End of training

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: llama3
+base_model: NousResearch/Hermes-3-Llama-3.1-8B
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: full
+  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. -->
+
+# full
+
+This model is a fine-tuned version of [NousResearch/Hermes-3-Llama-3.1-8B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B) on the None dataset.
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.2.0
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "NousResearch/Hermes-3-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128040,
+  "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": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128040,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2a3bb11c4d81fe30b5d11136b0b9824a524dd49fd95ae3798460334078e68b
+size 4988251656

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc81f2abcf48e543fd333faad21ea70979ad69daf24749d9bbe331cf29c447bb
+size 4899116440

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ced7a53bec5db3ebdde1ac170c7e10ae483cf6c6abe721c9f963105e1da51da
+size 4999813120

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1409da7da60128ab7c3fcaeb2d38a00477f018772743fb6ed6173cfe86f62e3d
+size 4999813128

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f462b4f76d31f2edc7f60b81316e5853cec061f7c727ebb4db5c0950f54b0b83
+size 4832007496

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e9bcf28c541b6b4015542662bab14c125908e7d3387940925cc29547cb37978
+size 3724710464

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 28443678720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2082 @@
+{
+  "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128003": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128012": {
+      "content": "</tools>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128013": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128014": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128015": {
+      "content": "<schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128016": {
+      "content": "</schema>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128017": {
+      "content": "<scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128018": {
+      "content": "</scratch_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128019": {
+      "content": "<SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128020": {
+      "content": "</SCRATCHPAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128021": {
+      "content": "<REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128022": {
+      "content": "</REASONING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128023": {
+      "content": "<INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128024": {
+      "content": "</INNER_MONOLOGUE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128025": {
+      "content": "<PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128026": {
+      "content": "</PLAN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128027": {
+      "content": "<EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128028": {
+      "content": "</EXECUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128029": {
+      "content": "<REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128030": {
+      "content": "</REFLECTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128031": {
+      "content": "<THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128032": {
+      "content": "</THINKING>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128033": {
+      "content": "<SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128034": {
+      "content": "</SOLUTION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128035": {
+      "content": "<EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128036": {
+      "content": "</EXPLANATION>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128037": {
+      "content": "<UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128038": {
+      "content": "</UNIT_TEST>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128039": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128040": {
+      "content": "<|im_end|>",
+      "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
+    },
+    "128256": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{bos_token}}{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
+    },
+    {
+      "name": "tool_use",
+      "template": "{%- macro json_to_python_type(json_spec) %}\n{%- set basic_type_map = {\n    \"string\": \"str\",\n    \"number\": \"float\",\n    \"integer\": \"int\",\n    \"boolean\": \"bool\"\n} %}\n\n{%- if basic_type_map[json_spec.type] is defined %}\n    {{- basic_type_map[json_spec.type] }}\n{%- elif json_spec.type == \"array\" %}\n    {{- \"list[\" +  json_to_python_type(json_spec|items) + \"]\"}}\n{%- elif json_spec.type == \"object\" %}\n    {%- if json_spec.additionalProperties is defined %}\n        {{- \"dict[str, \" + json_to_python_type(json_spec.additionalProperties) + ']'}}\n    {%- else %}\n        {{- \"dict\" }}\n    {%- endif %}\n{%- elif json_spec.type is iterable %}\n    {{- \"Union[\" }}\n    {%- for t in json_spec.type %}\n      {{- json_to_python_type({\"type\": t}) }}\n      {%- if not loop.last %}\n        {{- \",\" }} \n    {%- endif %}\n    {%- endfor %}\n    {{- \"]\" }}\n{%- else %}\n    {{- \"Any\" }}\n{%- endif %}\n{%- endmacro %}\n\n\n{{- bos_token }}\n{{- '<|im_start|>system\n' }}\n{{- \"You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> \" }}\n{%- for tool in tools %}\n    {%- if tool.function is defined %}\n        {%- set tool = tool.function %}\n    {%- endif %}\n    {{- '{\"type\": \"function\", \"function\": ' }}\n    {{- '{\"name\": \"' + tool.name + '\", ' }}\n    {{- '\"description\": \"' + tool.name + '(' }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {{- param_name + \": \" + json_to_python_type(param_fields) }}\n        {%- if not loop.last %}\n            {{- \", \" }}\n        {%- endif %}\n    {%- endfor %}\n    {{- \")\" }}\n    {%- if tool.return is defined %}\n        {{- \" -> \" + json_to_python_type(tool.return) }}\n    {%- endif %}\n    {{- \" - \" + tool.description + \"\n\n\" }}\n    {%- for param_name, param_fields in tool.parameters.properties|items %}\n        {%- if loop.first %}\n            {{- \"    Args:\n\" }}\n        {%- endif %}\n        {{- \"        \" + param_name + \"(\" + json_to_python_type(param_fields) + \"): \" + param_fields.description|trim }}\n    {%- endfor %}\n    {%- if tool.return is defined and tool.return.description is defined %}\n        {{- \"\n    Returns:\n        \" + tool.return.description }}\n    {%- endif %}\n    {{- '\"' }}\n    {{- ', \"parameters\": ' }}\n    {%- if tool.parameters.properties | length == 0 %}\n        {{- \"{}\" }}\n    {%- else %}\n        {{- tool.parameters|tojson }}\n    {%- endif %}\n    {{- \"}\" }}\n    {%- if not loop.last %}\n        {{- \"\n\" }}\n    {%- endif %}\n{%- endfor %}\n{{- \" </tools>\" }}\n{{- 'Use the following pydantic model json schema for each tool call you will make: {\"properties\": {\"name\": {\"title\": \"Name\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"type\": \"object\"}}, \"required\": [\"name\", \"arguments\"], \"title\": \"FunctionCall\", \"type\": \"object\"}}\n' }}\n{{- \"For each function call return a json object with function name and arguments within <tool_call></tool_call> XML tags as follows:\n\" }}\n{{- \"<tool_call>\n\" }}\n{{- '{\"name\": <function-name>, \"arguments\": <args-dict>}\n' }}\n{{- '</tool_call><|im_end|>\n' }}\n{%- for message in messages %}\n    {%- if message.role == \"user\" or message.role == \"system\" or (message.role == \"assistant\" and message.tool_calls is not defined) %}\n        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n    {%- for tool_call in message.tool_calls %}\n       {{- '\n<tool_call>\n' }}           {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '{' }}\n            {{- '\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\"' }}\n            {{- ', '}}\n            {%- if tool_call.arguments is defined %}\n                {{- '\"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments|tojson }}\n                {%- endif %}\n            {%- endif %}\n             {{- '}' }}\n            {{- '\n</tool_call>' }}\n    {%- endfor %}\n        {{- '<|im_end|>\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>tool\n' }}\n        {%- endif %}\n        {{- '<tool_response>\n' }}\n        {{- message.content }}\n        {%- if not loop.last %}\n            {{- '\n</tool_response>\n' }}\n        {%- else %}\n            {{- '\n</tool_response>' }}\n        {%- endif %}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\n' }}\n{%- endif %}\n"
+    }
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|im_end|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1024,
+  "pad_token": "<|im_end|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,3129 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.984771573604061,
+  "eval_steps": 500,
+  "global_step": 441,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00676818950930626,
+      "grad_norm": 30.061185836791992,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 3.5407,
+      "step": 1
+    },
+    {
+      "epoch": 0.01353637901861252,
+      "grad_norm": 45.98220443725586,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 3.8623,
+      "step": 2
+    },
+    {
+      "epoch": 0.02030456852791878,
+      "grad_norm": 52.36494064331055,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 4.0388,
+      "step": 3
+    },
+    {
+      "epoch": 0.02707275803722504,
+      "grad_norm": 38.702606201171875,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 3.9038,
+      "step": 4
+    },
+    {
+      "epoch": 0.0338409475465313,
+      "grad_norm": 39.755348205566406,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 3.7208,
+      "step": 5
+    },
+    {
+      "epoch": 0.04060913705583756,
+      "grad_norm": 28.482959747314453,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 3.699,
+      "step": 6
+    },
+    {
+      "epoch": 0.047377326565143825,
+      "grad_norm": 33.6556510925293,
+      "learning_rate": 1e-05,
+      "loss": 3.2901,
+      "step": 7
+    },
+    {
+      "epoch": 0.05414551607445008,
+      "grad_norm": 10.973630905151367,
+      "learning_rate": 1.1428571428571429e-05,
+      "loss": 3.2131,
+      "step": 8
+    },
+    {
+      "epoch": 0.06091370558375635,
+      "grad_norm": 8.036073684692383,
+      "learning_rate": 1.2857142857142859e-05,
+      "loss": 3.2309,
+      "step": 9
+    },
+    {
+      "epoch": 0.0676818950930626,
+      "grad_norm": 7.630257606506348,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 3.2666,
+      "step": 10
+    },
+    {
+      "epoch": 0.07445008460236886,
+      "grad_norm": 7.535837650299072,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 3.1925,
