Upload folder using huggingface_hub

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,57 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-4B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 4b_galore
+  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. -->
+
+# 4b_galore
+
+This model is a fine-tuned version of [/root/autodl-tmp/ner_project/model/Qwen1.5-4B](https://huggingface.co//root/autodl-tmp/ner_project/model/Qwen1.5-4B) on the universal_ner_all 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

README.md

@@ -0,0 +1,57 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-4B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: 4b_galore
+  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. -->
+
+# 4b_galore
+
+This model is a fine-tuned version of [/root/autodl-tmp/ner_project/model/Qwen1.5-4B](https://huggingface.co//root/autodl-tmp/ner_project/model/Qwen1.5-4B) on the universal_ner_all 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: 1e-05
+- train_batch_size: 2
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.25344288444270907,
+    "train_runtime": 45378.653,
+    "train_samples_per_second": 2.033,
+    "train_steps_per_second": 0.127
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/root/autodl-tmp/ner_project/model/Qwen1.5-4B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 20,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 5000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44753e72a3f9d2bbcf8217cd2c47884ab3a726c37101eb8f8762ebb59dbcd5f7
+size 4989973456

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f123c4c4395a23665187a1012e2af6fb05a18b2fb4b1c6faef7d658829d564b5
+size 2910820520

model.safetensors.index.json

@@ -0,0 +1,490 @@
+{
+  "metadata": {
+    "total_size": 7900738560
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.25344288444270907,
+    "train_runtime": 45378.653,
+    "train_samples_per_second": 2.033,
+    "train_steps_per_second": 0.127
+}

trainer_state.json

@@ -0,0 +1,4062 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998915989159891,
+  "eval_steps": 500,
+  "global_step": 5765,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 92.0,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.7712,
+      "step": 10
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 84.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.7512,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 74.5,
+      "learning_rate": 1.5e-06,
+      "loss": 1.7434,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 73.5,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.5907,
+      "step": 40
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 60.25,
+      "learning_rate": 2.5e-06,
+      "loss": 1.5682,
+      "step": 50
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 42.0,
+      "learning_rate": 3e-06,
+      "loss": 1.3992,
+      "step": 60
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 26.375,
+      "learning_rate": 3.5e-06,
+      "loss": 1.1574,
+      "step": 70
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 22.375,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.0237,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 14.875,
+      "learning_rate": 4.5e-06,
+      "loss": 0.7855,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 11.625,
+      "learning_rate": 5e-06,
+      "loss": 0.661,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 8.9375,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.4601,
+      "step": 110
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 7.78125,
+      "learning_rate": 6e-06,
+      "loss": 0.4192,
+      "step": 120
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 8.5,
+      "learning_rate": 6.5000000000000004e-06,
+      "loss": 0.3707,
+      "step": 130
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.96875,
+      "learning_rate": 7e-06,
+      "loss": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.5625,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3235,
+      "step": 150
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.78125,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3424,
+      "step": 160
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 4.65625,
+      "learning_rate": 8.5e-06,
+      "loss": 0.3181,
+      "step": 170
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.65625,
+      "learning_rate": 9e-06,
+      "loss": 0.3155,
+      "step": 180
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.1875,
+      "learning_rate": 9.5e-06,
+      "loss": 0.3076,
+      "step": 190
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 7.40625,
+      "learning_rate": 1e-05,
+      "loss": 0.2837,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.9375,
+      "learning_rate": 9.999920327533304e-06,
+      "loss": 0.3127,
+      "step": 210
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.84375,
+      "learning_rate": 9.999681312672292e-06,
+      "loss": 0.2662,
+      "step": 220
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.6875,
+      "learning_rate": 9.999282963034126e-06,
+      "loss": 0.2758,
+      "step": 230
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 5.3125,
+      "learning_rate": 9.998725291313807e-06,
+      "loss": 0.2859,
+      "step": 240
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 6.71875,
+      "learning_rate": 9.998008315283767e-06,
+      "loss": 0.2986,
+      "step": 250
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.875,
+      "learning_rate": 9.997132057793306e-06,
+      "loss": 0.3098,
+      "step": 260
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.9375,
+      "learning_rate": 9.99609654676786e-06,
+      "loss": 0.2845,
+      "step": 270
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 6.25,
+      "learning_rate": 9.99490181520812e-06,
+      "loss": 0.2702,
+      "step": 280
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.65625,
+      "learning_rate": 9.993547901188966e-06,
+      "loss": 0.2765,
+      "step": 290
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.992034847858267e-06,
+      "loss": 0.3171,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 5.84375,
+      "learning_rate": 9.990362703435504e-06,
+      "loss": 0.2675,
+      "step": 310
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.59375,
+      "learning_rate": 9.988531521210219e-06,
+      "loss": 0.2757,
+      "step": 320
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.625,
+      "learning_rate": 9.986541359540337e-06,
+      "loss": 0.2659,
+      "step": 330
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.8125,
+      "learning_rate": 9.984392281850293e-06,
+      "loss": 0.2555,
+      "step": 340
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 4.65625,
+      "learning_rate": 9.982084356629014e-06,
+      "loss": 0.2934,
+      "step": 350
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.09375,
+      "learning_rate": 9.979617657427742e-06,
+      "loss": 0.2773,
+      "step": 360
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 5.375,
+      "learning_rate": 9.976992262857677e-06,
+      "loss": 0.2664,
+      "step": 370
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 6.15625,
+      "learning_rate": 9.974208256587488e-06,
+      "loss": 0.2833,
+      "step": 380
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 6.0,
+      "learning_rate": 9.971265727340627e-06,
+      "loss": 0.2797,
+      "step": 390
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.25,
+      "learning_rate": 9.968164768892527e-06,
+      "loss": 0.2636,
+      "step": 400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 9.25,
+      "learning_rate": 9.964905480067585e-06,
+      "loss": 0.2526,
+      "step": 410
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.961487964736038e-06,
+      "loss": 0.2647,
+      "step": 420
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 7.84375,
+      "learning_rate": 9.957912331810633e-06,
+      "loss": 0.2701,
+      "step": 430
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.84375,
+      "learning_rate": 9.954178695243171e-06,
+      "loss": 0.2953,
+      "step": 440
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.9375,
+      "learning_rate": 9.950287174020864e-06,
+      "loss": 0.2903,
+      "step": 450
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.3125,
+      "learning_rate": 9.94623789216255e-06,
+      "loss": 0.2421,
+      "step": 460
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.94203097871474e-06,
+      "loss": 0.2815,
+      "step": 470
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.90625,
+      "learning_rate": 9.9376665677475e-06,
+      "loss": 0.273,
+      "step": 480
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.933144798350191e-06,
+      "loss": 0.2521,
+      "step": 490
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.75,
+      "learning_rate": 9.928465814627016e-06,
+      "loss": 0.2625,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 4.75,
+      "learning_rate": 9.923629765692445e-06,
+      "loss": 0.2406,
+      "step": 510
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.918636805666459e-06,
+      "loss": 0.2282,
+      "step": 520
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.913487093669633e-06,
+      "loss": 0.2554,
+      "step": 530
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 5.375,
+      "learning_rate": 9.908180793818072e-06,
+      "loss": 0.2616,
+      "step": 540
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.59375,
+      "learning_rate": 9.902718075218176e-06,
+      "loss": 0.2643,
+      "step": 550
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.5625,
+      "learning_rate": 9.897099111961248e-06,
+      "loss": 0.2638,
+      "step": 560
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.5625,
+      "learning_rate": 9.891324083117954e-06,
+      "loss": 0.2652,
+      "step": 570
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.875,
+      "learning_rate": 9.885393172732615e-06,
+      "loss": 0.2469,
+      "step": 580
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.879306569817331e-06,
+      "loss": 0.2286,
+      "step": 590
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.87306446834597e-06,
+      "loss": 0.2333,
+      "step": 600
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.866667067247982e-06,
+      "loss": 0.2295,
+      "step": 610
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.860114570402055e-06,
+      "loss": 0.2569,
+      "step": 620
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.853407186629626e-06,
+      "loss": 0.2573,
+      "step": 630
