      "grad_norm": 67.77031346149326,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 3.8786,
+      "step": 16
+    },
+    {
+      "epoch": 0.06551059730250482,
+      "grad_norm": 82.90135582492816,
+      "learning_rate": 1.3076923076923078e-05,
+      "loss": 4.1657,
+      "step": 17
+    },
+    {
+      "epoch": 0.06936416184971098,
+      "grad_norm": 41.832941343610734,
+      "learning_rate": 1.3846153846153847e-05,
+      "loss": 3.408,
+      "step": 18
+    },
+    {
+      "epoch": 0.07321772639691715,
+      "grad_norm": 48.26728390692674,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 3.3997,
+      "step": 19
+    },
+    {
+      "epoch": 0.07707129094412331,
+      "grad_norm": 68.06129545630621,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 3.7407,
+      "step": 20
+    },
+    {
+      "epoch": 0.08092485549132948,
+      "grad_norm": 22.59279364181322,
+      "learning_rate": 1.6153846153846154e-05,
+      "loss": 3.2956,
+      "step": 21
+    },
+    {
+      "epoch": 0.08477842003853564,
+      "grad_norm": 15.9339021622544,
+      "learning_rate": 1.6923076923076924e-05,
+      "loss": 2.8921,
+      "step": 22
+    },
+    {
+      "epoch": 0.08863198458574181,
+      "grad_norm": 41.43770891931384,
+      "learning_rate": 1.7692307692307694e-05,
+      "loss": 3.2055,
+      "step": 23
+    },
+    {
+      "epoch": 0.09248554913294797,
+      "grad_norm": 42.58954954740387,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 3.2822,
+      "step": 24
+    },
+    {
+      "epoch": 0.09633911368015415,
+      "grad_norm": 23.174039496957583,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 2.7902,
+      "step": 25
+    },
+    {
+      "epoch": 0.1001926782273603,
+      "grad_norm": 21.687527912513175,
+      "learning_rate": 2e-05,
+      "loss": 2.7725,
+      "step": 26
+    },
+    {
+      "epoch": 0.10404624277456648,
+      "grad_norm": 25.192833588413695,
+      "learning_rate": 2.0769230769230772e-05,
+      "loss": 2.6381,
+      "step": 27
+    },
+    {
+      "epoch": 0.10789980732177264,
+      "grad_norm": 27.608898717578253,
+      "learning_rate": 2.153846153846154e-05,
+      "loss": 2.633,
+      "step": 28
+    },
+    {
+      "epoch": 0.11175337186897881,
+      "grad_norm": 23.800035559481127,
+      "learning_rate": 2.230769230769231e-05,
+      "loss": 2.5231,
+      "step": 29
+    },
+    {
+      "epoch": 0.11560693641618497,
+      "grad_norm": 13.963396003674896,
+      "learning_rate": 2.3076923076923076e-05,
+      "loss": 2.1474,
+      "step": 30
+    },
+    {
+      "epoch": 0.11946050096339114,
+      "grad_norm": 13.74744780299132,
+      "learning_rate": 2.384615384615385e-05,
+      "loss": 2.0851,
+      "step": 31
+    },
+    {
+      "epoch": 0.1233140655105973,
+      "grad_norm": 14.540640312216865,
+      "learning_rate": 2.461538461538462e-05,
+      "loss": 2.0825,
+      "step": 32
+    },
+    {
+      "epoch": 0.12716763005780346,
+      "grad_norm": 13.210931532751994,
+      "learning_rate": 2.5384615384615386e-05,
+      "loss": 1.8231,
+      "step": 33
+    },
+    {
+      "epoch": 0.13102119460500963,
+      "grad_norm": 14.18049338122164,
+      "learning_rate": 2.6153846153846157e-05,
+      "loss": 2.0161,
+      "step": 34
+    },
+    {
+      "epoch": 0.1348747591522158,
+      "grad_norm": 7.365239232178003,
+      "learning_rate": 2.6923076923076927e-05,
+      "loss": 1.636,
+      "step": 35
+    },
+    {
+      "epoch": 0.13872832369942195,
+      "grad_norm": 11.42487604515666,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 1.7636,
+      "step": 36
+    },
+    {
+      "epoch": 0.14258188824662812,
+      "grad_norm": 10.521730704250018,
+      "learning_rate": 2.8461538461538464e-05,
+      "loss": 1.6425,
+      "step": 37
+    },
+    {
+      "epoch": 0.1464354527938343,
+      "grad_norm": 15.837868821185545,
+      "learning_rate": 2.923076923076923e-05,
+      "loss": 1.7335,
+      "step": 38
+    },
+    {
+      "epoch": 0.15028901734104047,
+      "grad_norm": 10.63875357372187,
+      "learning_rate": 3.0000000000000004e-05,
+      "loss": 1.4748,
+      "step": 39
+    },
+    {
+      "epoch": 0.15414258188824662,
+      "grad_norm": 15.842407967828168,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.4917,
+      "step": 40
+    },
+    {
+      "epoch": 0.1579961464354528,
+      "grad_norm": 8.822203607549136,
+      "learning_rate": 3.153846153846154e-05,
+      "loss": 1.4943,
+      "step": 41
+    },
+    {
+      "epoch": 0.16184971098265896,
+      "grad_norm": 13.809138343712586,
+      "learning_rate": 3.230769230769231e-05,
+      "loss": 1.5356,
+      "step": 42
+    },
+    {
+      "epoch": 0.16570327552986513,
+      "grad_norm": 9.367395780583822,
+      "learning_rate": 3.307692307692308e-05,
+      "loss": 1.4704,
+      "step": 43
+    },
+    {
+      "epoch": 0.16955684007707128,
+      "grad_norm": 10.227364292661408,
+      "learning_rate": 3.384615384615385e-05,
+      "loss": 1.3102,
+      "step": 44
+    },
+    {
+      "epoch": 0.17341040462427745,
+      "grad_norm": 9.413833051288245,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 1.255,
+      "step": 45
+    },
+    {
+      "epoch": 0.17726396917148363,
+      "grad_norm": 9.94687228320031,
+      "learning_rate": 3.538461538461539e-05,
+      "loss": 1.3163,
+      "step": 46
+    },
+    {
+      "epoch": 0.1811175337186898,
+      "grad_norm": 7.092554527238564,
+      "learning_rate": 3.615384615384616e-05,
+      "loss": 1.2354,
+      "step": 47
+    },
+    {
+      "epoch": 0.18497109826589594,
+      "grad_norm": 9.149268401400676,
+      "learning_rate": 3.692307692307693e-05,
+      "loss": 1.2504,
+      "step": 48
+    },
+    {
+      "epoch": 0.18882466281310212,
+      "grad_norm": 6.289853231412649,
+      "learning_rate": 3.769230769230769e-05,
+      "loss": 1.1468,
+      "step": 49
+    },
+    {
+      "epoch": 0.1926782273603083,
+      "grad_norm": 9.45344983093482,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 1.2058,
+      "step": 50
+    },
+    {
+      "epoch": 0.19653179190751446,
+      "grad_norm": 10.360186688388032,
+      "learning_rate": 3.923076923076923e-05,
+      "loss": 1.3109,
+      "step": 51
+    },
+    {
+      "epoch": 0.2003853564547206,
+      "grad_norm": 9.072775454723184,
+      "learning_rate": 4e-05,
+      "loss": 1.2695,
+      "step": 52
+    },
+    {
+      "epoch": 0.20423892100192678,
+      "grad_norm": 8.438625780983935,
+      "learning_rate": 3.999954550797489e-05,
+      "loss": 1.3253,
+      "step": 53
+    },
+    {
+      "epoch": 0.20809248554913296,
+      "grad_norm": 7.900240323931455,
+      "learning_rate": 3.999818205255586e-05,
+      "loss": 1.1021,
+      "step": 54
+    },
+    {
+      "epoch": 0.2119460500963391,
+      "grad_norm": 5.82014263071836,
+      "learning_rate": 3.9995909695710856e-05,
+      "loss": 1.0841,
+      "step": 55
+    },
+    {
+      "epoch": 0.21579961464354527,
+      "grad_norm": 7.201881900115451,
+      "learning_rate": 3.999272854071669e-05,
+      "loss": 1.133,
+      "step": 56
+    },
+    {
+      "epoch": 0.21965317919075145,
+      "grad_norm": 7.6958656122670295,
+      "learning_rate": 3.998863873215434e-05,
+      "loss": 1.0334,
+      "step": 57
+    },
+    {
+      "epoch": 0.22350674373795762,
+      "grad_norm": 5.905685554617661,
+      "learning_rate": 3.998364045590232e-05,
+      "loss": 1.017,
+      "step": 58
+    },
+    {
+      "epoch": 0.22736030828516376,
+      "grad_norm": 6.204779741056835,
+      "learning_rate": 3.9977733939128304e-05,
+      "loss": 1.0027,
+      "step": 59
+    },
+    {
+      "epoch": 0.23121387283236994,
+      "grad_norm": 4.951471635667849,
+      "learning_rate": 3.997091945027878e-05,
+      "loss": 0.9547,
+      "step": 60
+    },
+    {
+      "epoch": 0.2350674373795761,
+      "grad_norm": 7.304094138753475,
+      "learning_rate": 3.996319729906682e-05,
+      "loss": 1.1246,
+      "step": 61
+    },
+    {
+      "epoch": 0.23892100192678228,
+      "grad_norm": 6.298474879300807,
+      "learning_rate": 3.995456783645805e-05,
+      "loss": 1.0221,
+      "step": 62
+    },
+    {
+      "epoch": 0.24277456647398843,
+      "grad_norm": 7.776498792672179,
+      "learning_rate": 3.994503145465464e-05,
+      "loss": 1.097,
+      "step": 63
+    },
+    {
+      "epoch": 0.2466281310211946,
+      "grad_norm": 5.607410872804594,
+      "learning_rate": 3.993458858707756e-05,
+      "loss": 1.0371,
+      "step": 64
+    },
+    {
+      "epoch": 0.2504816955684008,
+      "grad_norm": 4.77643068735735,
+      "learning_rate": 3.992323970834682e-05,
+      "loss": 1.004,
+      "step": 65
+    },
+    {
+      "epoch": 0.2543352601156069,
+      "grad_norm": 7.743150531664644,
+      "learning_rate": 3.991098533425988e-05,
+      "loss": 1.0132,
+      "step": 66
+    },
+    {
+      "epoch": 0.2581888246628131,
+      "grad_norm": 5.8368050703956245,
+      "learning_rate": 3.989782602176829e-05,
+      "loss": 0.9401,
+      "step": 67
+    },
+    {
+      "epoch": 0.26204238921001927,
+      "grad_norm": 3.2101782475861,
+      "learning_rate": 3.988376236895231e-05,
+      "loss": 0.9025,
+      "step": 68
+    },
+    {
+      "epoch": 0.2658959537572254,
+      "grad_norm": 13.049333458920938,
+      "learning_rate": 3.986879501499373e-05,
+      "loss": 1.0269,
+      "step": 69
+    },
+    {
+      "epoch": 0.2697495183044316,
+      "grad_norm": 7.880498887675296,
+      "learning_rate": 3.985292464014686e-05,
+      "loss": 1.0398,
+      "step": 70
+    },
+    {
+      "epoch": 0.27360308285163776,
+      "grad_norm": 5.313107024369285,
+      "learning_rate": 3.9836151965707585e-05,
+      "loss": 0.958,
+      "step": 71
+    },
+    {
+      "epoch": 0.2774566473988439,
+      "grad_norm": 4.395056829854694,
+      "learning_rate": 3.9818477753980566e-05,
+      "loss": 0.9323,
+      "step": 72
+    },
+    {
+      "epoch": 0.2813102119460501,
+      "grad_norm": 6.266655645573501,
+      "learning_rate": 3.979990280824465e-05,
+      "loss": 0.9909,
+      "step": 73
+    },
+    {
+      "epoch": 0.28516377649325625,
+      "grad_norm": 3.957118496983222,
+      "learning_rate": 3.9780427972716296e-05,
+      "loss": 1.0391,
+      "step": 74
+    },
+    {
+      "epoch": 0.28901734104046245,
+      "grad_norm": 3.508018525774183,
+      "learning_rate": 3.976005413251125e-05,
+      "loss": 1.0032,
+      "step": 75
+    },
+    {
+      "epoch": 0.2928709055876686,
+      "grad_norm": 10.69825193127433,
+      "learning_rate": 3.9738782213604305e-05,
+      "loss": 1.0472,
+      "step": 76
+    },
+    {
+      "epoch": 0.29672447013487474,
+      "grad_norm": 6.501782774298941,
+      "learning_rate": 3.971661318278721e-05,
+      "loss": 1.0126,
+      "step": 77
+    },
+    {
+      "epoch": 0.30057803468208094,
+      "grad_norm": 5.11168856069891,
+      "learning_rate": 3.969354804762473e-05,
+      "loss": 0.96,
+      "step": 78
+    },
+    {
+      "epoch": 0.3044315992292871,
+      "grad_norm": 5.039914432332962,
+      "learning_rate": 3.966958785640887e-05,
+      "loss": 0.9067,
+      "step": 79
+    },
+    {
+      "epoch": 0.30828516377649323,
+      "grad_norm": 6.647066379901366,