+      "step": 11
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 10.59571361541748,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 3.1352,
+      "step": 12
+    },
+    {
+      "epoch": 0.08798646362098139,
+      "grad_norm": 8.021005630493164,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 2.8961,
+      "step": 13
+    },
+    {
+      "epoch": 0.09475465313028765,
+      "grad_norm": 5.240553855895996,
+      "learning_rate": 2e-05,
+      "loss": 3.0844,
+      "step": 14
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 5.916426658630371,
+      "learning_rate": 1.9999729347501484e-05,
+      "loss": 3.1558,
+      "step": 15
+    },
+    {
+      "epoch": 0.10829103214890017,
+      "grad_norm": 5.597356796264648,
+      "learning_rate": 1.9998917404656488e-05,
+      "loss": 3.091,
+      "step": 16
+    },
+    {
+      "epoch": 0.11505922165820642,
+      "grad_norm": 6.339421272277832,
+      "learning_rate": 1.9997564215415886e-05,
+      "loss": 3.1522,
+      "step": 17
+    },
+    {
+      "epoch": 0.1218274111675127,
+      "grad_norm": 8.770332336425781,
+      "learning_rate": 1.9995669853028485e-05,
+      "loss": 3.1213,
+      "step": 18
+    },
+    {
+      "epoch": 0.12859560067681894,
+      "grad_norm": 8.278801918029785,
+      "learning_rate": 1.9993234420037072e-05,
+      "loss": 3.1599,
+      "step": 19
+    },
+    {
+      "epoch": 0.1353637901861252,
+      "grad_norm": 4.014164447784424,
+      "learning_rate": 1.999025804827285e-05,
+      "loss": 2.9919,
+      "step": 20
+    },
+    {
+      "epoch": 0.14213197969543148,
+      "grad_norm": 4.980748653411865,
+      "learning_rate": 1.9986740898848306e-05,
+      "loss": 3.0508,
+      "step": 21
+    },
+    {
+      "epoch": 0.14890016920473773,
+      "grad_norm": 4.607733249664307,
+      "learning_rate": 1.99826831621485e-05,
+      "loss": 3.0403,
+      "step": 22
+    },
+    {
+      "epoch": 0.155668358714044,
+      "grad_norm": 4.822920799255371,
+      "learning_rate": 1.997808505782075e-05,
+      "loss": 3.1426,
+      "step": 23
+    },
+    {
+      "epoch": 0.16243654822335024,
+      "grad_norm": 6.66705846786499,
+      "learning_rate": 1.9972946834762732e-05,
+      "loss": 3.1822,
+      "step": 24
+    },
+    {
+      "epoch": 0.1692047377326565,
+      "grad_norm": 8.534043312072754,
+      "learning_rate": 1.9967268771109037e-05,
+      "loss": 3.0409,
+      "step": 25
+    },
+    {
+      "epoch": 0.17597292724196278,
+      "grad_norm": 5.848859786987305,
+      "learning_rate": 1.996105117421608e-05,
+      "loss": 2.9325,
+      "step": 26
+    },
+    {
+      "epoch": 0.18274111675126903,
+      "grad_norm": 3.849553108215332,
+      "learning_rate": 1.9954294380645497e-05,
+      "loss": 2.9975,
+      "step": 27
+    },
+    {
+      "epoch": 0.1895093062605753,
+      "grad_norm": 5.086816787719727,
+      "learning_rate": 1.9946998756145894e-05,
+      "loss": 3.0159,
+      "step": 28
+    },
+    {
+      "epoch": 0.19627749576988154,
+      "grad_norm": 5.160210132598877,
+      "learning_rate": 1.9939164695633067e-05,
+      "loss": 3.1489,
+      "step": 29
+    },
+    {
+      "epoch": 0.20304568527918782,
+      "grad_norm": 5.439467430114746,
+      "learning_rate": 1.9930792623168638e-05,
+      "loss": 3.09,
+      "step": 30
+    },
+    {
+      "epoch": 0.2098138747884941,
+      "grad_norm": 6.836553573608398,
+      "learning_rate": 1.992188299193706e-05,
+      "loss": 3.1017,
+      "step": 31
+    },
+    {
+      "epoch": 0.21658206429780033,
+      "grad_norm": 6.904626846313477,
+      "learning_rate": 1.9912436284221134e-05,
+      "loss": 2.798,
+      "step": 32
+    },
+    {
+      "epoch": 0.2233502538071066,
+      "grad_norm": 3.7659807205200195,
+      "learning_rate": 1.9902453011375865e-05,
+      "loss": 2.9905,
+      "step": 33
+    },
+    {
+      "epoch": 0.23011844331641285,
+      "grad_norm": 4.325652122497559,
+      "learning_rate": 1.98919337138008e-05,
+      "loss": 3.004,
+      "step": 34
+    },
+    {
+      "epoch": 0.23688663282571912,
+      "grad_norm": 5.1247100830078125,
+      "learning_rate": 1.9880878960910772e-05,
+      "loss": 2.9883,
+      "step": 35
+    },
+    {
+      "epoch": 0.2436548223350254,
+      "grad_norm": 5.715439319610596,
+      "learning_rate": 1.9869289351105087e-05,
+      "loss": 3.106,
+      "step": 36
+    },
+    {
+      "epoch": 0.25042301184433163,
+      "grad_norm": 6.596778392791748,
+      "learning_rate": 1.9857165511735105e-05,
+      "loss": 3.094,
+      "step": 37
+    },
+    {
+      "epoch": 0.2571912013536379,
+      "grad_norm": 5.765414714813232,
+      "learning_rate": 1.9844508099070313e-05,
+      "loss": 2.9328,
+      "step": 38
+    },
+    {
+      "epoch": 0.2639593908629442,
+      "grad_norm": 3.2168986797332764,
+      "learning_rate": 1.9831317798262787e-05,
+      "loss": 2.9776,
+      "step": 39
+    },
+    {
+      "epoch": 0.2707275803722504,
+      "grad_norm": 3.423891067504883,
+      "learning_rate": 1.98175953233101e-05,
+      "loss": 2.9672,
+      "step": 40
+    },
+    {
+      "epoch": 0.27749576988155666,
+      "grad_norm": 4.785609245300293,
+      "learning_rate": 1.980334141701667e-05,
+      "loss": 3.1273,
+      "step": 41
+    },
+    {
+      "epoch": 0.28426395939086296,
+      "grad_norm": 5.194344997406006,
+      "learning_rate": 1.978855685095358e-05,
+      "loss": 3.0137,
+      "step": 42
+    },
+    {
+      "epoch": 0.2910321489001692,
+      "grad_norm": 5.609189510345459,
+      "learning_rate": 1.977324242541677e-05,
+      "loss": 3.0037,
+      "step": 43
+    },
+    {
+      "epoch": 0.29780033840947545,
+      "grad_norm": 6.650205612182617,
+      "learning_rate": 1.9757398969383752e-05,
+      "loss": 2.901,
+      "step": 44
+    },
+    {
+      "epoch": 0.30456852791878175,
+      "grad_norm": 4.614665985107422,
+      "learning_rate": 1.974102734046872e-05,
+      "loss": 2.9467,
+      "step": 45
+    },
+    {
+      "epoch": 0.311336717428088,
+      "grad_norm": 3.8143110275268555,
+      "learning_rate": 1.9724128424876117e-05,
+      "loss": 2.9703,
+      "step": 46
+    },
+    {
+      "epoch": 0.31810490693739424,
+      "grad_norm": 5.5977067947387695,
+      "learning_rate": 1.9706703137352695e-05,
+      "loss": 2.9885,
+      "step": 47
+    },
+    {
+      "epoch": 0.3248730964467005,
+      "grad_norm": 6.040333271026611,
+      "learning_rate": 1.968875242113798e-05,
+      "loss": 3.0303,
+      "step": 48
+    },
+    {
+      "epoch": 0.3316412859560068,
+      "grad_norm": 6.05629825592041,
+      "learning_rate": 1.9670277247913205e-05,
+      "loss": 2.9001,
+      "step": 49
+    },
+    {
+      "epoch": 0.338409475465313,
+      "grad_norm": 7.62821102142334,
+      "learning_rate": 1.965127861774873e-05,
+      "loss": 2.8845,
+      "step": 50
+    },
+    {
+      "epoch": 0.34517766497461927,
+      "grad_norm": 3.4944276809692383,
+      "learning_rate": 1.96317575590499e-05,
+      "loss": 2.8731,
+      "step": 51
+    },
+    {
+      "epoch": 0.35194585448392557,
+      "grad_norm": 3.9865429401397705,
+      "learning_rate": 1.9611715128501378e-05,
+      "loss": 2.936,
+      "step": 52
+    },
+    {
+      "epoch": 0.3587140439932318,
+      "grad_norm": 4.1927385330200195,
+      "learning_rate": 1.9591152411009942e-05,
+      "loss": 2.9779,
+      "step": 53
+    },
+    {
+      "epoch": 0.36548223350253806,
+      "grad_norm": 4.403099060058594,
+      "learning_rate": 1.9570070519645767e-05,
+      "loss": 2.9444,
+      "step": 54
+    },
+    {
+      "epoch": 0.37225042301184436,
+      "grad_norm": 5.183342456817627,
+      "learning_rate": 1.9548470595582166e-05,
+      "loss": 2.9487,
+      "step": 55
+    },
+    {
+      "epoch": 0.3790186125211506,
+      "grad_norm": 6.125980854034424,
+      "learning_rate": 1.9526353808033827e-05,
+      "loss": 2.7997,
+      "step": 56
+    },
+    {
+      "epoch": 0.38578680203045684,
+      "grad_norm": 5.613026142120361,
+      "learning_rate": 1.9503721354193507e-05,
+      "loss": 2.8006,
+      "step": 57
+    },
+    {
+      "epoch": 0.3925549915397631,
+      "grad_norm": 5.052882194519043,
+      "learning_rate": 1.948057445916724e-05,
+      "loss": 2.8919,
+      "step": 58
+    },
+    {
+      "epoch": 0.3993231810490694,
+      "grad_norm": 3.8712987899780273,
+      "learning_rate": 1.9456914375908026e-05,
+      "loss": 2.912,
+      "step": 59
+    },
+    {
+      "epoch": 0.40609137055837563,
+      "grad_norm": 5.594967365264893,
+      "learning_rate": 1.9432742385147988e-05,
+      "loss": 3.0025,
+      "step": 60
+    },
+    {
+      "epoch": 0.4128595600676819,
+      "grad_norm": 5.751216411590576,
+      "learning_rate": 1.9408059795329073e-05,
+      "loss": 2.9587,
+      "step": 61
+    },
+    {
+      "epoch": 0.4196277495769882,
+      "grad_norm": 6.2975993156433105,
+      "learning_rate": 1.9382867942532195e-05,
+      "loss": 2.8469,
+      "step": 62
+    },
+    {
+      "epoch": 0.4263959390862944,
+      "grad_norm": 5.6724724769592285,
+      "learning_rate": 1.9357168190404937e-05,
+      "loss": 2.8086,
+      "step": 63
+    },
+    {
+      "epoch": 0.43316412859560066,
+      "grad_norm": 3.814537525177002,
+      "learning_rate": 1.9330961930087724e-05,
+      "loss": 2.8346,
+      "step": 64
+    },
+    {
+      "epoch": 0.43993231810490696,
+      "grad_norm": 4.25925874710083,
+      "learning_rate": 1.9304250580138524e-05,
+      "loss": 2.9784,
+      "step": 65
+    },
+    {
+      "epoch": 0.4467005076142132,
+      "grad_norm": 3.799999237060547,
+      "learning_rate": 1.9277035586456056e-05,
+      "loss": 2.8535,
+      "step": 66
+    },
+    {
+      "epoch": 0.45346869712351945,
+      "grad_norm": 6.35882568359375,
+      "learning_rate": 1.9249318422201524e-05,
+      "loss": 2.9694,
+      "step": 67
+    },
+    {
+      "epoch": 0.4602368866328257,
+      "grad_norm": 6.477646827697754,
+      "learning_rate": 1.9221100587718884e-05,
+      "loss": 3.0061,
+      "step": 68
+    },
+    {
+      "epoch": 0.467005076142132,
+      "grad_norm": 5.934814929962158,
+      "learning_rate": 1.919238361045362e-05,
+      "loss": 2.7579,
+      "step": 69
+    },
+    {
+      "epoch": 0.47377326565143824,
+      "grad_norm": 3.154392719268799,
+      "learning_rate": 1.916316904487005e-05,
+      "loss": 2.7796,
+      "step": 70
+    },
+    {
+      "epoch": 0.4805414551607445,
+      "grad_norm": 4.2975616455078125,
+      "learning_rate": 1.9133458472367216e-05,
+      "loss": 2.8438,
+      "step": 71
+    },
+    {
+      "epoch": 0.4873096446700508,
+      "grad_norm": 3.5001091957092285,
+      "learning_rate": 1.9103253501193256e-05,
+      "loss": 2.9239,
+      "step": 72
+    },
+    {
+      "epoch": 0.494077834179357,
+      "grad_norm": 5.083667278289795,
+      "learning_rate": 1.9072555766358346e-05,
+      "loss": 2.9237,
+      "step": 73
+    },
+    {