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.40625,
+      "learning_rate": 9.846545129688218e-06,
+      "loss": 0.2728,
+      "step": 640
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 4.34375,
+      "learning_rate": 9.839528618264633e-06,
+      "loss": 0.2387,
+      "step": 650
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.832357875967979e-06,
+      "loss": 0.2584,
+      "step": 660
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.825033131322548e-06,
+      "loss": 0.2672,
+      "step": 670
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.78125,
+      "learning_rate": 9.817554617760529e-06,
+      "loss": 0.2352,
+      "step": 680
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.75,
+      "learning_rate": 9.80992257361457e-06,
+      "loss": 0.2617,
+      "step": 690
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 4.6875,
+      "learning_rate": 9.802137242110185e-06,
+      "loss": 0.267,
+      "step": 700
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 7.0,
+      "learning_rate": 9.794198871358002e-06,
+      "loss": 0.2871,
+      "step": 710
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.5,
+      "learning_rate": 9.78610771434585e-06,
+      "loss": 0.2308,
+      "step": 720
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.4375,
+      "learning_rate": 9.777864028930705e-06,
+      "loss": 0.2549,
+      "step": 730
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.769468077830467e-06,
+      "loss": 0.273,
+      "step": 740
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 6.09375,
+      "learning_rate": 9.760920128615592e-06,
+      "loss": 0.2356,
+      "step": 750
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.1875,
+      "learning_rate": 9.752220453700556e-06,
+      "loss": 0.2354,
+      "step": 760
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 4.5625,
+      "learning_rate": 9.743369330335186e-06,
+      "loss": 0.2374,
+      "step": 770
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.734367040595813e-06,
+      "loss": 0.2604,
+      "step": 780
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.725213871376292e-06,
+      "loss": 0.2514,
+      "step": 790
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.3125,
+      "learning_rate": 9.715910114378845e-06,
+      "loss": 0.2446,
+      "step": 800
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.706456066104786e-06,
+      "loss": 0.2494,
+      "step": 810
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 4.40625,
+      "learning_rate": 9.69685202784505e-06,
+      "loss": 0.245,
+      "step": 820
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.687098305670606e-06,
+      "loss": 0.2491,
+      "step": 830
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.677195210422694e-06,
+      "loss": 0.249,
+      "step": 840
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.625,
+      "learning_rate": 9.667143057702926e-06,
+      "loss": 0.2512,
+      "step": 850
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.5625,
+      "learning_rate": 9.656942167863221e-06,
+      "loss": 0.2543,
+      "step": 860
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 7.375,
+      "learning_rate": 9.646592865995606e-06,
+      "loss": 0.2831,
+      "step": 870
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.63609548192184e-06,
+      "loss": 0.2498,
+      "step": 880
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 5.25,
+      "learning_rate": 9.625450350182919e-06,
+      "loss": 0.2649,
+      "step": 890
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.90625,
+      "learning_rate": 9.614657810028402e-06,
+      "loss": 0.2461,
+      "step": 900
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.5,
+      "learning_rate": 9.60371820540561e-06,
+      "loss": 0.2497,
+      "step": 910
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.592631884948654e-06,
+      "loss": 0.264,
+      "step": 920
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.3125,
+      "learning_rate": 9.581399201967336e-06,
+      "loss": 0.2464,
+      "step": 930
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.57002051443588e-06,
+      "loss": 0.2708,
+      "step": 940
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.9375,
+      "learning_rate": 9.558496184981525e-06,
+      "loss": 0.2542,
+      "step": 950
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 4.59375,
+      "learning_rate": 9.546826580872975e-06,
+      "loss": 0.2296,
+      "step": 960
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 5.6875,
+      "learning_rate": 9.535012074008688e-06,
+      "loss": 0.2507,
+      "step": 970
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 3.828125,
+      "learning_rate": 9.523053040905024e-06,
+      "loss": 0.2376,
+      "step": 980
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 6.5,
+      "learning_rate": 9.510949862684249e-06,
+      "loss": 0.2542,
+      "step": 990
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 5.96875,
+      "learning_rate": 9.498702925062393e-06,
+      "loss": 0.2341,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.28125,
+      "learning_rate": 9.486312618336944e-06,
+      "loss": 0.2549,
+      "step": 1010
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.84375,
+      "learning_rate": 9.473779337374422e-06,
+      "loss": 0.2472,
+      "step": 1020
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.8125,
+      "learning_rate": 9.461103481597795e-06,
+      "loss": 0.2287,
+      "step": 1030
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.3125,
+      "learning_rate": 9.448285454973739e-06,
+      "loss": 0.2331,
+      "step": 1040
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.375,
+      "learning_rate": 9.435325665999771e-06,
+      "loss": 0.212,
+      "step": 1050
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.71875,
+      "learning_rate": 9.422224527691236e-06,
+      "loss": 0.245,
+      "step": 1060
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 5.25,
+      "learning_rate": 9.408982457568138e-06,
+      "loss": 0.2361,
+      "step": 1070
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.395599877641832e-06,
+      "loss": 0.2422,
+      "step": 1080
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 3.859375,
+      "learning_rate": 9.382077214401578e-06,
+      "loss": 0.2378,
+      "step": 1090
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 4.34375,
+      "learning_rate": 9.368414898800951e-06,
+      "loss": 0.2358,
+      "step": 1100
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 4.78125,
+      "learning_rate": 9.354613366244108e-06,
+      "loss": 0.2427,
+      "step": 1110
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 5.71875,
+      "learning_rate": 9.3406730565719e-06,
+      "loss": 0.255,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.625,
+      "learning_rate": 9.326594414047877e-06,
+      "loss": 0.2356,
+      "step": 1130
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.312377887344105e-06,
+      "loss": 0.2535,
+      "step": 1140
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.8125,
+      "learning_rate": 9.298023929526888e-06,
+      "loss": 0.2507,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.78125,
+      "learning_rate": 9.283532998042314e-06,
+      "loss": 0.2428,
+      "step": 1160
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.21875,
+      "learning_rate": 9.268905554701686e-06,
+      "loss": 0.2119,
+      "step": 1170
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5.53125,
+      "learning_rate": 9.254142065666802e-06,
+      "loss": 0.2296,
+      "step": 1180
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.239243001435095e-06,
+      "loss": 0.2247,
+      "step": 1190
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.75,
+      "learning_rate": 9.224208836824646e-06,
+      "loss": 0.2581,
+      "step": 1200
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.25,
+      "learning_rate": 9.209040050959048e-06,
+      "loss": 0.2118,
+      "step": 1210
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 4.28125,
+      "learning_rate": 9.193737127252132e-06,
+      "loss": 0.2242,
+      "step": 1220
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 6.28125,
+      "learning_rate": 9.178300553392574e-06,
+      "loss": 0.2034,
+      "step": 1230
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.162730821328338e-06,
+      "loss": 0.2251,
+      "step": 1240
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.14702842725101e-06,
+      "loss": 0.2518,
+      "step": 1250
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.131193871579975e-06,
+      "loss": 0.2258,
+      "step": 1260
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.115227658946479e-06,
+      "loss": 0.2365,
+      "step": 1270
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 4.34375,
+      "learning_rate": 9.099130298177538e-06,
+      "loss": 0.2382,
+      "step": 1280
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 6.78125,
+      "learning_rate": 9.082902302279728e-06,
+      "loss": 0.2425,
+      "step": 1290
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 5.6875,
+      "learning_rate": 9.066544188422837e-06,
+      "loss": 0.2398,
+      "step": 1300
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.625,
+      "learning_rate": 9.050056477923373e-06,
+      "loss": 0.2401,
+      "step": 1310
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.9375,
+      "learning_rate": 9.033439696227966e-06,
+      "loss": 0.2307,
+      "step": 1320
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.016694372896609e-06,
+      "loss": 0.2127,
+      "step": 1330
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 4.84375,
+      "learning_rate": 8.999821041585788e-06,
+      "loss": 0.2414,
+      "step": 1340
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.65625,
+      "learning_rate": 8.982820240031473e-06,
+      "loss": 0.2347,
+      "step": 1350
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.5625,
+      "learning_rate": 8.965692510031985e-06,
+      "loss": 0.235,
+      "step": 1360
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.8125,
+      "learning_rate": 8.948438397430721e-06,
+      "loss": 0.238,
+      "step": 1370
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.84375,
+      "learning_rate": 8.931058452098767e-06,
+      "loss": 0.2306,
+      "step": 1380
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.40625,
+      "learning_rate": 8.913553227917366e-06,
+      "loss": 0.2514,
+      "step": 1390
