Upload 13 files

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: toolalpaca
+  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. -->
+
+# toolalpaca
+
+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 toolalpaca dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2505
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.2781        | 0.7407 | 500  | 0.2681          |
+| 0.1417        | 1.4815 | 1000 | 0.2399          |
+| 0.0362        | 2.2222 | 1500 | 0.2555          |
+| 0.0244        | 2.9630 | 2000 | 0.2507          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.25052565336227417,
+    "eval_runtime": 110.0112,
+    "eval_samples_per_second": 2.727,
+    "eval_steps_per_second": 1.363,
+    "total_flos": 15334618890240.0,
+    "train_loss": 0.13858298796930432,
+    "train_runtime": 10686.6427,
+    "train_samples_per_second": 0.758,
+    "train_steps_per_second": 0.189
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_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
+  ],
+  "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": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.25052565336227417,
+    "eval_runtime": 110.0112,
+    "eval_samples_per_second": 2.727,
+    "eval_steps_per_second": 1.363
+}

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": "4.44.2"
+}

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 15334618890240.0,
+    "train_loss": 0.13858298796930432,
+    "train_runtime": 10686.6427,
+    "train_samples_per_second": 0.758,
+    "train_steps_per_second": 0.189
+}

trainer_log.jsonl

@@ -0,0 +1,207 @@
+{"current_steps": 10, "total_steps": 2025, "loss": 0.5936, "learning_rate": 4.926108374384237e-07, "epoch": 0.014814814814814815, "percentage": 0.49, "elapsed_time": "0:00:52", "remaining_time": "2:57:46"}
+{"current_steps": 20, "total_steps": 2025, "loss": 0.3977, "learning_rate": 9.852216748768474e-07, "epoch": 0.02962962962962963, "percentage": 0.99, "elapsed_time": "0:01:41", "remaining_time": "2:49:57"}
+{"current_steps": 30, "total_steps": 2025, "loss": 0.2758, "learning_rate": 1.4778325123152712e-06, "epoch": 0.044444444444444446, "percentage": 1.48, "elapsed_time": "0:02:31", "remaining_time": "2:47:30"}
+{"current_steps": 40, "total_steps": 2025, "loss": 0.206, "learning_rate": 1.970443349753695e-06, "epoch": 0.05925925925925926, "percentage": 1.98, "elapsed_time": "0:03:15", "remaining_time": "2:41:25"}
+{"current_steps": 50, "total_steps": 2025, "loss": 0.2267, "learning_rate": 2.4630541871921186e-06, "epoch": 0.07407407407407407, "percentage": 2.47, "elapsed_time": "0:04:04", "remaining_time": "2:40:38"}
+{"current_steps": 60, "total_steps": 2025, "loss": 0.2088, "learning_rate": 2.9556650246305424e-06, "epoch": 0.08888888888888889, "percentage": 2.96, "elapsed_time": "0:04:53", "remaining_time": "2:40:09"}
+{"current_steps": 70, "total_steps": 2025, "loss": 0.197, "learning_rate": 3.448275862068966e-06, "epoch": 0.1037037037037037, "percentage": 3.46, "elapsed_time": "0:05:43", "remaining_time": "2:39:43"}
+{"current_steps": 80, "total_steps": 2025, "loss": 0.1934, "learning_rate": 3.94088669950739e-06, "epoch": 0.11851851851851852, "percentage": 3.95, "elapsed_time": "0:06:32", "remaining_time": "2:38:55"}
+{"current_steps": 90, "total_steps": 2025, "loss": 0.2117, "learning_rate": 4.4334975369458135e-06, "epoch": 0.13333333333333333, "percentage": 4.44, "elapsed_time": "0:07:21", "remaining_time": "2:38:07"}
+{"current_steps": 100, "total_steps": 2025, "loss": 0.2408, "learning_rate": 4.926108374384237e-06, "epoch": 0.14814814814814814, "percentage": 4.94, "elapsed_time": "0:08:09", "remaining_time": "2:36:54"}
+{"current_steps": 110, "total_steps": 2025, "loss": 0.2066, "learning_rate": 5.41871921182266e-06, "epoch": 0.16296296296296298, "percentage": 5.43, "elapsed_time": "0:08:58", "remaining_time": "2:36:11"}
+{"current_steps": 120, "total_steps": 2025, "loss": 0.2281, "learning_rate": 5.911330049261085e-06, "epoch": 0.17777777777777778, "percentage": 5.93, "elapsed_time": "0:09:47", "remaining_time": "2:35:28"}
+{"current_steps": 130, "total_steps": 2025, "loss": 0.234, "learning_rate": 6.403940886699508e-06, "epoch": 0.1925925925925926, "percentage": 6.42, "elapsed_time": "0:10:36", "remaining_time": "2:34:44"}
+{"current_steps": 140, "total_steps": 2025, "loss": 0.2239, "learning_rate": 6.896551724137932e-06, "epoch": 0.2074074074074074, "percentage": 6.91, "elapsed_time": "0:11:25", "remaining_time": "2:33:52"}
+{"current_steps": 150, "total_steps": 2025, "loss": 0.2339, "learning_rate": 7.3891625615763555e-06, "epoch": 0.2222222222222222, "percentage": 7.41, "elapsed_time": "0:12:14", "remaining_time": "2:33:00"}
+{"current_steps": 160, "total_steps": 2025, "loss": 0.2261, "learning_rate": 7.88177339901478e-06, "epoch": 0.23703703703703705, "percentage": 7.9, "elapsed_time": "0:13:03", "remaining_time": "2:32:12"}
+{"current_steps": 170, "total_steps": 2025, "loss": 0.253, "learning_rate": 8.374384236453203e-06, "epoch": 0.2518518518518518, "percentage": 8.4, "elapsed_time": "0:13:51", "remaining_time": "2:31:14"}
+{"current_steps": 180, "total_steps": 2025, "loss": 0.2592, "learning_rate": 8.866995073891627e-06, "epoch": 0.26666666666666666, "percentage": 8.89, "elapsed_time": "0:14:40", "remaining_time": "2:30:24"}
+{"current_steps": 190, "total_steps": 2025, "loss": 0.2558, "learning_rate": 9.359605911330049e-06, "epoch": 0.2814814814814815, "percentage": 9.38, "elapsed_time": "0:15:28", "remaining_time": "2:29:30"}
+{"current_steps": 200, "total_steps": 2025, "loss": 0.2791, "learning_rate": 9.852216748768475e-06, "epoch": 0.2962962962962963, "percentage": 9.88, "elapsed_time": "0:16:17", "remaining_time": "2:28:40"}
+{"current_steps": 210, "total_steps": 2025, "loss": 0.266, "learning_rate": 9.99963580513638e-06, "epoch": 0.3111111111111111, "percentage": 10.37, "elapsed_time": "0:17:06", "remaining_time": "2:27:55"}
+{"current_steps": 220, "total_steps": 2025, "loss": 0.2644, "learning_rate": 9.997852121279563e-06, "epoch": 0.32592592592592595, "percentage": 10.86, "elapsed_time": "0:17:55", "remaining_time": "2:27:04"}
+{"current_steps": 230, "total_steps": 2025, "loss": 0.2398, "learning_rate": 9.994582585118449e-06, "epoch": 0.34074074074074073, "percentage": 11.36, "elapsed_time": "0:18:45", "remaining_time": "2:26:19"}
+{"current_steps": 240, "total_steps": 2025, "loss": 0.2459, "learning_rate": 9.989828168680164e-06, "epoch": 0.35555555555555557, "percentage": 11.85, "elapsed_time": "0:19:33", "remaining_time": "2:25:27"}
+{"current_steps": 250, "total_steps": 2025, "loss": 0.2874, "learning_rate": 9.983590285444025e-06, "epoch": 0.37037037037037035, "percentage": 12.35, "elapsed_time": "0:20:20", "remaining_time": "2:24:25"}
+{"current_steps": 260, "total_steps": 2025, "loss": 0.243, "learning_rate": 9.975870789921322e-06, "epoch": 0.3851851851851852, "percentage": 12.84, "elapsed_time": "0:21:09", "remaining_time": "2:23:38"}
+{"current_steps": 270, "total_steps": 2025, "loss": 0.2418, "learning_rate": 9.966671977103972e-06, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:21:59", "remaining_time": "2:22:53"}
+{"current_steps": 280, "total_steps": 2025, "loss": 0.3023, "learning_rate": 9.955996581782218e-06, "epoch": 0.4148148148148148, "percentage": 13.83, "elapsed_time": "0:22:48", "remaining_time": "2:22:11"}
+{"current_steps": 290, "total_steps": 2025, "loss": 0.2765, "learning_rate": 9.943847777731584e-06, "epoch": 0.42962962962962964, "percentage": 14.32, "elapsed_time": "0:23:38", "remaining_time": "2:21:25"}
+{"current_steps": 300, "total_steps": 2025, "loss": 0.2804, "learning_rate": 9.93022917676932e-06, "epoch": 0.4444444444444444, "percentage": 14.81, "elapsed_time": "0:24:27", "remaining_time": "2:20:36"}
+{"current_steps": 310, "total_steps": 2025, "loss": 0.2703, "learning_rate": 9.915144827680606e-06, "epoch": 0.45925925925925926, "percentage": 15.31, "elapsed_time": "0:25:16", "remaining_time": "2:19:47"}
+{"current_steps": 320, "total_steps": 2025, "loss": 0.2875, "learning_rate": 9.898599215014868e-06, "epoch": 0.4740740740740741, "percentage": 15.8, "elapsed_time": "0:26:05", "remaining_time": "2:18:59"}
+{"current_steps": 330, "total_steps": 2025, "loss": 0.2639, "learning_rate": 9.880597257752522e-06, "epoch": 0.4888888888888889, "percentage": 16.3, "elapsed_time": "0:26:52", "remaining_time": "2:18:02"}
+{"current_steps": 340, "total_steps": 2025, "loss": 0.2339, "learning_rate": 9.861144307842574e-06, "epoch": 0.5037037037037037, "percentage": 16.79, "elapsed_time": "0:27:39", "remaining_time": "2:17:02"}
+{"current_steps": 350, "total_steps": 2025, "loss": 0.2552, "learning_rate": 9.840246148611485e-06, "epoch": 0.5185185185185185, "percentage": 17.28, "elapsed_time": "0:28:27", "remaining_time": "2:16:12"}
+{"current_steps": 360, "total_steps": 2025, "loss": 0.2817, "learning_rate": 9.817908993043819e-06, "epoch": 0.5333333333333333, "percentage": 17.78, "elapsed_time": "0:29:16", "remaining_time": "2:15:23"}
+{"current_steps": 370, "total_steps": 2025, "loss": 0.2641, "learning_rate": 9.794139481935108e-06, "epoch": 0.5481481481481482, "percentage": 18.27, "elapsed_time": "0:30:05", "remaining_time": "2:14:36"}
+{"current_steps": 380, "total_steps": 2025, "loss": 0.2826, "learning_rate": 9.768944681917582e-06, "epoch": 0.562962962962963, "percentage": 18.77, "elapsed_time": "0:30:55", "remaining_time": "2:13:50"}
+{"current_steps": 390, "total_steps": 2025, "loss": 0.2559, "learning_rate": 9.742332083359252e-06, "epoch": 0.5777777777777777, "percentage": 19.26, "elapsed_time": "0:31:43", "remaining_time": "2:13:00"}
+{"current_steps": 400, "total_steps": 2025, "loss": 0.2306, "learning_rate": 9.714309598137045e-06, "epoch": 0.5925925925925926, "percentage": 19.75, "elapsed_time": "0:32:32", "remaining_time": "2:12:14"}
+{"current_steps": 410, "total_steps": 2025, "loss": 0.2682, "learning_rate": 9.68488555728462e-06, "epoch": 0.6074074074074074, "percentage": 20.25, "elapsed_time": "0:33:20", "remaining_time": "2:11:21"}