+      "epoch": 0.5008460236886633,
+      "grad_norm": 5.127432346343994,
+      "learning_rate": 1.904136692954622e-05,
+      "loss": 2.9601,
+      "step": 74
+    },
+    {
+      "epoch": 0.5076142131979695,
+      "grad_norm": 6.419186115264893,
+      "learning_rate": 1.900968867902419e-05,
+      "loss": 2.8173,
+      "step": 75
+    },
+    {
+      "epoch": 0.5143824027072758,
+      "grad_norm": 3.2118561267852783,
+      "learning_rate": 1.89775227295518e-05,
+      "loss": 2.7624,
+      "step": 76
+    },
+    {
+      "epoch": 0.5211505922165821,
+      "grad_norm": 4.4183807373046875,
+      "learning_rate": 1.8944870822287957e-05,
+      "loss": 2.84,
+      "step": 77
+    },
+    {
+      "epoch": 0.5279187817258884,
+      "grad_norm": 4.880641460418701,
+      "learning_rate": 1.891173472469672e-05,
+      "loss": 2.8241,
+      "step": 78
+    },
+    {
+      "epoch": 0.5346869712351946,
+      "grad_norm": 4.362979888916016,
+      "learning_rate": 1.8878116230451615e-05,
+      "loss": 2.8896,
+      "step": 79
+    },
+    {
+      "epoch": 0.5414551607445008,
+      "grad_norm": 5.762423515319824,
+      "learning_rate": 1.884401715933853e-05,
+      "loss": 2.8949,
+      "step": 80
+    },
+    {
+      "epoch": 0.5482233502538071,
+      "grad_norm": 8.867072105407715,
+      "learning_rate": 1.8809439357157226e-05,
+      "loss": 2.9593,
+      "step": 81
+    },
+    {
+      "epoch": 0.5549915397631133,
+      "grad_norm": 5.437422752380371,
+      "learning_rate": 1.8774384695621407e-05,
+      "loss": 2.6622,
+      "step": 82
+    },
+    {
+      "epoch": 0.5617597292724196,
+      "grad_norm": 3.8561763763427734,
+      "learning_rate": 1.8738855072257428e-05,
+      "loss": 2.8984,
+      "step": 83
+    },
+    {
+      "epoch": 0.5685279187817259,
+      "grad_norm": 4.806951522827148,
+      "learning_rate": 1.8702852410301556e-05,
+      "loss": 2.8228,
+      "step": 84
+    },
+    {
+      "epoch": 0.5752961082910322,
+      "grad_norm": 4.01973295211792,
+      "learning_rate": 1.8666378658595863e-05,
+      "loss": 2.8602,
+      "step": 85
+    },
+    {
+      "epoch": 0.5820642978003384,
+      "grad_norm": 4.8082170486450195,
+      "learning_rate": 1.8629435791482765e-05,
+      "loss": 2.9552,
+      "step": 86
+    },
+    {
+      "epoch": 0.5888324873096447,
+      "grad_norm": 6.550163269042969,
+      "learning_rate": 1.8592025808698116e-05,
+      "loss": 2.7965,
+      "step": 87
+    },
+    {
+      "epoch": 0.5956006768189509,
+      "grad_norm": 6.67849588394165,
+      "learning_rate": 1.8554150735262975e-05,
+      "loss": 2.7528,
+      "step": 88
+    },
+    {
+      "epoch": 0.6023688663282571,
+      "grad_norm": 2.8771703243255615,
+      "learning_rate": 1.8515812621373998e-05,
+      "loss": 2.8308,
+      "step": 89
+    },
+    {
+      "epoch": 0.6091370558375635,
+      "grad_norm": 5.142778396606445,
+      "learning_rate": 1.8477013542292446e-05,
+      "loss": 2.7588,
+      "step": 90
+    },
+    {
+      "epoch": 0.6159052453468697,
+      "grad_norm": 6.1177873611450195,
+      "learning_rate": 1.8437755598231857e-05,
+      "loss": 2.8855,
+      "step": 91
+    },
+    {
+      "epoch": 0.622673434856176,
+      "grad_norm": 6.153074741363525,
+      "learning_rate": 1.8398040914244363e-05,
+      "loss": 2.982,
+      "step": 92
+    },
+    {
+      "epoch": 0.6294416243654822,
+      "grad_norm": 5.2112345695495605,
+      "learning_rate": 1.8357871640105648e-05,
+      "loss": 2.8087,
+      "step": 93
+    },
+    {
+      "epoch": 0.6362098138747885,
+      "grad_norm": 8.335490226745605,
+      "learning_rate": 1.8317249950198598e-05,
+      "loss": 2.6842,
+      "step": 94
+    },
+    {
+      "epoch": 0.6429780033840947,
+      "grad_norm": 5.8389668464660645,
+      "learning_rate": 1.8276178043395588e-05,
+      "loss": 2.7224,
+      "step": 95
+    },
+    {
+      "epoch": 0.649746192893401,
+      "grad_norm": 3.2980704307556152,
+      "learning_rate": 1.8234658142939454e-05,
+      "loss": 2.8933,
+      "step": 96
+    },
+    {
+      "epoch": 0.6565143824027073,
+      "grad_norm": 5.305524826049805,
+      "learning_rate": 1.8192692496323158e-05,
+      "loss": 2.8103,
+      "step": 97
+    },
+    {
+      "epoch": 0.6632825719120136,
+      "grad_norm": 6.091310977935791,
+      "learning_rate": 1.8150283375168112e-05,
+      "loss": 2.9352,
+      "step": 98
+    },
+    {
+      "epoch": 0.6700507614213198,
+      "grad_norm": 5.697042465209961,
+      "learning_rate": 1.8107433075101254e-05,
+      "loss": 2.8545,
+      "step": 99
+    },
+    {
+      "epoch": 0.676818950930626,
+      "grad_norm": 7.473045349121094,
+      "learning_rate": 1.8064143915630723e-05,
+      "loss": 2.6375,
+      "step": 100
+    },
+    {
+      "epoch": 0.6835871404399323,
+      "grad_norm": 2.685059070587158,
+      "learning_rate": 1.8020418240020362e-05,
+      "loss": 2.7562,
+      "step": 101
+    },
+    {
+      "epoch": 0.6903553299492385,
+      "grad_norm": 3.2231831550598145,
+      "learning_rate": 1.7976258415162836e-05,
+      "loss": 2.8718,
+      "step": 102
+    },
+    {
+      "epoch": 0.6971235194585449,
+      "grad_norm": 3.358761787414551,
+      "learning_rate": 1.7931666831451536e-05,
+      "loss": 2.8679,
+      "step": 103
+    },
+    {
+      "epoch": 0.7038917089678511,
+      "grad_norm": 4.336738109588623,
+      "learning_rate": 1.7886645902651166e-05,
+      "loss": 2.797,
+      "step": 104
+    },
+    {
+      "epoch": 0.7106598984771574,
+      "grad_norm": 4.629664421081543,
+      "learning_rate": 1.7841198065767107e-05,
+      "loss": 2.7675,
+      "step": 105
+    },
+    {
+      "epoch": 0.7174280879864636,
+      "grad_norm": 6.125463485717773,
+      "learning_rate": 1.779532578091347e-05,
+      "loss": 2.627,
+      "step": 106
+    },
+    {
+      "epoch": 0.7241962774957699,
+      "grad_norm": 4.7176361083984375,
+      "learning_rate": 1.7749031531179962e-05,
+      "loss": 2.6226,
+      "step": 107
+    },
+    {
+      "epoch": 0.7309644670050761,
+      "grad_norm": 3.0627963542938232,
+      "learning_rate": 1.7702317822497457e-05,
+      "loss": 2.8128,
+      "step": 108
+    },
+    {
+      "epoch": 0.7377326565143824,
+      "grad_norm": 4.201870918273926,
+      "learning_rate": 1.7655187183502344e-05,
+      "loss": 2.7452,
+      "step": 109
+    },
+    {
+      "epoch": 0.7445008460236887,
+      "grad_norm": 4.618666648864746,
+      "learning_rate": 1.7607642165399665e-05,
+      "loss": 2.8431,
+      "step": 110
+    },
+    {
+      "epoch": 0.751269035532995,
+      "grad_norm": 5.060817718505859,
+      "learning_rate": 1.755968534182501e-05,
+      "loss": 2.9154,
+      "step": 111
+    },
+    {
+      "epoch": 0.7580372250423012,
+      "grad_norm": 5.751707553863525,
+      "learning_rate": 1.7511319308705198e-05,
+      "loss": 2.7316,
+      "step": 112
+    },
+    {
+      "epoch": 0.7648054145516074,
+      "grad_norm": 5.403834342956543,
+      "learning_rate": 1.746254668411778e-05,
+      "loss": 2.6888,
+      "step": 113
+    },
+    {
+      "epoch": 0.7715736040609137,
+      "grad_norm": 3.657097339630127,
+      "learning_rate": 1.7413370108149288e-05,
+      "loss": 2.7851,
+      "step": 114
+    },
+    {
+      "epoch": 0.7783417935702199,
+      "grad_norm": 3.560981035232544,
+      "learning_rate": 1.7363792242752354e-05,
+      "loss": 2.8977,
+      "step": 115
+    },
+    {
+      "epoch": 0.7851099830795262,
+      "grad_norm": 5.971733570098877,
+      "learning_rate": 1.731381577160161e-05,
+      "loss": 2.7807,
+      "step": 116
+    },
+    {
+      "epoch": 0.7918781725888325,
+      "grad_norm": 5.342052459716797,
+      "learning_rate": 1.726344339994841e-05,
+      "loss": 2.8701,
+      "step": 117
+    },
+    {
+      "epoch": 0.7986463620981388,
+      "grad_norm": 5.152158737182617,
+      "learning_rate": 1.7212677854474402e-05,
+      "loss": 2.6611,
+      "step": 118
+    },
+    {
+      "epoch": 0.805414551607445,
+      "grad_norm": 5.67462682723999,
+      "learning_rate": 1.7161521883143936e-05,
+      "loss": 2.6134,
+      "step": 119
+    },
+    {
+      "epoch": 0.8121827411167513,
+      "grad_norm": 4.32338285446167,
+      "learning_rate": 1.7109978255055295e-05,
+      "loss": 2.7922,
+      "step": 120
+    },
+    {
+      "epoch": 0.8189509306260575,
+      "grad_norm": 4.190022945404053,
+      "learning_rate": 1.705804976029083e-05,
+      "loss": 2.7966,
+      "step": 121
+    },
+    {
+      "epoch": 0.8257191201353637,
+      "grad_norm": 3.7118101119995117,
+      "learning_rate": 1.7005739209765906e-05,
+      "loss": 2.8186,
+      "step": 122
+    },
+    {
+      "epoch": 0.8324873096446701,
+      "grad_norm": 5.160277366638184,
+      "learning_rate": 1.6953049435076768e-05,
+      "loss": 2.9102,
+      "step": 123
+    },
+    {
+      "epoch": 0.8392554991539763,
+      "grad_norm": 5.411961078643799,
+      "learning_rate": 1.6899983288347248e-05,
+      "loss": 2.7617,
+      "step": 124
+    },
+    {
+      "epoch": 0.8460236886632826,
+      "grad_norm": 7.095698356628418,
+      "learning_rate": 1.6846543642074382e-05,
+      "loss": 2.6926,
+      "step": 125
+    },
+    {
+      "epoch": 0.8527918781725888,
+      "grad_norm": 2.7258427143096924,
+      "learning_rate": 1.679273338897293e-05,
+      "loss": 2.6996,
+      "step": 126
+    },
+    {
+      "epoch": 0.8595600676818951,
+      "grad_norm": 3.8327107429504395,
+      "learning_rate": 1.6738555441818785e-05,
+      "loss": 2.7992,
+      "step": 127
+    },
+    {
+      "epoch": 0.8663282571912013,
+      "grad_norm": 4.773505687713623,
+      "learning_rate": 1.668401273329129e-05,
+      "loss": 2.7682,
+      "step": 128
+    },
+    {
+      "epoch": 0.8730964467005076,
+      "grad_norm": 4.107465744018555,
+      "learning_rate": 1.6629108215814523e-05,
+      "loss": 2.8903,
+      "step": 129
+    },
+    {
+      "epoch": 0.8798646362098139,
+      "grad_norm": 4.615577220916748,
+      "learning_rate": 1.6573844861397444e-05,
+      "loss": 2.8723,
+      "step": 130
+    },
+    {
+      "epoch": 0.8866328257191202,
+      "grad_norm": 7.497233867645264,
+      "learning_rate": 1.6518225661473045e-05,
+      "loss": 2.8291,
+      "step": 131
+    },
+    {
+      "epoch": 0.8934010152284264,
+      "grad_norm": 7.081593036651611,
+      "learning_rate": 1.6462253626736413e-05,
+      "loss": 2.5866,
+      "step": 132
+    },
+    {
+      "epoch": 0.9001692047377327,
+      "grad_norm": 3.4112582206726074,
+      "learning_rate": 1.6405931786981753e-05,
+      "loss": 2.7011,
+      "step": 133
+    },
+    {
+      "epoch": 0.9069373942470389,
+      "grad_norm": 4.411227226257324,
+      "learning_rate": 1.63492631909384e-05,
+      "loss": 2.7789,
+      "step": 134
+    },
+    {
+      "epoch": 0.9137055837563451,
+      "grad_norm": 5.724678993225098,
+      "learning_rate": 1.629225090610577e-05,