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.1875,
+      "learning_rate": 8.89592328276028e-06,
+      "loss": 0.2172,
+      "step": 1400
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.59375,
+      "learning_rate": 8.87816917847599e-06,
+      "loss": 0.2327,
+      "step": 1410
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.1875,
+      "learning_rate": 8.860291480869814e-06,
+      "loss": 0.2281,
+      "step": 1420
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 6.0625,
+      "learning_rate": 8.842290759685857e-06,
+      "loss": 0.2304,
+      "step": 1430
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.625,
+      "learning_rate": 8.824167588588862e-06,
+      "loss": 0.2179,
+      "step": 1440
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.34375,
+      "learning_rate": 8.805922545145929e-06,
+      "loss": 0.2323,
+      "step": 1450
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 5.5,
+      "learning_rate": 8.787556210808101e-06,
+      "loss": 0.2341,
+      "step": 1460
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.875,
+      "learning_rate": 8.769069170891845e-06,
+      "loss": 0.2508,
+      "step": 1470
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.28125,
+      "learning_rate": 8.750462014560391e-06,
+      "loss": 0.2418,
+      "step": 1480
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 5.53125,
+      "learning_rate": 8.731735334804953e-06,
+      "loss": 0.2229,
+      "step": 1490
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.21875,
+      "learning_rate": 8.712889728425842e-06,
+      "loss": 0.2274,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.5625,
+      "learning_rate": 8.693925796013434e-06,
+      "loss": 0.2435,
+      "step": 1510
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.375,
+      "learning_rate": 8.67484414192904e-06,
+      "loss": 0.252,
+      "step": 1520
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.03125,
+      "learning_rate": 8.655645374285637e-06,
+      "loss": 0.2215,
+      "step": 1530
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.375,
+      "learning_rate": 8.6363301049285e-06,
+      "loss": 0.2539,
+      "step": 1540
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 6.3125,
+      "learning_rate": 8.616898949415688e-06,
+      "loss": 0.2166,
+      "step": 1550
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.597352526998437e-06,
+      "loss": 0.2447,
+      "step": 1560
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.3125,
+      "learning_rate": 8.577691460601422e-06,
+      "loss": 0.2308,
+      "step": 1570
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 5.0625,
+      "learning_rate": 8.55791637680291e-06,
+      "loss": 0.2145,
+      "step": 1580
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.96875,
+      "learning_rate": 8.538027905814778e-06,
+      "loss": 0.2396,
+      "step": 1590
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.96875,
+      "learning_rate": 8.518026681462448e-06,
+      "loss": 0.2334,
+      "step": 1600
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 5.1875,
+      "learning_rate": 8.49791334116467e-06,
+      "loss": 0.2455,
+      "step": 1610
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.5625,
+      "learning_rate": 8.477688525913215e-06,
+      "loss": 0.2369,
+      "step": 1620
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.15625,
+      "learning_rate": 8.457352880252456e-06,
+      "loss": 0.2176,
+      "step": 1630
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.78125,
+      "learning_rate": 8.436907052258809e-06,
+      "loss": 0.2447,
+      "step": 1640
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 5.53125,
+      "learning_rate": 8.4163516935201e-06,
+      "loss": 0.2366,
+      "step": 1650
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.395687459114776e-06,
+      "loss": 0.2467,
+      "step": 1660
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.5,
+      "learning_rate": 8.374915007591053e-06,
+      "loss": 0.2193,
+      "step": 1670
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 6.75,
+      "learning_rate": 8.35403500094591e-06,
+      "loss": 0.2238,
+      "step": 1680
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.71875,
+      "learning_rate": 8.333048104604e-06,
+      "loss": 0.2221,
+      "step": 1690
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.0625,
+      "learning_rate": 8.311954987396444e-06,
+      "loss": 0.2428,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.9375,
+      "learning_rate": 8.290756321539514e-06,
+      "loss": 0.2244,
+      "step": 1710
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.75,
+      "learning_rate": 8.269452782613208e-06,
+      "loss": 0.2114,
+      "step": 1720
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 6.125,
+      "learning_rate": 8.248045049539726e-06,
+      "loss": 0.2331,
+      "step": 1730
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 4.71875,
+      "learning_rate": 8.226533804561828e-06,
+      "loss": 0.2488,
+      "step": 1740
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.34375,
+      "learning_rate": 8.20491973322109e-06,
+      "loss": 0.2438,
+      "step": 1750
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.40625,
+      "learning_rate": 8.183203524336067e-06,
+      "loss": 0.2414,
+      "step": 1760
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.125,
+      "learning_rate": 8.161385869980332e-06,
+      "loss": 0.2205,
+      "step": 1770
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.71875,
+      "learning_rate": 8.139467465460417e-06,
+      "loss": 0.225,
+      "step": 1780
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.0625,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.232,
+      "step": 1790
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 4.15625,
+      "learning_rate": 8.095331203185969e-06,
+      "loss": 0.2099,
+      "step": 1800
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 5.53125,
+      "learning_rate": 8.073114752009388e-06,
+      "loss": 0.23,
+      "step": 1810
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.0625,
+      "learning_rate": 8.050800363779711e-06,
+      "loss": 0.2312,
+      "step": 1820
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.1875,
+      "learning_rate": 8.028388749633882e-06,
+      "loss": 0.2315,
+      "step": 1830
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.0,
+      "learning_rate": 8.005880623807332e-06,
+      "loss": 0.2432,
+      "step": 1840
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.98327670361122e-06,
+      "loss": 0.2396,
+      "step": 1850
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.960577709409585e-06,
+      "loss": 0.2241,
+      "step": 1860
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.21875,
+      "learning_rate": 7.937784364596364e-06,
+      "loss": 0.2601,
+      "step": 1870
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 5.25,
+      "learning_rate": 7.914897395572362e-06,
+      "loss": 0.2221,
+      "step": 1880
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.53125,
+      "learning_rate": 7.891917531722088e-06,
+      "loss": 0.2263,
+      "step": 1890
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 5.0625,
+      "learning_rate": 7.86884550539052e-06,
+      "loss": 0.2255,
+      "step": 1900
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.845682051859757e-06,
+      "loss": 0.2243,
+      "step": 1910
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 5.625,
+      "learning_rate": 7.822427909325592e-06,
+      "loss": 0.2369,
+      "step": 1920
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 4.1875,
+      "learning_rate": 7.79908381887398e-06,
+      "loss": 0.2174,
+      "step": 1930
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.4375,
+      "learning_rate": 7.775650524457431e-06,
+      "loss": 0.2596,
+      "step": 1940
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 5.625,
+      "learning_rate": 7.752128772871292e-06,
+      "loss": 0.226,
+      "step": 1950
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.728519313729953e-06,
+      "loss": 0.2111,
+      "step": 1960
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 6.84375,
+      "learning_rate": 7.70482289944295e-06,
+      "loss": 0.2247,
+      "step": 1970
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.5,
+      "learning_rate": 7.681040285190995e-06,
+      "loss": 0.2218,
+      "step": 1980
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.375,
+      "learning_rate": 7.657172228901906e-06,
+      "loss": 0.2374,
+      "step": 1990
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 5.59375,
+      "learning_rate": 7.63321949122645e-06,
+      "loss": 0.2245,
+      "step": 2000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 4.875,
+      "learning_rate": 7.609182835514104e-06,
+      "loss": 0.2428,
+      "step": 2010
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 5.15625,
+      "learning_rate": 7.58506302778873e-06,
+      "loss": 0.245,
+      "step": 2020
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 6.40625,
+      "learning_rate": 7.5608608367241595e-06,
+      "loss": 0.2212,
+      "step": 2030
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 5.875,
+      "learning_rate": 7.536577033619698e-06,
+      "loss": 0.2383,
+      "step": 2040
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.0,
+      "learning_rate": 7.5122123923755396e-06,
+      "loss": 0.2065,
+      "step": 2050
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.09375,
+      "learning_rate": 7.487767689468114e-06,
+      "loss": 0.2437,
+      "step": 2060
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 4.25,
+      "learning_rate": 7.463243703925333e-06,
+      "loss": 0.2242,
+      "step": 2070
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.21875,
+      "learning_rate": 7.438641217301763e-06,
+      "loss": 0.2209,
+      "step": 2080
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.0,
+      "learning_rate": 7.413961013653725e-06,
+      "loss": 0.2331,
+      "step": 2090
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 5.1875,
+      "learning_rate": 7.3892038795142995e-06,
+      "loss": 0.2316,
+      "step": 2100
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.125,
+      "learning_rate": 7.3643706038682625e-06,
+      "loss": 0.2223,
+      "step": 2110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 7.15625,
+      "learning_rate": 7.339461978126947e-06,
+      "loss": 0.2353,
+      "step": 2120