+{"current_steps": 420, "total_steps": 2025, "loss": 0.2607, "learning_rate": 9.654068708515564e-06, "epoch": 0.6222222222222222, "percentage": 20.74, "elapsed_time": "0:34:09", "remaining_time": "2:10:31"}
+{"current_steps": 430, "total_steps": 2025, "loss": 0.2383, "learning_rate": 9.621868213622713e-06, "epoch": 0.6370370370370371, "percentage": 21.23, "elapsed_time": "0:34:58", "remaining_time": "2:09:42"}
+{"current_steps": 440, "total_steps": 2025, "loss": 0.293, "learning_rate": 9.588293645754363e-06, "epoch": 0.6518518518518519, "percentage": 21.73, "elapsed_time": "0:35:47", "remaining_time": "2:08:55"}
+{"current_steps": 450, "total_steps": 2025, "loss": 0.2942, "learning_rate": 9.553354986568201e-06, "epoch": 0.6666666666666666, "percentage": 22.22, "elapsed_time": "0:36:36", "remaining_time": "2:08:08"}
+{"current_steps": 460, "total_steps": 2025, "loss": 0.2524, "learning_rate": 9.517062623263768e-06, "epoch": 0.6814814814814815, "percentage": 22.72, "elapsed_time": "0:37:26", "remaining_time": "2:07:22"}
+{"current_steps": 470, "total_steps": 2025, "loss": 0.2623, "learning_rate": 9.479427345494366e-06, "epoch": 0.6962962962962963, "percentage": 23.21, "elapsed_time": "0:38:13", "remaining_time": "2:06:29"}
+{"current_steps": 480, "total_steps": 2025, "loss": 0.2786, "learning_rate": 9.440460342159314e-06, "epoch": 0.7111111111111111, "percentage": 23.7, "elapsed_time": "0:39:02", "remaining_time": "2:05:41"}
+{"current_steps": 490, "total_steps": 2025, "loss": 0.2276, "learning_rate": 9.40017319807751e-06, "epoch": 0.725925925925926, "percentage": 24.2, "elapsed_time": "0:39:52", "remaining_time": "2:04:53"}
+{"current_steps": 500, "total_steps": 2025, "loss": 0.2781, "learning_rate": 9.358577890543277e-06, "epoch": 0.7407407407407407, "percentage": 24.69, "elapsed_time": "0:40:41", "remaining_time": "2:04:07"}
+{"current_steps": 500, "total_steps": 2025, "eval_loss": 0.2680646777153015, "epoch": 0.7407407407407407, "percentage": 24.69, "elapsed_time": "0:42:32", "remaining_time": "2:09:45"}
+{"current_steps": 510, "total_steps": 2025, "loss": 0.2637, "learning_rate": 9.315686785765556e-06, "epoch": 0.7555555555555555, "percentage": 25.19, "elapsed_time": "0:44:44", "remaining_time": "2:12:53"}
+{"current_steps": 520, "total_steps": 2025, "loss": 0.2707, "learning_rate": 9.271512635191427e-06, "epoch": 0.7703703703703704, "percentage": 25.68, "elapsed_time": "0:45:33", "remaining_time": "2:11:51"}
+{"current_steps": 530, "total_steps": 2025, "loss": 0.2376, "learning_rate": 9.22606857171515e-06, "epoch": 0.7851851851851852, "percentage": 26.17, "elapsed_time": "0:46:22", "remaining_time": "2:10:48"}
+{"current_steps": 540, "total_steps": 2025, "loss": 0.2495, "learning_rate": 9.179368105773768e-06, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:47:11", "remaining_time": "2:09:46"}
+{"current_steps": 550, "total_steps": 2025, "loss": 0.2379, "learning_rate": 9.131425121330477e-06, "epoch": 0.8148148148148148, "percentage": 27.16, "elapsed_time": "0:48:00", "remaining_time": "2:08:45"}
+{"current_steps": 560, "total_steps": 2025, "loss": 0.2702, "learning_rate": 9.082253871746962e-06, "epoch": 0.8296296296296296, "percentage": 27.65, "elapsed_time": "0:48:49", "remaining_time": "2:07:44"}
+{"current_steps": 570, "total_steps": 2025, "loss": 0.2961, "learning_rate": 9.031868975545884e-06, "epoch": 0.8444444444444444, "percentage": 28.15, "elapsed_time": "0:49:39", "remaining_time": "2:06:45"}
+{"current_steps": 580, "total_steps": 2025, "loss": 0.2381, "learning_rate": 8.980285412064827e-06, "epoch": 0.8592592592592593, "percentage": 28.64, "elapsed_time": "0:50:28", "remaining_time": "2:05:46"}
+{"current_steps": 590, "total_steps": 2025, "loss": 0.2258, "learning_rate": 8.92751851700297e-06, "epoch": 0.8740740740740741, "percentage": 29.14, "elapsed_time": "0:51:14", "remaining_time": "2:04:36"}
+{"current_steps": 600, "total_steps": 2025, "loss": 0.2395, "learning_rate": 8.873583977861802e-06, "epoch": 0.8888888888888888, "percentage": 29.63, "elapsed_time": "0:52:00", "remaining_time": "2:03:32"}
+{"current_steps": 610, "total_steps": 2025, "loss": 0.2458, "learning_rate": 8.818497829281272e-06, "epoch": 0.9037037037037037, "percentage": 30.12, "elapsed_time": "0:52:50", "remaining_time": "2:02:34"}
+{"current_steps": 620, "total_steps": 2025, "loss": 0.2552, "learning_rate": 8.762276448272709e-06, "epoch": 0.9185185185185185, "percentage": 30.62, "elapsed_time": "0:53:39", "remaining_time": "2:01:35"}
+{"current_steps": 630, "total_steps": 2025, "loss": 0.2909, "learning_rate": 8.70493654934996e-06, "epoch": 0.9333333333333333, "percentage": 31.11, "elapsed_time": "0:54:29", "remaining_time": "2:00:38"}
+{"current_steps": 640, "total_steps": 2025, "loss": 0.2564, "learning_rate": 8.646495179560221e-06, "epoch": 0.9481481481481482, "percentage": 31.6, "elapsed_time": "0:55:18", "remaining_time": "1:59:41"}
+{"current_steps": 650, "total_steps": 2025, "loss": 0.2374, "learning_rate": 8.586969713415949e-06, "epoch": 0.9629629629629629, "percentage": 32.1, "elapsed_time": "0:56:07", "remaining_time": "1:58:44"}
+{"current_steps": 660, "total_steps": 2025, "loss": 0.2441, "learning_rate": 8.526377847729475e-06, "epoch": 0.9777777777777777, "percentage": 32.59, "elapsed_time": "0:56:56", "remaining_time": "1:57:46"}
+{"current_steps": 670, "total_steps": 2025, "loss": 0.2566, "learning_rate": 8.46473759635176e-06, "epoch": 0.9925925925925926, "percentage": 33.09, "elapsed_time": "0:57:43", "remaining_time": "1:56:45"}
+{"current_steps": 680, "total_steps": 2025, "loss": 0.1853, "learning_rate": 8.402067284816919e-06, "epoch": 1.0074074074074073, "percentage": 33.58, "elapsed_time": "0:58:33", "remaining_time": "1:55:48"}
+{"current_steps": 690, "total_steps": 2025, "loss": 0.127, "learning_rate": 8.338385544894073e-06, "epoch": 1.0222222222222221, "percentage": 34.07, "elapsed_time": "0:59:22", "remaining_time": "1:54:52"}
+{"current_steps": 700, "total_steps": 2025, "loss": 0.1254, "learning_rate": 8.273711309048145e-06, "epoch": 1.037037037037037, "percentage": 34.57, "elapsed_time": "1:00:11", "remaining_time": "1:53:56"}
+{"current_steps": 710, "total_steps": 2025, "loss": 0.1385, "learning_rate": 8.208063804811293e-06, "epoch": 1.0518518518518518, "percentage": 35.06, "elapsed_time": "1:01:00", "remaining_time": "1:53:00"}
+{"current_steps": 720, "total_steps": 2025, "loss": 0.1344, "learning_rate": 8.141462549066581e-06, "epoch": 1.0666666666666667, "percentage": 35.56, "elapsed_time": "1:01:50", "remaining_time": "1:52:05"}
+{"current_steps": 730, "total_steps": 2025, "loss": 0.1419, "learning_rate": 8.073927342245663e-06, "epoch": 1.0814814814814815, "percentage": 36.05, "elapsed_time": "1:02:38", "remaining_time": "1:51:06"}
+{"current_steps": 740, "total_steps": 2025, "loss": 0.1308, "learning_rate": 8.005478262442132e-06, "epoch": 1.0962962962962963, "percentage": 36.54, "elapsed_time": "1:03:26", "remaining_time": "1:50:10"}
+{"current_steps": 750, "total_steps": 2025, "loss": 0.133, "learning_rate": 7.936135659442355e-06, "epoch": 1.1111111111111112, "percentage": 37.04, "elapsed_time": "1:04:15", "remaining_time": "1:49:14"}
+{"current_steps": 760, "total_steps": 2025, "loss": 0.1099, "learning_rate": 7.86592014867551e-06, "epoch": 1.125925925925926, "percentage": 37.53, "elapsed_time": "1:05:04", "remaining_time": "1:48:19"}
+{"current_steps": 770, "total_steps": 2025, "loss": 0.1429, "learning_rate": 7.794852605084661e-06, "epoch": 1.1407407407407408, "percentage": 38.02, "elapsed_time": "1:05:54", "remaining_time": "1:47:24"}
+{"current_steps": 780, "total_steps": 2025, "loss": 0.1227, "learning_rate": 7.722954156920675e-06, "epoch": 1.1555555555555554, "percentage": 38.52, "elapsed_time": "1:06:42", "remaining_time": "1:46:28"}
+{"current_steps": 790, "total_steps": 2025, "loss": 0.1499, "learning_rate": 7.650246179460826e-06, "epoch": 1.1703703703703703, "percentage": 39.01, "elapsed_time": "1:07:31", "remaining_time": "1:45:33"}
+{"current_steps": 800, "total_steps": 2025, "loss": 0.1564, "learning_rate": 7.57675028865397e-06, "epoch": 1.1851851851851851, "percentage": 39.51, "elapsed_time": "1:08:18", "remaining_time": "1:44:35"}
+{"current_steps": 810, "total_steps": 2025, "loss": 0.1441, "learning_rate": 7.502488334694167e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "1:09:07", "remaining_time": "1:43:41"}
+{"current_steps": 820, "total_steps": 2025, "loss": 0.1317, "learning_rate": 7.427482395524646e-06, "epoch": 1.2148148148148148, "percentage": 40.49, "elapsed_time": "1:09:55", "remaining_time": "1:42:45"}
+{"current_steps": 830, "total_steps": 2025, "loss": 0.1211, "learning_rate": 7.35175477027408e-06, "epoch": 1.2296296296296296, "percentage": 40.99, "elapsed_time": "1:10:44", "remaining_time": "1:41:51"}
+{"current_steps": 840, "total_steps": 2025, "loss": 0.1284, "learning_rate": 7.2753279726271e-06, "epoch": 1.2444444444444445, "percentage": 41.48, "elapsed_time": "1:11:34", "remaining_time": "1:40:57"}
+{"current_steps": 850, "total_steps": 2025, "loss": 0.1436, "learning_rate": 7.198224724131012e-06, "epoch": 1.2592592592592593, "percentage": 41.98, "elapsed_time": "1:12:23", "remaining_time": "1:40:03"}
+{"current_steps": 860, "total_steps": 2025, "loss": 0.1221, "learning_rate": 7.120467947440719e-06, "epoch": 1.2740740740740741, "percentage": 42.47, "elapsed_time": "1:13:11", "remaining_time": "1:39:08"}
+{"current_steps": 870, "total_steps": 2025, "loss": 0.1162, "learning_rate": 7.042080759503866e-06, "epoch": 1.2888888888888888, "percentage": 42.96, "elapsed_time": "1:13:59", "remaining_time": "1:38:13"}
+{"current_steps": 880, "total_steps": 2025, "loss": 0.1291, "learning_rate": 6.963086464688209e-06, "epoch": 1.3037037037037038, "percentage": 43.46, "elapsed_time": "1:14:48", "remaining_time": "1:37:19"}
+{"current_steps": 890, "total_steps": 2025, "loss": 0.1319, "learning_rate": 6.883508547853268e-06, "epoch": 1.3185185185185184, "percentage": 43.95, "elapsed_time": "1:15:37", "remaining_time": "1:36:26"}
+{"current_steps": 900, "total_steps": 2025, "loss": 0.125, "learning_rate": 6.8033706673683276e-06, "epoch": 1.3333333333333333, "percentage": 44.44, "elapsed_time": "1:16:26", "remaining_time": "1:35:33"}