+      "learning_rate": 3.9644733698111206e-05,
+      "loss": 0.9367,
+      "step": 80
+    },
+    {
+      "epoch": 0.31213872832369943,
+      "grad_norm": 3.5432939083746655,
+      "learning_rate": 3.9618986702333424e-05,
+      "loss": 0.854,
+      "step": 81
+    },
+    {
+      "epoch": 0.3159922928709056,
+      "grad_norm": 2.9831981250415525,
+      "learning_rate": 3.959234803925594e-05,
+      "loss": 0.8707,
+      "step": 82
+    },
+    {
+      "epoch": 0.3198458574181118,
+      "grad_norm": 4.000857879722409,
+      "learning_rate": 3.956481891958475e-05,
+      "loss": 0.8518,
+      "step": 83
+    },
+    {
+      "epoch": 0.3236994219653179,
+      "grad_norm": 3.4582769025055793,
+      "learning_rate": 3.9536400594496386e-05,
+      "loss": 0.8765,
+      "step": 84
+    },
+    {
+      "epoch": 0.32755298651252407,
+      "grad_norm": 3.930610795014948,
+      "learning_rate": 3.950709435558106e-05,
+      "loss": 0.9758,
+      "step": 85
+    },
+    {
+      "epoch": 0.33140655105973027,
+      "grad_norm": 3.7172875758901154,
+      "learning_rate": 3.947690153478396e-05,
+      "loss": 0.91,
+      "step": 86
+    },
+    {
+      "epoch": 0.3352601156069364,
+      "grad_norm": 4.5575804046102455,
+      "learning_rate": 3.9445823504344725e-05,
+      "loss": 0.8402,
+      "step": 87
+    },
+    {
+      "epoch": 0.33911368015414256,
+      "grad_norm": 3.8988704845029223,
+      "learning_rate": 3.9413861676735034e-05,
+      "loss": 0.9235,
+      "step": 88
+    },
+    {
+      "epoch": 0.34296724470134876,
+      "grad_norm": 3.965085606406442,
+      "learning_rate": 3.938101750459447e-05,
+      "loss": 0.8447,
+      "step": 89
+    },
+    {
+      "epoch": 0.3468208092485549,
+      "grad_norm": 3.046774416650305,
+      "learning_rate": 3.9347292480664465e-05,
+      "loss": 0.8227,
+      "step": 90
+    },
+    {
+      "epoch": 0.35067437379576105,
+      "grad_norm": 4.720525497029076,
+      "learning_rate": 3.931268813772047e-05,
+      "loss": 0.8303,
+      "step": 91
+    },
+    {
+      "epoch": 0.35452793834296725,
+      "grad_norm": 3.961704867922078,
+      "learning_rate": 3.927720604850226e-05,
+      "loss": 0.8955,
+      "step": 92
+    },
+    {
+      "epoch": 0.3583815028901734,
+      "grad_norm": 3.3173574867131967,
+      "learning_rate": 3.92408478256425e-05,
+      "loss": 0.8748,
+      "step": 93
+    },
+    {
+      "epoch": 0.3622350674373796,
+      "grad_norm": 4.270129625253774,
+      "learning_rate": 3.920361512159343e-05,
+      "loss": 0.8354,
+      "step": 94
+    },
+    {
+      "epoch": 0.36608863198458574,
+      "grad_norm": 4.083301813465707,
+      "learning_rate": 3.916550962855174e-05,
+      "loss": 0.8428,
+      "step": 95
+    },
+    {
+      "epoch": 0.3699421965317919,
+      "grad_norm": 3.8426066258082745,
+      "learning_rate": 3.912653307838173e-05,
+      "loss": 0.882,
+      "step": 96
+    },
+    {
+      "epoch": 0.3737957610789981,
+      "grad_norm": 4.858960264331484,
+      "learning_rate": 3.908668724253649e-05,
+      "loss": 0.883,
+      "step": 97
+    },
+    {
+      "epoch": 0.37764932562620424,
+      "grad_norm": 3.529748790118145,
+      "learning_rate": 3.9045973931977495e-05,
+      "loss": 0.8818,
+      "step": 98
+    },
+    {
+      "epoch": 0.3815028901734104,
+      "grad_norm": 4.3956107314706685,
+      "learning_rate": 3.900439499709224e-05,
+      "loss": 0.8682,
+      "step": 99
+    },
+    {
+      "epoch": 0.3853564547206166,
+      "grad_norm": 4.190396012770089,
+      "learning_rate": 3.896195232761016e-05,
+      "loss": 0.8228,
+      "step": 100
+    },
+    {
+      "epoch": 0.3892100192678227,
+      "grad_norm": 3.10753800197593,
+      "learning_rate": 3.891864785251673e-05,
+      "loss": 0.8403,
+      "step": 101
+    },
+    {
+      "epoch": 0.3930635838150289,
+      "grad_norm": 2.9288118038221125,
+      "learning_rate": 3.887448353996582e-05,
+      "loss": 0.8621,
+      "step": 102
+    },
+    {
+      "epoch": 0.3969171483622351,
+      "grad_norm": 5.08781315771577,
+      "learning_rate": 3.88294613971902e-05,
+      "loss": 0.9015,
+      "step": 103
+    },
+    {
+      "epoch": 0.4007707129094412,
+      "grad_norm": 2.825525117803277,
+      "learning_rate": 3.8783583470410365e-05,
+      "loss": 0.746,
+      "step": 104
+    },
+    {
+      "epoch": 0.4046242774566474,
+      "grad_norm": 3.7918665790803674,
+      "learning_rate": 3.87368518447415e-05,
+      "loss": 0.7484,
+      "step": 105
+    },
+    {
+      "epoch": 0.40847784200385356,
+      "grad_norm": 2.600804604880562,
+      "learning_rate": 3.8689268644098715e-05,
+      "loss": 0.8912,
+      "step": 106
+    },
+    {
+      "epoch": 0.4123314065510597,
+      "grad_norm": 3.3941246553611775,
+      "learning_rate": 3.864083603110053e-05,
+      "loss": 0.7785,
+      "step": 107
+    },
+    {
+      "epoch": 0.4161849710982659,
+      "grad_norm": 4.397542143481628,
+      "learning_rate": 3.8591556206970594e-05,
+      "loss": 0.8569,
+      "step": 108
+    },
+    {
+      "epoch": 0.42003853564547206,
+      "grad_norm": 3.0636662940182124,
+      "learning_rate": 3.8541431411437616e-05,
+      "loss": 0.8718,
+      "step": 109
+    },
+    {
+      "epoch": 0.4238921001926782,
+      "grad_norm": 4.18117825185653,
+      "learning_rate": 3.8490463922633564e-05,
+      "loss": 0.7702,
+      "step": 110
+    },
+    {
+      "epoch": 0.4277456647398844,
+      "grad_norm": 2.43373547813132,
+      "learning_rate": 3.843865605699017e-05,
+      "loss": 0.7936,
+      "step": 111
+    },
+    {
+      "epoch": 0.43159922928709055,
+      "grad_norm": 3.943685910342036,
+      "learning_rate": 3.8386010169133596e-05,
+      "loss": 0.8022,
+      "step": 112
+    },
+    {
+      "epoch": 0.43545279383429675,
+      "grad_norm": 3.655514814817605,
+      "learning_rate": 3.833252865177748e-05,
+      "loss": 0.774,
+      "step": 113
+    },
+    {
+      "epoch": 0.4393063583815029,
+      "grad_norm": 3.0272004910923487,
+      "learning_rate": 3.8278213935614126e-05,
+      "loss": 0.7132,
+      "step": 114
+    },
+    {
+      "epoch": 0.44315992292870904,
+      "grad_norm": 4.609405687465504,
+      "learning_rate": 3.8223068489204064e-05,
+      "loss": 0.9129,
+      "step": 115
+    },
+    {
+      "epoch": 0.44701348747591524,
+      "grad_norm": 3.223236986816773,
+      "learning_rate": 3.816709481886386e-05,
+      "loss": 0.766,
+      "step": 116
+    },
+    {
+      "epoch": 0.4508670520231214,
+      "grad_norm": 3.4852321075320933,
+      "learning_rate": 3.81102954685522e-05,
+      "loss": 0.7169,
+      "step": 117
+    },
+    {
+      "epoch": 0.45472061657032753,
+      "grad_norm": 2.6796073181657745,
+      "learning_rate": 3.805267301975424e-05,
+      "loss": 0.7362,
+      "step": 118
+    },
+    {
+      "epoch": 0.45857418111753373,
+      "grad_norm": 2.839001944033485,
+      "learning_rate": 3.799423009136434e-05,
+      "loss": 0.8818,
+      "step": 119
+    },
+    {
+      "epoch": 0.4624277456647399,
+      "grad_norm": 2.328668662319875,
+      "learning_rate": 3.793496933956699e-05,
+      "loss": 0.7686,
+      "step": 120
+    },
+    {
+      "epoch": 0.4662813102119461,
+      "grad_norm": 3.5890624141236764,
+      "learning_rate": 3.7874893457716086e-05,
+      "loss": 0.7887,
+      "step": 121
+    },
+    {
+      "epoch": 0.4701348747591522,
+      "grad_norm": 3.2377955419056494,
+      "learning_rate": 3.7814005176212555e-05,
+      "loss": 0.8295,
+      "step": 122
+    },
+    {
+      "epoch": 0.47398843930635837,
+      "grad_norm": 3.1936213076859197,
+      "learning_rate": 3.775230726238023e-05,
+      "loss": 0.7653,
+      "step": 123
+    },
+    {
+      "epoch": 0.47784200385356457,
+      "grad_norm": 3.314436046941277,
+      "learning_rate": 3.7689802520340103e-05,
+      "loss": 0.7326,
+      "step": 124
+    },
+    {
+      "epoch": 0.4816955684007707,
+      "grad_norm": 1.6311346221294762,
+      "learning_rate": 3.7626493790882846e-05,
+      "loss": 0.7467,
+      "step": 125
+    },
+    {
+      "epoch": 0.48554913294797686,
+      "grad_norm": 3.364013140417832,
+      "learning_rate": 3.756238395133972e-05,
+      "loss": 0.7601,
+      "step": 126
+    },
+    {
+      "epoch": 0.48940269749518306,
+      "grad_norm": 2.347603254239086,
+      "learning_rate": 3.7497475915451806e-05,
+      "loss": 0.823,
+      "step": 127
+    },
+    {
+      "epoch": 0.4932562620423892,
+      "grad_norm": 3.847030422820461,
+      "learning_rate": 3.743177263323758e-05,
+      "loss": 0.7091,
+      "step": 128
+    },
+    {
+      "epoch": 0.49710982658959535,
+      "grad_norm": 3.463187618636158,
+      "learning_rate": 3.7365277090858815e-05,
+      "loss": 0.7412,
+      "step": 129
+    },
+    {
+      "epoch": 0.5009633911368016,
+      "grad_norm": 2.818735989314964,
+      "learning_rate": 3.729799231048488e-05,
+      "loss": 0.7571,
+      "step": 130
+    },
+    {
+      "epoch": 0.5048169556840078,
+      "grad_norm": 3.5601441226127655,
+      "learning_rate": 3.722992135015539e-05,
+      "loss": 0.6498,
+      "step": 131
+    },
+    {
+      "epoch": 0.5086705202312138,
+      "grad_norm": 3.3243689525232716,
+      "learning_rate": 3.71610673036412e-05,
+      "loss": 0.7063,
+      "step": 132
+    },
+    {
+      "epoch": 0.51252408477842,
+      "grad_norm": 2.79620087521176,
+      "learning_rate": 3.709143330030383e-05,
+      "loss": 0.7519,
+      "step": 133
+    },
+    {
+      "epoch": 0.5163776493256262,
+      "grad_norm": 2.6274884881066813,
+      "learning_rate": 3.702102250495318e-05,
+      "loss": 0.6862,
+      "step": 134
+    },
+    {
+      "epoch": 0.5202312138728323,
+      "grad_norm": 1.310261156652054,
+      "learning_rate": 3.694983811770375e-05,
+      "loss": 0.5968,
+      "step": 135
+    },
+    {
+      "epoch": 0.5240847784200385,
+      "grad_norm": 2.961796401692403,
+      "learning_rate": 3.687788337382918e-05,
+      "loss": 0.6842,
+      "step": 136
+    },
+    {
+      "epoch": 0.5279383429672447,
+      "grad_norm": 3.715435487194137,
+      "learning_rate": 3.6805161543615186e-05,
+      "loss": 0.7836,
+      "step": 137
+    },
+    {
+      "epoch": 0.5317919075144508,
+      "grad_norm": 1.9101920792437495,
+      "learning_rate": 3.673167593221097e-05,
+      "loss": 0.6828,
+      "step": 138
+    },
+    {
+      "epoch": 0.535645472061657,
+      "grad_norm": 4.2524126868327885,
+      "learning_rate": 3.665742987947895e-05,
+      "loss": 0.7685,
+      "step": 139
+    },
+    {
+      "epoch": 0.5394990366088632,
+      "grad_norm": 2.3826617460275217,
+      "learning_rate": 3.658242675984302e-05,
+      "loss": 0.6548,
+      "step": 140
+    },
+    {
+      "epoch": 0.5433526011560693,
+      "grad_norm": 2.7362234194986823,
+      "learning_rate": 3.6506669982135166e-05,
+      "loss": 0.7131,
+      "step": 141
+    },
+    {
+      "epoch": 0.5472061657032755,
+      "grad_norm": 2.839379036151834,
+      "learning_rate": 3.6430162989440495e-05,
+      "loss": 0.6846,
+      "step": 142
+    },
+    {
+      "epoch": 0.5510597302504817,
+      "grad_norm": 2.217944430478911,
+      "learning_rate": 3.635290925894083e-05,
+      "loss": 0.7183,
+      "step": 143
+    },