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 3.90625,
+      "learning_rate": 7.314478796103015e-06,
+      "loss": 0.2419,
+      "step": 2130
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.289421853985162e-06,
+      "loss": 0.2325,
+      "step": 2140
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.2642919503127405e-06,
+      "loss": 0.2296,
+      "step": 2150
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 4.90625,
+      "learning_rate": 7.239089885950317e-06,
+      "loss": 0.2496,
+      "step": 2160
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.75,
+      "learning_rate": 7.213816464062144e-06,
+      "loss": 0.2338,
+      "step": 2170
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.1875,
+      "learning_rate": 7.188472490086569e-06,
+      "loss": 0.2062,
+      "step": 2180
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.1875,
+      "learning_rate": 7.16305877171036e-06,
+      "loss": 0.2374,
+      "step": 2190
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.53125,
+      "learning_rate": 7.137576118842969e-06,
+      "loss": 0.227,
+      "step": 2200
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.03125,
+      "learning_rate": 7.112025343590721e-06,
+      "loss": 0.2266,
+      "step": 2210
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.0864072602309335e-06,
+      "loss": 0.2432,
+      "step": 2220
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 5.0625,
+      "learning_rate": 7.060722685185961e-06,
+      "loss": 0.2328,
+      "step": 2230
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 5.15625,
+      "learning_rate": 7.034972436997185e-06,
+      "loss": 0.2156,
+      "step": 2240
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.9375,
+      "learning_rate": 7.009157336298924e-06,
+      "loss": 0.2422,
+      "step": 2250
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 4.6875,
+      "learning_rate": 6.983278205792274e-06,
+      "loss": 0.2234,
+      "step": 2260
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 5.28125,
+      "learning_rate": 6.957335870218906e-06,
+      "loss": 0.2126,
+      "step": 2270
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 5.125,
+      "learning_rate": 6.931331156334759e-06,
+      "loss": 0.2404,
+      "step": 2280
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.8125,
+      "learning_rate": 6.905264892883722e-06,
+      "loss": 0.2244,
+      "step": 2290
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.125,
+      "learning_rate": 6.879137910571191e-06,
+      "loss": 0.24,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.28125,
+      "learning_rate": 6.852951042037622e-06,
+      "loss": 0.2398,
+      "step": 2310
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 4.4375,
+      "learning_rate": 6.8267051218319766e-06,
+      "loss": 0.1964,
+      "step": 2320
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.0625,
+      "learning_rate": 6.800400986385136e-06,
+      "loss": 0.2456,
+      "step": 2330
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.774039473983244e-06,
+      "loss": 0.2122,
+      "step": 2340
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 5.875,
+      "learning_rate": 6.747621424740986e-06,
+      "loss": 0.2022,
+      "step": 2350
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 5.125,
+      "learning_rate": 6.7211476805748254e-06,
+      "loss": 0.2533,
+      "step": 2360
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 5.0,
+      "learning_rate": 6.694619085176159e-06,
+      "loss": 0.2399,
+      "step": 2370
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 5.65625,
+      "learning_rate": 6.668036483984441e-06,
+      "loss": 0.209,
+      "step": 2380
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 5.5,
+      "learning_rate": 6.641400724160235e-06,
+      "loss": 0.2116,
+      "step": 2390
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.5625,
+      "learning_rate": 6.614712654558215e-06,
+      "loss": 0.2246,
+      "step": 2400
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 8.6875,
+      "learning_rate": 6.587973125700117e-06,
+      "loss": 0.2353,
+      "step": 2410
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.15625,
+      "learning_rate": 6.561182989747629e-06,
+      "loss": 0.2245,
+      "step": 2420
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 5.65625,
+      "learning_rate": 6.5343431004752375e-06,
+      "loss": 0.2266,
+      "step": 2430
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.96875,
+      "learning_rate": 6.507454313243016e-06,
+      "loss": 0.2434,
+      "step": 2440
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.96875,
+      "learning_rate": 6.480517484969366e-06,
+      "loss": 0.2087,
+      "step": 2450
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 5.25,
+      "learning_rate": 6.45353347410371e-06,
+      "loss": 0.2161,
+      "step": 2460
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.71875,
+      "learning_rate": 6.426503140599129e-06,
+      "loss": 0.2437,
+      "step": 2470
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.25,
+      "learning_rate": 6.399427345884964e-06,
+      "loss": 0.2176,
+      "step": 2480
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 5.75,
+      "learning_rate": 6.3723069528393535e-06,
+      "loss": 0.233,
+      "step": 2490
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 4.34375,
+      "learning_rate": 6.345142825761745e-06,
+      "loss": 0.2262,
+      "step": 2500
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.9375,
+      "learning_rate": 6.3179358303453386e-06,
+      "loss": 0.2256,
+      "step": 2510
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.84375,
+      "learning_rate": 6.290686833649513e-06,
+      "loss": 0.2081,
+      "step": 2520
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.3125,
+      "learning_rate": 6.263396704072177e-06,
+      "loss": 0.2416,
+      "step": 2530
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.65625,
+      "learning_rate": 6.236066311322111e-06,
+      "loss": 0.2141,
+      "step": 2540
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 4.40625,
+      "learning_rate": 6.208696526391235e-06,
+      "loss": 0.222,
+      "step": 2550
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.96875,
+      "learning_rate": 6.181288221526858e-06,
+      "loss": 0.2375,
+      "step": 2560
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.5625,
+      "learning_rate": 6.153842270203887e-06,
+      "loss": 0.2115,
+      "step": 2570
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.03125,
+      "learning_rate": 6.126359547096975e-06,
+      "loss": 0.2059,
+      "step": 2580
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 3.859375,
+      "learning_rate": 6.098840928052663e-06,
+      "loss": 0.2266,
+      "step": 2590
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.09375,
+      "learning_rate": 6.0712872900614515e-06,
+      "loss": 0.2311,
+      "step": 2600
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.875,
+      "learning_rate": 6.043699511229864e-06,
+      "loss": 0.2357,
+      "step": 2610
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 5.375,
+      "learning_rate": 6.0160784707524566e-06,
+      "loss": 0.2199,
+      "step": 2620
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 5.53125,
+      "learning_rate": 5.988425048883799e-06,
+      "loss": 0.2235,
+      "step": 2630
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 5.53125,
+      "learning_rate": 5.960740126910426e-06,
+      "loss": 0.2267,
+      "step": 2640
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 5.0,
+      "learning_rate": 5.933024587122745e-06,
+      "loss": 0.2168,
+      "step": 2650
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 4.0625,
+      "learning_rate": 5.905279312786928e-06,
+      "loss": 0.2118,
+      "step": 2660
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 5.375,
+      "learning_rate": 5.877505188116749e-06,
+      "loss": 0.2182,
+      "step": 2670
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 5.3125,
+      "learning_rate": 5.84970309824542e-06,
+      "loss": 0.2284,
+      "step": 2680
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.9375,
+      "learning_rate": 5.821873929197371e-06,
+      "loss": 0.2111,
+      "step": 2690
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.15625,
+      "learning_rate": 5.794018567860021e-06,
+      "loss": 0.2238,
+      "step": 2700
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.5,
+      "learning_rate": 5.766137901955511e-06,
+      "loss": 0.2321,
+      "step": 2710
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.71875,
+      "learning_rate": 5.738232820012407e-06,
+      "loss": 0.2277,
+      "step": 2720
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.78125,
+      "learning_rate": 5.7103042113373964e-06,
+      "loss": 0.2242,
+      "step": 2730
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.65625,
+      "learning_rate": 5.682352965986936e-06,
+      "loss": 0.2096,
+      "step": 2740
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.96875,
+      "learning_rate": 5.654379974738893e-06,
+      "loss": 0.2043,
+      "step": 2750
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 6.6875,
+      "learning_rate": 5.626386129064152e-06,
+      "loss": 0.2083,
+      "step": 2760
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.78125,
+      "learning_rate": 5.598372321098209e-06,
+      "loss": 0.1889,
+      "step": 2770
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.75,
+      "learning_rate": 5.570339443612734e-06,
+      "loss": 0.2284,
+      "step": 2780
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.25,
+      "learning_rate": 5.542288389987128e-06,
+      "loss": 0.2106,
+      "step": 2790
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.96875,
+      "learning_rate": 5.514220054180046e-06,
+      "loss": 0.2405,
+      "step": 2800
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.9375,
+      "learning_rate": 5.486135330700906e-06,
+      "loss": 0.2166,
+      "step": 2810
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 6.9375,
+      "learning_rate": 5.45803511458139e-06,
+      "loss": 0.2198,
+      "step": 2820
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.429920301346907e-06,
+      "loss": 0.2462,
+      "step": 2830
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 4.21875,
+      "learning_rate": 5.401791786988068e-06,
+      "loss": 0.2134,
+      "step": 2840
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 5.8125,
+      "learning_rate": 5.373650467932122e-06,
