Upload checkpoint-9000

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,47 @@
+---
+license: apache-2.0
+language:
+- ko
+- en
+tags:
+- text-generation
+- pytorch
+- causal-lm
+library_name: transformers
+---
+
+# gemma3-1b-cpt-final-checkpoint-9000
+
+이 모델은 파인튜닝된 언어 모델 체크포인트입니다.
+
+## 모델 정보
+- **베이스 모델**: gemma3-1b-cpt-final
+- **체크포인트**: checkpoint-9000
+- **타입**: Causal Language Model
+- **라이선스**: Apache 2.0
+
+## 사용 방법
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "NTIS/gemma3-1b-cpt-final-checkpoint-9000"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+# 텍스트 생성
+text = "안녕하세요"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+```
+
+## 주의사항
+- 이 모델은 연구/실험 목적으로 제공됩니다
+- 상업적 사용 전에 라이선스를 확인하세요

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9656f474dab758ad81706f6228dfe9def4a941080b3e0a1b35d6879d692c8a1f
+size 3999582960

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5116d9b328542383c26c3e32268e86a595f48cf610cc372854aff1f3d6c50f62
+size 1207959680

model.safetensors.index.json

@@ -0,0 +1,348 @@
+{
+  "metadata": {
+    "total_size": 5207503360
+  },
+  "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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00001-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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00001-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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c39f3ed1194fa9722bfe597f72d66a992c6d1319fc7baccd1e14eb8c6089898
+size 7999404498

pytorch_model_fsdp.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038074afc576b23da4a7ca606ec12459fefba37598efd3cd92a0b001ccd6c38e
+size 5207811855

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49155bf5be2143d19dc963e707b2cf99f36392e32382c71c19accef16a28abc4
+size 15920

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9603e347e54861f9951f5b045c477ae8dd40b36bf5f506a5c51a4e0f5e406439
+size 15920

rng_state_10.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b36133d32c26198d5b72c654e073132d3fc0d0274cdba8a3d84ea95c4cbfecf
+size 15933

rng_state_11.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8899dd63a2505bab0c917a89ae69bca7524ea1692d97b14b6c133c61008d371f
+size 15933

rng_state_12.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1b64f3f3d75bd2ddc5b309f0290a3398285bbacdd2ca2f27c9f5dfcfe9c793
+size 15933

rng_state_13.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead61d6d4ab8f666a09ecb54772069c902aab6da73b02a7dbb3d565c94414b6f
+size 15933

rng_state_14.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8daf832cb7794c740bebb1e2c957ac6c44345f1aaa186d867adda650a106388f
+size 15933

rng_state_15.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e734dbf5964ac54f7b12279998a488cec909c86caef5e3ea64fbadd416bff8fa
+size 15933

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27f7ac4f0baa34e6c46f3f5a4202eb38239e820c598ed6042647efaa235a7e3
+size 15920

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76da9eea4ad67c02aa2a2dabc4e63c1ed589272e8a61103582f544fe7da04cbe
+size 15920

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d786c78894a70cfd2ce6c6a10979368c67528018770933dd58f79da01be2f05d
+size 15920

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead3705195901c25aaeba3c9eb88da984a9d8ce585c5a92823da344bf036f900
+size 15920

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f8a446ab26361d1891464fead11f5883a0142ca30674dcef60a24567946ac9
+size 15920

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73ea20d6f62ee2d6382f35171f28ec9ccd79413e7f8cb665467277a7af8ff4f
+size 15920

rng_state_8.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f5d7e9d81767989631dea79d2d4d8a4308fa0e970351fa69d6e7a16b612238
+size 15920

rng_state_9.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3e1fdd2d34bc37a294cf97a9d3a9ff1dc15e3ec523ec5fc06c6613bbaa97c6
+size 15920

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce50378452437349f5819cf4ac065a5f1a14c8ac7f44a0913406a6430cd5be9e
+size 1064