+      "loss": 2.8353,
+      "step": 135
+    },
+    {
+      "epoch": 0.9204737732656514,
+      "grad_norm": 5.374405860900879,
+      "learning_rate": 1.6234898018587336e-05,
+      "loss": 2.9269,
+      "step": 136
+    },
+    {
+      "epoch": 0.9272419627749577,
+      "grad_norm": 5.2880072593688965,
+      "learning_rate": 1.6177207632923558e-05,
+      "loss": 2.7229,
+      "step": 137
+    },
+    {
+      "epoch": 0.934010152284264,
+      "grad_norm": 5.647241115570068,
+      "learning_rate": 1.6119182871923834e-05,
+      "loss": 2.6128,
+      "step": 138
+    },
+    {
+      "epoch": 0.9407783417935702,
+      "grad_norm": 3.1383461952209473,
+      "learning_rate": 1.606082687649748e-05,
+      "loss": 2.708,
+      "step": 139
+    },
+    {
+      "epoch": 0.9475465313028765,
+      "grad_norm": 3.174626111984253,
+      "learning_rate": 1.6002142805483686e-05,
+      "loss": 2.8192,
+      "step": 140
+    },
+    {
+      "epoch": 0.9543147208121827,
+      "grad_norm": 3.3176159858703613,
+      "learning_rate": 1.5943133835480536e-05,
+      "loss": 2.8202,
+      "step": 141
+    },
+    {
+      "epoch": 0.961082910321489,
+      "grad_norm": 4.013696193695068,
+      "learning_rate": 1.588380316067307e-05,
+      "loss": 2.7887,
+      "step": 142
+    },
+    {
+      "epoch": 0.9678510998307953,
+      "grad_norm": 5.064754009246826,
+      "learning_rate": 1.582415399266036e-05,
+      "loss": 2.8008,
+      "step": 143
+    },
+    {
+      "epoch": 0.9746192893401016,
+      "grad_norm": 5.884125232696533,
+      "learning_rate": 1.5764189560281677e-05,
+      "loss": 2.6257,
+      "step": 144
+    },
+    {
+      "epoch": 0.9813874788494078,
+      "grad_norm": 3.0231032371520996,
+      "learning_rate": 1.5703913109441715e-05,
+      "loss": 2.7147,
+      "step": 145
+    },
+    {
+      "epoch": 0.988155668358714,
+      "grad_norm": 3.241084337234497,
+      "learning_rate": 1.564332790293487e-05,
+      "loss": 2.7612,
+      "step": 146
+    },
+    {
+      "epoch": 0.9949238578680203,
+      "grad_norm": 4.9145121574401855,
+      "learning_rate": 1.5582437220268648e-05,
+      "loss": 2.8171,
+      "step": 147
+    },
+    {
+      "epoch": 1.0016920473773265,
+      "grad_norm": 5.478322982788086,
+      "learning_rate": 1.5521244357486132e-05,
+      "loss": 2.6166,
+      "step": 148
+    },
+    {
+      "epoch": 1.0084602368866329,
+      "grad_norm": 2.909008502960205,
+      "learning_rate": 1.5459752626987563e-05,
+      "loss": 2.4026,
+      "step": 149
+    },
+    {
+      "epoch": 1.015228426395939,
+      "grad_norm": 3.355454206466675,
+      "learning_rate": 1.5397965357351035e-05,
+      "loss": 2.2265,
+      "step": 150
+    },
+    {
+      "epoch": 1.0219966159052454,
+      "grad_norm": 3.659177541732788,
+      "learning_rate": 1.5335885893152335e-05,
+      "loss": 2.1872,
+      "step": 151
+    },
+    {
+      "epoch": 1.0287648054145515,
+      "grad_norm": 4.308448791503906,
+      "learning_rate": 1.5273517594783878e-05,
+      "loss": 2.0188,
+      "step": 152
+    },
+    {
+      "epoch": 1.0355329949238579,
+      "grad_norm": 4.801682949066162,
+      "learning_rate": 1.521086383827282e-05,
+      "loss": 1.9166,
+      "step": 153
+    },
+    {
+      "epoch": 1.0423011844331642,
+      "grad_norm": 6.2991790771484375,
+      "learning_rate": 1.5147928015098309e-05,
+      "loss": 1.6925,
+      "step": 154
+    },
+    {
+      "epoch": 1.0490693739424704,
+      "grad_norm": 7.9047417640686035,
+      "learning_rate": 1.5084713532007906e-05,
+      "loss": 2.5637,
+      "step": 155
+    },
+    {
+      "epoch": 1.0558375634517767,
+      "grad_norm": 6.511372089385986,
+      "learning_rate": 1.5021223810833165e-05,
+      "loss": 2.3506,
+      "step": 156
+    },
+    {
+      "epoch": 1.0626057529610828,
+      "grad_norm": 5.02034854888916,
+      "learning_rate": 1.4957462288304421e-05,
+      "loss": 2.1029,
+      "step": 157
+    },
+    {
+      "epoch": 1.0693739424703892,
+      "grad_norm": 5.005341529846191,
+      "learning_rate": 1.489343241586475e-05,
+      "loss": 2.0565,
+      "step": 158
+    },
+    {
+      "epoch": 1.0761421319796955,
+      "grad_norm": 5.689651012420654,
+      "learning_rate": 1.4829137659483144e-05,
+      "loss": 1.9412,
+      "step": 159
+    },
+    {
+      "epoch": 1.0829103214890017,
+      "grad_norm": 6.038967609405518,
+      "learning_rate": 1.4764581499466895e-05,
+      "loss": 1.675,
+      "step": 160
+    },
+    {
+      "epoch": 1.089678510998308,
+      "grad_norm": 4.393552303314209,
+      "learning_rate": 1.4699767430273202e-05,
+      "loss": 2.1734,
+      "step": 161
+    },
+    {
+      "epoch": 1.0964467005076142,
+      "grad_norm": 3.555631637573242,
+      "learning_rate": 1.4634698960320018e-05,
+      "loss": 2.187,
+      "step": 162
+    },
+    {
+      "epoch": 1.1032148900169205,
+      "grad_norm": 3.7586710453033447,
+      "learning_rate": 1.4569379611796137e-05,
+      "loss": 1.9961,
+      "step": 163
+    },
+    {
+      "epoch": 1.1099830795262267,
+      "grad_norm": 4.319566249847412,
+      "learning_rate": 1.4503812920470535e-05,
+      "loss": 1.958,
+      "step": 164
+    },
+    {
+      "epoch": 1.116751269035533,
+      "grad_norm": 4.831964015960693,
+      "learning_rate": 1.443800243550098e-05,
+      "loss": 1.7072,
+      "step": 165
+    },
+    {
+      "epoch": 1.1235194585448394,
+      "grad_norm": 6.157094478607178,
+      "learning_rate": 1.4371951719241906e-05,
+      "loss": 1.7674,
+      "step": 166
+    },
+    {
+      "epoch": 1.1302876480541455,
+      "grad_norm": 4.833260536193848,
+      "learning_rate": 1.4305664347051586e-05,
+      "loss": 1.9227,
+      "step": 167
+    },
+    {
+      "epoch": 1.1370558375634519,
+      "grad_norm": 3.5581912994384766,
+      "learning_rate": 1.423914390709861e-05,
+      "loss": 2.3748,
+      "step": 168
+    },
+    {
+      "epoch": 1.143824027072758,
+      "grad_norm": 3.734834909439087,
+      "learning_rate": 1.4172394000167625e-05,
+      "loss": 2.0371,
+      "step": 169
+    },
+    {
+      "epoch": 1.1505922165820643,
+      "grad_norm": 4.00279426574707,
+      "learning_rate": 1.4105418239464452e-05,
+      "loss": 2.0383,
+      "step": 170
+    },
+    {
+      "epoch": 1.1573604060913705,
+      "grad_norm": 4.664214134216309,
+      "learning_rate": 1.4038220250420487e-05,
+      "loss": 1.9445,
+      "step": 171
+    },
+    {
+      "epoch": 1.1641285956006768,
+      "grad_norm": 5.319397926330566,
+      "learning_rate": 1.3970803670496453e-05,
+      "loss": 1.7367,
+      "step": 172
+    },
+    {
+      "epoch": 1.1708967851099832,
+      "grad_norm": 5.559267520904541,
+      "learning_rate": 1.390317214898551e-05,
+      "loss": 1.7855,
+      "step": 173
+    },
+    {
+      "epoch": 1.1776649746192893,
+      "grad_norm": 3.4772238731384277,
+      "learning_rate": 1.3835329346815716e-05,
+      "loss": 2.3614,
+      "step": 174
+    },
+    {
+      "epoch": 1.1844331641285957,
+      "grad_norm": 3.456766366958618,
+      "learning_rate": 1.3767278936351853e-05,
+      "loss": 2.1906,
+      "step": 175
+    },
+    {
+      "epoch": 1.1912013536379018,
+      "grad_norm": 3.739302635192871,
+      "learning_rate": 1.3699024601196641e-05,
+      "loss": 2.0554,
+      "step": 176
+    },
+    {
+      "epoch": 1.1979695431472082,
+      "grad_norm": 4.194780349731445,
+      "learning_rate": 1.3630570035991352e-05,
+      "loss": 1.8769,
+      "step": 177
+    },
+    {
+      "epoch": 1.2047377326565143,
+      "grad_norm": 5.365659713745117,
+      "learning_rate": 1.3561918946215807e-05,
+      "loss": 1.7156,
+      "step": 178
+    },
+    {
+      "epoch": 1.2115059221658206,
+      "grad_norm": 6.615947723388672,
+      "learning_rate": 1.34930750479878e-05,
+      "loss": 1.6489,
+      "step": 179
+    },
+    {
+      "epoch": 1.218274111675127,
+      "grad_norm": 4.608173847198486,
+      "learning_rate": 1.3424042067861944e-05,
+      "loss": 2.4078,
+      "step": 180
+    },
+    {
+      "epoch": 1.2250423011844331,
+      "grad_norm": 3.3148863315582275,
+      "learning_rate": 1.335482374262795e-05,
+      "loss": 2.2092,
+      "step": 181
+    },
+    {
+      "epoch": 1.2318104906937395,
+      "grad_norm": 4.692728519439697,
+      "learning_rate": 1.3285423819108349e-05,
+      "loss": 1.9361,
+      "step": 182
+    },
+    {
+      "epoch": 1.2385786802030456,
+      "grad_norm": 4.571840763092041,
+      "learning_rate": 1.3215846053955683e-05,
+      "loss": 1.9115,
+      "step": 183
+    },
+    {
+      "epoch": 1.245346869712352,
+      "grad_norm": 5.025711536407471,
+      "learning_rate": 1.3146094213449148e-05,
+      "loss": 1.7432,
+      "step": 184
+    },
+    {
+      "epoch": 1.252115059221658,
+      "grad_norm": 6.1127095222473145,
+      "learning_rate": 1.3076172073290726e-05,
+      "loss": 1.5802,
+      "step": 185
+    },
+    {
+      "epoch": 1.2588832487309645,
+      "grad_norm": 5.005325794219971,
+      "learning_rate": 1.3006083418400799e-05,
+      "loss": 2.2672,
+      "step": 186
+    },
+    {
+      "epoch": 1.2656514382402708,
+      "grad_norm": 3.2444660663604736,
+      "learning_rate": 1.2935832042713288e-05,
+      "loss": 2.2101,
+      "step": 187
+    },
+    {
+      "epoch": 1.272419627749577,
+      "grad_norm": 3.3180994987487793,
+      "learning_rate": 1.2865421748970257e-05,
+      "loss": 2.1237,
+      "step": 188
+    },
+    {
+      "epoch": 1.2791878172588833,
+      "grad_norm": 4.625007629394531,
+      "learning_rate": 1.2794856348516095e-05,
+      "loss": 1.9741,
+      "step": 189
+    },
+    {
+      "epoch": 1.2859560067681894,
+      "grad_norm": 4.619353294372559,
+      "learning_rate": 1.2724139661091188e-05,
+      "loss": 1.9425,
+      "step": 190
+    },
+    {
+      "epoch": 1.2927241962774958,
+      "grad_norm": 5.504361152648926,
+      "learning_rate": 1.2653275514625165e-05,
+      "loss": 1.7012,
+      "step": 191
+    },
+    {
+      "epoch": 1.299492385786802,
+      "grad_norm": 4.399888515472412,
+      "learning_rate": 1.2582267745029685e-05,
+      "loss": 1.9316,
+      "step": 192
+    },
+    {
+      "epoch": 1.3062605752961083,
+      "grad_norm": 3.53360915184021,
+      "learning_rate": 1.2511120195990797e-05,
+      "loss": 2.3907,
+      "step": 193
+    },
+    {
+      "epoch": 1.3130287648054146,
+      "grad_norm": 3.4914515018463135,
+      "learning_rate": 1.2439836718760887e-05,
+      "loss": 2.0797,
+      "step": 194
+    },
+    {
+      "epoch": 1.3197969543147208,
+      "grad_norm": 3.7882394790649414,
+      "learning_rate": 1.2368421171950193e-05,
+      "loss": 1.955,
+      "step": 195
+    },
+    {
+      "epoch": 1.3265651438240271,
+      "grad_norm": 4.370715141296387,
+      "learning_rate": 1.2296877421317958e-05,
+      "loss": 1.8437,
+      "step": 196
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 5.414830207824707,