+      "loss": 0.217,
+      "step": 2850
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.34549724101439e-06,
+      "loss": 0.2063,
+      "step": 2860
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.15625,
+      "learning_rate": 5.3173330034496875e-06,
+      "loss": 0.2393,
+      "step": 2870
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.8125,
+      "learning_rate": 5.2891586528037255e-06,
+      "loss": 0.2496,
+      "step": 2880
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.25,
+      "learning_rate": 5.2609750869645085e-06,
+      "loss": 0.226,
+      "step": 2890
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.28125,
+      "learning_rate": 5.23278320411372e-06,
+      "loss": 0.2199,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.5,
+      "learning_rate": 5.204583902698101e-06,
+      "loss": 0.2366,
+      "step": 2910
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 4.40625,
+      "learning_rate": 5.176378081400813e-06,
+      "loss": 0.2398,
+      "step": 2920
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 4.625,
+      "learning_rate": 5.148166639112799e-06,
+      "loss": 0.2296,
+      "step": 2930
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 4.46875,
+      "learning_rate": 5.119950474904137e-06,
+      "loss": 0.2049,
+      "step": 2940
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 4.71875,
+      "learning_rate": 5.091730487995387e-06,
+      "loss": 0.2451,
+      "step": 2950
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 5.09375,
+      "learning_rate": 5.063507577728938e-06,
+      "loss": 0.215,
+      "step": 2960
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.8125,
+      "learning_rate": 5.035282643540338e-06,
+      "loss": 0.2292,
+      "step": 2970
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.9375,
+      "learning_rate": 5.007056584929642e-06,
+      "loss": 0.2382,
+      "step": 2980
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.625,
+      "learning_rate": 4.978830301432738e-06,
+      "loss": 0.2292,
+      "step": 2990
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 4.34375,
+      "learning_rate": 4.9506046925926725e-06,
+      "loss": 0.207,
+      "step": 3000
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.40625,
+      "learning_rate": 4.922380657931001e-06,
+      "loss": 0.2277,
+      "step": 3010
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.894159096919109e-06,
+      "loss": 0.202,
+      "step": 3020
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.125,
+      "learning_rate": 4.865940908949546e-06,
+      "loss": 0.2271,
+      "step": 3030
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 5.96875,
+      "learning_rate": 4.837726993307372e-06,
+      "loss": 0.2405,
+      "step": 3040
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.09375,
+      "learning_rate": 4.809518249141484e-06,
+      "loss": 0.242,
+      "step": 3050
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 5.65625,
+      "learning_rate": 4.7813155754359794e-06,
+      "loss": 0.237,
+      "step": 3060
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 5.5625,
+      "learning_rate": 4.753119870981486e-06,
+      "loss": 0.2286,
+      "step": 3070
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 5.1875,
+      "learning_rate": 4.724932034346536e-06,
+      "loss": 0.2201,
+      "step": 3080
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.53125,
+      "learning_rate": 4.69675296384892e-06,
+      "loss": 0.2346,
+      "step": 3090
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.53125,
+      "learning_rate": 4.66858355752706e-06,
+      "loss": 0.2283,
+      "step": 3100
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.59375,
+      "learning_rate": 4.640424713111389e-06,
+      "loss": 0.2206,
+      "step": 3110
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.46875,
+      "learning_rate": 4.612277327995746e-06,
+      "loss": 0.2232,
+      "step": 3120
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.03125,
+      "learning_rate": 4.584142299208773e-06,
+      "loss": 0.2103,
+      "step": 3130
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.03125,
+      "learning_rate": 4.556020523385326e-06,
+      "loss": 0.2136,
+      "step": 3140
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.527912896737907e-06,
+      "loss": 0.2161,
+      "step": 3150
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.15625,
+      "learning_rate": 4.499820315028092e-06,
+      "loss": 0.2281,
+      "step": 3160
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 5.59375,
+      "learning_rate": 4.471743673537994e-06,
+      "loss": 0.2355,
+      "step": 3170
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.75,
+      "learning_rate": 4.443683867041727e-06,
+      "loss": 0.2465,
+      "step": 3180
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 4.40625,
+      "learning_rate": 4.4156417897768906e-06,
+      "loss": 0.2367,
+      "step": 3190
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.0,
+      "learning_rate": 4.387618335416073e-06,
+      "loss": 0.22,
+      "step": 3200
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.90625,
+      "learning_rate": 4.3596143970383665e-06,
+      "loss": 0.2312,
+      "step": 3210
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.0,
+      "learning_rate": 4.331630867100909e-06,
+      "loss": 0.218,
+      "step": 3220
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 5.5,
+      "learning_rate": 4.303668637410444e-06,
+      "loss": 0.2291,
+      "step": 3230
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 4.78125,
+      "learning_rate": 4.2757285990948995e-06,
+      "loss": 0.222,
+      "step": 3240
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.3125,
+      "learning_rate": 4.247811642574981e-06,
+      "loss": 0.2325,
+      "step": 3250
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 3.734375,
+      "learning_rate": 4.219918657535806e-06,
+      "loss": 0.2049,
+      "step": 3260
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 4.4375,
+      "learning_rate": 4.192050532898543e-06,
+      "loss": 0.2106,
+      "step": 3270
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.1642081567920845e-06,
+      "loss": 0.2282,
+      "step": 3280
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.21875,
+      "learning_rate": 4.136392416524742e-06,
+      "loss": 0.2258,
+      "step": 3290
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.375,
+      "learning_rate": 4.108604198555974e-06,
+      "loss": 0.2242,
+      "step": 3300
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 5.03125,
+      "learning_rate": 4.080844388468129e-06,
+      "loss": 0.2108,
+      "step": 3310
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.15625,
+      "learning_rate": 4.053113870938224e-06,
+      "loss": 0.2329,
+      "step": 3320
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.46875,
+      "learning_rate": 4.025413529709751e-06,
+      "loss": 0.2317,
+      "step": 3330
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.78125,
+      "learning_rate": 3.9977442475645195e-06,
+      "loss": 0.2388,
+      "step": 3340
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.970106906294509e-06,
+      "loss": 0.2381,
+      "step": 3350
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.5625,
+      "learning_rate": 3.9425023866737824e-06,
+      "loss": 0.2413,
+      "step": 3360
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.78125,
+      "learning_rate": 3.91493156843041e-06,
+      "loss": 0.244,
+      "step": 3370
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.2283,
+      "step": 3380
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 5.5625,
+      "learning_rate": 3.859894549589848e-06,
+      "loss": 0.2417,
+      "step": 3390
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 5.0625,
+      "learning_rate": 3.832430102966678e-06,
+      "loss": 0.2257,
+      "step": 3400
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 4.46875,
+      "learning_rate": 3.8050028656130046e-06,
+      "loss": 0.212,
+      "step": 3410
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.777613711607087e-06,
+      "loss": 0.2303,
+      "step": 3420
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 3.75,
+      "learning_rate": 3.7502635138135125e-06,
+      "loss": 0.2265,
+      "step": 3430
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.7229531438553666e-06,
+      "loss": 0.2373,
+      "step": 3440
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.6956834720864704e-06,
+      "loss": 0.1923,
+      "step": 3450
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.875,
+      "learning_rate": 3.668455367563625e-06,
+      "loss": 0.2475,
+      "step": 3460
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.625,
+      "learning_rate": 3.641269698018934e-06,
+      "loss": 0.2263,
+      "step": 3470
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 6.03125,
+      "learning_rate": 3.614127329832139e-06,
+      "loss": 0.2138,
+      "step": 3480
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 5.40625,
+      "learning_rate": 3.587029128003006e-06,
+      "loss": 0.2131,
+      "step": 3490
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 5.875,
+      "learning_rate": 3.5599759561237725e-06,
+      "loss": 0.2279,
+      "step": 3500
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 6.4375,
+      "learning_rate": 3.532968676351609e-06,
+      "loss": 0.2145,
+      "step": 3510
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 5.0,
+      "learning_rate": 3.5060081493811587e-06,
+      "loss": 0.2032,
+      "step": 3520
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 4.53125,
+      "learning_rate": 3.4790952344170927e-06,
+      "loss": 0.2211,
+      "step": 3530
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 4.8125,
+      "learning_rate": 3.4522307891467416e-06,
+      "loss": 0.2276,
+      "step": 3540
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.5625,
+      "learning_rate": 3.425415669712754e-06,
+      "loss": 0.2297,
+      "step": 3550
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.398650730685813e-06,
+      "loss": 0.267,
+      "step": 3560
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 4.375,
+      "learning_rate": 3.3719368250374036e-06,
+      "loss": 0.2102,
+      "step": 3570
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.345274804112629e-06,
+      "loss": 0.2213,
+      "step": 3580
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.318665517603083e-06,