+{"current_steps": 910, "total_steps": 2025, "loss": 0.1382, "learning_rate": 6.722696648078838e-06, "epoch": 1.348148148148148, "percentage": 44.94, "elapsed_time": "1:17:15", "remaining_time": "1:34:40"}
+{"current_steps": 920, "total_steps": 2025, "loss": 0.1311, "learning_rate": 6.641510474223338e-06, "epoch": 1.362962962962963, "percentage": 45.43, "elapsed_time": "1:18:05", "remaining_time": "1:33:47"}
+{"current_steps": 930, "total_steps": 2025, "loss": 0.1416, "learning_rate": 6.559836282302984e-06, "epoch": 1.3777777777777778, "percentage": 45.93, "elapsed_time": "1:18:52", "remaining_time": "1:32:51"}
+{"current_steps": 940, "total_steps": 2025, "loss": 0.1519, "learning_rate": 6.477698353905808e-06, "epoch": 1.3925925925925926, "percentage": 46.42, "elapsed_time": "1:19:41", "remaining_time": "1:31:58"}
+{"current_steps": 950, "total_steps": 2025, "loss": 0.1179, "learning_rate": 6.395121108487855e-06, "epoch": 1.4074074074074074, "percentage": 46.91, "elapsed_time": "1:20:29", "remaining_time": "1:31:04"}
+{"current_steps": 960, "total_steps": 2025, "loss": 0.1329, "learning_rate": 6.312129096113313e-06, "epoch": 1.4222222222222223, "percentage": 47.41, "elapsed_time": "1:21:18", "remaining_time": "1:30:11"}
+{"current_steps": 970, "total_steps": 2025, "loss": 0.0981, "learning_rate": 6.228746990155831e-06, "epoch": 1.4370370370370371, "percentage": 47.9, "elapsed_time": "1:22:07", "remaining_time": "1:29:19"}
+{"current_steps": 980, "total_steps": 2025, "loss": 0.116, "learning_rate": 6.144999579963164e-06, "epoch": 1.4518518518518517, "percentage": 48.4, "elapsed_time": "1:22:56", "remaining_time": "1:28:26"}
+{"current_steps": 990, "total_steps": 2025, "loss": 0.136, "learning_rate": 6.060911763487353e-06, "epoch": 1.4666666666666668, "percentage": 48.89, "elapsed_time": "1:23:45", "remaining_time": "1:27:33"}
+{"current_steps": 1000, "total_steps": 2025, "loss": 0.1417, "learning_rate": 5.976508539882604e-06, "epoch": 1.4814814814814814, "percentage": 49.38, "elapsed_time": "1:24:34", "remaining_time": "1:26:40"}
+{"current_steps": 1000, "total_steps": 2025, "eval_loss": 0.23991718888282776, "epoch": 1.4814814814814814, "percentage": 49.38, "elapsed_time": "1:26:24", "remaining_time": "1:28:33"}
+{"current_steps": 1010, "total_steps": 2025, "loss": 0.1118, "learning_rate": 5.891815002073081e-06, "epoch": 1.4962962962962962, "percentage": 49.88, "elapsed_time": "1:28:27", "remaining_time": "1:28:54"}
+{"current_steps": 1020, "total_steps": 2025, "loss": 0.1202, "learning_rate": 5.806856329292839e-06, "epoch": 1.511111111111111, "percentage": 50.37, "elapsed_time": "1:29:16", "remaining_time": "1:27:58"}
+{"current_steps": 1030, "total_steps": 2025, "loss": 0.1256, "learning_rate": 5.721657779600071e-06, "epoch": 1.525925925925926, "percentage": 50.86, "elapsed_time": "1:30:06", "remaining_time": "1:27:02"}
+{"current_steps": 1040, "total_steps": 2025, "loss": 0.1402, "learning_rate": 5.636244682367937e-06, "epoch": 1.5407407407407407, "percentage": 51.36, "elapsed_time": "1:30:55", "remaining_time": "1:26:06"}
+{"current_steps": 1050, "total_steps": 2025, "loss": 0.1034, "learning_rate": 5.5506424307541895e-06, "epoch": 1.5555555555555556, "percentage": 51.85, "elapsed_time": "1:31:44", "remaining_time": "1:25:11"}
+{"current_steps": 1060, "total_steps": 2025, "loss": 0.1302, "learning_rate": 5.464876474151835e-06, "epoch": 1.5703703703703704, "percentage": 52.35, "elapsed_time": "1:32:33", "remaining_time": "1:24:16"}
+{"current_steps": 1070, "total_steps": 2025, "loss": 0.128, "learning_rate": 5.3789723106230675e-06, "epoch": 1.585185185185185, "percentage": 52.84, "elapsed_time": "1:33:22", "remaining_time": "1:23:20"}
+{"current_steps": 1080, "total_steps": 2025, "loss": 0.1265, "learning_rate": 5.292955479318756e-06, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "1:34:09", "remaining_time": "1:22:23"}
+{"current_steps": 1090, "total_steps": 2025, "loss": 0.1276, "learning_rate": 5.206851552885691e-06, "epoch": 1.6148148148148147, "percentage": 53.83, "elapsed_time": "1:34:57", "remaining_time": "1:21:27"}
+{"current_steps": 1100, "total_steps": 2025, "loss": 0.1131, "learning_rate": 5.120686129863882e-06, "epoch": 1.6296296296296298, "percentage": 54.32, "elapsed_time": "1:35:46", "remaining_time": "1:20:32"}
+{"current_steps": 1110, "total_steps": 2025, "loss": 0.1353, "learning_rate": 5.0344848270761635e-06, "epoch": 1.6444444444444444, "percentage": 54.81, "elapsed_time": "1:36:35", "remaining_time": "1:19:37"}
+{"current_steps": 1120, "total_steps": 2025, "loss": 0.1256, "learning_rate": 4.948273272012363e-06, "epoch": 1.6592592592592592, "percentage": 55.31, "elapsed_time": "1:37:24", "remaining_time": "1:18:42"}
+{"current_steps": 1130, "total_steps": 2025, "loss": 0.1223, "learning_rate": 4.862077095210284e-06, "epoch": 1.674074074074074, "percentage": 55.8, "elapsed_time": "1:38:13", "remaining_time": "1:17:48"}
+{"current_steps": 1140, "total_steps": 2025, "loss": 0.1101, "learning_rate": 4.775921922635806e-06, "epoch": 1.6888888888888889, "percentage": 56.3, "elapsed_time": "1:39:02", "remaining_time": "1:16:53"}
+{"current_steps": 1150, "total_steps": 2025, "loss": 0.1136, "learning_rate": 4.689833368064326e-06, "epoch": 1.7037037037037037, "percentage": 56.79, "elapsed_time": "1:39:48", "remaining_time": "1:15:56"}
+{"current_steps": 1160, "total_steps": 2025, "loss": 0.0936, "learning_rate": 4.603837025465829e-06, "epoch": 1.7185185185185186, "percentage": 57.28, "elapsed_time": "1:40:37", "remaining_time": "1:15:02"}
+{"current_steps": 1170, "total_steps": 2025, "loss": 0.1035, "learning_rate": 4.517958461395846e-06, "epoch": 1.7333333333333334, "percentage": 57.78, "elapsed_time": "1:41:26", "remaining_time": "1:14:07"}
+{"current_steps": 1180, "total_steps": 2025, "loss": 0.0978, "learning_rate": 4.432223207394577e-06, "epoch": 1.748148148148148, "percentage": 58.27, "elapsed_time": "1:42:15", "remaining_time": "1:13:13"}
+{"current_steps": 1190, "total_steps": 2025, "loss": 0.1234, "learning_rate": 4.346656752396388e-06, "epoch": 1.762962962962963, "percentage": 58.77, "elapsed_time": "1:43:04", "remaining_time": "1:12:19"}
+{"current_steps": 1200, "total_steps": 2025, "loss": 0.1117, "learning_rate": 4.261284535152016e-06, "epoch": 1.7777777777777777, "percentage": 59.26, "elapsed_time": "1:43:52", "remaining_time": "1:11:24"}
+{"current_steps": 1210, "total_steps": 2025, "loss": 0.1151, "learning_rate": 4.176131936665669e-06, "epoch": 1.7925925925925927, "percentage": 59.75, "elapsed_time": "1:44:41", "remaining_time": "1:10:30"}
+{"current_steps": 1220, "total_steps": 2025, "loss": 0.1087, "learning_rate": 4.0912242726493e-06, "epoch": 1.8074074074074074, "percentage": 60.25, "elapsed_time": "1:45:30", "remaining_time": "1:09:37"}
+{"current_steps": 1230, "total_steps": 2025, "loss": 0.1094, "learning_rate": 4.006586785996285e-06, "epoch": 1.8222222222222222, "percentage": 60.74, "elapsed_time": "1:46:19", "remaining_time": "1:08:43"}
+{"current_steps": 1240, "total_steps": 2025, "loss": 0.1077, "learning_rate": 3.922244639276773e-06, "epoch": 1.837037037037037, "percentage": 61.23, "elapsed_time": "1:47:08", "remaining_time": "1:07:49"}
+{"current_steps": 1250, "total_steps": 2025, "loss": 0.1106, "learning_rate": 3.838222907256884e-06, "epoch": 1.8518518518518519, "percentage": 61.73, "elapsed_time": "1:47:57", "remaining_time": "1:06:56"}
+{"current_steps": 1260, "total_steps": 2025, "loss": 0.1075, "learning_rate": 3.7545465694440363e-06, "epoch": 1.8666666666666667, "percentage": 62.22, "elapsed_time": "1:48:46", "remaining_time": "1:06:02"}
+{"current_steps": 1270, "total_steps": 2025, "loss": 0.1097, "learning_rate": 3.6712405026605792e-06, "epoch": 1.8814814814814815, "percentage": 62.72, "elapsed_time": "1:49:35", "remaining_time": "1:05:09"}
+{"current_steps": 1280, "total_steps": 2025, "loss": 0.1004, "learning_rate": 3.5883294736479612e-06, "epoch": 1.8962962962962964, "percentage": 63.21, "elapsed_time": "1:50:21", "remaining_time": "1:04:13"}
+{"current_steps": 1290, "total_steps": 2025, "loss": 0.0906, "learning_rate": 3.5058381317036285e-06, "epoch": 1.911111111111111, "percentage": 63.7, "elapsed_time": "1:51:08", "remaining_time": "1:03:19"}
+{"current_steps": 1300, "total_steps": 2025, "loss": 0.1209, "learning_rate": 3.423791001352823e-06, "epoch": 1.925925925925926, "percentage": 64.2, "elapsed_time": "1:51:56", "remaining_time": "1:02:25"}
+{"current_steps": 1310, "total_steps": 2025, "loss": 0.1084, "learning_rate": 3.3422124750574902e-06, "epoch": 1.9407407407407407, "percentage": 64.69, "elapsed_time": "1:52:45", "remaining_time": "1:01:32"}
+{"current_steps": 1320, "total_steps": 2025, "loss": 0.0974, "learning_rate": 3.2611268059644535e-06, "epoch": 1.9555555555555557, "percentage": 65.19, "elapsed_time": "1:53:33", "remaining_time": "1:00:39"}
+{"current_steps": 1330, "total_steps": 2025, "loss": 0.1291, "learning_rate": 3.1805581006949856e-06, "epoch": 1.9703703703703703, "percentage": 65.68, "elapsed_time": "1:54:22", "remaining_time": "0:59:45"}
+{"current_steps": 1340, "total_steps": 2025, "loss": 0.1028, "learning_rate": 3.100530312177956e-06, "epoch": 1.9851851851851852, "percentage": 66.17, "elapsed_time": "1:55:10", "remaining_time": "0:58:52"}
+{"current_steps": 1350, "total_steps": 2025, "loss": 0.1026, "learning_rate": 3.0210672325286806e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:55:59", "remaining_time": "0:57:59"}
+{"current_steps": 1360, "total_steps": 2025, "loss": 0.0428, "learning_rate": 2.9421924859755525e-06, "epoch": 2.0148148148148146, "percentage": 67.16, "elapsed_time": "1:56:45", "remaining_time": "0:57:05"}
+{"current_steps": 1370, "total_steps": 2025, "loss": 0.0373, "learning_rate": 2.8639295218366115e-06, "epoch": 2.0296296296296297, "percentage": 67.65, "elapsed_time": "1:57:32", "remaining_time": "0:56:11"}
+{"current_steps": 1380, "total_steps": 2025, "loss": 0.0354, "learning_rate": 2.78630160754811e-06, "epoch": 2.0444444444444443, "percentage": 68.15, "elapsed_time": "1:58:21", "remaining_time": "0:55:18"}