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

trainer_state.json

@@ -0,0 +1,1294 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02335995286480622,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00012977751591559012,
+      "grad_norm": 29.529769897460938,
+      "learning_rate": 2.1196980511755674e-09,
+      "loss": 2.2098,
+      "step": 50
+    },
+    {
+      "epoch": 0.00025955503183118023,
+      "grad_norm": 30.7341251373291,
+      "learning_rate": 4.282655246252677e-09,
+      "loss": 2.2367,
+      "step": 100
+    },
+    {
+      "epoch": 0.00038933254774677035,
+      "grad_norm": 29.822181701660156,
+      "learning_rate": 6.4456124413297865e-09,
+      "loss": 2.198,
+      "step": 150
+    },
+    {
+      "epoch": 0.0005191100636623605,
+      "grad_norm": 28.564294815063477,
+      "learning_rate": 8.608569636406895e-09,
+      "loss": 2.2167,
+      "step": 200
+    },
+    {
+      "epoch": 0.0006488875795779505,
+      "grad_norm": 28.514026641845703,
+      "learning_rate": 1.0771526831484006e-08,
+      "loss": 2.2001,
+      "step": 250
+    },
+    {
+      "epoch": 0.0007786650954935407,
+      "grad_norm": 29.033863067626953,
+      "learning_rate": 1.2934484026561114e-08,
+      "loss": 2.1908,
+      "step": 300
+    },
+    {
+      "epoch": 0.0009084426114091308,
+      "grad_norm": 4.49394416809082,
+      "learning_rate": 1.5097441221638225e-08,
+      "loss": 2.1841,
+      "step": 350
+    },
+    {
+      "epoch": 0.001038220127324721,
+      "grad_norm": 2.1610796451568604,
+      "learning_rate": 1.7260398416715337e-08,
+      "loss": 2.1702,
+      "step": 400
+    },
+    {
+      "epoch": 0.0011679976432403109,
+      "grad_norm": 1.9879209995269775,
+      "learning_rate": 1.9423355611792444e-08,
+      "loss": 2.1613,
+      "step": 450
+    },
+    {
+      "epoch": 0.001297775159155901,
+      "grad_norm": 1.880299687385559,
+      "learning_rate": 2.1586312806869556e-08,
+      "loss": 2.1529,
+      "step": 500
+    },
+    {
+      "epoch": 0.0014275526750714912,
+      "grad_norm": 1.7597101926803589,
+      "learning_rate": 2.3749270001946664e-08,
+      "loss": 2.1641,
+      "step": 550
+    },
+    {
+      "epoch": 0.0015573301909870814,
+      "grad_norm": 1.5660640001296997,
+      "learning_rate": 2.591222719702377e-08,
+      "loss": 2.1501,
+      "step": 600
+    },
+    {
+      "epoch": 0.0016871077069026714,
+      "grad_norm": 1.5481892824172974,
+      "learning_rate": 2.8075184392100883e-08,
+      "loss": 2.1583,
+      "step": 650
+    },
+    {
+      "epoch": 0.0018168852228182615,
+      "grad_norm": 1.525515079498291,
+      "learning_rate": 3.0238141587177994e-08,
+      "loss": 2.1547,
+      "step": 700
+    },
+    {
+      "epoch": 0.0019466627387338517,
+      "grad_norm": 1.4705111980438232,
+      "learning_rate": 3.24010987822551e-08,
+      "loss": 2.1365,
+      "step": 750
+    },
+    {
+      "epoch": 0.002076440254649442,
+      "grad_norm": 1.3471802473068237,
+      "learning_rate": 3.4564055977332216e-08,
+      "loss": 2.1777,
+      "step": 800
+    },
+    {
+      "epoch": 0.002206217770565032,
+      "grad_norm": 1.3963252305984497,
+      "learning_rate": 3.6727013172409324e-08,
+      "loss": 2.1356,
+      "step": 850
+    },
+    {
+      "epoch": 0.0023359952864806218,
+      "grad_norm": 1.2665836811065674,
+      "learning_rate": 3.888997036748643e-08,
+      "loss": 2.1565,
+      "step": 900
+    },
+    {
+      "epoch": 0.002465772802396212,
+      "grad_norm": 1.4085878133773804,
+      "learning_rate": 4.105292756256354e-08,
+      "loss": 2.1497,
+      "step": 950
+    },
+    {
+      "epoch": 0.002595550318311802,
+      "grad_norm": 1.4020620584487915,
+      "learning_rate": 4.3215884757640654e-08,