+    {
+      "epoch": 0.5549132947976878,
+      "grad_norm": 2.2686355763545203,
+      "learning_rate": 3.627491230175661e-05,
+      "loss": 0.6742,
+      "step": 144
+    },
+    {
+      "epoch": 0.558766859344894,
+      "grad_norm": 2.8612073083735075,
+      "learning_rate": 3.6196175662787326e-05,
+      "loss": 0.6969,
+      "step": 145
+    },
+    {
+      "epoch": 0.5626204238921002,
+      "grad_norm": 2.379426816508497,
+      "learning_rate": 3.6116702920550445e-05,
+      "loss": 0.7102,
+      "step": 146
+    },
+    {
+      "epoch": 0.5664739884393064,
+      "grad_norm": 3.5635505745818774,
+      "learning_rate": 3.6036497687018704e-05,
+      "loss": 0.737,
+      "step": 147
+    },
+    {
+      "epoch": 0.5703275529865125,
+      "grad_norm": 2.5565000760425094,
+      "learning_rate": 3.5955563607456025e-05,
+      "loss": 0.6599,
+      "step": 148
+    },
+    {
+      "epoch": 0.5741811175337187,
+      "grad_norm": 2.7437675382633326,
+      "learning_rate": 3.5873904360251766e-05,
+      "loss": 0.7464,
+      "step": 149
+    },
+    {
+      "epoch": 0.5780346820809249,
+      "grad_norm": 2.3771605731220986,
+      "learning_rate": 3.579152365675359e-05,
+      "loss": 0.6092,
+      "step": 150
+    },
+    {
+      "epoch": 0.581888246628131,
+      "grad_norm": 2.393218132886115,
+      "learning_rate": 3.570842524109878e-05,
+      "loss": 0.711,
+      "step": 151
+    },
+    {
+      "epoch": 0.5857418111753372,
+      "grad_norm": 2.4377648761435196,
+      "learning_rate": 3.562461289004406e-05,
+      "loss": 0.6765,
+      "step": 152
+    },
+    {
+      "epoch": 0.5895953757225434,
+      "grad_norm": 1.726127421558755,
+      "learning_rate": 3.5540090412793926e-05,
+      "loss": 0.6122,
+      "step": 153
+    },
+    {
+      "epoch": 0.5934489402697495,
+      "grad_norm": 2.2397924893238628,
+      "learning_rate": 3.545486165082759e-05,
+      "loss": 0.6207,
+      "step": 154
+    },
+    {
+      "epoch": 0.5973025048169557,
+      "grad_norm": 2.0431721405303764,
+      "learning_rate": 3.53689304777243e-05,
+      "loss": 0.621,
+      "step": 155
+    },
+    {
+      "epoch": 0.6011560693641619,
+      "grad_norm": 1.8373936110598785,
+      "learning_rate": 3.528230079898734e-05,
+      "loss": 0.6832,
+      "step": 156
+    },
+    {
+      "epoch": 0.605009633911368,
+      "grad_norm": 3.218900986872675,
+      "learning_rate": 3.5194976551866535e-05,
+      "loss": 0.6867,
+      "step": 157
+    },
+    {
+      "epoch": 0.6088631984585742,
+      "grad_norm": 2.7681277459165186,
+      "learning_rate": 3.510696170517927e-05,
+      "loss": 0.6388,
+      "step": 158
+    },
+    {
+      "epoch": 0.6127167630057804,
+      "grad_norm": 2.789942125405049,
+      "learning_rate": 3.5018260259130134e-05,
+      "loss": 0.65,
+      "step": 159
+    },
+    {
+      "epoch": 0.6165703275529865,
+      "grad_norm": 2.3067452480491193,
+      "learning_rate": 3.492887624512912e-05,
+      "loss": 0.5852,
+      "step": 160
+    },
+    {
+      "epoch": 0.6204238921001927,
+      "grad_norm": 1.5893723542941685,
+      "learning_rate": 3.483881372560837e-05,
+      "loss": 0.6286,
+      "step": 161
+    },
+    {
+      "epoch": 0.6242774566473989,
+      "grad_norm": 2.8053299102587146,
+      "learning_rate": 3.474807679383758e-05,
+      "loss": 0.6866,
+      "step": 162
+    },
+    {
+      "epoch": 0.628131021194605,
+      "grad_norm": 1.9932305081667505,
+      "learning_rate": 3.4656669573737934e-05,
+      "loss": 0.6618,
+      "step": 163
+    },
+    {
+      "epoch": 0.6319845857418112,
+      "grad_norm": 2.5322390617691677,
+      "learning_rate": 3.456459621969469e-05,
+      "loss": 0.6699,
+      "step": 164
+    },
+    {
+      "epoch": 0.6358381502890174,
+      "grad_norm": 2.714324952697276,
+      "learning_rate": 3.447186091636836e-05,
+      "loss": 0.567,
+      "step": 165
+    },
+    {
+      "epoch": 0.6396917148362236,
+      "grad_norm": 2.3260631874283795,
+      "learning_rate": 3.437846787850454e-05,
+      "loss": 0.6787,
+      "step": 166
+    },
+    {
+      "epoch": 0.6435452793834296,
+      "grad_norm": 3.244130833526928,
+      "learning_rate": 3.42844213507423e-05,
+      "loss": 0.6283,
+      "step": 167
+    },
+    {
+      "epoch": 0.6473988439306358,
+      "grad_norm": 2.2697249458670403,
+      "learning_rate": 3.418972560742133e-05,
+      "loss": 0.6043,
+      "step": 168
+    },
+    {
+      "epoch": 0.651252408477842,
+      "grad_norm": 2.261002336792345,
+      "learning_rate": 3.409438495238765e-05,
+      "loss": 0.7039,
+      "step": 169
+    },
+    {
+      "epoch": 0.6551059730250481,
+      "grad_norm": 2.9798712765043542,
+      "learning_rate": 3.3998403718798005e-05,
+      "loss": 0.687,
+      "step": 170
+    },
+    {
+      "epoch": 0.6589595375722543,
+      "grad_norm": 1.7575260995525863,
+      "learning_rate": 3.390178626892291e-05,
+      "loss": 0.5704,
+      "step": 171
+    },
+    {
+      "epoch": 0.6628131021194605,
+      "grad_norm": 1.959592501385033,
+      "learning_rate": 3.38045369939484e-05,
+      "loss": 0.6365,
+      "step": 172
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 2.7459302559428127,
+      "learning_rate": 3.370666031377648e-05,
+      "loss": 0.6081,
+      "step": 173
+    },
+    {
+      "epoch": 0.6705202312138728,
+      "grad_norm": 1.868927815180204,
+      "learning_rate": 3.3608160676824216e-05,
+      "loss": 0.5927,
+      "step": 174
+    },
+    {
+      "epoch": 0.674373795761079,
+      "grad_norm": 3.4467192352082856,
+      "learning_rate": 3.350904255982154e-05,
+      "loss": 0.6956,
+      "step": 175
+    },
+    {
+      "epoch": 0.6782273603082851,
+      "grad_norm": 1.740260469132678,
+      "learning_rate": 3.3409310467607824e-05,
+      "loss": 0.5574,
+      "step": 176
+    },
+    {
+      "epoch": 0.6820809248554913,
+      "grad_norm": 2.055938978641809,
+      "learning_rate": 3.330896893292714e-05,
+      "loss": 0.5761,
+      "step": 177
+    },
+    {
+      "epoch": 0.6859344894026975,
+      "grad_norm": 2.2106935577605427,
+      "learning_rate": 3.3208022516222195e-05,
+      "loss": 0.5955,
+      "step": 178
+    },
+    {
+      "epoch": 0.6897880539499036,
+      "grad_norm": 1.8460288906944335,
+      "learning_rate": 3.310647580542715e-05,
+      "loss": 0.5769,
+      "step": 179
+    },
+    {
+      "epoch": 0.6936416184971098,
+      "grad_norm": 2.1583501173847024,
+      "learning_rate": 3.300433341575901e-05,
+      "loss": 0.5949,
+      "step": 180
+    },
+    {
+      "epoch": 0.697495183044316,
+      "grad_norm": 2.748430083318313,
+      "learning_rate": 3.2901599989507935e-05,
+      "loss": 0.5629,
+      "step": 181
+    },
+    {
+      "epoch": 0.7013487475915221,
+      "grad_norm": 1.942682422315833,
+      "learning_rate": 3.279828019582621e-05,
+      "loss": 0.612,
+      "step": 182
+    },
+    {
+      "epoch": 0.7052023121387283,
+      "grad_norm": 3.1214108190867487,
+      "learning_rate": 3.2694378730516074e-05,
+      "loss": 0.5638,
+      "step": 183
+    },
+    {
+      "epoch": 0.7090558766859345,
+      "grad_norm": 2.5088639648861912,
+      "learning_rate": 3.2589900315816266e-05,
+      "loss": 0.5643,
+      "step": 184
+    },
+    {
+      "epoch": 0.7129094412331407,
+      "grad_norm": 1.6797637949182582,
+      "learning_rate": 3.24848497001874e-05,
+      "loss": 0.5467,
+      "step": 185
+    },
+    {
+      "epoch": 0.7167630057803468,
+      "grad_norm": 2.2031923107978004,
+      "learning_rate": 3.237923165809619e-05,
+      "loss": 0.6403,
+      "step": 186
+    },
+    {
+      "epoch": 0.720616570327553,
+      "grad_norm": 2.217707978859453,
+      "learning_rate": 3.227305098979842e-05,
+      "loss": 0.5575,
+      "step": 187
+    },
+    {
+      "epoch": 0.7244701348747592,
+      "grad_norm": 1.8030994444840251,
+      "learning_rate": 3.2166312521120775e-05,
+      "loss": 0.5964,
+      "step": 188
+    },
+    {
+      "epoch": 0.7283236994219653,
+      "grad_norm": 2.7881810961948035,
+      "learning_rate": 3.2059021103241556e-05,
+      "loss": 0.5627,
+      "step": 189
+    },
+    {
+      "epoch": 0.7321772639691715,
+      "grad_norm": 1.6025626542354654,
+      "learning_rate": 3.195118161247011e-05,
+      "loss": 0.5366,
+      "step": 190
+    },
+    {
+      "epoch": 0.7360308285163777,
+      "grad_norm": 2.7898667044495196,
+      "learning_rate": 3.184279895002533e-05,
+      "loss": 0.6269,
+      "step": 191
+    },
+    {
+      "epoch": 0.7398843930635838,
+      "grad_norm": 2.012521948946768,
+      "learning_rate": 3.1733878041812756e-05,
+      "loss": 0.578,
+      "step": 192
+    },
+    {
+      "epoch": 0.74373795761079,
+      "grad_norm": 1.7202183467823577,
+      "learning_rate": 3.1624423838200824e-05,
+      "loss": 0.6021,
+      "step": 193
+    },
+    {
+      "epoch": 0.7475915221579962,
+      "grad_norm": 2.391244509621585,
+      "learning_rate": 3.151444131379579e-05,
+      "loss": 0.6227,
+      "step": 194
+    },
+    {
+      "epoch": 0.7514450867052023,
+      "grad_norm": 1.290881388687675,
+      "learning_rate": 3.140393546721569e-05,
+      "loss": 0.4976,
+      "step": 195
+    },
+    {
+      "epoch": 0.7552986512524085,
+      "grad_norm": 2.747140614154264,
+      "learning_rate": 3.1292911320863104e-05,
+      "loss": 0.5795,
+      "step": 196
+    },
+    {
+      "epoch": 0.7591522157996147,
+      "grad_norm": 2.1090959982249022,
+      "learning_rate": 3.118137392069696e-05,
+      "loss": 0.5987,
+      "step": 197
+    },
+    {
+      "epoch": 0.7630057803468208,
+      "grad_norm": 1.920242941952473,
+      "learning_rate": 3.106932833600314e-05,
+      "loss": 0.5862,
+      "step": 198
+    },
+    {
+      "epoch": 0.766859344894027,
+      "grad_norm": 2.4556835621447477,
+      "learning_rate": 3.095677965916411e-05,
+      "loss": 0.5432,
+      "step": 199
+    },
+    {
+      "epoch": 0.7707129094412332,
+      "grad_norm": 1.7404959875815949,
+      "learning_rate": 3.084373300542748e-05,
+      "loss": 0.4656,
+      "step": 200
+    },
+    {
+      "epoch": 0.7745664739884393,
+      "grad_norm": 2.4156874663926433,
+      "learning_rate": 3.0730193512673515e-05,
+      "loss": 0.6341,
+      "step": 201
+    },
+    {
+      "epoch": 0.7784200385356455,
+      "grad_norm": 1.9237119705970884,
+      "learning_rate": 3.06161663411816e-05,
+      "loss": 0.4988,
+      "step": 202
+    },
+    {
+      "epoch": 0.7822736030828517,
+      "grad_norm": 2.1640461913240245,
+      "learning_rate": 3.0501656673395756e-05,
+      "loss": 0.5871,
+      "step": 203
+    },
+    {
+      "epoch": 0.7861271676300579,
+      "grad_norm": 2.7705536239605704,
+      "learning_rate": 3.0386669713689057e-05,
+      "loss": 0.6961,
+      "step": 204
+    },
+    {
+      "epoch": 0.789980732177264,
+      "grad_norm": 2.361536461003985,
+      "learning_rate": 3.0271210688127123e-05,
+      "loss": 0.5827,
+      "step": 205
+    },
+    {
+      "epoch": 0.7938342967244701,
+      "grad_norm": 1.724308147378069,
+      "learning_rate": 3.015528484423059e-05,
+      "loss": 0.5157,
+      "step": 206
+    },
+    {
+      "epoch": 0.7976878612716763,
+      "grad_norm": 1.8279294004024718,