+{"current_steps": 1390, "total_steps": 2025, "loss": 0.0265, "learning_rate": 2.709331821747133e-06, "epoch": 2.0592592592592593, "percentage": 68.64, "elapsed_time": "1:59:09", "remaining_time": "0:54:26"}
+{"current_steps": 1400, "total_steps": 2025, "loss": 0.0278, "learning_rate": 2.63304304741037e-06, "epoch": 2.074074074074074, "percentage": 69.14, "elapsed_time": "1:59:58", "remaining_time": "0:53:33"}
+{"current_steps": 1410, "total_steps": 2025, "loss": 0.0487, "learning_rate": 2.55745796505105e-06, "epoch": 2.088888888888889, "percentage": 69.63, "elapsed_time": "2:00:47", "remaining_time": "0:52:41"}
+{"current_steps": 1420, "total_steps": 2025, "loss": 0.0364, "learning_rate": 2.482599045976059e-06, "epoch": 2.1037037037037036, "percentage": 70.12, "elapsed_time": "2:01:36", "remaining_time": "0:51:48"}
+{"current_steps": 1430, "total_steps": 2025, "loss": 0.045, "learning_rate": 2.408488545605265e-06, "epoch": 2.1185185185185187, "percentage": 70.62, "elapsed_time": "2:02:25", "remaining_time": "0:50:56"}
+{"current_steps": 1440, "total_steps": 2025, "loss": 0.0368, "learning_rate": 2.3351484968550264e-06, "epoch": 2.1333333333333333, "percentage": 71.11, "elapsed_time": "2:03:11", "remaining_time": "0:50:02"}
+{"current_steps": 1450, "total_steps": 2025, "loss": 0.0421, "learning_rate": 2.2626007035878377e-06, "epoch": 2.148148148148148, "percentage": 71.6, "elapsed_time": "2:04:00", "remaining_time": "0:49:10"}
+{"current_steps": 1460, "total_steps": 2025, "loss": 0.0315, "learning_rate": 2.1908667341300923e-06, "epoch": 2.162962962962963, "percentage": 72.1, "elapsed_time": "2:04:49", "remaining_time": "0:48:18"}
+{"current_steps": 1470, "total_steps": 2025, "loss": 0.0348, "learning_rate": 2.1199679148598434e-06, "epoch": 2.1777777777777776, "percentage": 72.59, "elapsed_time": "2:05:38", "remaining_time": "0:47:26"}
+{"current_steps": 1480, "total_steps": 2025, "loss": 0.0496, "learning_rate": 2.0499253238665284e-06, "epoch": 2.1925925925925926, "percentage": 73.09, "elapsed_time": "2:06:26", "remaining_time": "0:46:33"}
+{"current_steps": 1490, "total_steps": 2025, "loss": 0.0287, "learning_rate": 1.9807597846844737e-06, "epoch": 2.2074074074074073, "percentage": 73.58, "elapsed_time": "2:07:16", "remaining_time": "0:45:41"}
+{"current_steps": 1500, "total_steps": 2025, "loss": 0.0362, "learning_rate": 1.9124918601021124e-06, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "2:08:05", "remaining_time": "0:44:49"}
+{"current_steps": 1500, "total_steps": 2025, "eval_loss": 0.25548920035362244, "epoch": 2.2222222222222223, "percentage": 74.07, "elapsed_time": "2:09:55", "remaining_time": "0:45:28"}
+{"current_steps": 1510, "total_steps": 2025, "loss": 0.0327, "learning_rate": 1.845141846048691e-06, "epoch": 2.237037037037037, "percentage": 74.57, "elapsed_time": "2:11:58", "remaining_time": "0:45:00"}
+{"current_steps": 1520, "total_steps": 2025, "loss": 0.0275, "learning_rate": 1.778729765560337e-06, "epoch": 2.251851851851852, "percentage": 75.06, "elapsed_time": "2:12:47", "remaining_time": "0:44:07"}
+{"current_steps": 1530, "total_steps": 2025, "loss": 0.0465, "learning_rate": 1.7132753628272403e-06, "epoch": 2.2666666666666666, "percentage": 75.56, "elapsed_time": "2:13:36", "remaining_time": "0:43:13"}
+{"current_steps": 1540, "total_steps": 2025, "loss": 0.0308, "learning_rate": 1.6487980973237434e-06, "epoch": 2.2814814814814817, "percentage": 76.05, "elapsed_time": "2:14:25", "remaining_time": "0:42:20"}
+{"current_steps": 1550, "total_steps": 2025, "loss": 0.0345, "learning_rate": 1.5853171380230791e-06, "epoch": 2.2962962962962963, "percentage": 76.54, "elapsed_time": "2:15:14", "remaining_time": "0:41:26"}
+{"current_steps": 1560, "total_steps": 2025, "loss": 0.0281, "learning_rate": 1.5228513576984633e-06, "epoch": 2.311111111111111, "percentage": 77.04, "elapsed_time": "2:16:03", "remaining_time": "0:40:33"}
+{"current_steps": 1570, "total_steps": 2025, "loss": 0.0445, "learning_rate": 1.4614193273122562e-06, "epoch": 2.325925925925926, "percentage": 77.53, "elapsed_time": "2:16:52", "remaining_time": "0:39:40"}
+{"current_steps": 1580, "total_steps": 2025, "loss": 0.0435, "learning_rate": 1.401039310494855e-06, "epoch": 2.3407407407407406, "percentage": 78.02, "elapsed_time": "2:17:40", "remaining_time": "0:38:46"}
+{"current_steps": 1590, "total_steps": 2025, "loss": 0.0353, "learning_rate": 1.3417292581149388e-06, "epoch": 2.3555555555555556, "percentage": 78.52, "elapsed_time": "2:18:30", "remaining_time": "0:37:53"}
+{"current_steps": 1600, "total_steps": 2025, "loss": 0.0299, "learning_rate": 1.2835068029427188e-06, "epoch": 2.3703703703703702, "percentage": 79.01, "elapsed_time": "2:19:17", "remaining_time": "0:36:59"}
+{"current_steps": 1610, "total_steps": 2025, "loss": 0.0351, "learning_rate": 1.2263892544077439e-06, "epoch": 2.3851851851851853, "percentage": 79.51, "elapsed_time": "2:20:00", "remaining_time": "0:36:05"}
+{"current_steps": 1620, "total_steps": 2025, "loss": 0.0449, "learning_rate": 1.1703935934528327e-06, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "2:20:47", "remaining_time": "0:35:11"}
+{"current_steps": 1630, "total_steps": 2025, "loss": 0.0279, "learning_rate": 1.1155364674856834e-06, "epoch": 2.414814814814815, "percentage": 80.49, "elapsed_time": "2:21:36", "remaining_time": "0:34:18"}
+{"current_steps": 1640, "total_steps": 2025, "loss": 0.0443, "learning_rate": 1.0618341854296176e-06, "epoch": 2.4296296296296296, "percentage": 80.99, "elapsed_time": "2:22:25", "remaining_time": "0:33:26"}
+{"current_steps": 1650, "total_steps": 2025, "loss": 0.0398, "learning_rate": 1.0093027128749722e-06, "epoch": 2.4444444444444446, "percentage": 81.48, "elapsed_time": "2:23:13", "remaining_time": "0:32:33"}
+{"current_steps": 1660, "total_steps": 2025, "loss": 0.0392, "learning_rate": 9.57957667332562e-07, "epoch": 2.4592592592592593, "percentage": 81.98, "elapsed_time": "2:24:02", "remaining_time": "0:31:40"}
+{"current_steps": 1670, "total_steps": 2025, "loss": 0.0361, "learning_rate": 9.078143135906154e-07, "epoch": 2.474074074074074, "percentage": 82.47, "elapsed_time": "2:24:51", "remaining_time": "0:30:47"}
+{"current_steps": 1680, "total_steps": 2025, "loss": 0.0424, "learning_rate": 8.588875591765838e-07, "epoch": 2.488888888888889, "percentage": 82.96, "elapsed_time": "2:25:38", "remaining_time": "0:29:54"}
+{"current_steps": 1690, "total_steps": 2025, "loss": 0.0265, "learning_rate": 8.111919499251653e-07, "epoch": 2.5037037037037035, "percentage": 83.46, "elapsed_time": "2:26:27", "remaining_time": "0:29:01"}
+{"current_steps": 1700, "total_steps": 2025, "loss": 0.0379, "learning_rate": 7.647416656538464e-07, "epoch": 2.5185185185185186, "percentage": 83.95, "elapsed_time": "2:27:17", "remaining_time": "0:28:09"}
+{"current_steps": 1710, "total_steps": 2025, "loss": 0.0269, "learning_rate": 7.195505159472726e-07, "epoch": 2.533333333333333, "percentage": 84.44, "elapsed_time": "2:28:06", "remaining_time": "0:27:16"}
+{"current_steps": 1720, "total_steps": 2025, "loss": 0.0276, "learning_rate": 6.756319360516856e-07, "epoch": 2.5481481481481483, "percentage": 84.94, "elapsed_time": "2:28:54", "remaining_time": "0:26:24"}
+{"current_steps": 1730, "total_steps": 2025, "loss": 0.0283, "learning_rate": 6.329989828806482e-07, "epoch": 2.562962962962963, "percentage": 85.43, "elapsed_time": "2:29:43", "remaining_time": "0:25:31"}
+{"current_steps": 1740, "total_steps": 2025, "loss": 0.0391, "learning_rate": 5.916643311332438e-07, "epoch": 2.5777777777777775, "percentage": 85.93, "elapsed_time": "2:30:30", "remaining_time": "0:24:39"}
+{"current_steps": 1750, "total_steps": 2025, "loss": 0.0324, "learning_rate": 5.516402695259165e-07, "epoch": 2.5925925925925926, "percentage": 86.42, "elapsed_time": "2:31:19", "remaining_time": "0:23:46"}
+{"current_steps": 1760, "total_steps": 2025, "loss": 0.0298, "learning_rate": 5.12938697139056e-07, "epoch": 2.6074074074074076, "percentage": 86.91, "elapsed_time": "2:32:07", "remaining_time": "0:22:54"}
+{"current_steps": 1770, "total_steps": 2025, "loss": 0.0323, "learning_rate": 4.755711198794233e-07, "epoch": 2.6222222222222222, "percentage": 87.41, "elapsed_time": "2:32:55", "remaining_time": "0:22:01"}
+{"current_steps": 1780, "total_steps": 2025, "loss": 0.0256, "learning_rate": 4.395486470594645e-07, "epoch": 2.637037037037037, "percentage": 87.9, "elapsed_time": "2:33:45", "remaining_time": "0:21:09"}
+{"current_steps": 1790, "total_steps": 2025, "loss": 0.0291, "learning_rate": 4.048819880945337e-07, "epoch": 2.651851851851852, "percentage": 88.4, "elapsed_time": "2:34:33", "remaining_time": "0:20:17"}
+{"current_steps": 1800, "total_steps": 2025, "loss": 0.0262, "learning_rate": 3.7158144931900395e-07, "epoch": 2.6666666666666665, "percentage": 88.89, "elapsed_time": "2:35:22", "remaining_time": "0:19:25"}
+{"current_steps": 1810, "total_steps": 2025, "loss": 0.0282, "learning_rate": 3.396569309222114e-07, "epoch": 2.6814814814814816, "percentage": 89.38, "elapsed_time": "2:36:11", "remaining_time": "0:18:33"}
+{"current_steps": 1820, "total_steps": 2025, "loss": 0.0282, "learning_rate": 3.091179240051462e-07, "epoch": 2.696296296296296, "percentage": 89.88, "elapsed_time": "2:36:58", "remaining_time": "0:17:40"}
+{"current_steps": 1830, "total_steps": 2025, "loss": 0.036, "learning_rate": 2.799735077587695e-07, "epoch": 2.7111111111111112, "percentage": 90.37, "elapsed_time": "2:37:46", "remaining_time": "0:16:48"}
+{"current_steps": 1840, "total_steps": 2025, "loss": 0.0236, "learning_rate": 2.5223234676478193e-07, "epoch": 2.725925925925926, "percentage": 90.86, "elapsed_time": "2:38:35", "remaining_time": "0:15:56"}
+{"current_steps": 1850, "total_steps": 2025, "loss": 0.0306, "learning_rate": 2.2590268841966357e-07, "epoch": 2.7407407407407405, "percentage": 91.36, "elapsed_time": "2:39:24", "remaining_time": "0:15:04"}
+{"current_steps": 1860, "total_steps": 2025, "loss": 0.0306, "learning_rate": 2.0099236048273407e-07, "epoch": 2.7555555555555555, "percentage": 91.85, "elapsed_time": "2:40:13", "remaining_time": "0:14:12"}