+      "loss": 2.1549,
+      "step": 1000
+    },
+    {
+      "epoch": 0.002725327834227392,
+      "grad_norm": 1.5391197204589844,
+      "learning_rate": 4.5378841952717755e-08,
+      "loss": 2.1519,
+      "step": 1050
+    },
+    {
+      "epoch": 0.0028551053501429825,
+      "grad_norm": 1.2532999515533447,
+      "learning_rate": 4.754179914779487e-08,
+      "loss": 2.1411,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0029848828660585724,
+      "grad_norm": 1.2143096923828125,
+      "learning_rate": 4.970475634287198e-08,
+      "loss": 2.1435,
+      "step": 1150
+    },
+    {
+      "epoch": 0.003114660381974163,
+      "grad_norm": 1.4227972030639648,
+      "learning_rate": 5.1867713537949086e-08,
+      "loss": 2.142,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0032444378978897528,
+      "grad_norm": 1.0749537944793701,
+      "learning_rate": 5.40306707330262e-08,
+      "loss": 2.1134,
+      "step": 1250
+    },
+    {
+      "epoch": 0.0033742154138053427,
+      "grad_norm": 1.169149398803711,
+      "learning_rate": 5.619362792810331e-08,
+      "loss": 2.1215,
+      "step": 1300
+    },
+    {
+      "epoch": 0.003503992929720933,
+      "grad_norm": 1.3452564477920532,
+      "learning_rate": 5.8356585123180416e-08,
+      "loss": 2.1524,
+      "step": 1350
+    },
+    {
+      "epoch": 0.003633770445636523,
+      "grad_norm": 1.3610825538635254,
+      "learning_rate": 6.051954231825752e-08,
+      "loss": 2.1389,
+      "step": 1400
+    },
+    {
+      "epoch": 0.003763547961552113,
+      "grad_norm": 1.2172240018844604,
+      "learning_rate": 6.268249951333464e-08,
+      "loss": 2.1428,
+      "step": 1450
+    },
+    {
+      "epoch": 0.0038933254774677034,
+      "grad_norm": 1.1681610345840454,
+      "learning_rate": 6.484545670841174e-08,
+      "loss": 2.1253,
+      "step": 1500
+    },
+    {
+      "epoch": 0.004023102993383294,
+      "grad_norm": 1.0709235668182373,
+      "learning_rate": 6.700841390348886e-08,
+      "loss": 2.1533,
+      "step": 1550
+    },
+    {
+      "epoch": 0.004152880509298884,
+      "grad_norm": 1.2001404762268066,
+      "learning_rate": 6.917137109856597e-08,
+      "loss": 2.1371,
+      "step": 1600
+    },
+    {
+      "epoch": 0.004282658025214474,
+      "grad_norm": 1.2642266750335693,
+      "learning_rate": 7.133432829364308e-08,
+      "loss": 2.129,
+      "step": 1650
+    },
+    {
+      "epoch": 0.004412435541130064,
+      "grad_norm": 1.030280590057373,
+      "learning_rate": 7.349728548872018e-08,
+      "loss": 2.128,
+      "step": 1700
+    },
+    {
+      "epoch": 0.004542213057045654,
+      "grad_norm": 1.4037690162658691,
+      "learning_rate": 7.566024268379729e-08,
+      "loss": 2.1383,
+      "step": 1750
+    },
+    {
+      "epoch": 0.0046719905729612436,
+      "grad_norm": 1.1600065231323242,
+      "learning_rate": 7.78231998788744e-08,
+      "loss": 2.1193,
+      "step": 1800
+    },
+    {
+      "epoch": 0.004801768088876834,
+      "grad_norm": 1.2075531482696533,
+      "learning_rate": 7.998615707395151e-08,
+      "loss": 2.1126,
+      "step": 1850
+    },
+    {
+      "epoch": 0.004931545604792424,
+      "grad_norm": 1.1088111400604248,
+      "learning_rate": 8.214911426902863e-08,
+      "loss": 2.1394,
+      "step": 1900
+    },
+    {
+      "epoch": 0.005061323120708014,
+      "grad_norm": 1.195092797279358,
+      "learning_rate": 8.431207146410574e-08,
+      "loss": 2.1359,
+      "step": 1950
+    },
+    {
+      "epoch": 0.005191100636623604,
+      "grad_norm": 1.1595982313156128,
+      "learning_rate": 8.647502865918283e-08,
+      "loss": 2.1366,
+      "step": 2000
+    },
+    {
+      "epoch": 0.005320878152539194,