+      "learning_rate": 1.2225209339563144e-05,
+      "loss": 1.8579,
+      "step": 197
+    },
+    {
+      "epoch": 1.3401015228426396,
+      "grad_norm": 5.272250652313232,
+      "learning_rate": 1.215342080611484e-05,
+      "loss": 1.7614,
+      "step": 198
+    },
+    {
+      "epoch": 1.3468697123519457,
+      "grad_norm": 4.075460910797119,
+      "learning_rate": 1.2081515706922226e-05,
+      "loss": 2.3666,
+      "step": 199
+    },
+    {
+      "epoch": 1.353637901861252,
+      "grad_norm": 2.9030683040618896,
+      "learning_rate": 1.2009497934244257e-05,
+      "loss": 2.0487,
+      "step": 200
+    },
+    {
+      "epoch": 1.3604060913705585,
+      "grad_norm": 4.147029876708984,
+      "learning_rate": 1.1937371386438954e-05,
+      "loss": 1.9878,
+      "step": 201
+    },
+    {
+      "epoch": 1.3671742808798646,
+      "grad_norm": 5.0643439292907715,
+      "learning_rate": 1.186513996775239e-05,
+      "loss": 1.8252,
+      "step": 202
+    },
+    {
+      "epoch": 1.373942470389171,
+      "grad_norm": 5.364940166473389,
+      "learning_rate": 1.1792807588107358e-05,
+      "loss": 1.7401,
+      "step": 203
+    },
+    {
+      "epoch": 1.380710659898477,
+      "grad_norm": 6.356777191162109,
+      "learning_rate": 1.1720378162891709e-05,
+      "loss": 1.5169,
+      "step": 204
+    },
+    {
+      "epoch": 1.3874788494077834,
+      "grad_norm": 3.031667709350586,
+      "learning_rate": 1.1647855612746423e-05,
+      "loss": 2.3757,
+      "step": 205
+    },
+    {
+      "epoch": 1.3942470389170896,
+      "grad_norm": 3.478210926055908,
+      "learning_rate": 1.1575243863353383e-05,
+      "loss": 2.1897,
+      "step": 206
+    },
+    {
+      "epoch": 1.401015228426396,
+      "grad_norm": 3.7287087440490723,
+      "learning_rate": 1.150254684522286e-05,
+      "loss": 2.0368,
+      "step": 207
+    },
+    {
+      "epoch": 1.4077834179357023,
+      "grad_norm": 4.0293779373168945,
+      "learning_rate": 1.142976849348078e-05,
+      "loss": 1.9049,
+      "step": 208
+    },
+    {
+      "epoch": 1.4145516074450084,
+      "grad_norm": 4.953205108642578,
+      "learning_rate": 1.1356912747655687e-05,
+      "loss": 1.7872,
+      "step": 209
+    },
+    {
+      "epoch": 1.4213197969543148,
+      "grad_norm": 6.160380840301514,
+      "learning_rate": 1.1283983551465512e-05,
+      "loss": 1.7295,
+      "step": 210
+    },
+    {
+      "epoch": 1.4280879864636211,
+      "grad_norm": 5.149349212646484,
+      "learning_rate": 1.1210984852604084e-05,
+      "loss": 2.1102,
+      "step": 211
+    },
+    {
+      "epoch": 1.4348561759729273,
+      "grad_norm": 3.172128915786743,
+      "learning_rate": 1.1137920602527448e-05,
+      "loss": 2.2288,
+      "step": 212
+    },
+    {
+      "epoch": 1.4416243654822334,
+      "grad_norm": 3.4528701305389404,
+      "learning_rate": 1.1064794756239978e-05,
+      "loss": 2.0189,
+      "step": 213
+    },
+    {
+      "epoch": 1.4483925549915397,
+      "grad_norm": 4.66202449798584,
+      "learning_rate": 1.099161127208027e-05,
+      "loss": 1.8742,
+      "step": 214
+    },
+    {
+      "epoch": 1.455160744500846,
+      "grad_norm": 5.142988681793213,
+      "learning_rate": 1.0918374111506893e-05,
+      "loss": 1.9004,
+      "step": 215
+    },
+    {
+      "epoch": 1.4619289340101522,
+      "grad_norm": 5.548466205596924,
+      "learning_rate": 1.0845087238883945e-05,
+      "loss": 1.5929,
+      "step": 216
+    },
+    {
+      "epoch": 1.4686971235194586,
+      "grad_norm": 4.51755428314209,
+      "learning_rate": 1.0771754621266466e-05,
+      "loss": 1.9563,
+      "step": 217
+    },
+    {
+      "epoch": 1.475465313028765,
+      "grad_norm": 3.1326138973236084,
+      "learning_rate": 1.0698380228185685e-05,
+      "loss": 2.2197,
+      "step": 218
+    },
+    {
+      "epoch": 1.482233502538071,
+      "grad_norm": 3.594095468521118,
+      "learning_rate": 1.0624968031434174e-05,
+      "loss": 2.0466,
+      "step": 219
+    },
+    {
+      "epoch": 1.4890016920473772,
+      "grad_norm": 3.841886281967163,
+      "learning_rate": 1.0551522004850821e-05,
+      "loss": 1.9612,
+      "step": 220
+    },
+    {
+      "epoch": 1.4957698815566836,
+      "grad_norm": 4.422885417938232,
+      "learning_rate": 1.0478046124105746e-05,
+      "loss": 1.8449,
+      "step": 221
+    },
+    {
+      "epoch": 1.50253807106599,
+      "grad_norm": 5.432779788970947,
+      "learning_rate": 1.0404544366485094e-05,
+      "loss": 1.7364,
+      "step": 222
+    },
+    {
+      "epoch": 1.509306260575296,
+      "grad_norm": 5.873152256011963,
+      "learning_rate": 1.033102071067573e-05,
+      "loss": 1.6825,
+      "step": 223
+    },
+    {
+      "epoch": 1.5160744500846024,
+      "grad_norm": 3.36773943901062,
+      "learning_rate": 1.0257479136549889e-05,
+      "loss": 2.3463,
+      "step": 224
+    },
+    {
+      "epoch": 1.5228426395939088,
+      "grad_norm": 3.3323042392730713,
+      "learning_rate": 1.0183923624949721e-05,
+      "loss": 2.0683,
+      "step": 225
+    },
+    {
+      "epoch": 1.5296108291032149,
+      "grad_norm": 3.8202672004699707,
+      "learning_rate": 1.0110358157471825e-05,
+      "loss": 1.9565,
+      "step": 226
+    },
+    {
+      "epoch": 1.536379018612521,
+      "grad_norm": 4.67080545425415,
+      "learning_rate": 1.0036786716251721e-05,
+      "loss": 1.8865,
+      "step": 227
+    },
+    {
+      "epoch": 1.5431472081218274,
+      "grad_norm": 5.312952995300293,
+      "learning_rate": 9.963213283748282e-06,
+      "loss": 1.7068,
+      "step": 228
+    },
+    {
+      "epoch": 1.5499153976311337,
+      "grad_norm": 6.728119850158691,
+      "learning_rate": 9.889641842528179e-06,
+      "loss": 1.6627,
+      "step": 229
+    },
+    {
+      "epoch": 1.5566835871404399,
+      "grad_norm": 2.4371559619903564,
+      "learning_rate": 9.816076375050284e-06,
+      "loss": 2.3459,
+      "step": 230
+    },
+    {
+      "epoch": 1.5634517766497462,
+      "grad_norm": 2.8036484718322754,
+      "learning_rate": 9.742520863450116e-06,
+      "loss": 2.1804,
+      "step": 231
+    },
+    {
+      "epoch": 1.5702199661590526,
+      "grad_norm": 3.5675642490386963,
+      "learning_rate": 9.668979289324274e-06,
+      "loss": 2.0749,
+      "step": 232
+    },
+    {
+      "epoch": 1.5769881556683587,
+      "grad_norm": 4.099052906036377,
+      "learning_rate": 9.595455633514908e-06,
+      "loss": 1.8576,
+      "step": 233
+    },
+    {
+      "epoch": 1.5837563451776648,
+      "grad_norm": 4.900853633880615,
+      "learning_rate": 9.521953875894256e-06,
+      "loss": 1.7174,
+      "step": 234
+    },
+    {
+      "epoch": 1.5905245346869712,
+      "grad_norm": 5.890774726867676,
+      "learning_rate": 9.448477995149182e-06,
+      "loss": 1.4906,
+      "step": 235
+    },
+    {
+      "epoch": 1.5972927241962775,
+      "grad_norm": 4.369800567626953,
+      "learning_rate": 9.37503196856583e-06,
+      "loss": 2.0832,
+      "step": 236
+    },
+    {
+      "epoch": 1.6040609137055837,
+      "grad_norm": 3.1959829330444336,
+      "learning_rate": 9.301619771814317e-06,
+      "loss": 2.2265,
+      "step": 237
+    },
+    {
+      "epoch": 1.61082910321489,
+      "grad_norm": 3.255842924118042,
+      "learning_rate": 9.228245378733537e-06,
+      "loss": 2.0659,
+      "step": 238
+    },
+    {
+      "epoch": 1.6175972927241964,
+      "grad_norm": 3.865798234939575,
+      "learning_rate": 9.154912761116056e-06,
+      "loss": 1.9102,
+      "step": 239
+    },
+    {
+      "epoch": 1.6243654822335025,
+      "grad_norm": 4.725029945373535,
+      "learning_rate": 9.081625888493107e-06,
+      "loss": 1.7442,
+      "step": 240
+    },
+    {
+      "epoch": 1.6311336717428087,
+      "grad_norm": 8.740133285522461,
+      "learning_rate": 9.00838872791973e-06,
+      "loss": 1.6959,
+      "step": 241
+    },
+    {
+      "epoch": 1.637901861252115,
+      "grad_norm": 4.786500930786133,
+      "learning_rate": 8.935205243760022e-06,
+      "loss": 1.8628,
+      "step": 242
+    },
+    {
+      "epoch": 1.6446700507614214,
+      "grad_norm": 3.0056700706481934,
+      "learning_rate": 8.862079397472552e-06,
+      "loss": 2.2218,
+      "step": 243
+    },
+    {
+      "epoch": 1.6514382402707275,
+      "grad_norm": 3.35292911529541,
+      "learning_rate": 8.78901514739592e-06,
+      "loss": 2.0775,
+      "step": 244
+    },
+    {
+      "epoch": 1.6582064297800339,
+      "grad_norm": 3.997661590576172,
+      "learning_rate": 8.71601644853449e-06,
+      "loss": 1.9842,
+      "step": 245
+    },
+    {
+      "epoch": 1.6649746192893402,
+      "grad_norm": 4.569092273712158,
+      "learning_rate": 8.643087252344313e-06,
+      "loss": 1.8055,
+      "step": 246
+    },
+    {
+      "epoch": 1.6717428087986463,
+      "grad_norm": 5.217006683349609,
+      "learning_rate": 8.57023150651922e-06,
+      "loss": 1.5681,
+      "step": 247
+    },
+    {
+      "epoch": 1.6785109983079525,
+      "grad_norm": 5.526303291320801,
+      "learning_rate": 8.49745315477714e-06,
+      "loss": 1.7118,
+      "step": 248
+    },
+    {
+      "epoch": 1.6852791878172588,
+      "grad_norm": 2.5200791358947754,
+      "learning_rate": 8.424756136646624e-06,
+      "loss": 2.2932,
+      "step": 249
+    },
+    {
+      "epoch": 1.6920473773265652,
+      "grad_norm": 3.4209508895874023,
+      "learning_rate": 8.352144387253582e-06,
+      "loss": 2.0515,
+      "step": 250
+    },
+    {
+      "epoch": 1.6988155668358713,
+      "grad_norm": 3.7960565090179443,
+      "learning_rate": 8.279621837108295e-06,
+      "loss": 1.9207,
+      "step": 251
+    },
+    {
+      "epoch": 1.7055837563451777,
+      "grad_norm": 4.094236373901367,
+      "learning_rate": 8.207192411892645e-06,
+      "loss": 1.7885,
+      "step": 252
+    },
+    {
+      "epoch": 1.712351945854484,
+      "grad_norm": 4.837678909301758,
+      "learning_rate": 8.134860032247613e-06,
+      "loss": 1.6723,
+      "step": 253
+    },
+    {
+      "epoch": 1.7191201353637902,
+      "grad_norm": 6.248587608337402,
+      "learning_rate": 8.062628613561051e-06,
+      "loss": 1.4528,
+      "step": 254
+    },
+    {
+      "epoch": 1.7258883248730963,
+      "grad_norm": 2.59256911277771,
+      "learning_rate": 7.990502065755748e-06,
+      "loss": 2.3992,
+      "step": 255
+    },
+    {
+      "epoch": 1.7326565143824029,
+      "grad_norm": 2.9640893936157227,
+      "learning_rate": 7.918484293077777e-06,
+      "loss": 2.1847,
+      "step": 256
+    },
+    {
+      "epoch": 1.739424703891709,
+      "grad_norm": 3.4181110858917236,
+      "learning_rate": 7.846579193885165e-06,
+      "loss": 2.0231,
+      "step": 257
+    },
+    {
+      "epoch": 1.7461928934010151,
+      "grad_norm": 4.158235549926758,
+      "learning_rate": 7.774790660436857e-06,
+      "loss": 1.9362,
+      "step": 258
+    },
+    {
+      "epoch": 1.7529610829103215,