+{"current_steps": 1870, "total_steps": 2025, "loss": 0.0317, "learning_rate": 1.7750876874897627e-07, "epoch": 2.7703703703703706, "percentage": 92.35, "elapsed_time": "2:41:02", "remaining_time": "0:13:20"}
+{"current_steps": 1880, "total_steps": 2025, "loss": 0.0303, "learning_rate": 1.554588948473068e-07, "epoch": 2.785185185185185, "percentage": 92.84, "elapsed_time": "2:41:51", "remaining_time": "0:12:29"}
+{"current_steps": 1890, "total_steps": 2025, "loss": 0.0318, "learning_rate": 1.3484929416495096e-07, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "2:42:40", "remaining_time": "0:11:37"}
+{"current_steps": 1900, "total_steps": 2025, "loss": 0.0403, "learning_rate": 1.1568609389853546e-07, "epoch": 2.814814814814815, "percentage": 93.83, "elapsed_time": "2:43:27", "remaining_time": "0:10:45"}
+{"current_steps": 1910, "total_steps": 2025, "loss": 0.0284, "learning_rate": 9.7974991232489e-08, "epoch": 2.8296296296296295, "percentage": 94.32, "elapsed_time": "2:44:16", "remaining_time": "0:09:53"}
+{"current_steps": 1920, "total_steps": 2025, "loss": 0.0408, "learning_rate": 8.172125164527312e-08, "epoch": 2.8444444444444446, "percentage": 94.81, "elapsed_time": "2:45:05", "remaining_time": "0:09:01"}
+{"current_steps": 1930, "total_steps": 2025, "loss": 0.038, "learning_rate": 6.692970734397176e-08, "epoch": 2.859259259259259, "percentage": 95.31, "elapsed_time": "2:45:53", "remaining_time": "0:08:09"}
+{"current_steps": 1940, "total_steps": 2025, "loss": 0.0362, "learning_rate": 5.360475582768088e-08, "epoch": 2.8740740740740742, "percentage": 95.8, "elapsed_time": "2:46:42", "remaining_time": "0:07:18"}
+{"current_steps": 1950, "total_steps": 2025, "loss": 0.0294, "learning_rate": 4.175035858013987e-08, "epoch": 2.888888888888889, "percentage": 96.3, "elapsed_time": "2:47:28", "remaining_time": "0:06:26"}
+{"current_steps": 1960, "total_steps": 2025, "loss": 0.0303, "learning_rate": 3.13700398919925e-08, "epoch": 2.9037037037037035, "percentage": 96.79, "elapsed_time": "2:48:17", "remaining_time": "0:05:34"}
+{"current_steps": 1970, "total_steps": 2025, "loss": 0.0284, "learning_rate": 2.2466885813018925e-08, "epoch": 2.9185185185185185, "percentage": 97.28, "elapsed_time": "2:49:06", "remaining_time": "0:04:43"}
+{"current_steps": 1980, "total_steps": 2025, "loss": 0.0235, "learning_rate": 1.504354323466073e-08, "epoch": 2.9333333333333336, "percentage": 97.78, "elapsed_time": "2:49:55", "remaining_time": "0:03:51"}
+{"current_steps": 1990, "total_steps": 2025, "loss": 0.0383, "learning_rate": 9.102219103103161e-09, "epoch": 2.948148148148148, "percentage": 98.27, "elapsed_time": "2:50:44", "remaining_time": "0:03:00"}
+{"current_steps": 2000, "total_steps": 2025, "loss": 0.0244, "learning_rate": 4.644679763155524e-09, "epoch": 2.962962962962963, "percentage": 98.77, "elapsed_time": "2:51:33", "remaining_time": "0:02:08"}
+{"current_steps": 2000, "total_steps": 2025, "eval_loss": 0.2506597936153412, "epoch": 2.962962962962963, "percentage": 98.77, "elapsed_time": "2:53:23", "remaining_time": "0:02:10"}
+{"current_steps": 2010, "total_steps": 2025, "loss": 0.024, "learning_rate": 1.6722504331195822e-09, "epoch": 2.977777777777778, "percentage": 99.26, "elapsed_time": "2:55:34", "remaining_time": "0:01:18"}
+{"current_steps": 2020, "total_steps": 2025, "loss": 0.0264, "learning_rate": 1.8581481080415242e-10, "epoch": 2.9925925925925925, "percentage": 99.75, "elapsed_time": "2:56:22", "remaining_time": "0:00:26"}
+{"current_steps": 2025, "total_steps": 2025, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:58:06", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1488 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2025,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014814814814814815,
+      "grad_norm": 26.017102109115793,
+      "learning_rate": 4.926108374384237e-07,
+      "loss": 0.5936,
+      "step": 10
+    },
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 12.914864221350799,
+      "learning_rate": 9.852216748768474e-07,
+      "loss": 0.3977,
+      "step": 20
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 7.447780113204344,
+      "learning_rate": 1.4778325123152712e-06,
+      "loss": 0.2758,
+      "step": 30
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 7.2037494981971735,
+      "learning_rate": 1.970443349753695e-06,
+      "loss": 0.206,
+      "step": 40
+    },
+    {
+      "epoch": 0.07407407407407407,
+      "grad_norm": 9.39085512125214,
+      "learning_rate": 2.4630541871921186e-06,
+      "loss": 0.2267,
+      "step": 50
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 7.044937181975286,
+      "learning_rate": 2.9556650246305424e-06,
+      "loss": 0.2088,
+      "step": 60
+    },
+    {
+      "epoch": 0.1037037037037037,
+      "grad_norm": 5.795730113429066,
+      "learning_rate": 3.448275862068966e-06,
+      "loss": 0.197,
+      "step": 70
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 7.080218597087718,
+      "learning_rate": 3.94088669950739e-06,
+      "loss": 0.1934,
+      "step": 80
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 5.53348676182737,
+      "learning_rate": 4.4334975369458135e-06,
+      "loss": 0.2117,
+      "step": 90
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 5.286987282479059,
+      "learning_rate": 4.926108374384237e-06,
+      "loss": 0.2408,
+      "step": 100
+    },
+    {
+      "epoch": 0.16296296296296298,
+      "grad_norm": 6.606219609047498,
+      "learning_rate": 5.41871921182266e-06,
+      "loss": 0.2066,
+      "step": 110
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 4.701177482407085,
+      "learning_rate": 5.911330049261085e-06,
+      "loss": 0.2281,
+      "step": 120
+    },
+    {
+      "epoch": 0.1925925925925926,
+      "grad_norm": 5.456763973680646,
+      "learning_rate": 6.403940886699508e-06,
+      "loss": 0.234,
+      "step": 130
+    },
+    {
+      "epoch": 0.2074074074074074,
+      "grad_norm": 5.574928605824461,
+      "learning_rate": 6.896551724137932e-06,
+      "loss": 0.2239,
+      "step": 140
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 4.2789352272007095,
+      "learning_rate": 7.3891625615763555e-06,
+      "loss": 0.2339,
+      "step": 150
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 4.6444068197911585,
+      "learning_rate": 7.88177339901478e-06,
+      "loss": 0.2261,
+      "step": 160
+    },
+    {
+      "epoch": 0.2518518518518518,
+      "grad_norm": 4.889863953460466,
+      "learning_rate": 8.374384236453203e-06,
+      "loss": 0.253,
+      "step": 170
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 4.819379627675783,
+      "learning_rate": 8.866995073891627e-06,
+      "loss": 0.2592,
+      "step": 180
+    },
+    {
+      "epoch": 0.2814814814814815,
+      "grad_norm": 4.783281320760556,
+      "learning_rate": 9.359605911330049e-06,
+      "loss": 0.2558,
+      "step": 190
+    },
+    {
+      "epoch": 0.2962962962962963,
+      "grad_norm": 4.6210148664541055,
+      "learning_rate": 9.852216748768475e-06,
+      "loss": 0.2791,
+      "step": 200
+    },
+    {
+      "epoch": 0.3111111111111111,
+      "grad_norm": 6.194129626142383,
+      "learning_rate": 9.99963580513638e-06,
+      "loss": 0.266,
+      "step": 210
+    },
+    {
+      "epoch": 0.32592592592592595,
+      "grad_norm": 4.306028672789547,
+      "learning_rate": 9.997852121279563e-06,
+      "loss": 0.2644,
+      "step": 220
+    },
+    {
+      "epoch": 0.34074074074074073,
+      "grad_norm": 4.550912215301358,
+      "learning_rate": 9.994582585118449e-06,
+      "loss": 0.2398,
+      "step": 230
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 2.7873840728898416,
+      "learning_rate": 9.989828168680164e-06,
+      "loss": 0.2459,
+      "step": 240
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 5.670238707619235,
+      "learning_rate": 9.983590285444025e-06,
+      "loss": 0.2874,
+      "step": 250
+    },
+    {
+      "epoch": 0.3851851851851852,
+      "grad_norm": 3.666204083864708,
+      "learning_rate": 9.975870789921322e-06,
+      "loss": 0.243,
+      "step": 260
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.765419867995775,
+      "learning_rate": 9.966671977103972e-06,
+      "loss": 0.2418,
+      "step": 270
+    },
+    {
+      "epoch": 0.4148148148148148,
+      "grad_norm": 4.266352929836881,
+      "learning_rate": 9.955996581782218e-06,
+      "loss": 0.3023,
+      "step": 280
+    },
+    {
+      "epoch": 0.42962962962962964,
+      "grad_norm": 5.260394697457832,
+      "learning_rate": 9.943847777731584e-06,
+      "loss": 0.2765,
+      "step": 290
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 8.072668515977384,
+      "learning_rate": 9.93022917676932e-06,
+      "loss": 0.2804,
+      "step": 300
+    },
+    {
+      "epoch": 0.45925925925925926,
+      "grad_norm": 8.611241020880648,
+      "learning_rate": 9.915144827680606e-06,
+      "loss": 0.2703,
+      "step": 310
+    },
+    {
+      "epoch": 0.4740740740740741,
+      "grad_norm": 5.269422886099256,
+      "learning_rate": 9.898599215014868e-06,
+      "loss": 0.2875,
+      "step": 320
+    },
+    {
+      "epoch": 0.4888888888888889,
+      "grad_norm": 4.630321430071603,
+      "learning_rate": 9.880597257752522e-06,
+      "loss": 0.2639,
+      "step": 330
+    },
+    {
+      "epoch": 0.5037037037037037,
+      "grad_norm": 6.86287315478417,
+      "learning_rate": 9.861144307842574e-06,
+      "loss": 0.2339,
+      "step": 340
+    },
+    {
+      "epoch": 0.5185185185185185,
+      "grad_norm": 4.726853171099211,
+      "learning_rate": 9.840246148611485e-06,
+      "loss": 0.2552,
+      "step": 350
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 3.24789768577898,
+      "learning_rate": 9.817908993043819e-06,
+      "loss": 0.2817,
+      "step": 360
+    },
+    {
+      "epoch": 0.5481481481481482,
+      "grad_norm": 4.1350169337840965,
+      "learning_rate": 9.794139481935108e-06,
+      "loss": 0.2641,