+      "grad_norm": 1.1727768182754517,
+      "learning_rate": 8.863798585425995e-08,
+      "loss": 2.1106,
+      "step": 2050
+    },
+    {
+      "epoch": 0.005450655668454784,
+      "grad_norm": 1.2424023151397705,
+      "learning_rate": 9.080094304933706e-08,
+      "loss": 2.1339,
+      "step": 2100
+    },
+    {
+      "epoch": 0.005580433184370375,
+      "grad_norm": 1.2954424619674683,
+      "learning_rate": 9.296390024441417e-08,
+      "loss": 2.1107,
+      "step": 2150
+    },
+    {
+      "epoch": 0.005710210700285965,
+      "grad_norm": 1.0388058423995972,
+      "learning_rate": 9.512685743949129e-08,
+      "loss": 2.118,
+      "step": 2200
+    },
+    {
+      "epoch": 0.005839988216201555,
+      "grad_norm": 4.136488914489746,
+      "learning_rate": 9.728981463456838e-08,
+      "loss": 2.1159,
+      "step": 2250
+    },
+    {
+      "epoch": 0.005969765732117145,
+      "grad_norm": 1.0597412586212158,
+      "learning_rate": 9.945277182964549e-08,
+      "loss": 2.1303,
+      "step": 2300
+    },
+    {
+      "epoch": 0.006099543248032735,
+      "grad_norm": 1.0780799388885498,
+      "learning_rate": 1.0161572902472261e-07,
+      "loss": 2.1095,
+      "step": 2350
+    },
+    {
+      "epoch": 0.006229320763948326,
+      "grad_norm": 1.2739732265472412,
+      "learning_rate": 1.0377868621979972e-07,
+      "loss": 2.1264,
+      "step": 2400
+    },
+    {
+      "epoch": 0.0063590982798639156,
+      "grad_norm": 3.3836748600006104,
+      "learning_rate": 1.0594164341487683e-07,
+      "loss": 2.1183,
+      "step": 2450
+    },
+    {
+      "epoch": 0.0064888757957795055,
+      "grad_norm": 1.269440770149231,
+      "learning_rate": 1.0810460060995395e-07,
+      "loss": 2.1243,
+      "step": 2500
+    },
+    {
+      "epoch": 0.0066186533116950955,
+      "grad_norm": 1.1834193468093872,
+      "learning_rate": 1.1026755780503104e-07,
+      "loss": 2.1207,
+      "step": 2550
+    },
+    {
+      "epoch": 0.006748430827610685,
+      "grad_norm": 1.2411448955535889,
+      "learning_rate": 1.1243051500010815e-07,
+      "loss": 2.1201,
+      "step": 2600
+    },
+    {
+      "epoch": 0.006878208343526275,
+      "grad_norm": 1.1330574750900269,
+      "learning_rate": 1.1459347219518527e-07,
+      "loss": 2.1125,
+      "step": 2650
+    },
+    {
+      "epoch": 0.007007985859441866,
+      "grad_norm": 1.199055790901184,
+      "learning_rate": 1.1675642939026238e-07,
+      "loss": 2.13,
+      "step": 2700
+    },
+    {
+      "epoch": 0.007137763375357456,
+      "grad_norm": 1.2272251844406128,
+      "learning_rate": 1.1891938658533949e-07,
+      "loss": 2.1239,
+      "step": 2750
+    },
+    {
+      "epoch": 0.007267540891273046,
+      "grad_norm": 1.1257809400558472,
+      "learning_rate": 1.2108234378041658e-07,
+      "loss": 2.12,
+      "step": 2800
+    },
+    {
+      "epoch": 0.007397318407188636,
+      "grad_norm": 1.1028845310211182,
+      "learning_rate": 1.2324530097549372e-07,
+      "loss": 2.1227,
+      "step": 2850
+    },
+    {
+      "epoch": 0.007527095923104226,
+      "grad_norm": 1.2196507453918457,
+      "learning_rate": 1.254082581705708e-07,
+      "loss": 2.1241,
+      "step": 2900
+    },
+    {
+      "epoch": 0.007656873439019816,
+      "grad_norm": 1.0342847108840942,
+      "learning_rate": 1.275712153656479e-07,
+      "loss": 2.1148,
+      "step": 2950
+    },
+    {
+      "epoch": 0.007786650954935407,
+      "grad_norm": 1.1587927341461182,
+      "learning_rate": 1.2973417256072504e-07,
+      "loss": 2.1293,
+      "step": 3000
+    },
+    {
+      "epoch": 0.007916428470850997,
+      "grad_norm": 1.1751174926757812,
+      "learning_rate": 1.3189712975580215e-07,