+      "loss": 0.2292,
+      "step": 3590
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.125,
+      "learning_rate": 3.2921098135197565e-06,
+      "loss": 0.2429,
+      "step": 3600
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.265608538166034e-06,
+      "loss": 0.238,
+      "step": 3610
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 5.0625,
+      "learning_rate": 3.2391625361107033e-06,
+      "loss": 0.2208,
+      "step": 3620
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 5.0,
+      "learning_rate": 3.2127726501610558e-06,
+      "loss": 0.2275,
+      "step": 3630
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 4.75,
+      "learning_rate": 3.18643972133601e-06,
+      "loss": 0.2318,
+      "step": 3640
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 4.34375,
+      "learning_rate": 3.160164588839328e-06,
+      "loss": 0.2387,
+      "step": 3650
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.1339480900328555e-06,
+      "loss": 0.2218,
+      "step": 3660
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.65625,
+      "learning_rate": 3.107791060409845e-06,
+      "loss": 0.2536,
+      "step": 3670
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.125,
+      "learning_rate": 3.081694333568323e-06,
+      "loss": 0.2054,
+      "step": 3680
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.625,
+      "learning_rate": 3.0556587411845308e-06,
+      "loss": 0.2293,
+      "step": 3690
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 6.28125,
+      "learning_rate": 3.029685112986417e-06,
+      "loss": 0.2412,
+      "step": 3700
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.0037742767271894e-06,
+      "loss": 0.2212,
+      "step": 3710
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.3125,
+      "learning_rate": 2.9779270581589457e-06,
+      "loss": 0.2571,
+      "step": 3720
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.84375,
+      "learning_rate": 2.9521442810063516e-06,
+      "loss": 0.2453,
+      "step": 3730
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.15625,
+      "learning_rate": 2.926426766940384e-06,
+      "loss": 0.2348,
+      "step": 3740
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 7.1875,
+      "learning_rate": 2.9007753355521594e-06,
+      "loss": 0.2415,
+      "step": 3750
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 4.21875,
+      "learning_rate": 2.8751908043268024e-06,
+      "loss": 0.2152,
+      "step": 3760
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 6.3125,
+      "learning_rate": 2.8496739886173994e-06,
+      "loss": 0.2244,
+      "step": 3770
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.53125,
+      "learning_rate": 2.8242257016190065e-06,
+      "loss": 0.189,
+      "step": 3780
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.5,
+      "learning_rate": 2.7988467543427457e-06,
+      "loss": 0.242,
+      "step": 3790
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.34375,
+      "learning_rate": 2.773537955589951e-06,
+      "loss": 0.2139,
+      "step": 3800
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 4.5,
+      "learning_rate": 2.74830011192639e-06,
+      "loss": 0.2279,
+      "step": 3810
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.78125,
+      "learning_rate": 2.723134027656566e-06,
+      "loss": 0.2365,
+      "step": 3820
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.21875,
+      "learning_rate": 2.6980405047980853e-06,
+      "loss": 0.2068,
+      "step": 3830
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 5.3125,
+      "learning_rate": 2.6730203430560946e-06,
+      "loss": 0.2333,
+      "step": 3840
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 4.78125,
+      "learning_rate": 2.6480743397977914e-06,
+      "loss": 0.2348,
+      "step": 3850
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 5.0,
+      "learning_rate": 2.6232032900270254e-06,
+      "loss": 0.2367,
+      "step": 3860
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 5.6875,
+      "learning_rate": 2.5984079863589484e-06,
+      "loss": 0.2418,
+      "step": 3870
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 5.84375,
+      "learning_rate": 2.573689218994761e-06,
+      "loss": 0.228,
+      "step": 3880
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 6.59375,
+      "learning_rate": 2.549047775696533e-06,
+      "loss": 0.2119,
+      "step": 3890
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.84375,
+      "learning_rate": 2.524484441762091e-06,
+      "loss": 0.2263,
+      "step": 3900
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.65625,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.2285,
+      "step": 3910
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.84375,
+      "learning_rate": 2.475595230704607e-06,
+      "loss": 0.2283,
+      "step": 3920
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 4.40625,
+      "learning_rate": 2.451270911631178e-06,
+      "loss": 0.2086,
+      "step": 3930
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 5.71875,
+      "learning_rate": 2.4270278179711167e-06,
+      "loss": 0.2361,
+      "step": 3940
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.28125,
+      "learning_rate": 2.402866722327248e-06,
+      "loss": 0.2378,
+      "step": 3950
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 5.5,
+      "learning_rate": 2.3787883946892087e-06,
+      "loss": 0.2121,
+      "step": 3960
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.84375,
+      "learning_rate": 2.3547936024089045e-06,
+      "loss": 0.2041,
+      "step": 3970
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 4.59375,
+      "learning_rate": 2.330883110176049e-06,
+      "loss": 0.231,
+      "step": 3980
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 5.34375,
+      "learning_rate": 2.3070576799937973e-06,
+      "loss": 0.2292,
+      "step": 3990
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 5.0,
+      "learning_rate": 2.2833180711544694e-06,
+      "loss": 0.2365,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.625,
+      "learning_rate": 2.2596650402153437e-06,
+      "loss": 0.2317,
+      "step": 4010
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.0625,
+      "learning_rate": 2.236099340974549e-06,
+      "loss": 0.2263,
+      "step": 4020
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 6.09375,
+      "learning_rate": 2.212621724447037e-06,
+      "loss": 0.2354,
+      "step": 4030
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.28125,
+      "learning_rate": 2.1892329388406586e-06,
+      "loss": 0.2126,
+      "step": 4040
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 4.1875,
+      "learning_rate": 2.1659337295323117e-06,
+      "loss": 0.2137,
+      "step": 4050
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.0625,
+      "learning_rate": 2.1427248390441845e-06,
+      "loss": 0.2412,
+      "step": 4060
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 6.0625,
+      "learning_rate": 2.1196070070200998e-06,
+      "loss": 0.2199,
+      "step": 4070
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.0,
+      "learning_rate": 2.096580970201941e-06,
+      "loss": 0.2169,
+      "step": 4080
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.71875,
+      "learning_rate": 2.073647462406166e-06,
+      "loss": 0.2114,
+      "step": 4090
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.03125,
+      "learning_rate": 2.0508072145004284e-06,
+      "loss": 0.2496,
+      "step": 4100
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 4.90625,
+      "learning_rate": 2.0280609543802853e-06,
+      "loss": 0.2148,
+      "step": 4110
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 4.40625,
+      "learning_rate": 2.005409406946e-06,
+      "loss": 0.2104,
+      "step": 4120
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.59375,
+      "learning_rate": 1.9828532940794325e-06,
+      "loss": 0.2425,
+      "step": 4130
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.9603933346210446e-06,
+      "loss": 0.2243,
+      "step": 4140
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.6875,
+      "learning_rate": 1.9380302443469857e-06,
+      "loss": 0.2363,
+      "step": 4150
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 4.28125,
+      "learning_rate": 1.9157647359462828e-06,
+      "loss": 0.2003,
+      "step": 4160
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.25,
+      "learning_rate": 1.8935975189981231e-06,
+      "loss": 0.2121,
+      "step": 4170
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.78125,
+      "learning_rate": 1.8715292999492502e-06,
+      "loss": 0.2206,
+      "step": 4180
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 4.9375,
+      "learning_rate": 1.8495607820914451e-06,
+      "loss": 0.2289,
+      "step": 4190
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 5.84375,
+      "learning_rate": 1.8276926655391086e-06,
+      "loss": 0.2067,
+      "step": 4200
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 5.78125,
+      "learning_rate": 1.8059256472069542e-06,
+      "loss": 0.2078,
+      "step": 4210
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.7842604207878006e-06,
+      "loss": 0.228,
+      "step": 4220
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 4.78125,
+      "learning_rate": 1.762697676730462e-06,
+      "loss": 0.227,
+      "step": 4230
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.46875,
+      "learning_rate": 1.7412381022177382e-06,
+      "loss": 0.2123,
+      "step": 4240
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.7198823811445254e-06,
+      "loss": 0.2058,
+      "step": 4250
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.65625,
+      "learning_rate": 1.6986311940960148e-06,
+      "loss": 0.2157,
+      "step": 4260
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.9375,
+      "learning_rate": 1.6774852183260005e-06,
+      "loss": 0.2485,
+      "step": 4270
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.6564451277353045e-06,
+      "loss": 0.2293,
+      "step": 4280
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 4.75,
+      "learning_rate": 1.6355115928502936e-06,
+      "loss": 0.2246,
+      "step": 4290
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 6.375,
+      "learning_rate": 1.6146852808015133e-06,
+      "loss": 0.245,
+      "step": 4300
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.5939668553024234e-06,
+      "loss": 0.2275,
+      "step": 4310
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.625,