+      "step": 370
+    },
+    {
+      "epoch": 0.562962962962963,
+      "grad_norm": 2.730446652174673,
+      "learning_rate": 9.768944681917582e-06,
+      "loss": 0.2826,
+      "step": 380
+    },
+    {
+      "epoch": 0.5777777777777777,
+      "grad_norm": 3.9971570005802266,
+      "learning_rate": 9.742332083359252e-06,
+      "loss": 0.2559,
+      "step": 390
+    },
+    {
+      "epoch": 0.5925925925925926,
+      "grad_norm": 3.753217276080861,
+      "learning_rate": 9.714309598137045e-06,
+      "loss": 0.2306,
+      "step": 400
+    },
+    {
+      "epoch": 0.6074074074074074,
+      "grad_norm": 15.424898203468624,
+      "learning_rate": 9.68488555728462e-06,
+      "loss": 0.2682,
+      "step": 410
+    },
+    {
+      "epoch": 0.6222222222222222,
+      "grad_norm": 3.8975775295207318,
+      "learning_rate": 9.654068708515564e-06,
+      "loss": 0.2607,
+      "step": 420
+    },
+    {
+      "epoch": 0.6370370370370371,
+      "grad_norm": 4.141551276129438,
+      "learning_rate": 9.621868213622713e-06,
+      "loss": 0.2383,
+      "step": 430
+    },
+    {
+      "epoch": 0.6518518518518519,
+      "grad_norm": 3.9225855004559356,
+      "learning_rate": 9.588293645754363e-06,
+      "loss": 0.293,
+      "step": 440
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 3.2761325115244624,
+      "learning_rate": 9.553354986568201e-06,
+      "loss": 0.2942,
+      "step": 450
+    },
+    {
+      "epoch": 0.6814814814814815,
+      "grad_norm": 3.0682621048324945,
+      "learning_rate": 9.517062623263768e-06,
+      "loss": 0.2524,
+      "step": 460
+    },
+    {
+      "epoch": 0.6962962962962963,
+      "grad_norm": 3.231493961817089,
+      "learning_rate": 9.479427345494366e-06,
+      "loss": 0.2623,
+      "step": 470
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 5.3337328348116015,
+      "learning_rate": 9.440460342159314e-06,
+      "loss": 0.2786,
+      "step": 480
+    },
+    {
+      "epoch": 0.725925925925926,
+      "grad_norm": 4.944222927733353,
+      "learning_rate": 9.40017319807751e-06,
+      "loss": 0.2276,
+      "step": 490
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 4.898395138758685,
+      "learning_rate": 9.358577890543277e-06,
+      "loss": 0.2781,
+      "step": 500
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "eval_loss": 0.2680646777153015,
+      "eval_runtime": 110.7868,
+      "eval_samples_per_second": 2.708,
+      "eval_steps_per_second": 1.354,
+      "step": 500
+    },
+    {
+      "epoch": 0.7555555555555555,
+      "grad_norm": 3.853101145062431,
+      "learning_rate": 9.315686785765556e-06,
+      "loss": 0.2637,
+      "step": 510
+    },
+    {
+      "epoch": 0.7703703703703704,
+      "grad_norm": 4.4209909567001535,
+      "learning_rate": 9.271512635191427e-06,
+      "loss": 0.2707,
+      "step": 520
+    },
+    {
+      "epoch": 0.7851851851851852,
+      "grad_norm": 4.336113654547109,
+      "learning_rate": 9.22606857171515e-06,
+      "loss": 0.2376,
+      "step": 530
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.107334588558504,
+      "learning_rate": 9.179368105773768e-06,
+      "loss": 0.2495,
+      "step": 540
+    },
+    {
+      "epoch": 0.8148148148148148,
+      "grad_norm": 4.730641918906785,
+      "learning_rate": 9.131425121330477e-06,
+      "loss": 0.2379,
+      "step": 550
+    },
+    {
+      "epoch": 0.8296296296296296,
+      "grad_norm": 19.960301317231036,
+      "learning_rate": 9.082253871746962e-06,
+      "loss": 0.2702,
+      "step": 560
+    },
+    {
+      "epoch": 0.8444444444444444,
+      "grad_norm": 6.6215773453228115,
+      "learning_rate": 9.031868975545884e-06,
+      "loss": 0.2961,
+      "step": 570
+    },
+    {
+      "epoch": 0.8592592592592593,
+      "grad_norm": 3.0739713217438274,
+      "learning_rate": 8.980285412064827e-06,
+      "loss": 0.2381,
+      "step": 580
+    },
+    {
+      "epoch": 0.8740740740740741,
+      "grad_norm": 3.748817408124034,
+      "learning_rate": 8.92751851700297e-06,
+      "loss": 0.2258,
+      "step": 590
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 3.6234404866008996,
+      "learning_rate": 8.873583977861802e-06,
+      "loss": 0.2395,
+      "step": 600
+    },
+    {
+      "epoch": 0.9037037037037037,
+      "grad_norm": 4.04735847376876,
+      "learning_rate": 8.818497829281272e-06,
+      "loss": 0.2458,
+      "step": 610
+    },
+    {
+      "epoch": 0.9185185185185185,
+      "grad_norm": 3.6442745029714296,
+      "learning_rate": 8.762276448272709e-06,
+      "loss": 0.2552,
+      "step": 620
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 4.331703349382409,
+      "learning_rate": 8.70493654934996e-06,
+      "loss": 0.2909,
+      "step": 630
+    },
+    {
+      "epoch": 0.9481481481481482,
+      "grad_norm": 6.051325269419405,
+      "learning_rate": 8.646495179560221e-06,
+      "loss": 0.2564,
+      "step": 640
+    },
+    {
+      "epoch": 0.9629629629629629,
+      "grad_norm": 4.436797287629697,
+      "learning_rate": 8.586969713415949e-06,
+      "loss": 0.2374,
+      "step": 650
+    },
+    {
+      "epoch": 0.9777777777777777,
+      "grad_norm": 2.756495280511311,
+      "learning_rate": 8.526377847729475e-06,
+      "loss": 0.2441,
+      "step": 660
+    },
+    {
+      "epoch": 0.9925925925925926,
+      "grad_norm": 2.460062031773824,
+      "learning_rate": 8.46473759635176e-06,
+      "loss": 0.2566,
+      "step": 670
+    },
+    {
+      "epoch": 1.0074074074074073,
+      "grad_norm": 2.8968674379949215,
+      "learning_rate": 8.402067284816919e-06,
+      "loss": 0.1853,
+      "step": 680
+    },
+    {
+      "epoch": 1.0222222222222221,
+      "grad_norm": 3.1957903906863465,
+      "learning_rate": 8.338385544894073e-06,
+      "loss": 0.127,
+      "step": 690
+    },
+    {
+      "epoch": 1.037037037037037,
+      "grad_norm": 2.6559772016064587,
+      "learning_rate": 8.273711309048145e-06,
+      "loss": 0.1254,
+      "step": 700
+    },
+    {
+      "epoch": 1.0518518518518518,
+      "grad_norm": 3.0419408376224033,
+      "learning_rate": 8.208063804811293e-06,
+      "loss": 0.1385,
+      "step": 710
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 2.324938116275548,
+      "learning_rate": 8.141462549066581e-06,
+      "loss": 0.1344,
+      "step": 720
+    },
+    {
+      "epoch": 1.0814814814814815,
+      "grad_norm": 3.4270759875212233,
+      "learning_rate": 8.073927342245663e-06,
+      "loss": 0.1419,
+      "step": 730
+    },
+    {
+      "epoch": 1.0962962962962963,
+      "grad_norm": 2.6055600373408105,
+      "learning_rate": 8.005478262442132e-06,
+      "loss": 0.1308,
+      "step": 740
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 2.573600018786121,
+      "learning_rate": 7.936135659442355e-06,
+      "loss": 0.133,
+      "step": 750
+    },
+    {
+      "epoch": 1.125925925925926,
+      "grad_norm": 1.3199535934067952,
+      "learning_rate": 7.86592014867551e-06,
+      "loss": 0.1099,
+      "step": 760
+    },
+    {
+      "epoch": 1.1407407407407408,
+      "grad_norm": 2.5610850600680113,
+      "learning_rate": 7.794852605084661e-06,
+      "loss": 0.1429,
+      "step": 770
+    },
+    {
+      "epoch": 1.1555555555555554,
+      "grad_norm": 2.72955021912288,
+      "learning_rate": 7.722954156920675e-06,
+      "loss": 0.1227,
+      "step": 780
+    },
+    {
+      "epoch": 1.1703703703703703,
+      "grad_norm": 3.447611029467879,
+      "learning_rate": 7.650246179460826e-06,
+      "loss": 0.1499,
+      "step": 790
+    },
+    {
+      "epoch": 1.1851851851851851,
+      "grad_norm": 4.42799750544096,
+      "learning_rate": 7.57675028865397e-06,
+      "loss": 0.1564,
+      "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.9245723364864586,
+      "learning_rate": 7.502488334694167e-06,
+      "loss": 0.1441,
+      "step": 810
+    },
+    {
+      "epoch": 1.2148148148148148,
+      "grad_norm": 3.9787651452124524,
+      "learning_rate": 7.427482395524646e-06,
+      "loss": 0.1317,
+      "step": 820
+    },
+    {
+      "epoch": 1.2296296296296296,
+      "grad_norm": 3.5447225202330745,
+      "learning_rate": 7.35175477027408e-06,
+      "loss": 0.1211,
+      "step": 830
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 3.013749806838306,
+      "learning_rate": 7.2753279726271e-06,
+      "loss": 0.1284,
+      "step": 840
+    },
+    {
+      "epoch": 1.2592592592592593,
+      "grad_norm": 2.8757278244677553,
+      "learning_rate": 7.198224724131012e-06,
+      "loss": 0.1436,
+      "step": 850
+    },
+    {
+      "epoch": 1.2740740740740741,
+      "grad_norm": 3.813666156239548,
+      "learning_rate": 7.120467947440719e-06,
+      "loss": 0.1221,
+      "step": 860
+    },
+    {
+      "epoch": 1.2888888888888888,
+      "grad_norm": 2.3407714617223885,
+      "learning_rate": 7.042080759503866e-06,
+      "loss": 0.1162,
+      "step": 870
+    },
+    {
+      "epoch": 1.3037037037037038,
+      "grad_norm": 2.5559098463338397,
+      "learning_rate": 6.963086464688209e-06,
+      "loss": 0.1291,
+      "step": 880
+    },
+    {
+      "epoch": 1.3185185185185184,
+      "grad_norm": 2.5329035033815637,
+      "learning_rate": 6.883508547853268e-06,
+      "loss": 0.1319,
+      "step": 890
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 4.756367202905442,
+      "learning_rate": 6.8033706673683276e-06,
+      "loss": 0.125,
+      "step": 900
+    },
+    {
+      "epoch": 1.348148148148148,
+      "grad_norm": 2.4135868103281446,
+      "learning_rate": 6.722696648078838e-06,
+      "loss": 0.1382,
+      "step": 910
+    },
+    {
+      "epoch": 1.362962962962963,
+      "grad_norm": 2.1274954103320143,
+      "learning_rate": 6.641510474223338e-06,
+      "loss": 0.1311,
+      "step": 920
+    },
+    {
+      "epoch": 1.3777777777777778,
+      "grad_norm": 5.925560885437899,
+      "learning_rate": 6.559836282302984e-06,
+      "loss": 0.1416,
+      "step": 930
+    },
+    {
+      "epoch": 1.3925925925925926,