+      "learning_rate": 3.0038897450736612e-05,
+      "loss": 0.5094,
+      "step": 207
+    },
+    {
+      "epoch": 0.8015414258188824,
+      "grad_norm": 1.836316615161725,
+      "learning_rate": 2.9922053797359406e-05,
+      "loss": 0.5172,
+      "step": 208
+    },
+    {
+      "epoch": 0.8053949903660886,
+      "grad_norm": 1.6458484857811015,
+      "learning_rate": 2.980475919454984e-05,
+      "loss": 0.5253,
+      "step": 209
+    },
+    {
+      "epoch": 0.8092485549132948,
+      "grad_norm": 2.2344584087944535,
+      "learning_rate": 2.9687018973254055e-05,
+      "loss": 0.5379,
+      "step": 210
+    },
+    {
+      "epoch": 0.8131021194605009,
+      "grad_norm": 1.8412670292971436,
+      "learning_rate": 2.956883848467123e-05,
+      "loss": 0.5655,
+      "step": 211
+    },
+    {
+      "epoch": 0.8169556840077071,
+      "grad_norm": 1.6198673535897559,
+      "learning_rate": 2.945022310001032e-05,
+      "loss": 0.4977,
+      "step": 212
+    },
+    {
+      "epoch": 0.8208092485549133,
+      "grad_norm": 1.6875535729885185,
+      "learning_rate": 2.9331178210245962e-05,
+      "loss": 0.4592,
+      "step": 213
+    },
+    {
+      "epoch": 0.8246628131021194,
+      "grad_norm": 1.5196518137741946,
+      "learning_rate": 2.921170922587346e-05,
+      "loss": 0.5223,
+      "step": 214
+    },
+    {
+      "epoch": 0.8285163776493256,
+      "grad_norm": 1.5091415438145863,
+      "learning_rate": 2.909182157666287e-05,
+      "loss": 0.4706,
+      "step": 215
+    },
+    {
+      "epoch": 0.8323699421965318,
+      "grad_norm": 2.1212922277105,
+      "learning_rate": 2.897152071141225e-05,
+      "loss": 0.4369,
+      "step": 216
+    },
+    {
+      "epoch": 0.8362235067437379,
+      "grad_norm": 1.6767049591987147,
+      "learning_rate": 2.885081209769998e-05,
+      "loss": 0.5098,
+      "step": 217
+    },
+    {
+      "epoch": 0.8400770712909441,
+      "grad_norm": 1.6518844332576945,
+      "learning_rate": 2.8729701221636294e-05,
+      "loss": 0.5113,
+      "step": 218
+    },
+    {
+      "epoch": 0.8439306358381503,
+      "grad_norm": 2.0287593345047665,
+      "learning_rate": 2.8608193587613917e-05,
+      "loss": 0.5342,
+      "step": 219
+    },
+    {
+      "epoch": 0.8477842003853564,
+      "grad_norm": 1.4891909790069897,
+      "learning_rate": 2.8486294718057936e-05,
+      "loss": 0.4461,
+      "step": 220
+    },
+    {
+      "epoch": 0.8516377649325626,
+      "grad_norm": 1.52500498490846,
+      "learning_rate": 2.8364010153174733e-05,
+      "loss": 0.543,
+      "step": 221
+    },
+    {
+      "epoch": 0.8554913294797688,
+      "grad_norm": 1.5785692053698055,
+      "learning_rate": 2.8241345450700275e-05,
+      "loss": 0.4329,
+      "step": 222
+    },
+    {
+      "epoch": 0.859344894026975,
+      "grad_norm": 2.2507626884600187,
+      "learning_rate": 2.8118306185647458e-05,
+      "loss": 0.5709,
+      "step": 223
+    },
+    {
+      "epoch": 0.8631984585741811,
+      "grad_norm": 1.7477813182417148,
+      "learning_rate": 2.7994897950052764e-05,
+      "loss": 0.5607,
+      "step": 224
+    },
+    {
+      "epoch": 0.8670520231213873,
+      "grad_norm": 1.5393581266661793,
+      "learning_rate": 2.7871126352722086e-05,
+      "loss": 0.4671,
+      "step": 225
+    },
+    {
+      "epoch": 0.8709055876685935,
+      "grad_norm": 1.5948515405066201,
+      "learning_rate": 2.7746997018975804e-05,
+      "loss": 0.5141,
+      "step": 226
+    },
+    {
+      "epoch": 0.8747591522157996,
+      "grad_norm": 1.6725721797685633,
+      "learning_rate": 2.7622515590393158e-05,
+      "loss": 0.5134,
+      "step": 227
+    },
+    {
+      "epoch": 0.8786127167630058,
+      "grad_norm": 1.9430866061833014,
+      "learning_rate": 2.74976877245558e-05,
+      "loss": 0.4567,
+      "step": 228
+    },
+    {
+      "epoch": 0.882466281310212,
+      "grad_norm": 1.7951935855325456,
+      "learning_rate": 2.737251909479068e-05,
+      "loss": 0.5176,
+      "step": 229
+    },
+    {
+      "epoch": 0.8863198458574181,
+      "grad_norm": 1.5515427698063549,
+      "learning_rate": 2.7247015389912203e-05,
+      "loss": 0.4987,
+      "step": 230
+    },
+    {
+      "epoch": 0.8901734104046243,
+      "grad_norm": 2.423785012348166,
+      "learning_rate": 2.7121182313963666e-05,
+      "loss": 0.4493,
+      "step": 231
+    },
+    {
+      "epoch": 0.8940269749518305,
+      "grad_norm": 1.5248030223399374,
+      "learning_rate": 2.6995025585958026e-05,
+      "loss": 0.5154,
+      "step": 232
+    },
+    {
+      "epoch": 0.8978805394990366,
+      "grad_norm": 1.9085369464839403,
+      "learning_rate": 2.686855093961795e-05,
+      "loss": 0.4695,
+      "step": 233
+    },
+    {
+      "epoch": 0.9017341040462428,
+      "grad_norm": 2.4921294993771657,
+      "learning_rate": 2.674176412311527e-05,
+      "loss": 0.5108,
+      "step": 234
+    },
+    {
+      "epoch": 0.905587668593449,
+      "grad_norm": 1.016492898729909,
+      "learning_rate": 2.6614670898809675e-05,
+      "loss": 0.4305,
+      "step": 235
+    },
+    {
+      "epoch": 0.9094412331406551,
+      "grad_norm": 1.7973135593288705,
+      "learning_rate": 2.648727704298685e-05,
+      "loss": 0.5085,
+      "step": 236
+    },
+    {
+      "epoch": 0.9132947976878613,
+      "grad_norm": 1.298610518247185,
+      "learning_rate": 2.6359588345595956e-05,
+      "loss": 0.4336,
+      "step": 237
+    },
+    {
+      "epoch": 0.9171483622350675,
+      "grad_norm": 1.7615802157799905,
+      "learning_rate": 2.6231610609986442e-05,
+      "loss": 0.4425,
+      "step": 238
+    },
+    {
+      "epoch": 0.9210019267822736,
+      "grad_norm": 2.0393603639058404,
+      "learning_rate": 2.6103349652644356e-05,
+      "loss": 0.5329,
+      "step": 239
+    },
+    {
+      "epoch": 0.9248554913294798,
+      "grad_norm": 1.1646102704038852,
+      "learning_rate": 2.5974811302927907e-05,
+      "loss": 0.4098,
+      "step": 240
+    },
+    {
+      "epoch": 0.928709055876686,
+      "grad_norm": 1.6746235496159276,
+      "learning_rate": 2.5846001402802594e-05,
+      "loss": 0.4589,
+      "step": 241
+    },
+    {
+      "epoch": 0.9325626204238922,
+      "grad_norm": 1.4114912644400681,
+      "learning_rate": 2.5716925806575628e-05,
+      "loss": 0.4426,
+      "step": 242
+    },
+    {
+      "epoch": 0.9364161849710982,
+      "grad_norm": 1.5300374827507783,
+      "learning_rate": 2.5587590380629947e-05,
+      "loss": 0.4389,
+      "step": 243
+    },
+    {
+      "epoch": 0.9402697495183044,
+      "grad_norm": 2.084072213353826,
+      "learning_rate": 2.54580010031575e-05,
+      "loss": 0.5058,
+      "step": 244
+    },
+    {
+      "epoch": 0.9441233140655106,
+      "grad_norm": 1.3650050749477864,
+      "learning_rate": 2.5328163563892162e-05,
+      "loss": 0.4072,
+      "step": 245
+    },
+    {
+      "epoch": 0.9479768786127167,
+      "grad_norm": 1.3576937516102847,
+      "learning_rate": 2.5198083963841988e-05,
+      "loss": 0.4471,
+      "step": 246
+    },
+    {
+      "epoch": 0.9518304431599229,
+      "grad_norm": 1.5006654890833853,
+      "learning_rate": 2.5067768115021077e-05,
+      "loss": 0.4013,
+      "step": 247
+    },
+    {
+      "epoch": 0.9556840077071291,
+      "grad_norm": 1.3335516949676123,
+      "learning_rate": 2.493722194018082e-05,
+      "loss": 0.4171,
+      "step": 248
+    },
+    {
+      "epoch": 0.9595375722543352,
+      "grad_norm": 1.7188267137418751,
+      "learning_rate": 2.4806451372540767e-05,
+      "loss": 0.436,
+      "step": 249
+    },
+    {
+      "epoch": 0.9633911368015414,
+      "grad_norm": 1.5038230569609343,
+      "learning_rate": 2.467546235551892e-05,
+      "loss": 0.4305,
+      "step": 250
+    },
+    {
+      "epoch": 0.9672447013487476,
+      "grad_norm": 1.2898240292343814,
+      "learning_rate": 2.4544260842461638e-05,
+      "loss": 0.4476,
+      "step": 251
+    },
+    {
+      "epoch": 0.9710982658959537,
+      "grad_norm": 1.7360498495478183,
+      "learning_rate": 2.441285279637307e-05,
+      "loss": 0.4324,
+      "step": 252
+    },
+    {
+      "epoch": 0.9749518304431599,
+      "grad_norm": 1.8924393082812891,
+      "learning_rate": 2.4281244189644108e-05,
+      "loss": 0.439,
+      "step": 253
+    },
+    {
+      "epoch": 0.9788053949903661,
+      "grad_norm": 1.2832735489854135,
+      "learning_rate": 2.414944100378097e-05,
+      "loss": 0.3963,
+      "step": 254
+    },
+    {
+      "epoch": 0.9826589595375722,
+      "grad_norm": 1.9408813544452537,
+      "learning_rate": 2.401744922913334e-05,
+      "loss": 0.4501,
+      "step": 255
+    },
+    {
+      "epoch": 0.9865125240847784,
+      "grad_norm": 1.2867999932148788,
+      "learning_rate": 2.388527486462212e-05,
+      "loss": 0.3981,
+      "step": 256
+    },
+    {
+      "epoch": 0.9903660886319846,
+      "grad_norm": 1.0196210656417135,
+      "learning_rate": 2.3752923917466763e-05,
+      "loss": 0.4396,
+      "step": 257
+    },
+    {
+      "epoch": 0.9942196531791907,
+      "grad_norm": 1.2740978791601063,
+      "learning_rate": 2.362040240291227e-05,
+      "loss": 0.3905,
+      "step": 258
+    },
+    {
+      "epoch": 0.9980732177263969,
+      "grad_norm": 1.050993597160996,
+      "learning_rate": 2.34877163439558e-05,
+      "loss": 0.3971,
+      "step": 259
+    },
+    {
+      "epoch": 0.9980732177263969,
+      "eval_loss": 0.4258769750595093,
+      "eval_runtime": 151.7734,
+      "eval_samples_per_second": 13.164,
+      "eval_steps_per_second": 0.415,
+      "step": 259
+    },
+    {
+      "epoch": 1.001926782273603,
+      "grad_norm": 1.3018898740308236,
+      "learning_rate": 2.3354871771072906e-05,
+      "loss": 0.3663,
+      "step": 260
+    },
+    {
+      "epoch": 1.0057803468208093,
+      "grad_norm": 1.768289755543873,
+      "learning_rate": 2.3221874721943495e-05,
+      "loss": 0.3706,
+      "step": 261
+    },
+    {
+      "epoch": 1.0096339113680155,
+      "grad_norm": 1.3709089238690337,
+      "learning_rate": 2.3088731241177378e-05,
+      "loss": 0.4303,
+      "step": 262
+    },
+    {
+      "epoch": 1.0134874759152215,
+      "grad_norm": 1.2747609251876415,
+      "learning_rate": 2.2955447380039576e-05,
+      "loss": 0.3878,
+      "step": 263
+    },
+    {
+      "epoch": 1.0173410404624277,
+      "grad_norm": 1.833982622948961,
+      "learning_rate": 2.282202919617529e-05,
+      "loss": 0.4726,
+      "step": 264
+    },
+    {
+      "epoch": 1.0211946050096339,
+      "grad_norm": 1.0257892835642075,
+      "learning_rate": 2.2688482753334568e-05,
+      "loss": 0.4311,
+      "step": 265
+    },
+    {
+      "epoch": 1.02504816955684,
+      "grad_norm": 1.211081382753947,
+      "learning_rate": 2.2554814121096748e-05,
+      "loss": 0.3797,
+      "step": 266
+    },
+    {
+      "epoch": 1.0289017341040463,
+      "grad_norm": 1.603141836779412,
+      "learning_rate": 2.242102937459456e-05,
+      "loss": 0.4334,
+      "step": 267
+    },
+    {
+      "epoch": 1.0327552986512525,
+      "grad_norm": 0.9082356976857431,
+      "learning_rate": 2.228713459423804e-05,
+      "loss": 0.3477,
+      "step": 268
+    },
+    {
+      "epoch": 1.0366088631984587,
+      "grad_norm": 1.4556959201763473,