+      "learning_rate": 1.5733569766282493e-06,
+      "loss": 0.2254,
+      "step": 4320
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.21875,
+      "learning_rate": 1.5528563015949421e-06,
+      "loss": 0.211,
+      "step": 4330
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.5324654835382386e-06,
+      "loss": 0.2246,
+      "step": 4340
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.625,
+      "learning_rate": 1.5121851722928493e-06,
+      "loss": 0.2294,
+      "step": 4350
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.4920160141717433e-06,
+      "loss": 0.2408,
+      "step": 4360
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.4719586519455536e-06,
+      "loss": 0.2272,
+      "step": 4370
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 6.125,
+      "learning_rate": 1.4520137248220866e-06,
+      "loss": 0.243,
+      "step": 4380
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.90625,
+      "learning_rate": 1.432181868425961e-06,
+      "loss": 0.2272,
+      "step": 4390
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.4124637147783431e-06,
+      "loss": 0.2312,
+      "step": 4400
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 4.125,
+      "learning_rate": 1.392859892276812e-06,
+      "loss": 0.2263,
+      "step": 4410
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.5,
+      "learning_rate": 1.373371025675323e-06,
+      "loss": 0.2136,
+      "step": 4420
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.3539977360643054e-06,
+      "loss": 0.2462,
+      "step": 4430
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.625,
+      "learning_rate": 1.3347406408508695e-06,
+      "loss": 0.2344,
+      "step": 4440
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.53125,
+      "learning_rate": 1.3156003537391248e-06,
+      "loss": 0.2465,
+      "step": 4450
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 5.40625,
+      "learning_rate": 1.2965774847106273e-06,
+      "loss": 0.2042,
+      "step": 4460
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.1875,
+      "learning_rate": 1.277672640004936e-06,
+      "loss": 0.2283,
+      "step": 4470
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 6.375,
+      "learning_rate": 1.2588864221002978e-06,
+      "loss": 0.2228,
+      "step": 4480
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.2402194296944364e-06,
+      "loss": 0.2188,
+      "step": 4490
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.71875,
+      "learning_rate": 1.2216722576854861e-06,
+      "loss": 0.2232,
+      "step": 4500
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 5.09375,
+      "learning_rate": 1.203245497153026e-06,
+      "loss": 0.2312,
+      "step": 4510
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.21875,
+      "learning_rate": 1.18493973533924e-06,
+      "loss": 0.247,
+      "step": 4520
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 5.375,
+      "learning_rate": 1.1667555556302097e-06,
+      "loss": 0.2251,
+      "step": 4530
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 5.34375,
+      "learning_rate": 1.1486935375373127e-06,
+      "loss": 0.2329,
+      "step": 4540
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.75,
+      "learning_rate": 1.130754256678766e-06,
+      "loss": 0.2178,
+      "step": 4550
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.96875,
+      "learning_rate": 1.1129382847612708e-06,
+      "loss": 0.234,
+      "step": 4560
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 4.78125,
+      "learning_rate": 1.0952461895617983e-06,
+      "loss": 0.2456,
+      "step": 4570
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.0776785349094975e-06,
+      "loss": 0.2266,
+      "step": 4580
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.71875,
+      "learning_rate": 1.060235880667717e-06,
+      "loss": 0.235,
+      "step": 4590
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.8125,
+      "learning_rate": 1.0429187827161746e-06,
+      "loss": 0.2184,
+      "step": 4600
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.0257277929332332e-06,
+      "loss": 0.2334,
+      "step": 4610
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.09375,
+      "learning_rate": 1.0086634591783196e-06,
+      "loss": 0.2412,
+      "step": 4620
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 6.5,
+      "learning_rate": 9.917263252744553e-07,
+      "loss": 0.1987,
+      "step": 4630
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.0625,
+      "learning_rate": 9.749169309909385e-07,
+      "loss": 0.2434,
+      "step": 4640
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 7.0625,
+      "learning_rate": 9.58235812026128e-07,
+      "loss": 0.2253,
+      "step": 4650
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 5.625,
+      "learning_rate": 9.416834999903862e-07,
+      "loss": 0.2238,
+      "step": 4660
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 4.15625,
+      "learning_rate": 9.252605223891209e-07,
+      "loss": 0.2068,
+      "step": 4670
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.08967402605988e-07,
+      "loss": 0.2214,
+      "step": 4680
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 5.375,
+      "learning_rate": 8.928046598862066e-07,
+      "loss": 0.246,
+      "step": 4690
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.75,
+      "learning_rate": 8.767728093200061e-07,
+      "loss": 0.2271,
+      "step": 4700
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 5.25,
+      "learning_rate": 8.6087236182622e-07,
+      "loss": 0.2262,
+      "step": 4710
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 5.03125,
+      "learning_rate": 8.451038241359994e-07,
+      "loss": 0.2265,
+      "step": 4720
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.65625,
+      "learning_rate": 8.294676987766587e-07,
+      "loss": 0.2048,
+      "step": 4730
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.71875,
+      "learning_rate": 8.139644840556704e-07,
+      "loss": 0.2055,
+      "step": 4740
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 5.1875,
+      "learning_rate": 7.985946740447792e-07,
+      "loss": 0.2137,
+      "step": 4750
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.833587585642527e-07,
+      "loss": 0.2166,
+      "step": 4760
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 5.0625,
+      "learning_rate": 7.682572231672813e-07,
+      "loss": 0.2296,
+      "step": 4770
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.90625,
+      "learning_rate": 7.532905491244924e-07,
+      "loss": 0.2137,
+      "step": 4780
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 5.21875,
+      "learning_rate": 7.384592134086233e-07,
+      "loss": 0.2176,
+      "step": 4790
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.5,
+      "learning_rate": 7.237636886793159e-07,
+      "loss": 0.1989,
+      "step": 4800
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 4.21875,
+      "learning_rate": 7.092044432680489e-07,
+      "loss": 0.2245,
+      "step": 4810
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.625,
+      "learning_rate": 6.947819411632223e-07,
+      "loss": 0.2094,
+      "step": 4820
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.804966419953641e-07,
+      "loss": 0.2278,
+      "step": 4830
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.6875,
+      "learning_rate": 6.663490010224811e-07,
+      "loss": 0.221,
+      "step": 4840
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.5,
+      "learning_rate": 6.523394691155566e-07,
+      "loss": 0.2334,
+      "step": 4850
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 5.65625,
+      "learning_rate": 6.384684927441764e-07,
+      "loss": 0.2319,
+      "step": 4860
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.78125,
+      "learning_rate": 6.247365139623007e-07,
+      "loss": 0.2178,
+      "step": 4870
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 6.84375,
+      "learning_rate": 6.111439703941796e-07,
+      "loss": 0.2234,
+      "step": 4880
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.875,
+      "learning_rate": 5.976912952204017e-07,
+      "loss": 0.2498,
+      "step": 4890
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.875,
+      "learning_rate": 5.84378917164094e-07,
+      "loss": 0.218,
+      "step": 4900
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.3125,
+      "learning_rate": 5.712072604772539e-07,
+      "loss": 0.2444,
+      "step": 4910
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 5.1875,
+      "learning_rate": 5.581767449272346e-07,
+      "loss": 0.2188,
+      "step": 4920
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 6.0,
+      "learning_rate": 5.452877857833611e-07,
+      "loss": 0.2201,
+      "step": 4930
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 5.46875,
+      "learning_rate": 5.32540793803703e-07,
+      "loss": 0.2227,
+      "step": 4940
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.8125,
+      "learning_rate": 5.199361752219756e-07,
+      "loss": 0.2306,
+      "step": 4950
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.875,
+      "learning_rate": 5.074743317346009e-07,
+      "loss": 0.2116,
+      "step": 4960
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.125,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.2283,
+      "step": 4970
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.829805540654547e-07,
+      "loss": 0.201,
+      "step": 4980
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.7094940047555713e-07,
+      "loss": 0.2241,
+      "step": 4990
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.590625831388834e-07,
+      "loss": 0.2211,
+      "step": 5000
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.4732048087625877e-07,
+      "loss": 0.2482,
+      "step": 5010
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 4.53125,
+      "learning_rate": 4.357234678965827e-07,
+      "loss": 0.2288,
+      "step": 5020
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 5.34375,
+      "learning_rate": 4.242719137849077e-07,
+      "loss": 0.2337,
+      "step": 5030
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 5.65625,
+      "learning_rate": 4.129661834906601e-07,
+      "loss": 0.2058,
+      "step": 5040
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.9375,
+      "learning_rate": 4.0180663731600623e-07,
+      "loss": 0.224,
+      "step": 5050
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.5625,
+      "learning_rate": 3.907936309043753e-07,
+      "loss": 0.219,
+      "step": 5060