+      "grad_norm": 2.628591269898234,
+      "learning_rate": 6.477698353905808e-06,
+      "loss": 0.1519,
+      "step": 940
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 2.7741467084148925,
+      "learning_rate": 6.395121108487855e-06,
+      "loss": 0.1179,
+      "step": 950
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 2.4497960109998362,
+      "learning_rate": 6.312129096113313e-06,
+      "loss": 0.1329,
+      "step": 960
+    },
+    {
+      "epoch": 1.4370370370370371,
+      "grad_norm": 3.192126852233065,
+      "learning_rate": 6.228746990155831e-06,
+      "loss": 0.0981,
+      "step": 970
+    },
+    {
+      "epoch": 1.4518518518518517,
+      "grad_norm": 2.180408863260512,
+      "learning_rate": 6.144999579963164e-06,
+      "loss": 0.116,
+      "step": 980
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 2.60239822124948,
+      "learning_rate": 6.060911763487353e-06,
+      "loss": 0.136,
+      "step": 990
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "grad_norm": 2.9763711731701745,
+      "learning_rate": 5.976508539882604e-06,
+      "loss": 0.1417,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4814814814814814,
+      "eval_loss": 0.23991718888282776,
+      "eval_runtime": 110.0876,
+      "eval_samples_per_second": 2.725,
+      "eval_steps_per_second": 1.363,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4962962962962962,
+      "grad_norm": 1.5705062635477183,
+      "learning_rate": 5.891815002073081e-06,
+      "loss": 0.1118,
+      "step": 1010
+    },
+    {
+      "epoch": 1.511111111111111,
+      "grad_norm": 1.8570339015498183,
+      "learning_rate": 5.806856329292839e-06,
+      "loss": 0.1202,
+      "step": 1020
+    },
+    {
+      "epoch": 1.525925925925926,
+      "grad_norm": 2.9744617003579523,
+      "learning_rate": 5.721657779600071e-06,
+      "loss": 0.1256,
+      "step": 1030
+    },
+    {
+      "epoch": 1.5407407407407407,
+      "grad_norm": 3.0753703391352056,
+      "learning_rate": 5.636244682367937e-06,
+      "loss": 0.1402,
+      "step": 1040
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 2.464360253185267,
+      "learning_rate": 5.5506424307541895e-06,
+      "loss": 0.1034,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5703703703703704,
+      "grad_norm": 2.836329426651843,
+      "learning_rate": 5.464876474151835e-06,
+      "loss": 0.1302,
+      "step": 1060
+    },
+    {
+      "epoch": 1.585185185185185,
+      "grad_norm": 4.20442553150441,
+      "learning_rate": 5.3789723106230675e-06,
+      "loss": 0.128,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.189788584493857,
+      "learning_rate": 5.292955479318756e-06,
+      "loss": 0.1265,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6148148148148147,
+      "grad_norm": 2.1857430787318273,
+      "learning_rate": 5.206851552885691e-06,
+      "loss": 0.1276,
+      "step": 1090
+    },
+    {
+      "epoch": 1.6296296296296298,
+      "grad_norm": 2.0830677851745283,
+      "learning_rate": 5.120686129863882e-06,
+      "loss": 0.1131,
+      "step": 1100
+    },
+    {
+      "epoch": 1.6444444444444444,
+      "grad_norm": 2.399753090852167,
+      "learning_rate": 5.0344848270761635e-06,
+      "loss": 0.1353,
+      "step": 1110
+    },
+    {
+      "epoch": 1.6592592592592592,
+      "grad_norm": 2.972662069394894,
+      "learning_rate": 4.948273272012363e-06,
+      "loss": 0.1256,
+      "step": 1120
+    },
+    {
+      "epoch": 1.674074074074074,
+      "grad_norm": 2.725058666193907,
+      "learning_rate": 4.862077095210284e-06,
+      "loss": 0.1223,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6888888888888889,
+      "grad_norm": 2.403455581216295,
+      "learning_rate": 4.775921922635806e-06,
+      "loss": 0.1101,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7037037037037037,
+      "grad_norm": 2.954298808597469,
+      "learning_rate": 4.689833368064326e-06,
+      "loss": 0.1136,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7185185185185186,
+      "grad_norm": 2.065869616587133,
+      "learning_rate": 4.603837025465829e-06,
+      "loss": 0.0936,
+      "step": 1160
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 2.5225001244758434,
+      "learning_rate": 4.517958461395846e-06,
+      "loss": 0.1035,
+      "step": 1170
+    },
+    {
+      "epoch": 1.748148148148148,
+      "grad_norm": 2.278719889103367,
+      "learning_rate": 4.432223207394577e-06,
+      "loss": 0.0978,
+      "step": 1180
+    },
+    {
+      "epoch": 1.762962962962963,
+      "grad_norm": 3.0324188432282204,
+      "learning_rate": 4.346656752396388e-06,
+      "loss": 0.1234,
+      "step": 1190
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 3.15770874304934,
+      "learning_rate": 4.261284535152016e-06,
+      "loss": 0.1117,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7925925925925927,
+      "grad_norm": 2.4288815684292007,
+      "learning_rate": 4.176131936665669e-06,
+      "loss": 0.1151,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8074074074074074,
+      "grad_norm": 2.2345406971177586,
+      "learning_rate": 4.0912242726493e-06,
+      "loss": 0.1087,
+      "step": 1220
+    },
+    {
+      "epoch": 1.8222222222222222,
+      "grad_norm": 1.3631354507880038,
+      "learning_rate": 4.006586785996285e-06,
+      "loss": 0.1094,
+      "step": 1230
+    },
+    {
+      "epoch": 1.837037037037037,
+      "grad_norm": 2.759382864621944,
+      "learning_rate": 3.922244639276773e-06,
+      "loss": 0.1077,
+      "step": 1240
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 2.299484616218074,
+      "learning_rate": 3.838222907256884e-06,
+      "loss": 0.1106,
+      "step": 1250
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 3.450427642587667,
+      "learning_rate": 3.7545465694440363e-06,
+      "loss": 0.1075,
+      "step": 1260
+    },
+    {
+      "epoch": 1.8814814814814815,
+      "grad_norm": 1.946789383498192,
+      "learning_rate": 3.6712405026605792e-06,
+      "loss": 0.1097,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8962962962962964,
+      "grad_norm": 3.1898982494578663,
+      "learning_rate": 3.5883294736479612e-06,
+      "loss": 0.1004,
+      "step": 1280
+    },
+    {
+      "epoch": 1.911111111111111,
+      "grad_norm": 2.180121020731452,
+      "learning_rate": 3.5058381317036285e-06,
+      "loss": 0.0906,
+      "step": 1290
+    },
+    {
+      "epoch": 1.925925925925926,
+      "grad_norm": 2.4521692799587593,
+      "learning_rate": 3.423791001352823e-06,
+      "loss": 0.1209,
+      "step": 1300
+    },
+    {
+      "epoch": 1.9407407407407407,
+      "grad_norm": 2.578764727071429,
+      "learning_rate": 3.3422124750574902e-06,
+      "loss": 0.1084,
+      "step": 1310
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 2.9192101640040526,
+      "learning_rate": 3.2611268059644535e-06,
+      "loss": 0.0974,
+      "step": 1320
+    },
+    {
+      "epoch": 1.9703703703703703,
+      "grad_norm": 3.1900819524103254,
+      "learning_rate": 3.1805581006949856e-06,
+      "loss": 0.1291,
+      "step": 1330
+    },
+    {
+      "epoch": 1.9851851851851852,
+      "grad_norm": 3.5372332007233585,
+      "learning_rate": 3.100530312177956e-06,
+      "loss": 0.1028,
+      "step": 1340
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.682319850341937,
+      "learning_rate": 3.0210672325286806e-06,
+      "loss": 0.1026,
+      "step": 1350
+    },
+    {
+      "epoch": 2.0148148148148146,
+      "grad_norm": 1.3372912715867262,
+      "learning_rate": 2.9421924859755525e-06,
+      "loss": 0.0428,
+      "step": 1360
+    },
+    {
+      "epoch": 2.0296296296296297,
+      "grad_norm": 1.3386975885602668,
+      "learning_rate": 2.8639295218366115e-06,
+      "loss": 0.0373,
+      "step": 1370
+    },
+    {
+      "epoch": 2.0444444444444443,
+      "grad_norm": 1.2812593118990734,
+      "learning_rate": 2.78630160754811e-06,
+      "loss": 0.0354,
+      "step": 1380
+    },
+    {
+      "epoch": 2.0592592592592593,
+      "grad_norm": 1.290388617260846,
+      "learning_rate": 2.709331821747133e-06,
+      "loss": 0.0265,
+      "step": 1390
+    },
+    {
+      "epoch": 2.074074074074074,
+      "grad_norm": 1.573529577676281,
+      "learning_rate": 2.63304304741037e-06,
+      "loss": 0.0278,
+      "step": 1400
+    },
+    {
+      "epoch": 2.088888888888889,
+      "grad_norm": 2.419667316602129,
+      "learning_rate": 2.55745796505105e-06,
+      "loss": 0.0487,
+      "step": 1410
+    },
+    {
+      "epoch": 2.1037037037037036,
+      "grad_norm": 1.0785142520976503,
+      "learning_rate": 2.482599045976059e-06,
+      "loss": 0.0364,
+      "step": 1420
+    },
+    {
+      "epoch": 2.1185185185185187,
+      "grad_norm": 2.0952689701078784,
+      "learning_rate": 2.408488545605265e-06,
+      "loss": 0.045,
+      "step": 1430
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 2.823990301006105,
+      "learning_rate": 2.3351484968550264e-06,
+      "loss": 0.0368,
+      "step": 1440
+    },
+    {
+      "epoch": 2.148148148148148,
+      "grad_norm": 1.7955041398866707,
+      "learning_rate": 2.2626007035878377e-06,
+      "loss": 0.0421,
+      "step": 1450
+    },
+    {
+      "epoch": 2.162962962962963,
+      "grad_norm": 0.8109338878062605,
+      "learning_rate": 2.1908667341300923e-06,
+      "loss": 0.0315,
+      "step": 1460
+    },
+    {
+      "epoch": 2.1777777777777776,
+      "grad_norm": 1.9133299721589396,
+      "learning_rate": 2.1199679148598434e-06,
+      "loss": 0.0348,
+      "step": 1470
+    },
+    {
+      "epoch": 2.1925925925925926,
+      "grad_norm": 1.2071834999832143,
+      "learning_rate": 2.0499253238665284e-06,
+      "loss": 0.0496,
+      "step": 1480
+    },
+    {
+      "epoch": 2.2074074074074073,
+      "grad_norm": 1.0217372762938706,
+      "learning_rate": 1.9807597846844737e-06,
+      "loss": 0.0287,
+      "step": 1490
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.0023764675817943,
+      "learning_rate": 1.9124918601021124e-06,