+      "learning_rate": 2.215313586543818e-05,
+      "loss": 0.4605,
+      "step": 269
+    },
+    {
+      "epoch": 1.0404624277456647,
+      "grad_norm": 1.157918758481043,
+      "learning_rate": 2.2019039278330324e-05,
+      "loss": 0.3749,
+      "step": 270
+    },
+    {
+      "epoch": 1.0443159922928709,
+      "grad_norm": 1.2365434381583742,
+      "learning_rate": 2.188485092749744e-05,
+      "loss": 0.3438,
+      "step": 271
+    },
+    {
+      "epoch": 1.048169556840077,
+      "grad_norm": 1.3583710499888804,
+      "learning_rate": 2.1750576911693043e-05,
+      "loss": 0.4338,
+      "step": 272
+    },
+    {
+      "epoch": 1.0520231213872833,
+      "grad_norm": 1.373322024670892,
+      "learning_rate": 2.161622333356408e-05,
+      "loss": 0.4425,
+      "step": 273
+    },
+    {
+      "epoch": 1.0558766859344895,
+      "grad_norm": 1.5222033465026896,
+      "learning_rate": 2.148179629937352e-05,
+      "loss": 0.3746,
+      "step": 274
+    },
+    {
+      "epoch": 1.0597302504816957,
+      "grad_norm": 0.9301197570829759,
+      "learning_rate": 2.134730191872288e-05,
+      "loss": 0.3603,
+      "step": 275
+    },
+    {
+      "epoch": 1.0635838150289016,
+      "grad_norm": 1.3349261365465133,
+      "learning_rate": 2.1212746304274482e-05,
+      "loss": 0.3896,
+      "step": 276
+    },
+    {
+      "epoch": 1.0674373795761078,
+      "grad_norm": 1.6542379771126683,
+      "learning_rate": 2.1078135571473712e-05,
+      "loss": 0.4346,
+      "step": 277
+    },
+    {
+      "epoch": 1.071290944123314,
+      "grad_norm": 1.2625424774815728,
+      "learning_rate": 2.094347583827102e-05,
+      "loss": 0.4369,
+      "step": 278
+    },
+    {
+      "epoch": 1.0751445086705202,
+      "grad_norm": 1.242814350522191,
+      "learning_rate": 2.0808773224843882e-05,
+      "loss": 0.4306,
+      "step": 279
+    },
+    {
+      "epoch": 1.0789980732177264,
+      "grad_norm": 1.441960169277262,
+      "learning_rate": 2.0674033853318666e-05,
+      "loss": 0.3905,
+      "step": 280
+    },
+    {
+      "epoch": 1.0828516377649327,
+      "grad_norm": 1.176801789036799,
+      "learning_rate": 2.0539263847492355e-05,
+      "loss": 0.3745,
+      "step": 281
+    },
+    {
+      "epoch": 1.0867052023121386,
+      "grad_norm": 1.0478011807250012,
+      "learning_rate": 2.040446933255423e-05,
+      "loss": 0.4304,
+      "step": 282
+    },
+    {
+      "epoch": 1.0905587668593448,
+      "grad_norm": 0.991803808778807,
+      "learning_rate": 2.0269656434807504e-05,
+      "loss": 0.3328,
+      "step": 283
+    },
+    {
+      "epoch": 1.094412331406551,
+      "grad_norm": 1.536330372789938,
+      "learning_rate": 2.013483128139086e-05,
+      "loss": 0.391,
+      "step": 284
+    },
+    {
+      "epoch": 1.0982658959537572,
+      "grad_norm": 1.1995638320125537,
+      "learning_rate": 2e-05,
+      "loss": 0.4014,
+      "step": 285
+    },
+    {
+      "epoch": 1.1021194605009634,
+      "grad_norm": 1.0998808179080417,
+      "learning_rate": 1.9865168718609142e-05,
+      "loss": 0.3467,
+      "step": 286
+    },
+    {
+      "epoch": 1.1059730250481696,
+      "grad_norm": 1.1533276354863014,
+      "learning_rate": 1.9730343565192506e-05,
+      "loss": 0.3654,
+      "step": 287
+    },
+    {
+      "epoch": 1.1098265895953756,
+      "grad_norm": 1.395165430926343,
+      "learning_rate": 1.9595530667445775e-05,
+      "loss": 0.3897,
+      "step": 288
+    },
+    {
+      "epoch": 1.1136801541425818,
+      "grad_norm": 1.3829869394831174,
+      "learning_rate": 1.946073615250765e-05,
+      "loss": 0.3664,
+      "step": 289
+    },
+    {
+      "epoch": 1.117533718689788,
+      "grad_norm": 1.6694598636029911,
+      "learning_rate": 1.9325966146681337e-05,
+      "loss": 0.3937,
+      "step": 290
+    },
+    {
+      "epoch": 1.1213872832369942,
+      "grad_norm": 1.3093898924216434,
+      "learning_rate": 1.919122677515612e-05,
+      "loss": 0.4475,
+      "step": 291
+    },
+    {
+      "epoch": 1.1252408477842004,
+      "grad_norm": 1.2830702205218405,
+      "learning_rate": 1.905652416172899e-05,
+      "loss": 0.4055,
+      "step": 292
+    },
+    {
+      "epoch": 1.1290944123314066,
+      "grad_norm": 1.422016127363369,
+      "learning_rate": 1.8921864428526295e-05,
+      "loss": 0.4306,
+      "step": 293
+    },
+    {
+      "epoch": 1.1329479768786128,
+      "grad_norm": 1.0443832316958135,
+      "learning_rate": 1.8787253695725524e-05,
+      "loss": 0.306,
+      "step": 294
+    },
+    {
+      "epoch": 1.1368015414258188,
+      "grad_norm": 1.0396170075258768,
+      "learning_rate": 1.8652698081277127e-05,
+      "loss": 0.3808,
+      "step": 295
+    },
+    {
+      "epoch": 1.140655105973025,
+      "grad_norm": 1.4482799449738568,
+      "learning_rate": 1.851820370062648e-05,
+      "loss": 0.3766,
+      "step": 296
+    },
+    {
+      "epoch": 1.1445086705202312,
+      "grad_norm": 1.4383150667662055,
+      "learning_rate": 1.8383776666435927e-05,
+      "loss": 0.3807,
+      "step": 297
+    },
+    {
+      "epoch": 1.1483622350674374,
+      "grad_norm": 1.052851787398113,
+      "learning_rate": 1.824942308830696e-05,
+      "loss": 0.3193,
+      "step": 298
+    },
+    {
+      "epoch": 1.1522157996146436,
+      "grad_norm": 1.1901475083434114,
+      "learning_rate": 1.8115149072502564e-05,
+      "loss": 0.3644,
+      "step": 299
+    },
+    {
+      "epoch": 1.1560693641618498,
+      "grad_norm": 1.0719741190000858,
+      "learning_rate": 1.798096072166968e-05,
+      "loss": 0.3265,
+      "step": 300
+    },
+    {
+      "epoch": 1.1599229287090558,
+      "grad_norm": 0.9399484435440966,
+      "learning_rate": 1.7846864134561828e-05,
+      "loss": 0.3013,
+      "step": 301
+    },
+    {
+      "epoch": 1.163776493256262,
+      "grad_norm": 0.8649780684652991,
+      "learning_rate": 1.7712865405761967e-05,
+      "loss": 0.331,
+      "step": 302
+    },
+    {
+      "epoch": 1.1676300578034682,
+      "grad_norm": 1.093013914822741,
+      "learning_rate": 1.757897062540545e-05,
+      "loss": 0.3672,
+      "step": 303
+    },
+    {
+      "epoch": 1.1714836223506744,
+      "grad_norm": 1.3242259881261507,
+      "learning_rate": 1.7445185878903252e-05,
+      "loss": 0.3461,
+      "step": 304
+    },
+    {
+      "epoch": 1.1753371868978806,
+      "grad_norm": 1.5294924031862211,
+      "learning_rate": 1.7311517246665435e-05,
+      "loss": 0.3381,
+      "step": 305
+    },
+    {
+      "epoch": 1.1791907514450868,
+      "grad_norm": 1.4097073214129088,
+      "learning_rate": 1.7177970803824714e-05,
+      "loss": 0.4501,
+      "step": 306
+    },
+    {
+      "epoch": 1.183044315992293,
+      "grad_norm": 1.1405636655876248,
+      "learning_rate": 1.7044552619960434e-05,
+      "loss": 0.322,
+      "step": 307
+    },
+    {
+      "epoch": 1.186897880539499,
+      "grad_norm": 1.172637190005047,
+      "learning_rate": 1.691126875882263e-05,
+      "loss": 0.3453,
+      "step": 308
+    },
+    {
+      "epoch": 1.1907514450867052,
+      "grad_norm": 1.0104423854938296,
+      "learning_rate": 1.677812527805651e-05,
+      "loss": 0.3248,
+      "step": 309
+    },
+    {
+      "epoch": 1.1946050096339114,
+      "grad_norm": 0.9585927088271504,
+      "learning_rate": 1.6645128228927104e-05,
+      "loss": 0.3153,
+      "step": 310
+    },
+    {
+      "epoch": 1.1984585741811176,
+      "grad_norm": 0.7642180964221266,
+      "learning_rate": 1.6512283656044207e-05,
+      "loss": 0.3576,
+      "step": 311
+    },
+    {
+      "epoch": 1.2023121387283238,
+      "grad_norm": 1.064288446414666,
+      "learning_rate": 1.637959759708774e-05,
+      "loss": 0.3842,
+      "step": 312
+    },
+    {
+      "epoch": 1.2061657032755297,
+      "grad_norm": 1.1471701151580358,
+      "learning_rate": 1.6247076082533244e-05,
+      "loss": 0.3682,
+      "step": 313
+    },
+    {
+      "epoch": 1.210019267822736,
+      "grad_norm": 0.7613384576508663,
+      "learning_rate": 1.6114725135377883e-05,
+      "loss": 0.3671,
+      "step": 314
+    },
+    {
+      "epoch": 1.2138728323699421,
+      "grad_norm": 1.1314879376679692,
+      "learning_rate": 1.5982550770866665e-05,
+      "loss": 0.3509,
+      "step": 315
+    },
+    {
+      "epoch": 1.2177263969171483,
+      "grad_norm": 1.0721877801971562,
+      "learning_rate": 1.585055899621904e-05,
+      "loss": 0.388,
+      "step": 316
+    },
+    {
+      "epoch": 1.2215799614643545,
+      "grad_norm": 1.261955038248264,
+      "learning_rate": 1.5718755810355895e-05,
+      "loss": 0.3453,
+      "step": 317
+    },
+    {
+      "epoch": 1.2254335260115607,
+      "grad_norm": 1.2728238431643502,
+      "learning_rate": 1.5587147203626934e-05,
+      "loss": 0.3638,
+      "step": 318
+    },
+    {
+      "epoch": 1.229287090558767,
+      "grad_norm": 1.3228194347927702,
+      "learning_rate": 1.5455739157538362e-05,
+      "loss": 0.3922,
+      "step": 319
+    },
+    {
+      "epoch": 1.2331406551059731,
+      "grad_norm": 0.759365184137883,
+      "learning_rate": 1.532453764448109e-05,
+      "loss": 0.3769,
+      "step": 320
+    },
+    {
+      "epoch": 1.2369942196531791,
+      "grad_norm": 1.0387794799239043,
+      "learning_rate": 1.5193548627459238e-05,
+      "loss": 0.3487,
+      "step": 321
+    },
+    {
+      "epoch": 1.2408477842003853,
+      "grad_norm": 1.653174900496495,
+      "learning_rate": 1.5062778059819184e-05,
+      "loss": 0.3325,
+      "step": 322
+    },
+    {
+      "epoch": 1.2447013487475915,
+      "grad_norm": 0.9071493490028995,
+      "learning_rate": 1.493223188497893e-05,
+      "loss": 0.3099,
+      "step": 323
+    },
+    {
+      "epoch": 1.2485549132947977,
+      "grad_norm": 0.909128453253325,
+      "learning_rate": 1.4801916036158017e-05,
+      "loss": 0.3484,
+      "step": 324
+    },
+    {
+      "epoch": 1.252408477842004,
+      "grad_norm": 0.9104702137645303,
+      "learning_rate": 1.4671836436107851e-05,
+      "loss": 0.3151,
+      "step": 325
+    },
+    {
+      "epoch": 1.25626204238921,
+      "grad_norm": 1.0657384235342173,
+      "learning_rate": 1.4541998996842503e-05,
+      "loss": 0.3328,
+      "step": 326
+    },
+    {
+      "epoch": 1.260115606936416,
+      "grad_norm": 1.0115714194064442,
+      "learning_rate": 1.4412409619370058e-05,
+      "loss": 0.3114,
+      "step": 327
+    },
+    {
+      "epoch": 1.2639691714836223,
+      "grad_norm": 0.9001086745125582,
+      "learning_rate": 1.4283074193424379e-05,
+      "loss": 0.3188,
+      "step": 328
+    },
+    {
+      "epoch": 1.2678227360308285,
+      "grad_norm": 1.2276345166542122,
+      "learning_rate": 1.4153998597197417e-05,
+      "loss": 0.3498,
+      "step": 329
+    },
+    {
+      "epoch": 1.2716763005780347,
+      "grad_norm": 0.7533021116197035,
+      "learning_rate": 1.4025188697072098e-05,
+      "loss": 0.3418,
+      "step": 330
+    },
+    {
+      "epoch": 1.275529865125241,
+      "grad_norm": 0.7620164921410112,
+      "learning_rate": 1.3896650347355652e-05,
+      "loss": 0.2843,
+      "step": 331
+    },
+    {
+      "epoch": 1.2793834296724471,
+      "grad_norm": 1.085725296514296,
+      "learning_rate": 1.3768389390013558e-05,