+      "grad_norm": 4.829765796661377,
+      "learning_rate": 7.703122578682047e-06,
+      "loss": 1.7278,
+      "step": 259
+    },
+    {
+      "epoch": 1.7597292724196278,
+      "grad_norm": 5.691404819488525,
+      "learning_rate": 7.631578828049809e-06,
+      "loss": 1.6055,
+      "step": 260
+    },
+    {
+      "epoch": 1.766497461928934,
+      "grad_norm": 3.2796614170074463,
+      "learning_rate": 7.560163281239116e-06,
+      "loss": 2.0519,
+      "step": 261
+    },
+    {
+      "epoch": 1.77326565143824,
+      "grad_norm": 2.57660174369812,
+      "learning_rate": 7.488879804009206e-06,
+      "loss": 2.1934,
+      "step": 262
+    },
+    {
+      "epoch": 1.7800338409475467,
+      "grad_norm": 3.3291141986846924,
+      "learning_rate": 7.4177322549703165e-06,
+      "loss": 2.0575,
+      "step": 263
+    },
+    {
+      "epoch": 1.7868020304568528,
+      "grad_norm": 3.7897515296936035,
+      "learning_rate": 7.346724485374837e-06,
+      "loss": 1.7963,
+      "step": 264
+    },
+    {
+      "epoch": 1.793570219966159,
+      "grad_norm": 4.585766315460205,
+      "learning_rate": 7.275860338908815e-06,
+      "loss": 1.765,
+      "step": 265
+    },
+    {
+      "epoch": 1.8003384094754653,
+      "grad_norm": 5.705550670623779,
+      "learning_rate": 7.2051436514839064e-06,
+      "loss": 1.6657,
+      "step": 266
+    },
+    {
+      "epoch": 1.8071065989847717,
+      "grad_norm": 4.510739326477051,
+      "learning_rate": 7.134578251029745e-06,
+      "loss": 1.8443,
+      "step": 267
+    },
+    {
+      "epoch": 1.8138747884940778,
+      "grad_norm": 3.171539068222046,
+      "learning_rate": 7.064167957286714e-06,
+      "loss": 2.3002,
+      "step": 268
+    },
+    {
+      "epoch": 1.8206429780033841,
+      "grad_norm": 3.5727908611297607,
+      "learning_rate": 6.993916581599203e-06,
+      "loss": 2.0323,
+      "step": 269
+    },
+    {
+      "epoch": 1.8274111675126905,
+      "grad_norm": 3.5468742847442627,
+      "learning_rate": 6.923827926709277e-06,
+      "loss": 1.9025,
+      "step": 270
+    },
+    {
+      "epoch": 1.8341793570219966,
+      "grad_norm": 4.465723037719727,
+      "learning_rate": 6.853905786550855e-06,
+      "loss": 1.8105,
+      "step": 271
+    },
+    {
+      "epoch": 1.8409475465313028,
+      "grad_norm": 5.095712184906006,
+      "learning_rate": 6.784153946044321e-06,
+      "loss": 1.6591,
+      "step": 272
+    },
+    {
+      "epoch": 1.8477157360406091,
+      "grad_norm": 5.340912818908691,
+      "learning_rate": 6.714576180891653e-06,
+      "loss": 1.6851,
+      "step": 273
+    },
+    {
+      "epoch": 1.8544839255499155,
+      "grad_norm": 3.092374801635742,
+      "learning_rate": 6.645176257372054e-06,
+      "loss": 2.3331,
+      "step": 274
+    },
+    {
+      "epoch": 1.8612521150592216,
+      "grad_norm": 2.924107551574707,
+      "learning_rate": 6.5759579321380576e-06,
+      "loss": 2.1575,
+      "step": 275
+    },
+    {
+      "epoch": 1.868020304568528,
+      "grad_norm": 3.7559361457824707,
+      "learning_rate": 6.5069249520122026e-06,
+      "loss": 1.9893,
+      "step": 276
+    },
+    {
+      "epoch": 1.8747884940778343,
+      "grad_norm": 4.786612510681152,
+      "learning_rate": 6.438081053784197e-06,
+      "loss": 1.7583,
+      "step": 277
+    },
+    {
+      "epoch": 1.8815566835871405,
+      "grad_norm": 5.209157466888428,
+      "learning_rate": 6.36942996400865e-06,
+      "loss": 1.7118,
+      "step": 278
+    },
+    {
+      "epoch": 1.8883248730964466,
+      "grad_norm": 6.413548469543457,
+      "learning_rate": 6.300975398803362e-06,
+      "loss": 1.5219,
+      "step": 279
+    },
+    {
+      "epoch": 1.895093062605753,
+      "grad_norm": 2.4699904918670654,
+      "learning_rate": 6.232721063648148e-06,
+      "loss": 2.3592,
+      "step": 280
+    },
+    {
+      "epoch": 1.9018612521150593,
+      "grad_norm": 2.732497453689575,
+      "learning_rate": 6.1646706531842845e-06,
+      "loss": 2.0984,
+      "step": 281
+    },
+    {
+      "epoch": 1.9086294416243654,
+      "grad_norm": 3.4677207469940186,
+      "learning_rate": 6.09682785101449e-06,
+      "loss": 1.9303,
+      "step": 282
+    },
+    {
+      "epoch": 1.9153976311336718,
+      "grad_norm": 3.888166666030884,
+      "learning_rate": 6.029196329503548e-06,
+      "loss": 1.8503,
+      "step": 283
+    },
+    {
+      "epoch": 1.9221658206429781,
+      "grad_norm": 4.850317001342773,
+      "learning_rate": 5.961779749579516e-06,
+      "loss": 1.711,
+      "step": 284
+    },
+    {
+      "epoch": 1.9289340101522843,
+      "grad_norm": 5.663942813873291,
+      "learning_rate": 5.8945817605355495e-06,
+      "loss": 1.5138,
+      "step": 285
+    },
+    {
+      "epoch": 1.9357021996615904,
+      "grad_norm": 3.6366028785705566,
+      "learning_rate": 5.827605999832375e-06,
+      "loss": 2.0733,
+      "step": 286
+    },
+    {
+      "epoch": 1.9424703891708968,
+      "grad_norm": 2.522986650466919,
+      "learning_rate": 5.760856092901394e-06,
+      "loss": 2.2134,
+      "step": 287
+    },
+    {
+      "epoch": 1.9492385786802031,
+      "grad_norm": 3.196727991104126,
+      "learning_rate": 5.694335652948415e-06,
+      "loss": 2.0477,
+      "step": 288
+    },
+    {
+      "epoch": 1.9560067681895092,
+      "grad_norm": 3.9079673290252686,
+      "learning_rate": 5.628048280758096e-06,
+      "loss": 1.963,
+      "step": 289
+    },
+    {
+      "epoch": 1.9627749576988156,
+      "grad_norm": 4.57443380355835,
+      "learning_rate": 5.561997564499024e-06,
+      "loss": 1.7234,
+      "step": 290
+    },
+    {
+      "epoch": 1.969543147208122,
+      "grad_norm": 5.271142482757568,
+      "learning_rate": 5.4961870795294644e-06,
+      "loss": 1.6151,
+      "step": 291
+    },
+    {
+      "epoch": 1.976311336717428,
+      "grad_norm": 4.357114315032959,
+      "learning_rate": 5.430620388203866e-06,
+      "loss": 1.9279,
+      "step": 292
+    },
+    {
+      "epoch": 1.9830795262267342,
+      "grad_norm": 2.8121213912963867,
+      "learning_rate": 5.365301039679985e-06,
+      "loss": 2.1234,
+      "step": 293
+    },
+    {
+      "epoch": 1.9898477157360406,
+      "grad_norm": 4.057702541351318,
+      "learning_rate": 5.300232569726805e-06,
+      "loss": 1.9386,
+      "step": 294
+    },
+    {
+      "epoch": 1.996615905245347,
+      "grad_norm": 5.310722351074219,
+      "learning_rate": 5.2354185005331095e-06,
+      "loss": 1.6403,
+      "step": 295
+    },
+    {
+      "epoch": 2.003384094754653,
+      "grad_norm": 3.646991729736328,
+      "learning_rate": 5.170862340516858e-06,
+      "loss": 1.9625,
+      "step": 296
+    },
+    {
+      "epoch": 2.010152284263959,
+      "grad_norm": 3.910515069961548,
+      "learning_rate": 5.106567584135251e-06,
+      "loss": 1.6498,
+      "step": 297
+    },
+    {
+      "epoch": 2.0169204737732658,
+      "grad_norm": 5.364322662353516,
+      "learning_rate": 5.042537711695584e-06,
+      "loss": 1.4023,
+      "step": 298
+    },
+    {
+      "epoch": 2.023688663282572,
+      "grad_norm": 6.2862396240234375,
+      "learning_rate": 4.97877618916684e-06,
+      "loss": 1.0733,
+      "step": 299
+    },
+    {
+      "epoch": 2.030456852791878,
+      "grad_norm": 7.049383163452148,
+      "learning_rate": 4.915286467992098e-06,
+      "loss": 0.9028,
+      "step": 300
+    },
+    {
+      "epoch": 2.0372250423011846,
+      "grad_norm": 6.528897762298584,
+      "learning_rate": 4.852071984901696e-06,
+      "loss": 0.6975,
+      "step": 301
+    },
+    {
+      "epoch": 2.0439932318104908,
+      "grad_norm": 4.566006660461426,
+      "learning_rate": 4.789136161727184e-06,
+      "loss": 0.996,
+      "step": 302
+    },
+    {
+      "epoch": 2.050761421319797,
+      "grad_norm": 4.8525590896606445,
+      "learning_rate": 4.7264824052161255e-06,
+      "loss": 1.9084,
+      "step": 303
+    },
+    {
+      "epoch": 2.057529610829103,
+      "grad_norm": 8.884151458740234,
+      "learning_rate": 4.664114106847667e-06,
+      "loss": 1.2406,
+      "step": 304
+    },
+    {
+      "epoch": 2.0642978003384096,
+      "grad_norm": 9.265266418457031,
+      "learning_rate": 4.602034642648968e-06,
+      "loss": 0.974,
+      "step": 305
+    },
+    {
+      "epoch": 2.0710659898477157,
+      "grad_norm": 8.75934886932373,
+      "learning_rate": 4.5402473730124395e-06,
+      "loss": 0.8314,
+      "step": 306
+    },
+    {
+      "epoch": 2.077834179357022,
+      "grad_norm": 7.045146942138672,
+      "learning_rate": 4.478755642513868e-06,
+      "loss": 0.7014,
+      "step": 307
+    },
+    {
+      "epoch": 2.0846023688663284,
+      "grad_norm": 5.934751033782959,
+      "learning_rate": 4.417562779731355e-06,
+      "loss": 0.5536,
+      "step": 308
+    },
+    {
+      "epoch": 2.0913705583756346,
+      "grad_norm": 4.2714314460754395,
+      "learning_rate": 4.356672097065134e-06,
+      "loss": 1.954,
+      "step": 309
+    },
+    {
+      "epoch": 2.0981387478849407,
+      "grad_norm": 3.837898015975952,
+      "learning_rate": 4.2960868905582895e-06,
+      "loss": 1.4183,
+      "step": 310
+    },
+    {
+      "epoch": 2.104906937394247,
+      "grad_norm": 4.858175277709961,
+      "learning_rate": 4.235810439718327e-06,
+      "loss": 1.0733,
+      "step": 311
+    },
+    {
+      "epoch": 2.1116751269035534,
+      "grad_norm": 5.005491256713867,
+      "learning_rate": 4.175846007339644e-06,
+      "loss": 0.851,
+      "step": 312
+    },
+    {
+      "epoch": 2.1184433164128595,
+      "grad_norm": 5.400625228881836,
+      "learning_rate": 4.1161968393269324e-06,
+      "loss": 0.7486,
+      "step": 313
+    },
+    {
+      "epoch": 2.1252115059221657,
+      "grad_norm": 5.8098602294921875,
+      "learning_rate": 4.0568661645194656e-06,
+      "loss": 0.5741,
+      "step": 314
+    },
+    {
+      "epoch": 2.1319796954314723,
+      "grad_norm": 3.7481307983398438,
+      "learning_rate": 3.997857194516319e-06,
+      "loss": 1.7741,
+      "step": 315
+    },
+    {
+      "epoch": 2.1387478849407784,
+      "grad_norm": 3.240912675857544,
+      "learning_rate": 3.939173123502523e-06,
+      "loss": 1.5778,
+      "step": 316
+    },
+    {
+      "epoch": 2.1455160744500845,
+      "grad_norm": 4.222574710845947,
+      "learning_rate": 3.8808171280761665e-06,
+      "loss": 1.0852,
+      "step": 317
+    },
+    {
+      "epoch": 2.152284263959391,
+      "grad_norm": 4.52738618850708,
+      "learning_rate": 3.822792367076446e-06,
+      "loss": 0.9088,
+      "step": 318
+    },
+    {
+      "epoch": 2.1590524534686972,
+      "grad_norm": 5.184245586395264,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 0.7274,
+      "step": 319
+    },
+    {
+      "epoch": 2.1658206429780034,
+      "grad_norm": 6.21406364440918,
+      "learning_rate": 3.7077490938942307e-06,
+      "loss": 0.6568,
+      "step": 320
+    },
+    {