+      "loss": 2.1084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.008046205986766588,
+      "grad_norm": 12.056378364562988,
+      "learning_rate": 1.3406008695087926e-07,
+      "loss": 2.103,
+      "step": 3100
+    },
+    {
+      "epoch": 0.008175983502682177,
+      "grad_norm": 1.0078307390213013,
+      "learning_rate": 1.3622304414595637e-07,
+      "loss": 2.1345,
+      "step": 3150
+    },
+    {
+      "epoch": 0.008305761018597767,
+      "grad_norm": 1.0840246677398682,
+      "learning_rate": 1.3838600134103347e-07,
+      "loss": 2.1151,
+      "step": 3200
+    },
+    {
+      "epoch": 0.008435538534513357,
+      "grad_norm": 1.213310956954956,
+      "learning_rate": 1.4054895853611058e-07,
+      "loss": 2.1275,
+      "step": 3250
+    },
+    {
+      "epoch": 0.008565316050428947,
+      "grad_norm": 1.2903615236282349,
+      "learning_rate": 1.427119157311877e-07,
+      "loss": 2.1105,
+      "step": 3300
+    },
+    {
+      "epoch": 0.008695093566344536,
+      "grad_norm": 1.1746351718902588,
+      "learning_rate": 1.448748729262648e-07,
+      "loss": 2.1344,
+      "step": 3350
+    },
+    {
+      "epoch": 0.008824871082260127,
+      "grad_norm": 1.1928184032440186,
+      "learning_rate": 1.470378301213419e-07,
+      "loss": 2.1278,
+      "step": 3400
+    },
+    {
+      "epoch": 0.008954648598175718,
+      "grad_norm": 1.1132676601409912,
+      "learning_rate": 1.4920078731641904e-07,
+      "loss": 2.1134,
+      "step": 3450
+    },
+    {
+      "epoch": 0.009084426114091307,
+      "grad_norm": 1.4539573192596436,
+      "learning_rate": 1.5136374451149612e-07,
+      "loss": 2.0943,
+      "step": 3500
+    },
+    {
+      "epoch": 0.009214203630006898,
+      "grad_norm": 1.176128625869751,
+      "learning_rate": 1.5352670170657323e-07,
+      "loss": 2.1025,
+      "step": 3550
+    },
+    {
+      "epoch": 0.009343981145922487,
+      "grad_norm": 1.0798020362854004,
+      "learning_rate": 1.5568965890165036e-07,
+      "loss": 2.0946,
+      "step": 3600
+    },
+    {
+      "epoch": 0.009473758661838078,
+      "grad_norm": 1.1570450067520142,
+      "learning_rate": 1.5785261609672747e-07,
+      "loss": 2.1119,
+      "step": 3650
+    },
+    {
+      "epoch": 0.009603536177753669,
+      "grad_norm": 0.9933484792709351,
+      "learning_rate": 1.6001557329180458e-07,
+      "loss": 2.1171,
+      "step": 3700
+    },
+    {
+      "epoch": 0.009733313693669258,
+      "grad_norm": 1.1642405986785889,
+      "learning_rate": 1.6217853048688166e-07,
+      "loss": 2.1047,
+      "step": 3750
+    },
+    {
+      "epoch": 0.009863091209584849,
+      "grad_norm": 1.266423225402832,
+      "learning_rate": 1.643414876819588e-07,
+      "loss": 2.0984,
+      "step": 3800
+    },
+    {
+      "epoch": 0.009992868725500438,
+      "grad_norm": 1.0179153680801392,
+      "learning_rate": 1.665044448770359e-07,
+      "loss": 2.0977,
+      "step": 3850
+    },
+    {
+      "epoch": 0.010122646241416029,
+      "grad_norm": 1.0938276052474976,
+      "learning_rate": 1.68667402072113e-07,
+      "loss": 2.1249,
+      "step": 3900
+    },
+    {
+      "epoch": 0.01025242375733162,
+      "grad_norm": 1.1981333494186401,
+      "learning_rate": 1.7083035926719012e-07,
+      "loss": 2.1186,
+      "step": 3950
+    },
+    {
+      "epoch": 0.010382201273247208,
+      "grad_norm": 1.238035798072815,
+      "learning_rate": 1.7299331646226725e-07,
+      "loss": 2.1254,
+      "step": 4000
+    },
+    {
+      "epoch": 0.0105119787891628,
+      "grad_norm": 1.0942214727401733,
+      "learning_rate": 1.7515627365734433e-07,
+      "loss": 2.0972,
+      "step": 4050
+    },
+    {
+      "epoch": 0.010641756305078388,
+      "grad_norm": 1.1418002843856812,
+      "learning_rate": 1.7731923085242144e-07,