+      "loss": 0.3698,
+      "step": 332
+    },
+    {
+      "epoch": 1.2832369942196533,
+      "grad_norm": 0.7656462946423266,
+      "learning_rate": 1.3640411654404058e-05,
+      "loss": 0.3526,
+      "step": 333
+    },
+    {
+      "epoch": 1.2870905587668593,
+      "grad_norm": 0.8688261241761966,
+      "learning_rate": 1.3512722957013157e-05,
+      "loss": 0.3287,
+      "step": 334
+    },
+    {
+      "epoch": 1.2909441233140655,
+      "grad_norm": 0.9102316741848134,
+      "learning_rate": 1.3385329101190338e-05,
+      "loss": 0.3328,
+      "step": 335
+    },
+    {
+      "epoch": 1.2947976878612717,
+      "grad_norm": 0.8532527486919501,
+      "learning_rate": 1.3258235876884735e-05,
+      "loss": 0.3231,
+      "step": 336
+    },
+    {
+      "epoch": 1.298651252408478,
+      "grad_norm": 0.6725300585239861,
+      "learning_rate": 1.3131449060382053e-05,
+      "loss": 0.2852,
+      "step": 337
+    },
+    {
+      "epoch": 1.3025048169556839,
+      "grad_norm": 1.0698268373783526,
+      "learning_rate": 1.3004974414041987e-05,
+      "loss": 0.3087,
+      "step": 338
+    },
+    {
+      "epoch": 1.30635838150289,
+      "grad_norm": 1.1722160127956573,
+      "learning_rate": 1.287881768603634e-05,
+      "loss": 0.3365,
+      "step": 339
+    },
+    {
+      "epoch": 1.3102119460500963,
+      "grad_norm": 0.6736626507697272,
+      "learning_rate": 1.27529846100878e-05,
+      "loss": 0.2999,
+      "step": 340
+    },
+    {
+      "epoch": 1.3140655105973025,
+      "grad_norm": 1.1063913885843315,
+      "learning_rate": 1.2627480905209328e-05,
+      "loss": 0.2894,
+      "step": 341
+    },
+    {
+      "epoch": 1.3179190751445087,
+      "grad_norm": 1.109602932151094,
+      "learning_rate": 1.2502312275444205e-05,
+      "loss": 0.3495,
+      "step": 342
+    },
+    {
+      "epoch": 1.3217726396917149,
+      "grad_norm": 1.1957687821810759,
+      "learning_rate": 1.2377484409606848e-05,
+      "loss": 0.3601,
+      "step": 343
+    },
+    {
+      "epoch": 1.325626204238921,
+      "grad_norm": 1.128237352664405,
+      "learning_rate": 1.22530029810242e-05,
+      "loss": 0.3514,
+      "step": 344
+    },
+    {
+      "epoch": 1.3294797687861273,
+      "grad_norm": 1.415323100911558,
+      "learning_rate": 1.2128873647277919e-05,
+      "loss": 0.3287,
+      "step": 345
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 1.236826446216501,
+      "learning_rate": 1.200510204994724e-05,
+      "loss": 0.3062,
+      "step": 346
+    },
+    {
+      "epoch": 1.3371868978805395,
+      "grad_norm": 1.0869697615225693,
+      "learning_rate": 1.1881693814352543e-05,
+      "loss": 0.3372,
+      "step": 347
+    },
+    {
+      "epoch": 1.3410404624277457,
+      "grad_norm": 0.8579173376211442,
+      "learning_rate": 1.1758654549299735e-05,
+      "loss": 0.3162,
+      "step": 348
+    },
+    {
+      "epoch": 1.3448940269749519,
+      "grad_norm": 1.1076519772349536,
+      "learning_rate": 1.1635989846825275e-05,
+      "loss": 0.3595,
+      "step": 349
+    },
+    {
+      "epoch": 1.348747591522158,
+      "grad_norm": 1.0968809462254943,
+      "learning_rate": 1.1513705281942072e-05,
+      "loss": 0.3138,
+      "step": 350
+    },
+    {
+      "epoch": 1.352601156069364,
+      "grad_norm": 0.8097631352039958,
+      "learning_rate": 1.1391806412386086e-05,
+      "loss": 0.3064,
+      "step": 351
+    },
+    {
+      "epoch": 1.3564547206165702,
+      "grad_norm": 0.9302059439245486,
+      "learning_rate": 1.127029877836371e-05,
+      "loss": 0.3361,
+      "step": 352
+    },
+    {
+      "epoch": 1.3603082851637764,
+      "grad_norm": 1.1085708625474628,
+      "learning_rate": 1.1149187902300032e-05,
+      "loss": 0.2918,
+      "step": 353
+    },
+    {
+      "epoch": 1.3641618497109826,
+      "grad_norm": 1.2982099303179524,
+      "learning_rate": 1.102847928858776e-05,
+      "loss": 0.3243,
+      "step": 354
+    },
+    {
+      "epoch": 1.3680154142581888,
+      "grad_norm": 0.8325178281772523,
+      "learning_rate": 1.0908178423337135e-05,
+      "loss": 0.3042,
+      "step": 355
+    },
+    {
+      "epoch": 1.371868978805395,
+      "grad_norm": 1.0264691032333937,
+      "learning_rate": 1.0788290774126549e-05,
+      "loss": 0.3674,
+      "step": 356
+    },
+    {
+      "epoch": 1.3757225433526012,
+      "grad_norm": 1.5611140030270088,
+      "learning_rate": 1.0668821789754041e-05,
+      "loss": 0.3395,
+      "step": 357
+    },
+    {
+      "epoch": 1.3795761078998074,
+      "grad_norm": 0.6905356535042156,
+      "learning_rate": 1.0549776899989686e-05,
+      "loss": 0.326,
+      "step": 358
+    },
+    {
+      "epoch": 1.3834296724470134,
+      "grad_norm": 0.813432697566474,
+      "learning_rate": 1.043116151532877e-05,
+      "loss": 0.3308,
+      "step": 359
+    },
+    {
+      "epoch": 1.3872832369942196,
+      "grad_norm": 0.947125986929793,
+      "learning_rate": 1.0312981026745952e-05,
+      "loss": 0.3079,
+      "step": 360
+    },
+    {
+      "epoch": 1.3911368015414258,
+      "grad_norm": 0.9541134784519973,
+      "learning_rate": 1.019524080545017e-05,
+      "loss": 0.3527,
+      "step": 361
+    },
+    {
+      "epoch": 1.394990366088632,
+      "grad_norm": 0.650621794786191,
+      "learning_rate": 1.0077946202640603e-05,
+      "loss": 0.2879,
+      "step": 362
+    },
+    {
+      "epoch": 1.3988439306358382,
+      "grad_norm": 0.7999542405054426,
+      "learning_rate": 9.961102549263393e-06,
+      "loss": 0.293,
+      "step": 363
+    },
+    {
+      "epoch": 1.4026974951830442,
+      "grad_norm": 1.0074632544627469,
+      "learning_rate": 9.844715155769418e-06,
+      "loss": 0.3679,
+      "step": 364
+    },
+    {
+      "epoch": 1.4065510597302504,
+      "grad_norm": 0.7914057577416254,
+      "learning_rate": 9.72878931187288e-06,
+      "loss": 0.2646,
+      "step": 365
+    },
+    {
+      "epoch": 1.4104046242774566,
+      "grad_norm": 0.8463237752662545,
+      "learning_rate": 9.613330286310952e-06,
+      "loss": 0.2932,
+      "step": 366
+    },
+    {
+      "epoch": 1.4142581888246628,
+      "grad_norm": 0.932880991782926,
+      "learning_rate": 9.498343326604249e-06,
+      "loss": 0.3013,
+      "step": 367
+    },
+    {
+      "epoch": 1.418111753371869,
+      "grad_norm": 0.9821817374697017,
+      "learning_rate": 9.3838336588184e-06,
+      "loss": 0.3028,
+      "step": 368
+    },
+    {
+      "epoch": 1.4219653179190752,
+      "grad_norm": 0.8469145630358891,
+      "learning_rate": 9.269806487326491e-06,
+      "loss": 0.3345,
+      "step": 369
+    },
+    {
+      "epoch": 1.4258188824662814,
+      "grad_norm": 1.037169772414413,
+      "learning_rate": 9.156266994572518e-06,
+      "loss": 0.355,
+      "step": 370
+    },
+    {
+      "epoch": 1.4296724470134876,
+      "grad_norm": 0.7213160294660059,
+      "learning_rate": 9.043220340835895e-06,
+      "loss": 0.2769,
+      "step": 371
+    },
+    {
+      "epoch": 1.4335260115606936,
+      "grad_norm": 0.8831900688609602,
+      "learning_rate": 8.930671663996864e-06,
+      "loss": 0.2811,
+      "step": 372
+    },
+    {
+      "epoch": 1.4373795761078998,
+      "grad_norm": 0.9088605343264572,
+      "learning_rate": 8.818626079303038e-06,
+      "loss": 0.3326,
+      "step": 373
+    },
+    {
+      "epoch": 1.441233140655106,
+      "grad_norm": 1.0151812161616465,
+      "learning_rate": 8.707088679136898e-06,
+      "loss": 0.3964,
+      "step": 374
+    },
+    {
+      "epoch": 1.4450867052023122,
+      "grad_norm": 0.721796968080708,
+      "learning_rate": 8.59606453278432e-06,
+      "loss": 0.2616,
+      "step": 375
+    },
+    {
+      "epoch": 1.4489402697495182,
+      "grad_norm": 0.7436852548835157,
+      "learning_rate": 8.485558686204215e-06,
+      "loss": 0.3289,
+      "step": 376
+    },
+    {
+      "epoch": 1.4527938342967244,
+      "grad_norm": 0.9085710653664684,
+      "learning_rate": 8.37557616179918e-06,
+      "loss": 0.3263,
+      "step": 377
+    },
+    {
+      "epoch": 1.4566473988439306,
+      "grad_norm": 0.7242098860139589,
+      "learning_rate": 8.266121958187246e-06,
+      "loss": 0.3063,
+      "step": 378
+    },
+    {
+      "epoch": 1.4605009633911368,
+      "grad_norm": 0.8037417491106659,
+      "learning_rate": 8.15720104997468e-06,
+      "loss": 0.2835,
+      "step": 379
+    },
+    {
+      "epoch": 1.464354527938343,
+      "grad_norm": 0.6693841689504254,
+      "learning_rate": 8.048818387529888e-06,
+      "loss": 0.3096,
+      "step": 380
+    },
+    {
+      "epoch": 1.4682080924855492,
+      "grad_norm": 0.6386913396187637,
+      "learning_rate": 7.940978896758449e-06,
+      "loss": 0.2871,
+      "step": 381
+    },
+    {
+      "epoch": 1.4720616570327554,
+      "grad_norm": 0.7334763653626704,
+      "learning_rate": 7.833687478879228e-06,
+      "loss": 0.32,
+      "step": 382
+    },
+    {
+      "epoch": 1.4759152215799616,
+      "grad_norm": 0.7171482705229991,
+      "learning_rate": 7.726949010201585e-06,
+      "loss": 0.3153,
+      "step": 383
+    },
+    {
+      "epoch": 1.4797687861271676,
+      "grad_norm": 0.786019322707822,
+      "learning_rate": 7.620768341903817e-06,
+      "loss": 0.2843,
+      "step": 384
+    },
+    {
+      "epoch": 1.4836223506743738,
+      "grad_norm": 0.9217824425126812,
+      "learning_rate": 7.5151502998126035e-06,
+      "loss": 0.342,
+      "step": 385
+    },
+    {
+      "epoch": 1.48747591522158,
+      "grad_norm": 0.9974009492954946,
+      "learning_rate": 7.410099684183738e-06,
+      "loss": 0.2469,
+      "step": 386
+    },
+    {
+      "epoch": 1.4913294797687862,
+      "grad_norm": 0.7613952875838962,
+      "learning_rate": 7.305621269483927e-06,
+      "loss": 0.311,
+      "step": 387
+    },
+    {
+      "epoch": 1.4951830443159924,
+      "grad_norm": 0.8389199365953313,
+      "learning_rate": 7.201719804173797e-06,
+      "loss": 0.321,
+      "step": 388
+    },
+    {
+      "epoch": 1.4990366088631983,
+      "grad_norm": 0.8436343238052573,
+      "learning_rate": 7.098400010492079e-06,
+      "loss": 0.3375,
+      "step": 389
+    },
+    {
+      "epoch": 1.5028901734104045,
+      "grad_norm": 0.7057291557928584,
+      "learning_rate": 6.995666584240998e-06,
+      "loss": 0.2924,
+      "step": 390
+    },
+    {
+      "epoch": 1.5067437379576107,
+      "grad_norm": 0.7636872711492277,
+      "learning_rate": 6.893524194572856e-06,
+      "loss": 0.293,
+      "step": 391
+    },
+    {
+      "epoch": 1.510597302504817,
+      "grad_norm": 0.926804984511261,
+      "learning_rate": 6.791977483777808e-06,
+      "loss": 0.304,
+      "step": 392
+    },
+    {
+      "epoch": 1.5144508670520231,
+      "grad_norm": 0.8113244891141366,
+      "learning_rate": 6.691031067072866e-06,
+      "loss": 0.3202,
+      "step": 393
+    },
+    {
+      "epoch": 1.5183044315992293,
+      "grad_norm": 0.6667861770618242,
+      "learning_rate": 6.5906895323921805e-06,
+      "loss": 0.2816,
+      "step": 394
+    },
+    {
+      "epoch": 1.5221579961464355,
+      "grad_norm": 0.8795394551278755,
+      "learning_rate": 6.490957440178467e-06,
+      "loss": 0.2892,
+      "step": 395
+    },
+    {
+      "epoch": 1.5260115606936417,