+      "epoch": 2.1725888324873095,
+      "grad_norm": 4.0037126541137695,
+      "learning_rate": 3.6507368090616014e-06,
+      "loss": 1.3107,
+      "step": 321
+    },
+    {
+      "epoch": 2.179357021996616,
+      "grad_norm": 3.928704023361206,
+      "learning_rate": 3.594068213018249e-06,
+      "loss": 1.6134,
+      "step": 322
+    },
+    {
+      "epoch": 2.186125211505922,
+      "grad_norm": 4.245754718780518,
+      "learning_rate": 3.53774637326359e-06,
+      "loss": 1.1365,
+      "step": 323
+    },
+    {
+      "epoch": 2.1928934010152283,
+      "grad_norm": 4.95959997177124,
+      "learning_rate": 3.481774338526954e-06,
+      "loss": 0.9044,
+      "step": 324
+    },
+    {
+      "epoch": 2.199661590524535,
+      "grad_norm": 5.446150779724121,
+      "learning_rate": 3.426155138602558e-06,
+      "loss": 0.7641,
+      "step": 325
+    },
+    {
+      "epoch": 2.206429780033841,
+      "grad_norm": 6.039018630981445,
+      "learning_rate": 3.3708917841854782e-06,
+      "loss": 0.6246,
+      "step": 326
+    },
+    {
+      "epoch": 2.213197969543147,
+      "grad_norm": 5.4581427574157715,
+      "learning_rate": 3.3159872667087077e-06,
+      "loss": 0.9867,
+      "step": 327
+    },
+    {
+      "epoch": 2.2199661590524533,
+      "grad_norm": 3.5558555126190186,
+      "learning_rate": 3.2614445581812183e-06,
+      "loss": 1.8462,
+      "step": 328
+    },
+    {
+      "epoch": 2.22673434856176,
+      "grad_norm": 3.6573843955993652,
+      "learning_rate": 3.207266611027069e-06,
+      "loss": 1.2127,
+      "step": 329
+    },
+    {
+      "epoch": 2.233502538071066,
+      "grad_norm": 4.450440406799316,
+      "learning_rate": 3.1534563579256172e-06,
+      "loss": 0.8708,
+      "step": 330
+    },
+    {
+      "epoch": 2.240270727580372,
+      "grad_norm": 4.951565742492676,
+      "learning_rate": 3.1000167116527525e-06,
+      "loss": 0.7292,
+      "step": 331
+    },
+    {
+      "epoch": 2.2470389170896787,
+      "grad_norm": 5.573976516723633,
+      "learning_rate": 3.0469505649232333e-06,
+      "loss": 0.6443,
+      "step": 332
+    },
+    {
+      "epoch": 2.253807106598985,
+      "grad_norm": 5.918398857116699,
+      "learning_rate": 2.9942607902340946e-06,
+      "loss": 0.5702,
+      "step": 333
+    },
+    {
+      "epoch": 2.260575296108291,
+      "grad_norm": 3.47131085395813,
+      "learning_rate": 2.9419502397091715e-06,
+      "loss": 1.9211,
+      "step": 334
+    },
+    {
+      "epoch": 2.267343485617597,
+      "grad_norm": 3.5219008922576904,
+      "learning_rate": 2.8900217449447077e-06,
+      "loss": 1.3083,
+      "step": 335
+    },
+    {
+      "epoch": 2.2741116751269037,
+      "grad_norm": 4.355684280395508,
+      "learning_rate": 2.8384781168560693e-06,
+      "loss": 0.9792,
+      "step": 336
+    },
+    {
+      "epoch": 2.28087986463621,
+      "grad_norm": 4.637706756591797,
+      "learning_rate": 2.7873221455256006e-06,
+      "loss": 0.8071,
+      "step": 337
+    },
+    {
+      "epoch": 2.287648054145516,
+      "grad_norm": 5.174313068389893,
+      "learning_rate": 2.736556600051593e-06,
+      "loss": 0.658,
+      "step": 338
+    },
+    {
+      "epoch": 2.2944162436548226,
+      "grad_norm": 5.701674461364746,
+      "learning_rate": 2.6861842283983953e-06,
+      "loss": 0.5716,
+      "step": 339
+    },
+    {
+      "epoch": 2.3011844331641287,
+      "grad_norm": 3.603616714477539,
+      "learning_rate": 2.6362077572476495e-06,
+      "loss": 1.6573,
+      "step": 340
+    },
+    {
+      "epoch": 2.307952622673435,
+      "grad_norm": 3.46175217628479,
+      "learning_rate": 2.586629891850716e-06,
+      "loss": 1.5,
+      "step": 341
+    },
+    {
+      "epoch": 2.314720812182741,
+      "grad_norm": 4.137648105621338,
+      "learning_rate": 2.5374533158822225e-06,
+      "loss": 1.2069,
+      "step": 342
+    },
+    {
+      "epoch": 2.3214890016920475,
+      "grad_norm": 4.514110565185547,
+      "learning_rate": 2.4886806912948034e-06,
+      "loss": 0.8226,
+      "step": 343
+    },
+    {
+      "epoch": 2.3282571912013537,
+      "grad_norm": 5.722095012664795,
+      "learning_rate": 2.4403146581749925e-06,
+      "loss": 0.7436,
+      "step": 344
+    },
+    {
+      "epoch": 2.33502538071066,
+      "grad_norm": 5.680308818817139,
+      "learning_rate": 2.392357834600336e-06,
+      "loss": 0.583,
+      "step": 345
+    },
+    {
+      "epoch": 2.3417935702199664,
+      "grad_norm": 4.119960784912109,
+      "learning_rate": 2.3448128164976593e-06,
+      "loss": 1.2645,
+      "step": 346
+    },
+    {
+      "epoch": 2.3485617597292725,
+      "grad_norm": 3.0717074871063232,
+      "learning_rate": 2.297682177502546e-06,
+      "loss": 1.538,
+      "step": 347
+    },
+    {
+      "epoch": 2.3553299492385786,
+      "grad_norm": 4.0398335456848145,
+      "learning_rate": 2.2509684688200385e-06,
+      "loss": 1.0585,
+      "step": 348
+    },
+    {
+      "epoch": 2.3620981387478848,
+      "grad_norm": 4.792836666107178,
+      "learning_rate": 2.204674219086531e-06,
+      "loss": 0.8199,
+      "step": 349
+    },
+    {
+      "epoch": 2.3688663282571913,
+      "grad_norm": 5.0710883140563965,
+      "learning_rate": 2.158801934232897e-06,
+      "loss": 0.6387,
+      "step": 350
+    },
+    {
+      "epoch": 2.3756345177664975,
+      "grad_norm": 5.128052234649658,
+      "learning_rate": 2.113354097348834e-06,
+      "loss": 0.5425,
+      "step": 351
+    },
+    {
+      "epoch": 2.3824027072758036,
+      "grad_norm": 4.384050369262695,
+      "learning_rate": 2.0683331685484655e-06,
+      "loss": 0.9253,
+      "step": 352
+    },
+    {
+      "epoch": 2.38917089678511,
+      "grad_norm": 3.5379750728607178,
+      "learning_rate": 2.0237415848371666e-06,
+      "loss": 1.9209,
+      "step": 353
+    },
+    {
+      "epoch": 2.3959390862944163,
+      "grad_norm": 3.754819631576538,
+      "learning_rate": 1.979581759979642e-06,
+      "loss": 1.2382,
+      "step": 354
+    },
+    {
+      "epoch": 2.4027072758037225,
+      "grad_norm": 4.621876239776611,
+      "learning_rate": 1.9358560843692787e-06,
+      "loss": 0.9402,
+      "step": 355
+    },
+    {
+      "epoch": 2.4094754653130286,
+      "grad_norm": 5.234630584716797,
+      "learning_rate": 1.892566924898751e-06,
+      "loss": 0.7772,
+      "step": 356
+    },
+    {
+      "epoch": 2.416243654822335,
+      "grad_norm": 6.046688079833984,
+      "learning_rate": 1.8497166248318876e-06,
+      "loss": 0.6619,
+      "step": 357
+    },
+    {
+      "epoch": 2.4230118443316413,
+      "grad_norm": 5.794624328613281,
+      "learning_rate": 1.807307503676846e-06,
+      "loss": 0.5626,
+      "step": 358
+    },
+    {
+      "epoch": 2.4297800338409474,
+      "grad_norm": 3.271219253540039,
+      "learning_rate": 1.7653418570605474e-06,
+      "loss": 1.8406,
+      "step": 359
+    },
+    {
+      "epoch": 2.436548223350254,
+      "grad_norm": 3.5998053550720215,
+      "learning_rate": 1.7238219566044145e-06,
+      "loss": 1.3465,
+      "step": 360
+    },
+    {
+      "epoch": 2.44331641285956,
+      "grad_norm": 4.231540679931641,
+      "learning_rate": 1.6827500498014026e-06,
+      "loss": 1.0409,
+      "step": 361
+    },
+    {
+      "epoch": 2.4500846023688663,
+      "grad_norm": 4.704120635986328,
+      "learning_rate": 1.6421283598943526e-06,
+      "loss": 0.7836,
+      "step": 362
+    },
+    {
+      "epoch": 2.4568527918781724,
+      "grad_norm": 5.459336757659912,
+      "learning_rate": 1.601959085755641e-06,
+      "loss": 0.6894,
+      "step": 363
+    },
+    {
+      "epoch": 2.463620981387479,
+      "grad_norm": 5.819806098937988,
+      "learning_rate": 1.5622444017681438e-06,
+      "loss": 0.5779,
+      "step": 364
+    },
+    {
+      "epoch": 2.470389170896785,
+      "grad_norm": 3.3774378299713135,
+      "learning_rate": 1.5229864577075548e-06,
+      "loss": 1.6054,
+      "step": 365
+    },
+    {
+      "epoch": 2.4771573604060912,
+      "grad_norm": 3.6015894412994385,
+      "learning_rate": 1.4841873786260019e-06,
+      "loss": 1.4402,
+      "step": 366
+    },
+    {
+      "epoch": 2.483925549915398,
+      "grad_norm": 4.313451766967773,
+      "learning_rate": 1.445849264737026e-06,
+      "loss": 0.9478,
+      "step": 367
+    },
+    {
+      "epoch": 2.490693739424704,
+      "grad_norm": 5.062134265899658,
+      "learning_rate": 1.4079741913018863e-06,
+      "loss": 0.8397,
+      "step": 368
+    },
+    {
+      "epoch": 2.49746192893401,
+      "grad_norm": 5.357868194580078,
+      "learning_rate": 1.3705642085172367e-06,
+      "loss": 0.5926,
+      "step": 369
+    },
+    {
+      "epoch": 2.504230118443316,
+      "grad_norm": 5.440720558166504,
+      "learning_rate": 1.3336213414041387e-06,
+      "loss": 0.5514,
+      "step": 370
+    },
+    {
+      "epoch": 2.510998307952623,
+      "grad_norm": 3.912086248397827,
+      "learning_rate": 1.2971475896984475e-06,
+      "loss": 1.3175,
+      "step": 371
+    },
+    {
+      "epoch": 2.517766497461929,
+      "grad_norm": 3.4451215267181396,
+      "learning_rate": 1.2611449277425715e-06,
+      "loss": 1.7101,
+      "step": 372
+    },
+    {
+      "epoch": 2.524534686971235,
+      "grad_norm": 3.9773149490356445,
+      "learning_rate": 1.2256153043785911e-06,
+      "loss": 1.0656,
+      "step": 373
+    },
+    {
+      "epoch": 2.5313028764805416,
+      "grad_norm": 4.944250106811523,
+      "learning_rate": 1.1905606428427775e-06,
+      "loss": 0.88,
+      "step": 374
+    },
+    {
+      "epoch": 2.5380710659898478,
+      "grad_norm": 5.475653171539307,
+      "learning_rate": 1.1559828406614716e-06,
+      "loss": 0.6841,
+      "step": 375
+    },
+    {
+      "epoch": 2.544839255499154,
+      "grad_norm": 6.01757287979126,
+      "learning_rate": 1.1218837695483853e-06,
+      "loss": 0.5779,
+      "step": 376
+    },
+    {
+      "epoch": 2.55160744500846,
+      "grad_norm": 4.852456569671631,
+      "learning_rate": 1.0882652753032797e-06,
+      "loss": 0.9251,
+      "step": 377
+    },
+    {
+      "epoch": 2.5583756345177666,
+      "grad_norm": 3.3849077224731445,
+      "learning_rate": 1.0551291777120465e-06,
+      "loss": 1.936,
+      "step": 378
+    },
+    {
+      "epoch": 2.5651438240270727,
+      "grad_norm": 3.5754101276397705,
+      "learning_rate": 1.0224772704482033e-06,
+      "loss": 1.2097,
+      "step": 379
+    },
+    {
+      "epoch": 2.571912013536379,
+      "grad_norm": 4.511597633361816,
+      "learning_rate": 9.903113209758098e-07,
+      "loss": 0.999,
+      "step": 380
+    },
+    {
+      "epoch": 2.5786802030456855,
+      "grad_norm": 4.68709659576416,
+      "learning_rate": 9.58633070453785e-07,
+      "loss": 0.7136,
+      "step": 381
+    },
+    {
+      "epoch": 2.5854483925549916,
+      "grad_norm": 6.031564712524414,
+      "learning_rate": 9.274442336416567e-07,
+      "loss": 0.6703,