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.7992751522912265e-07,
+      "loss": 0.2273,
+      "step": 5070
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.5,
+      "learning_rate": 3.6920863658234387e-07,
+      "loss": 0.2172,
+      "step": 5080
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.6875,
+      "learning_rate": 3.586373365638385e-07,
+      "loss": 0.2104,
+      "step": 5090
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.4821395207022767e-07,
+      "loss": 0.2324,
+      "step": 5100
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.5,
+      "learning_rate": 3.3793881528421223e-07,
+      "loss": 0.2118,
+      "step": 5110
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.2781225366398885e-07,
+      "loss": 0.2551,
+      "step": 5120
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 5.125,
+      "learning_rate": 3.17834589932815e-07,
+      "loss": 0.2037,
+      "step": 5130
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.080061420687241e-07,
+      "loss": 0.2105,
+      "step": 5140
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 4.875,
+      "learning_rate": 2.9832722329439015e-07,
+      "loss": 0.2272,
+      "step": 5150
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 5.25,
+      "learning_rate": 2.8879814206714597e-07,
+      "loss": 0.2047,
+      "step": 5160
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.7941920206915443e-07,
+      "loss": 0.2639,
+      "step": 5170
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.5625,
+      "learning_rate": 2.701907021977296e-07,
+      "loss": 0.2215,
+      "step": 5180
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.71875,
+      "learning_rate": 2.6111293655581185e-07,
+      "loss": 0.2357,
+      "step": 5190
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 5.53125,
+      "learning_rate": 2.5218619444259186e-07,
+      "loss": 0.2235,
+      "step": 5200
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 4.8125,
+      "learning_rate": 2.434107603442959e-07,
+      "loss": 0.2158,
+      "step": 5210
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.5,
+      "learning_rate": 2.347869139251169e-07,
+      "loss": 0.2213,
+      "step": 5220
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.84375,
+      "learning_rate": 2.2631493001829984e-07,
+      "loss": 0.2249,
+      "step": 5230
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.625,
+      "learning_rate": 2.179950786173879e-07,
+      "loss": 0.2311,
+      "step": 5240
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.84375,
+      "learning_rate": 2.098276248676151e-07,
+      "loss": 0.22,
+      "step": 5250
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.90625,
+      "learning_rate": 2.0181282905745615e-07,
+      "loss": 0.2438,
+      "step": 5260
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 4.125,
+      "learning_rate": 1.939509466103312e-07,
+      "loss": 0.2152,
+      "step": 5270
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.8624222807646753e-07,
+      "loss": 0.2105,
+      "step": 5280
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.15625,
+      "learning_rate": 1.7868691912491355e-07,
+      "loss": 0.2286,
+      "step": 5290
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.375,
+      "learning_rate": 1.712852605357096e-07,
+      "loss": 0.2326,
+      "step": 5300
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 7.21875,
+      "learning_rate": 1.6403748819221464e-07,
+      "loss": 0.2364,
+      "step": 5310
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.5694383307358896e-07,
+      "loss": 0.2311,
+      "step": 5320
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 5.5,
+      "learning_rate": 1.5000452124743326e-07,
+      "loss": 0.239,
+      "step": 5330
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.28125,
+      "learning_rate": 1.432197738625829e-07,
+      "loss": 0.2127,
+      "step": 5340
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.53125,
+      "learning_rate": 1.3658980714206238e-07,
+      "loss": 0.2314,
+      "step": 5350
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.15625,
+      "learning_rate": 1.3011483237619306e-07,
+      "loss": 0.2147,
+      "step": 5360
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.2379505591585905e-07,
+      "loss": 0.2227,
+      "step": 5370
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.1763067916593263e-07,
+      "loss": 0.2327,
+      "step": 5380
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 4.375,
+      "learning_rate": 1.1162189857885364e-07,
+      "loss": 0.2124,
+      "step": 5390
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.46875,
+      "learning_rate": 1.0576890564837184e-07,
+      "loss": 0.2294,
+      "step": 5400
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 5.8125,
+      "learning_rate": 1.000718869034395e-07,
+      "loss": 0.2313,
+      "step": 5410
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.21875,
+      "learning_rate": 9.453102390227176e-08,
+      "loss": 0.2288,
+      "step": 5420
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.53125,
+      "learning_rate": 8.914649322655844e-08,
+      "loss": 0.2232,
+      "step": 5430
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 4.5625,
+      "learning_rate": 8.391846647583468e-08,
+      "loss": 0.2146,
+      "step": 5440
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 4.875,
+      "learning_rate": 7.884711026201586e-08,
+      "loss": 0.2203,
+      "step": 5450
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 5.375,
+      "learning_rate": 7.393258620408627e-08,
+      "loss": 0.2145,
+      "step": 5460
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 5.03125,
+      "learning_rate": 6.917505092294663e-08,
+      "loss": 0.2318,
+      "step": 5470
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 5.84375,
+      "learning_rate": 6.457465603642577e-08,
+      "loss": 0.2284,
+      "step": 5480
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 5.5625,
+      "learning_rate": 6.013154815444733e-08,
+      "loss": 0.2027,
+      "step": 5490
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 5.0,
+      "learning_rate": 5.584586887435739e-08,
+      "loss": 0.2309,
+      "step": 5500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.28125,
+      "learning_rate": 5.171775477641139e-08,
+      "loss": 0.2315,
+      "step": 5510
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.774733741942206e-08,
+      "loss": 0.1957,
+      "step": 5520
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.9375,
+      "learning_rate": 4.393474333656833e-08,
+      "loss": 0.2238,
+      "step": 5530
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 4.375,
+      "learning_rate": 4.0280094031359685e-08,
+      "loss": 0.2117,
+      "step": 5540
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.09375,
+      "learning_rate": 3.678350597376645e-08,
+      "loss": 0.2129,
+      "step": 5550
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.344509059650613e-08,
+      "loss": 0.2214,
+      "step": 5560
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 5.09375,
+      "learning_rate": 3.0264954291494006e-08,
+      "loss": 0.2495,
+      "step": 5570
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 5.84375,
+      "learning_rate": 2.7243198406453062e-08,
+      "loss": 0.226,
+      "step": 5580
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 6.25,
+      "learning_rate": 2.4379919241679373e-08,
+      "loss": 0.2417,
+      "step": 5590
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 5.53125,
+      "learning_rate": 2.167520804698009e-08,
+      "loss": 0.2411,
+      "step": 5600
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 5.65625,
+      "learning_rate": 1.9129151018759117e-08,
+      "loss": 0.216,
+      "step": 5610
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 6.28125,
+      "learning_rate": 1.6741829297274303e-08,
+      "loss": 0.223,
+      "step": 5620
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.40625,
+      "learning_rate": 1.451331896405006e-08,
+      "loss": 0.2077,
+      "step": 5630
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.84375,
+      "learning_rate": 1.2443691039452644e-08,
+      "loss": 0.252,
+      "step": 5640
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 5.375,
+      "learning_rate": 1.0533011480426403e-08,
+      "loss": 0.2554,
+      "step": 5650
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.5625,
+      "learning_rate": 8.781341178393244e-09,
+      "loss": 0.2399,
+      "step": 5660
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.188735957309734e-09,
+      "loss": 0.2202,
+      "step": 5670
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 6.5,
+      "learning_rate": 5.755246571891304e-09,
+      "loss": 0.2225,
+      "step": 5680
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 5.3125,
+      "learning_rate": 4.4809187059913216e-09,
+      "loss": 0.2338,
+      "step": 5690
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.96875,
+      "learning_rate": 3.365792971148918e-09,
+      "loss": 0.2187,
+      "step": 5700
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 5.09375,
+      "learning_rate": 2.409904905289473e-09,
+      "loss": 0.2262,
+      "step": 5710
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 3.625,
+      "learning_rate": 1.6132849715988496e-09,
+      "loss": 0.2174,
+      "step": 5720
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 4.0625,
+      "learning_rate": 9.75958557545842e-10,
+      "loss": 0.2178,
+      "step": 5730
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.03125,
+      "learning_rate": 4.979459740778181e-10,
+      "loss": 0.2309,
+      "step": 5740
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.59375,
+      "learning_rate": 1.7926245497179584e-10,
+      "loss": 0.1973,
+      "step": 5750
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.4375,
+      "learning_rate": 1.9918156347609184e-11,
+      "loss": 0.2183,
+      "step": 5760
+    },
+    {
+      "epoch": 1.0,
+      "step": 5765,
+      "total_flos": 1.4509829557850112e+18,
+      "train_loss": 0.25344288444270907,
+      "train_runtime": 45378.653,
+      "train_samples_per_second": 2.033,
+      "train_steps_per_second": 0.127
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5765,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "total_flos": 1.4509829557850112e+18,
+  "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:d3856dc714dd427422a911d8a5f684ee5dfb1af0a69336be0645fa21575945c4
+size 5112