+      "grad_norm": 0.9108462944261728,
+      "learning_rate": 6.391839323175788e-06,
+      "loss": 0.3503,
+      "step": 396
+    },
+    {
+      "epoch": 1.529865125240848,
+      "grad_norm": 0.8980380594575577,
+      "learning_rate": 6.293339686223521e-06,
+      "loss": 0.3322,
+      "step": 397
+    },
+    {
+      "epoch": 1.533718689788054,
+      "grad_norm": 0.6868397537542229,
+      "learning_rate": 6.1954630060516005e-06,
+      "loss": 0.2826,
+      "step": 398
+    },
+    {
+      "epoch": 1.5375722543352601,
+      "grad_norm": 0.7791737364861953,
+      "learning_rate": 6.098213731077101e-06,
+      "loss": 0.3134,
+      "step": 399
+    },
+    {
+      "epoch": 1.5414258188824663,
+      "grad_norm": 0.6867571528771647,
+      "learning_rate": 6.001596281201998e-06,
+      "loss": 0.2865,
+      "step": 400
+    },
+    {
+      "epoch": 1.5452793834296723,
+      "grad_norm": 0.9804075340302699,
+      "learning_rate": 5.905615047612352e-06,
+      "loss": 0.3528,
+      "step": 401
+    },
+    {
+      "epoch": 1.5491329479768785,
+      "grad_norm": 0.6720710667167724,
+      "learning_rate": 5.810274392578672e-06,
+      "loss": 0.2754,
+      "step": 402
+    },
+    {
+      "epoch": 1.5529865125240847,
+      "grad_norm": 0.6802925027816661,
+      "learning_rate": 5.715578649257709e-06,
+      "loss": 0.2516,
+      "step": 403
+    },
+    {
+      "epoch": 1.556840077071291,
+      "grad_norm": 0.7494941138748478,
+      "learning_rate": 5.621532121495468e-06,
+      "loss": 0.2928,
+      "step": 404
+    },
+    {
+      "epoch": 1.560693641618497,
+      "grad_norm": 0.5855579359311635,
+      "learning_rate": 5.528139083631641e-06,
+      "loss": 0.2755,
+      "step": 405
+    },
+    {
+      "epoch": 1.5645472061657033,
+      "grad_norm": 0.8765684000753372,
+      "learning_rate": 5.4354037803053124e-06,
+      "loss": 0.2721,
+      "step": 406
+    },
+    {
+      "epoch": 1.5684007707129095,
+      "grad_norm": 0.8693102037593315,
+      "learning_rate": 5.343330426262075e-06,
+      "loss": 0.2847,
+      "step": 407
+    },
+    {
+      "epoch": 1.5722543352601157,
+      "grad_norm": 1.0221938673812996,
+      "learning_rate": 5.2519232061624255e-06,
+      "loss": 0.3375,
+      "step": 408
+    },
+    {
+      "epoch": 1.576107899807322,
+      "grad_norm": 0.6916381894839094,
+      "learning_rate": 5.161186274391632e-06,
+      "loss": 0.2952,
+      "step": 409
+    },
+    {
+      "epoch": 1.579961464354528,
+      "grad_norm": 0.6607350250192912,
+      "learning_rate": 5.071123754870888e-06,
+      "loss": 0.2892,
+      "step": 410
+    },
+    {
+      "epoch": 1.583815028901734,
+      "grad_norm": 0.709997113458217,
+      "learning_rate": 4.981739740869866e-06,
+      "loss": 0.3006,
+      "step": 411
+    },
+    {
+      "epoch": 1.5876685934489403,
+      "grad_norm": 0.8317299871071954,
+      "learning_rate": 4.893038294820736e-06,
+      "loss": 0.2681,
+      "step": 412
+    },
+    {
+      "epoch": 1.5915221579961463,
+      "grad_norm": 0.6514943944174995,
+      "learning_rate": 4.805023448133468e-06,
+      "loss": 0.3109,
+      "step": 413
+    },
+    {
+      "epoch": 1.5953757225433525,
+      "grad_norm": 0.7060506760393167,
+      "learning_rate": 4.717699201012658e-06,
+      "loss": 0.2561,
+      "step": 414
+    },
+    {
+      "epoch": 1.5992292870905587,
+      "grad_norm": 0.6560682680927723,
+      "learning_rate": 4.6310695222757065e-06,
+      "loss": 0.351,
+      "step": 415
+    },
+    {
+      "epoch": 1.6030828516377649,
+      "grad_norm": 0.7519900581847846,
+      "learning_rate": 4.545138349172418e-06,
+      "loss": 0.2967,
+      "step": 416
+    },
+    {
+      "epoch": 1.606936416184971,
+      "grad_norm": 0.7734834025884938,
+      "learning_rate": 4.459909587206082e-06,
+      "loss": 0.2859,
+      "step": 417
+    },
+    {
+      "epoch": 1.6107899807321773,
+      "grad_norm": 0.6021137879538668,
+      "learning_rate": 4.375387109955953e-06,
+      "loss": 0.2766,
+      "step": 418
+    },
+    {
+      "epoch": 1.6146435452793835,
+      "grad_norm": 0.617528729879879,
+      "learning_rate": 4.291574758901224e-06,
+      "loss": 0.2882,
+      "step": 419
+    },
+    {
+      "epoch": 1.6184971098265897,
+      "grad_norm": 0.6024787320260311,
+      "learning_rate": 4.208476343246417e-06,
+      "loss": 0.3055,
+      "step": 420
+    },
+    {
+      "epoch": 1.6223506743737959,
+      "grad_norm": 0.7809194181983308,
+      "learning_rate": 4.12609563974824e-06,
+      "loss": 0.3413,
+      "step": 421
+    },
+    {
+      "epoch": 1.626204238921002,
+      "grad_norm": 0.7428919044347968,
+      "learning_rate": 4.0444363925439845e-06,
+      "loss": 0.2822,
+      "step": 422
+    },
+    {
+      "epoch": 1.630057803468208,
+      "grad_norm": 0.8313087879713988,
+      "learning_rate": 3.963502312981298e-06,
+      "loss": 0.3037,
+      "step": 423
+    },
+    {
+      "epoch": 1.6339113680154143,
+      "grad_norm": 0.7485349105988456,
+      "learning_rate": 3.883297079449559e-06,
+      "loss": 0.2736,
+      "step": 424
+    },
+    {
+      "epoch": 1.6377649325626205,
+      "grad_norm": 0.6278539139461561,
+      "learning_rate": 3.803824337212678e-06,
+      "loss": 0.2834,
+      "step": 425
+    },
+    {
+      "epoch": 1.6416184971098264,
+      "grad_norm": 0.6237587967099586,
+      "learning_rate": 3.7250876982433947e-06,
+      "loss": 0.275,
+      "step": 426
+    },
+    {
+      "epoch": 1.6454720616570326,
+      "grad_norm": 0.6345631909381717,
+      "learning_rate": 3.6470907410591695e-06,
+      "loss": 0.2961,
+      "step": 427
+    },
+    {
+      "epoch": 1.6493256262042388,
+      "grad_norm": 0.6867481603368362,
+      "learning_rate": 3.569837010559505e-06,
+      "loss": 0.3018,
+      "step": 428
+    },
+    {
+      "epoch": 1.653179190751445,
+      "grad_norm": 0.5911022328472578,
+      "learning_rate": 3.4933300178648423e-06,
+      "loss": 0.257,
+      "step": 429
+    },
+    {
+      "epoch": 1.6570327552986512,
+      "grad_norm": 0.6804693404362794,
+      "learning_rate": 3.417573240156984e-06,
+      "loss": 0.296,
+      "step": 430
+    },
+    {
+      "epoch": 1.6608863198458574,
+      "grad_norm": 0.72735026642116,
+      "learning_rate": 3.3425701205210557e-06,
+      "loss": 0.3169,
+      "step": 431
+    },
+    {
+      "epoch": 1.6647398843930636,
+      "grad_norm": 0.6635536624459238,
+      "learning_rate": 3.2683240677890373e-06,
+      "loss": 0.2652,
+      "step": 432
+    },
+    {
+      "epoch": 1.6685934489402698,
+      "grad_norm": 0.607762952833936,
+      "learning_rate": 3.194838456384819e-06,
+      "loss": 0.2476,
+      "step": 433
+    },
+    {
+      "epoch": 1.672447013487476,
+      "grad_norm": 0.5435405578589255,
+      "learning_rate": 3.122116626170826e-06,
+      "loss": 0.2365,
+      "step": 434
+    },
+    {
+      "epoch": 1.6763005780346822,
+      "grad_norm": 0.6817577487553824,
+      "learning_rate": 3.0501618822962566e-06,
+      "loss": 0.3021,
+      "step": 435
+    },
+    {
+      "epoch": 1.6801541425818882,
+      "grad_norm": 0.7502351560290864,
+      "learning_rate": 2.9789774950468265e-06,
+      "loss": 0.3289,
+      "step": 436
+    },
+    {
+      "epoch": 1.6840077071290944,
+      "grad_norm": 0.6694176059458067,
+      "learning_rate": 2.908566699696174e-06,
+      "loss": 0.2915,
+      "step": 437
+    },
+    {
+      "epoch": 1.6878612716763006,
+      "grad_norm": 0.6629312059099088,
+      "learning_rate": 2.838932696358798e-06,
+      "loss": 0.3103,
+      "step": 438
+    },
+    {
+      "epoch": 1.6917148362235066,
+      "grad_norm": 0.8349480949645633,
+      "learning_rate": 2.77007864984461e-06,
+      "loss": 0.2938,
+      "step": 439
+    },
+    {
+      "epoch": 1.6955684007707128,
+      "grad_norm": 0.7489107344916376,
+      "learning_rate": 2.7020076895151226e-06,
+      "loss": 0.3284,
+      "step": 440
+    },
+    {
+      "epoch": 1.699421965317919,
+      "grad_norm": 0.6851569068577846,
+      "learning_rate": 2.6347229091411876e-06,
+      "loss": 0.3074,
+      "step": 441
+    },
+    {
+      "epoch": 1.7032755298651252,
+      "grad_norm": 0.4757754476528696,
+      "learning_rate": 2.5682273667624235e-06,
+      "loss": 0.2425,
+      "step": 442
+    },
+    {
+      "epoch": 1.7071290944123314,
+      "grad_norm": 0.6049269606790216,
+      "learning_rate": 2.5025240845481945e-06,
+      "loss": 0.2709,
+      "step": 443
+    },
+    {
+      "epoch": 1.7109826589595376,
+      "grad_norm": 0.6082751240069765,
+      "learning_rate": 2.4376160486602875e-06,
+      "loss": 0.3106,
+      "step": 444
+    },
+    {
+      "epoch": 1.7148362235067438,
+      "grad_norm": 0.6511104858946544,
+      "learning_rate": 2.37350620911716e-06,
+      "loss": 0.2983,
+      "step": 445
+    },
+    {
+      "epoch": 1.71868978805395,
+      "grad_norm": 0.6008366910511428,
+      "learning_rate": 2.3101974796599015e-06,
+      "loss": 0.2836,
+      "step": 446
+    },
+    {
+      "epoch": 1.7225433526011562,
+      "grad_norm": 0.6288330836855687,
+      "learning_rate": 2.247692737619769e-06,
+      "loss": 0.2594,
+      "step": 447
+    },
+    {
+      "epoch": 1.7263969171483622,
+      "grad_norm": 0.6073567738874573,
+      "learning_rate": 2.1859948237874517e-06,
+      "loss": 0.2655,
+      "step": 448
+    },
+    {
+      "epoch": 1.7302504816955684,
+      "grad_norm": 0.5540646853483305,
+      "learning_rate": 2.1251065422839212e-06,
+      "loss": 0.2721,
+      "step": 449
+    },
+    {
+      "epoch": 1.7341040462427746,
+      "grad_norm": 0.6179650224299514,
+      "learning_rate": 2.0650306604330163e-06,
+      "loss": 0.2871,
+      "step": 450
+    },
+    {
+      "epoch": 1.7379576107899806,
+      "grad_norm": 0.784590739172643,
+      "learning_rate": 2.005769908635662e-06,
+      "loss": 0.3636,
+      "step": 451
+    },
+    {
+      "epoch": 1.7418111753371868,
+      "grad_norm": 0.48504899559732223,
+      "learning_rate": 1.947326980245763e-06,
+      "loss": 0.2493,
+      "step": 452
+    },
+    {
+      "epoch": 1.745664739884393,
+      "grad_norm": 0.8987552328931523,
+      "learning_rate": 1.889704531447809e-06,
+      "loss": 0.2573,
+      "step": 453
+    },
+    {
+      "epoch": 1.7495183044315992,
+      "grad_norm": 0.5767751215303322,
+      "learning_rate": 1.832905181136142e-06,
+      "loss": 0.2385,
+      "step": 454
+    },
+    {
+      "epoch": 1.7533718689788054,
+      "grad_norm": 0.6027911760471953,
+      "learning_rate": 1.7769315107959385e-06,
+      "loss": 0.2577,
+      "step": 455
+    },
+    {
+      "epoch": 1.7572254335260116,
+      "grad_norm": 0.5310368311114125,
+      "learning_rate": 1.7217860643858797e-06,
+      "loss": 0.2632,
+      "step": 456
+    },
+    {
+      "epoch": 1.7610789980732178,
+      "grad_norm": 0.907578227845979,
+      "learning_rate": 1.6674713482225246e-06,
+      "loss": 0.2815,
+      "step": 457
+    },
+    {
+      "epoch": 1.764932562620424,
+      "grad_norm": 0.6172664735840684,
+      "learning_rate": 1.6139898308664093e-06,
+      "loss": 0.2779,
+      "step": 458
+    },
+    {
+      "epoch": 1.7687861271676302,
+      "grad_norm": 0.6470799229179937,