+      "loss": 0.0362,
+      "step": 1500
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "eval_loss": 0.25548920035362244,
+      "eval_runtime": 109.9471,
+      "eval_samples_per_second": 2.729,
+      "eval_steps_per_second": 1.364,
+      "step": 1500
+    },
+    {
+      "epoch": 2.237037037037037,
+      "grad_norm": 3.3820011756317867,
+      "learning_rate": 1.845141846048691e-06,
+      "loss": 0.0327,
+      "step": 1510
+    },
+    {
+      "epoch": 2.251851851851852,
+      "grad_norm": 1.8639592123431572,
+      "learning_rate": 1.778729765560337e-06,
+      "loss": 0.0275,
+      "step": 1520
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 1.924019925176325,
+      "learning_rate": 1.7132753628272403e-06,
+      "loss": 0.0465,
+      "step": 1530
+    },
+    {
+      "epoch": 2.2814814814814817,
+      "grad_norm": 1.152773684003778,
+      "learning_rate": 1.6487980973237434e-06,
+      "loss": 0.0308,
+      "step": 1540
+    },
+    {
+      "epoch": 2.2962962962962963,
+      "grad_norm": 1.894824044203695,
+      "learning_rate": 1.5853171380230791e-06,
+      "loss": 0.0345,
+      "step": 1550
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 1.3328611183809627,
+      "learning_rate": 1.5228513576984633e-06,
+      "loss": 0.0281,
+      "step": 1560
+    },
+    {
+      "epoch": 2.325925925925926,
+      "grad_norm": 3.750377643295275,
+      "learning_rate": 1.4614193273122562e-06,
+      "loss": 0.0445,
+      "step": 1570
+    },
+    {
+      "epoch": 2.3407407407407406,
+      "grad_norm": 3.8759939460354915,
+      "learning_rate": 1.401039310494855e-06,
+      "loss": 0.0435,
+      "step": 1580
+    },
+    {
+      "epoch": 2.3555555555555556,
+      "grad_norm": 3.0989225284077917,
+      "learning_rate": 1.3417292581149388e-06,
+      "loss": 0.0353,
+      "step": 1590
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.9919766228227254,
+      "learning_rate": 1.2835068029427188e-06,
+      "loss": 0.0299,
+      "step": 1600
+    },
+    {
+      "epoch": 2.3851851851851853,
+      "grad_norm": 1.1007285921225456,
+      "learning_rate": 1.2263892544077439e-06,
+      "loss": 0.0351,
+      "step": 1610
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.8350934062145996,
+      "learning_rate": 1.1703935934528327e-06,
+      "loss": 0.0449,
+      "step": 1620
+    },
+    {
+      "epoch": 2.414814814814815,
+      "grad_norm": 1.0737399447700786,
+      "learning_rate": 1.1155364674856834e-06,
+      "loss": 0.0279,
+      "step": 1630
+    },
+    {
+      "epoch": 2.4296296296296296,
+      "grad_norm": 1.1914051412570683,
+      "learning_rate": 1.0618341854296176e-06,
+      "loss": 0.0443,
+      "step": 1640
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 1.4625234311241986,
+      "learning_rate": 1.0093027128749722e-06,
+      "loss": 0.0398,
+      "step": 1650
+    },
+    {
+      "epoch": 2.4592592592592593,
+      "grad_norm": 2.809214532722792,
+      "learning_rate": 9.57957667332562e-07,
+      "loss": 0.0392,
+      "step": 1660
+    },
+    {
+      "epoch": 2.474074074074074,
+      "grad_norm": 2.048944419289513,
+      "learning_rate": 9.078143135906154e-07,
+      "loss": 0.0361,
+      "step": 1670
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 2.2346039939090168,
+      "learning_rate": 8.588875591765838e-07,
+      "loss": 0.0424,
+      "step": 1680
+    },
+    {
+      "epoch": 2.5037037037037035,
+      "grad_norm": 0.8685048120192506,
+      "learning_rate": 8.111919499251653e-07,
+      "loss": 0.0265,
+      "step": 1690
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 5.531554078682163,
+      "learning_rate": 7.647416656538464e-07,
+      "loss": 0.0379,
+      "step": 1700
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 2.567773799038788,
+      "learning_rate": 7.195505159472726e-07,
+      "loss": 0.0269,
+      "step": 1710
+    },
+    {
+      "epoch": 2.5481481481481483,
+      "grad_norm": 1.5337559661912539,
+      "learning_rate": 6.756319360516856e-07,
+      "loss": 0.0276,
+      "step": 1720
+    },
+    {
+      "epoch": 2.562962962962963,
+      "grad_norm": 2.401685833878839,
+      "learning_rate": 6.329989828806482e-07,
+      "loss": 0.0283,
+      "step": 1730
+    },
+    {
+      "epoch": 2.5777777777777775,
+      "grad_norm": 1.682913358837789,
+      "learning_rate": 5.916643311332438e-07,
+      "loss": 0.0391,
+      "step": 1740
+    },
+    {
+      "epoch": 2.5925925925925926,
+      "grad_norm": 1.689757637438205,
+      "learning_rate": 5.516402695259165e-07,
+      "loss": 0.0324,
+      "step": 1750
+    },
+    {
+      "epoch": 2.6074074074074076,
+      "grad_norm": 1.2197797882219985,
+      "learning_rate": 5.12938697139056e-07,
+      "loss": 0.0298,
+      "step": 1760
+    },
+    {
+      "epoch": 2.6222222222222222,
+      "grad_norm": 2.191377307550078,
+      "learning_rate": 4.755711198794233e-07,
+      "loss": 0.0323,
+      "step": 1770
+    },
+    {
+      "epoch": 2.637037037037037,
+      "grad_norm": 1.103714063244568,
+      "learning_rate": 4.395486470594645e-07,
+      "loss": 0.0256,
+      "step": 1780
+    },
+    {
+      "epoch": 2.651851851851852,
+      "grad_norm": 1.6229391835726705,
+      "learning_rate": 4.048819880945337e-07,
+      "loss": 0.0291,
+      "step": 1790
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.6366466447258576,
+      "learning_rate": 3.7158144931900395e-07,
+      "loss": 0.0262,
+      "step": 1800
+    },
+    {
+      "epoch": 2.6814814814814816,
+      "grad_norm": 1.3157936293009576,
+      "learning_rate": 3.396569309222114e-07,
+      "loss": 0.0282,
+      "step": 1810
+    },
+    {
+      "epoch": 2.696296296296296,
+      "grad_norm": 1.3484419903044749,
+      "learning_rate": 3.091179240051462e-07,
+      "loss": 0.0282,
+      "step": 1820
+    },
+    {
+      "epoch": 2.7111111111111112,
+      "grad_norm": 2.820403024559756,
+      "learning_rate": 2.799735077587695e-07,
+      "loss": 0.036,
+      "step": 1830
+    },
+    {
+      "epoch": 2.725925925925926,
+      "grad_norm": 1.108338803655822,
+      "learning_rate": 2.5223234676478193e-07,
+      "loss": 0.0236,
+      "step": 1840
+    },
+    {
+      "epoch": 2.7407407407407405,
+      "grad_norm": 1.1593020570108006,
+      "learning_rate": 2.2590268841966357e-07,
+      "loss": 0.0306,
+      "step": 1850
+    },
+    {
+      "epoch": 2.7555555555555555,
+      "grad_norm": 0.9513752742372911,
+      "learning_rate": 2.0099236048273407e-07,
+      "loss": 0.0306,
+      "step": 1860
+    },
+    {
+      "epoch": 2.7703703703703706,
+      "grad_norm": 2.6444015892408417,
+      "learning_rate": 1.7750876874897627e-07,
+      "loss": 0.0317,
+      "step": 1870
+    },
+    {
+      "epoch": 2.785185185185185,
+      "grad_norm": 2.028461793078949,
+      "learning_rate": 1.554588948473068e-07,
+      "loss": 0.0303,
+      "step": 1880
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 2.9681404257688637,
+      "learning_rate": 1.3484929416495096e-07,
+      "loss": 0.0318,
+      "step": 1890
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 1.7073934684848604,
+      "learning_rate": 1.1568609389853546e-07,
+      "loss": 0.0403,
+      "step": 1900
+    },
+    {
+      "epoch": 2.8296296296296295,
+      "grad_norm": 1.5684215370418764,
+      "learning_rate": 9.7974991232489e-08,
+      "loss": 0.0284,
+      "step": 1910
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 1.742009123872279,
+      "learning_rate": 8.172125164527312e-08,
+      "loss": 0.0408,
+      "step": 1920
+    },
+    {
+      "epoch": 2.859259259259259,
+      "grad_norm": 1.7024512023509764,
+      "learning_rate": 6.692970734397176e-08,
+      "loss": 0.038,
+      "step": 1930
+    },
+    {
+      "epoch": 2.8740740740740742,
+      "grad_norm": 1.0455017584864013,
+      "learning_rate": 5.360475582768088e-08,
+      "loss": 0.0362,
+      "step": 1940
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 1.3244853973367365,
+      "learning_rate": 4.175035858013987e-08,
+      "loss": 0.0294,
+      "step": 1950
+    },
+    {
+      "epoch": 2.9037037037037035,
+      "grad_norm": 1.3623719555386105,
+      "learning_rate": 3.13700398919925e-08,
+      "loss": 0.0303,
+      "step": 1960
+    },
+    {
+      "epoch": 2.9185185185185185,
+      "grad_norm": 1.417988437962572,
+      "learning_rate": 2.2466885813018925e-08,
+      "loss": 0.0284,
+      "step": 1970
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.8742047293170354,
+      "learning_rate": 1.504354323466073e-08,
+      "loss": 0.0235,
+      "step": 1980
+    },
+    {
+      "epoch": 2.948148148148148,
+      "grad_norm": 1.9231464337238604,
+      "learning_rate": 9.102219103103161e-09,
+      "loss": 0.0383,
+      "step": 1990
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 2.1190416620342303,
+      "learning_rate": 4.644679763155524e-09,
+      "loss": 0.0244,
+      "step": 2000
+    },
+    {
+      "epoch": 2.962962962962963,
+      "eval_loss": 0.2506597936153412,
+      "eval_runtime": 109.9607,
+      "eval_samples_per_second": 2.728,
+      "eval_steps_per_second": 1.364,
+      "step": 2000
+    },
+    {
+      "epoch": 2.977777777777778,
+      "grad_norm": 1.0361197122874597,
+      "learning_rate": 1.6722504331195822e-09,
+      "loss": 0.024,
+      "step": 2010
+    },
+    {
+      "epoch": 2.9925925925925925,
+      "grad_norm": 1.8532792834690945,
+      "learning_rate": 1.8581481080415242e-10,
+      "loss": 0.0264,
+      "step": 2020
+    },
+    {
+      "epoch": 3.0,
+      "step": 2025,
+      "total_flos": 15334618890240.0,
+      "train_loss": 0.13858298796930432,
+      "train_runtime": 10686.6427,
+      "train_samples_per_second": 0.758,
+      "train_steps_per_second": 0.189
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2025,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 15334618890240.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff59a7f39daf7697a917c2e8abd8209004558406b11900367663f270d5bbbce
+size 7032