+      "step": 382
+    },
+    {
+      "epoch": 2.5922165820642977,
+      "grad_norm": 5.676982402801514,
+      "learning_rate": 8.967464988067476e-07,
+      "loss": 0.5741,
+      "step": 383
+    },
+    {
+      "epoch": 2.598984771573604,
+      "grad_norm": 3.2455053329467773,
+      "learning_rate": 8.665415276327871e-07,
+      "loss": 2.0339,
+      "step": 384
+    },
+    {
+      "epoch": 2.6057529610829104,
+      "grad_norm": 3.556863784790039,
+      "learning_rate": 8.368309551299536e-07,
+      "loss": 1.325,
+      "step": 385
+    },
+    {
+      "epoch": 2.6125211505922166,
+      "grad_norm": 4.362199306488037,
+      "learning_rate": 8.076163895463862e-07,
+      "loss": 1.0078,
+      "step": 386
+    },
+    {
+      "epoch": 2.6192893401015227,
+      "grad_norm": 4.831475257873535,
+      "learning_rate": 7.788994122811178e-07,
+      "loss": 0.8614,
+      "step": 387
+    },
+    {
+      "epoch": 2.6260575296108293,
+      "grad_norm": 5.154886245727539,
+      "learning_rate": 7.506815777984788e-07,
+      "loss": 0.5961,
+      "step": 388
+    },
+    {
+      "epoch": 2.6328257191201354,
+      "grad_norm": 5.211191654205322,
+      "learning_rate": 7.229644135439473e-07,
+      "loss": 0.5393,
+      "step": 389
+    },
+    {
+      "epoch": 2.6395939086294415,
+      "grad_norm": 3.482469081878662,
+      "learning_rate": 6.957494198614778e-07,
+      "loss": 1.725,
+      "step": 390
+    },
+    {
+      "epoch": 2.6463620981387477,
+      "grad_norm": 3.1785717010498047,
+      "learning_rate": 6.690380699122767e-07,
+      "loss": 1.58,
+      "step": 391
+    },
+    {
+      "epoch": 2.6531302876480543,
+      "grad_norm": 3.89457368850708,
+      "learning_rate": 6.428318095950648e-07,
+      "loss": 1.0373,
+      "step": 392
+    },
+    {
+      "epoch": 2.6598984771573604,
+      "grad_norm": 4.530887126922607,
+      "learning_rate": 6.171320574678064e-07,
+      "loss": 0.8817,
+      "step": 393
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 5.074831008911133,
+      "learning_rate": 5.919402046709288e-07,
+      "loss": 0.6199,
+      "step": 394
+    },
+    {
+      "epoch": 2.673434856175973,
+      "grad_norm": 5.216182231903076,
+      "learning_rate": 5.672576148520136e-07,
+      "loss": 0.5777,
+      "step": 395
+    },
+    {
+      "epoch": 2.6802030456852792,
+      "grad_norm": 4.10127067565918,
+      "learning_rate": 5.430856240919779e-07,
+      "loss": 1.3062,
+      "step": 396
+    },
+    {
+      "epoch": 2.6869712351945854,
+      "grad_norm": 3.1244003772735596,
+      "learning_rate": 5.19425540832762e-07,
+      "loss": 1.6781,
+      "step": 397
+    },
+    {
+      "epoch": 2.6937394247038915,
+      "grad_norm": 3.911149501800537,
+      "learning_rate": 4.962786458064972e-07,
+      "loss": 1.1371,
+      "step": 398
+    },
+    {
+      "epoch": 2.700507614213198,
+      "grad_norm": 4.34928560256958,
+      "learning_rate": 4.73646191966175e-07,
+      "loss": 0.9204,
+      "step": 399
+    },
+    {
+      "epoch": 2.707275803722504,
+      "grad_norm": 5.3247551918029785,
+      "learning_rate": 4.515294044178331e-07,
+      "loss": 0.7054,
+      "step": 400
+    },
+    {
+      "epoch": 2.7140439932318103,
+      "grad_norm": 5.384613990783691,
+      "learning_rate": 4.299294803542331e-07,
+      "loss": 0.6055,
+      "step": 401
+    },
+    {
+      "epoch": 2.720812182741117,
+      "grad_norm": 4.743732452392578,
+      "learning_rate": 4.0884758899006007e-07,
+      "loss": 0.9645,
+      "step": 402
+    },
+    {
+      "epoch": 2.727580372250423,
+      "grad_norm": 3.20401930809021,
+      "learning_rate": 3.882848714986243e-07,
+      "loss": 1.8007,
+      "step": 403
+    },
+    {
+      "epoch": 2.734348561759729,
+      "grad_norm": 3.646068811416626,
+      "learning_rate": 3.6824244095010064e-07,
+      "loss": 1.2693,
+      "step": 404
+    },
+    {
+      "epoch": 2.7411167512690353,
+      "grad_norm": 4.450921058654785,
+      "learning_rate": 3.4872138225127137e-07,
+      "loss": 0.9719,
+      "step": 405
+    },
+    {
+      "epoch": 2.747884940778342,
+      "grad_norm": 4.953512668609619,
+      "learning_rate": 3.2972275208679625e-07,
+      "loss": 0.8174,
+      "step": 406
+    },
+    {
+      "epoch": 2.754653130287648,
+      "grad_norm": 5.153395175933838,
+      "learning_rate": 3.112475788620217e-07,
+      "loss": 0.6039,
+      "step": 407
+    },
+    {
+      "epoch": 2.761421319796954,
+      "grad_norm": 5.268378257751465,
+      "learning_rate": 2.932968626473065e-07,
+      "loss": 0.5195,
+      "step": 408
+    },
+    {
+      "epoch": 2.7681895093062607,
+      "grad_norm": 3.0056629180908203,
+      "learning_rate": 2.758715751238872e-07,
+      "loss": 1.8951,
+      "step": 409
+    },
+    {
+      "epoch": 2.774957698815567,
+      "grad_norm": 3.4584174156188965,
+      "learning_rate": 2.589726595312858e-07,
+      "loss": 1.258,
+      "step": 410
+    },
+    {
+      "epoch": 2.781725888324873,
+      "grad_norm": 4.383852481842041,
+      "learning_rate": 2.426010306162485e-07,
+      "loss": 0.947,
+      "step": 411
+    },
+    {
+      "epoch": 2.788494077834179,
+      "grad_norm": 5.073363304138184,
+      "learning_rate": 2.2675757458323066e-07,
+      "loss": 0.7545,
+      "step": 412
+    },
+    {
+      "epoch": 2.7952622673434857,
+      "grad_norm": 5.620312213897705,
+      "learning_rate": 2.1144314904642194e-07,
+      "loss": 0.612,
+      "step": 413
+    },
+    {
+      "epoch": 2.802030456852792,
+      "grad_norm": 5.6198530197143555,
+      "learning_rate": 1.9665858298333006e-07,
+      "loss": 0.584,
+      "step": 414
+    },
+    {
+      "epoch": 2.808798646362098,
+      "grad_norm": 3.5097062587738037,
+      "learning_rate": 1.824046766899046e-07,
+      "loss": 1.7121,
+      "step": 415
+    },
+    {
+      "epoch": 2.8155668358714045,
+      "grad_norm": 3.444314479827881,
+      "learning_rate": 1.6868220173721472e-07,
+      "loss": 1.4931,
+      "step": 416
+    },
+    {
+      "epoch": 2.8223350253807107,
+      "grad_norm": 4.086292743682861,
+      "learning_rate": 1.5549190092968736e-07,
+      "loss": 0.96,
+      "step": 417
+    },
+    {
+      "epoch": 2.829103214890017,
+      "grad_norm": 4.669743061065674,
+      "learning_rate": 1.4283448826489798e-07,
+      "loss": 0.7836,
+      "step": 418
+    },
+    {
+      "epoch": 2.835871404399323,
+      "grad_norm": 5.329158782958984,
+      "learning_rate": 1.3071064889491723e-07,
+      "loss": 0.713,
+      "step": 419
+    },
+    {
+      "epoch": 2.8426395939086295,
+      "grad_norm": 5.7975664138793945,
+      "learning_rate": 1.1912103908922945e-07,
+      "loss": 0.5847,
+      "step": 420
+    },
+    {
+      "epoch": 2.8494077834179357,
+      "grad_norm": 3.9617557525634766,
+      "learning_rate": 1.0806628619920322e-07,
+      "loss": 1.3451,
+      "step": 421
+    },
+    {
+      "epoch": 2.8561759729272422,
+      "grad_norm": 3.1097750663757324,
+      "learning_rate": 9.754698862413758e-08,
+      "loss": 1.4706,
+      "step": 422
+    },
+    {
+      "epoch": 2.8629441624365484,
+      "grad_norm": 3.8327267169952393,
+      "learning_rate": 8.756371577886891e-08,
+      "loss": 1.1243,
+      "step": 423
+    },
+    {
+      "epoch": 2.8697123519458545,
+      "grad_norm": 4.473137855529785,
+      "learning_rate": 7.81170080629412e-08,
+      "loss": 0.9026,
+      "step": 424
+    },
+    {
+      "epoch": 2.8764805414551606,
+      "grad_norm": 5.105331897735596,
+      "learning_rate": 6.920737683136614e-08,
+      "loss": 0.6808,
+      "step": 425
+    },
+    {
+      "epoch": 2.8832487309644668,
+      "grad_norm": 6.36986780166626,
+      "learning_rate": 6.083530436693408e-08,
+      "loss": 0.6489,
+      "step": 426
+    },
+    {
+      "epoch": 2.8900169204737733,
+      "grad_norm": 4.548642635345459,
+      "learning_rate": 5.300124385410943e-08,
+      "loss": 0.9101,
+      "step": 427
+    },
+    {
+      "epoch": 2.8967851099830795,
+      "grad_norm": 3.0376877784729004,
+      "learning_rate": 4.570561935450468e-08,
+      "loss": 1.8025,
+      "step": 428
+    },
+    {
+      "epoch": 2.903553299492386,
+      "grad_norm": 3.8811256885528564,
+      "learning_rate": 3.894882578391879e-08,
+      "loss": 1.2524,
+      "step": 429
+    },
+    {
+      "epoch": 2.910321489001692,
+      "grad_norm": 4.729759693145752,
+      "learning_rate": 3.273122889096536e-08,
+      "loss": 0.8427,
+      "step": 430
+    },
+    {
+      "epoch": 2.9170896785109983,
+      "grad_norm": 5.370926856994629,
+      "learning_rate": 2.705316523726853e-08,
+      "loss": 0.6915,
+      "step": 431
+    },
+    {
+      "epoch": 2.9238578680203045,
+      "grad_norm": 5.328631401062012,
+      "learning_rate": 2.1914942179253052e-08,
+      "loss": 0.5848,
+      "step": 432
+    },
+    {
+      "epoch": 2.9306260575296106,
+      "grad_norm": 5.493933200836182,
+      "learning_rate": 1.7316837851499845e-08,
+      "loss": 0.5372,
+      "step": 433
+    },
+    {
+      "epoch": 2.937394247038917,
+      "grad_norm": 3.3873283863067627,
+      "learning_rate": 1.325910115169471e-08,
+      "loss": 1.9925,
+      "step": 434
+    },
+    {
+      "epoch": 2.9441624365482233,
+      "grad_norm": 3.6963796615600586,
+      "learning_rate": 9.74195172715242e-09,
+      "loss": 1.3562,
+      "step": 435
+    },
+    {
+      "epoch": 2.95093062605753,
+      "grad_norm": 4.348772048950195,
+      "learning_rate": 6.7655799629284815e-09,
+      "loss": 0.8997,
+      "step": 436
+    },
+    {
+      "epoch": 2.957698815566836,
+      "grad_norm": 4.724446773529053,
+      "learning_rate": 4.330146971515126e-09,
+      "loss": 0.7332,
+      "step": 437
+    },
+    {
+      "epoch": 2.964467005076142,
+      "grad_norm": 6.034689903259277,
+      "learning_rate": 2.435784584114975e-09,
+      "loss": 0.663,
+      "step": 438
+    },
+    {
+      "epoch": 2.9712351945854483,
+      "grad_norm": 5.839619159698486,
+      "learning_rate": 1.0825953435122938e-09,
+      "loss": 0.5757,
+      "step": 439
+    },
+    {
+      "epoch": 2.9780033840947544,
+      "grad_norm": 3.8592047691345215,
+      "learning_rate": 2.706524985174319e-10,
+      "loss": 1.5785,
+      "step": 440
+    },
+    {
+      "epoch": 2.984771573604061,
+      "grad_norm": 3.915963888168335,
+      "learning_rate": 0.0,
+      "loss": 1.1236,
+      "step": 441
+    },
+    {
+      "epoch": 2.984771573604061,
+      "step": 441,
+      "total_flos": 4.015937399291904e+16,
+      "train_loss": 1.9800935814710432,
+      "train_runtime": 828.1657,
+      "train_samples_per_second": 34.203,
+      "train_steps_per_second": 0.533
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 441,
+  "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": 4.015937399291904e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65126db1186bbfbe8d9ebc7cab2426135c639471e8e4130e41cbc1807f009a59
+size 5496