+      "learning_rate": 1.5613439430098388e-06,
+      "loss": 0.3075,
+      "step": 459
+    },
+    {
+      "epoch": 1.7726396917148364,
+      "grad_norm": 0.6173914059389243,
+      "learning_rate": 1.5095360773664402e-06,
+      "loss": 0.2604,
+      "step": 460
+    },
+    {
+      "epoch": 1.7764932562620424,
+      "grad_norm": 0.6555070912013644,
+      "learning_rate": 1.4585685885623901e-06,
+      "loss": 0.3061,
+      "step": 461
+    },
+    {
+      "epoch": 1.7803468208092486,
+      "grad_norm": 0.5423585126994777,
+      "learning_rate": 1.4084437930294059e-06,
+      "loss": 0.2416,
+      "step": 462
+    },
+    {
+      "epoch": 1.7842003853564548,
+      "grad_norm": 0.5128625019538622,
+      "learning_rate": 1.359163968899473e-06,
+      "loss": 0.2296,
+      "step": 463
+    },
+    {
+      "epoch": 1.7880539499036607,
+      "grad_norm": 0.8828336205245328,
+      "learning_rate": 1.3107313559012936e-06,
+      "loss": 0.2975,
+      "step": 464
+    },
+    {
+      "epoch": 1.791907514450867,
+      "grad_norm": 0.6056697475279614,
+      "learning_rate": 1.2631481552585067e-06,
+      "loss": 0.2689,
+      "step": 465
+    },
+    {
+      "epoch": 1.7957610789980731,
+      "grad_norm": 0.7746740424893049,
+      "learning_rate": 1.2164165295896392e-06,
+      "loss": 0.2669,
+      "step": 466
+    },
+    {
+      "epoch": 1.7996146435452793,
+      "grad_norm": 0.6006232506779448,
+      "learning_rate": 1.1705386028098009e-06,
+      "loss": 0.3039,
+      "step": 467
+    },
+    {
+      "epoch": 1.8034682080924855,
+      "grad_norm": 0.5403526649265826,
+      "learning_rate": 1.1255164600341816e-06,
+      "loss": 0.2754,
+      "step": 468
+    },
+    {
+      "epoch": 1.8073217726396917,
+      "grad_norm": 0.5862736861808353,
+      "learning_rate": 1.08135214748327e-06,
+      "loss": 0.287,
+      "step": 469
+    },
+    {
+      "epoch": 1.811175337186898,
+      "grad_norm": 0.7474202062547819,
+      "learning_rate": 1.0380476723898458e-06,
+      "loss": 0.3006,
+      "step": 470
+    },
+    {
+      "epoch": 1.8150289017341041,
+      "grad_norm": 0.5942504408819616,
+      "learning_rate": 9.956050029077646e-07,
+      "loss": 0.2911,
+      "step": 471
+    },
+    {
+      "epoch": 1.8188824662813103,
+      "grad_norm": 0.5958984883417842,
+      "learning_rate": 9.540260680225133e-07,
+      "loss": 0.3008,
+      "step": 472
+    },
+    {
+      "epoch": 1.8227360308285165,
+      "grad_norm": 0.5546378435963755,
+      "learning_rate": 9.133127574635181e-07,
+      "loss": 0.2325,
+      "step": 473
+    },
+    {
+      "epoch": 1.8265895953757225,
+      "grad_norm": 0.6588191099653756,
+      "learning_rate": 8.734669216182779e-07,
+      "loss": 0.2822,
+      "step": 474
+    },
+    {
+      "epoch": 1.8304431599229287,
+      "grad_norm": 0.5229342432978052,
+      "learning_rate": 8.344903714482555e-07,
+      "loss": 0.248,
+      "step": 475
+    },
+    {
+      "epoch": 1.834296724470135,
+      "grad_norm": 0.5268589130032248,
+      "learning_rate": 7.963848784065753e-07,
+      "loss": 0.3033,
+      "step": 476
+    },
+    {
+      "epoch": 1.838150289017341,
+      "grad_norm": 0.6011796025596555,
+      "learning_rate": 7.591521743575003e-07,
+      "loss": 0.289,
+      "step": 477
+    },
+    {
+      "epoch": 1.842003853564547,
+      "grad_norm": 0.6073026645436564,
+      "learning_rate": 7.227939514977422e-07,
+      "loss": 0.3053,
+      "step": 478
+    },
+    {
+      "epoch": 1.8458574181117533,
+      "grad_norm": 0.5341540712274524,
+      "learning_rate": 6.87311862279536e-07,
+      "loss": 0.2535,
+      "step": 479
+    },
+    {
+      "epoch": 1.8497109826589595,
+      "grad_norm": 0.6384475776837815,
+      "learning_rate": 6.527075193355337e-07,
+      "loss": 0.3018,
+      "step": 480
+    },
+    {
+      "epoch": 1.8535645472061657,
+      "grad_norm": 0.6168993774079564,
+      "learning_rate": 6.189824954055335e-07,
+      "loss": 0.3332,
+      "step": 481
+    },
+    {
+      "epoch": 1.857418111753372,
+      "grad_norm": 0.6689061938191962,
+      "learning_rate": 5.861383232649708e-07,
+      "loss": 0.3018,
+      "step": 482
+    },
+    {
+      "epoch": 1.861271676300578,
+      "grad_norm": 0.5773513436403104,
+      "learning_rate": 5.541764956552831e-07,
+      "loss": 0.3086,
+      "step": 483
+    },
+    {
+      "epoch": 1.8651252408477843,
+      "grad_norm": 0.5674684683333645,
+      "learning_rate": 5.230984652160387e-07,
+      "loss": 0.2904,
+      "step": 484
+    },
+    {
+      "epoch": 1.8689788053949905,
+      "grad_norm": 0.6136551285882403,
+      "learning_rate": 4.92905644418944e-07,
+      "loss": 0.2868,
+      "step": 485
+    },
+    {
+      "epoch": 1.8728323699421965,
+      "grad_norm": 0.5814884659334725,
+      "learning_rate": 4.635994055036208e-07,
+      "loss": 0.2837,
+      "step": 486
+    },
+    {
+      "epoch": 1.8766859344894027,
+      "grad_norm": 0.5724578775003472,
+      "learning_rate": 4.3518108041525675e-07,
+      "loss": 0.266,
+      "step": 487
+    },
+    {
+      "epoch": 1.8805394990366089,
+      "grad_norm": 0.5758555299044388,
+      "learning_rate": 4.0765196074406433e-07,
+      "loss": 0.2733,
+      "step": 488
+    },
+    {
+      "epoch": 1.8843930635838149,
+      "grad_norm": 1.583650395260831,
+      "learning_rate": 3.8101329766657924e-07,
+      "loss": 0.2487,
+      "step": 489
+    },
+    {
+      "epoch": 1.888246628131021,
+      "grad_norm": 0.5001989878794011,
+      "learning_rate": 3.5526630188879475e-07,
+      "loss": 0.2928,
+      "step": 490
+    },
+    {
+      "epoch": 1.8921001926782273,
+      "grad_norm": 0.5835273327136795,
+      "learning_rate": 3.304121435911345e-07,
+      "loss": 0.2951,
+      "step": 491
+    },
+    {
+      "epoch": 1.8959537572254335,
+      "grad_norm": 0.6058658063907555,
+      "learning_rate": 3.064519523752751e-07,
+      "loss": 0.3092,
+      "step": 492
+    },
+    {
+      "epoch": 1.8998073217726397,
+      "grad_norm": 0.48508060199041647,
+      "learning_rate": 2.8338681721279627e-07,
+      "loss": 0.2587,
+      "step": 493
+    },
+    {
+      "epoch": 1.9036608863198459,
+      "grad_norm": 0.6173948412532628,
+      "learning_rate": 2.612177863956977e-07,
+      "loss": 0.3553,
+      "step": 494
+    },
+    {
+      "epoch": 1.907514450867052,
+      "grad_norm": 0.5583615292360055,
+      "learning_rate": 2.3994586748875116e-07,
+      "loss": 0.2629,
+      "step": 495
+    },
+    {
+      "epoch": 1.9113680154142583,
+      "grad_norm": 0.6358847375735043,
+      "learning_rate": 2.1957202728370542e-07,
+      "loss": 0.3183,
+      "step": 496
+    },
+    {
+      "epoch": 1.9152215799614645,
+      "grad_norm": 0.5168808695590897,
+      "learning_rate": 2.000971917553529e-07,
+      "loss": 0.2417,
+      "step": 497
+    },
+    {
+      "epoch": 1.9190751445086707,
+      "grad_norm": 0.6311552147683044,
+      "learning_rate": 1.8152224601943435e-07,
+      "loss": 0.297,
+      "step": 498
+    },
+    {
+      "epoch": 1.9229287090558767,
+      "grad_norm": 0.6268922330585508,
+      "learning_rate": 1.6384803429242202e-07,
+      "loss": 0.3107,
+      "step": 499
+    },
+    {
+      "epoch": 1.9267822736030829,
+      "grad_norm": 0.4990465421997129,
+      "learning_rate": 1.4707535985314158e-07,
+      "loss": 0.2362,
+      "step": 500
+    },
+    {
+      "epoch": 1.930635838150289,
+      "grad_norm": 0.5842077868087064,
+      "learning_rate": 1.3120498500627243e-07,
+      "loss": 0.2877,
+      "step": 501
+    },
+    {
+      "epoch": 1.934489402697495,
+      "grad_norm": 0.6539135809078528,
+      "learning_rate": 1.1623763104769536e-07,
+      "loss": 0.2189,
+      "step": 502
+    },
+    {
+      "epoch": 1.9383429672447012,
+      "grad_norm": 0.5738597010304898,
+      "learning_rate": 1.0217397823170771e-07,
+      "loss": 0.3352,
+      "step": 503
+    },
+    {
+      "epoch": 1.9421965317919074,
+      "grad_norm": 0.5459102574082527,
+      "learning_rate": 8.901466574011919e-08,
+      "loss": 0.2929,
+      "step": 504
+    },
+    {
+      "epoch": 1.9460500963391136,
+      "grad_norm": 0.5914038878762246,
+      "learning_rate": 7.676029165318622e-08,
+      "loss": 0.2649,
+      "step": 505
+    },
+    {
+      "epoch": 1.9499036608863198,
+      "grad_norm": 0.48711166138829143,
+      "learning_rate": 6.541141292243814e-08,
+      "loss": 0.2734,
+      "step": 506
+    },
+    {
+      "epoch": 1.953757225433526,
+      "grad_norm": 0.5110998668531642,
+      "learning_rate": 5.496854534536189e-08,
+      "loss": 0.2689,
+      "step": 507
+    },
+    {
+      "epoch": 1.9576107899807322,
+      "grad_norm": 0.580604888687543,
+      "learning_rate": 4.5432163541960785e-08,
+      "loss": 0.2636,
+      "step": 508
+    },
+    {
+      "epoch": 1.9614643545279384,
+      "grad_norm": 0.5478455993832356,
+      "learning_rate": 3.680270093318505e-08,
+      "loss": 0.2662,
+      "step": 509
+    },
+    {
+      "epoch": 1.9653179190751446,
+      "grad_norm": 0.5860745443181511,
+      "learning_rate": 2.9080549721225426e-08,
+      "loss": 0.2812,
+      "step": 510
+    },
+    {
+      "epoch": 1.9691714836223508,
+      "grad_norm": 0.5859204655633964,
+      "learning_rate": 2.226606087169847e-08,
+      "loss": 0.2682,
+      "step": 511
+    },
+    {
+      "epoch": 1.9730250481695568,
+      "grad_norm": 0.552238848617358,
+      "learning_rate": 1.6359544097686033e-08,
+      "loss": 0.2589,
+      "step": 512
+    },
+    {
+      "epoch": 1.976878612716763,
+      "grad_norm": 0.6319565374117269,
+      "learning_rate": 1.136126784566649e-08,
+      "loss": 0.28,
+      "step": 513
+    },
+    {
+      "epoch": 1.9807321772639692,
+      "grad_norm": 0.6410471677739641,
+      "learning_rate": 7.271459283308968e-09,
+      "loss": 0.3306,
+      "step": 514
+    },
+    {
+      "epoch": 1.9845857418111752,
+      "grad_norm": 0.5612641252616729,
+      "learning_rate": 4.090304289150471e-09,
+      "loss": 0.2771,
+      "step": 515
+    },
+    {
+      "epoch": 1.9884393063583814,
+      "grad_norm": 0.49679899268137545,
+      "learning_rate": 1.817947444149315e-09,
+      "loss": 0.2396,
+      "step": 516
+    },
+    {
+      "epoch": 1.9922928709055876,
+      "grad_norm": 0.559672250420135,
+      "learning_rate": 4.544920251126073e-10,
+      "loss": 0.2364,
+      "step": 517
+    },
+    {
+      "epoch": 1.9961464354527938,
+      "grad_norm": 0.5094885850047902,
+      "learning_rate": 0.0,
+      "loss": 0.2353,
+      "step": 518
+    },
+    {
+      "epoch": 1.9961464354527938,
+      "eval_loss": 0.27941030263900757,
+      "eval_runtime": 147.0149,
+      "eval_samples_per_second": 13.59,
+      "eval_steps_per_second": 0.429,
+      "step": 518
+    },
+    {
+      "epoch": 1.9961464354527938,
+      "step": 518,
+      "total_flos": 2.6836433607911014e+17,
+      "train_loss": 0.7686227933723033,
+      "train_runtime": 16387.3806,
+      "train_samples_per_second": 4.053,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 518,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6836433607911014e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e1266a7a422213fba9f733ef9139759486ca38c095227b7de0a6af27dadae7
+size 7096