+      "loss": 2.1286,
+      "step": 4100
+    },
+    {
+      "epoch": 0.01077153382099398,
+      "grad_norm": 2.164984703063965,
+      "learning_rate": 1.7948218804749858e-07,
+      "loss": 2.1195,
+      "step": 4150
+    },
+    {
+      "epoch": 0.010901311336909568,
+      "grad_norm": 1.119779109954834,
+      "learning_rate": 1.8164514524257566e-07,
+      "loss": 2.1242,
+      "step": 4200
+    },
+    {
+      "epoch": 0.011031088852825159,
+      "grad_norm": 1.0193780660629272,
+      "learning_rate": 1.8380810243765277e-07,
+      "loss": 2.0951,
+      "step": 4250
+    },
+    {
+      "epoch": 0.01116086636874075,
+      "grad_norm": 1.1878997087478638,
+      "learning_rate": 1.859710596327299e-07,
+      "loss": 2.1067,
+      "step": 4300
+    },
+    {
+      "epoch": 0.011290643884656339,
+      "grad_norm": 1.048115849494934,
+      "learning_rate": 1.8813401682780698e-07,
+      "loss": 2.0861,
+      "step": 4350
+    },
+    {
+      "epoch": 0.01142042140057193,
+      "grad_norm": 1.1059479713439941,
+      "learning_rate": 1.9029697402288412e-07,
+      "loss": 2.1204,
+      "step": 4400
+    },
+    {
+      "epoch": 0.011550198916487519,
+      "grad_norm": 0.942563533782959,
+      "learning_rate": 1.9245993121796122e-07,
+      "loss": 2.1256,
+      "step": 4450
+    },
+    {
+      "epoch": 0.01167997643240311,
+      "grad_norm": 3.292470932006836,
+      "learning_rate": 1.946228884130383e-07,
+      "loss": 2.0964,
+      "step": 4500
+    },
+    {
+      "epoch": 0.0118097539483187,
+      "grad_norm": 1.131181001663208,
+      "learning_rate": 1.9678584560811544e-07,
+      "loss": 2.1079,
+      "step": 4550
+    },
+    {
+      "epoch": 0.01193953146423429,
+      "grad_norm": 1.1684244871139526,
+      "learning_rate": 1.9894880280319255e-07,
+      "loss": 2.0918,
+      "step": 4600
+    },
+    {
+      "epoch": 0.01206930898014988,
+      "grad_norm": 1.094470500946045,
+      "learning_rate": 2.0111175999826965e-07,
+      "loss": 2.1129,
+      "step": 4650
+    },
+    {
+      "epoch": 0.01219908649606547,
+      "grad_norm": 1.1580520868301392,
+      "learning_rate": 2.0327471719334676e-07,
+      "loss": 2.1175,
+      "step": 4700
+    },
+    {
+      "epoch": 0.01232886401198106,
+      "grad_norm": 1.110461711883545,
+      "learning_rate": 2.054376743884239e-07,
+      "loss": 2.1188,
+      "step": 4750
+    },
+    {
+      "epoch": 0.012458641527896651,
+      "grad_norm": 1.1533987522125244,
+      "learning_rate": 2.0760063158350098e-07,
+      "loss": 2.1072,
+      "step": 4800
+    },
+    {
+      "epoch": 0.01258841904381224,
+      "grad_norm": 1.3358995914459229,
+      "learning_rate": 2.0976358877857809e-07,
+      "loss": 2.1031,
+      "step": 4850
+    },
+    {
+      "epoch": 0.012718196559727831,
+      "grad_norm": 1.100576639175415,
+      "learning_rate": 2.119265459736552e-07,
+      "loss": 2.0903,
+      "step": 4900
+    },
+    {
+      "epoch": 0.01284797407564342,
+      "grad_norm": 1.1505376100540161,
+      "learning_rate": 2.140895031687323e-07,
+      "loss": 2.123,
+      "step": 4950
+    },
+    {
+      "epoch": 0.012977751591559011,
+      "grad_norm": 1.063899278640747,
+      "learning_rate": 2.1625246036380944e-07,
+      "loss": 2.0802,
+      "step": 5000
+    },
+    {
+      "epoch": 0.0131075291074746,
+      "grad_norm": 0.9469916224479675,
+      "learning_rate": 2.1841541755888652e-07,
+      "loss": 2.0917,
+      "step": 5050
+    },
+    {
+      "epoch": 0.013237306623390191,
+      "grad_norm": 1.1475921869277954,
+      "learning_rate": 2.2057837475396363e-07,
+      "loss": 2.116,
+      "step": 5100
+    },
+    {
+      "epoch": 0.013367084139305782,
+      "grad_norm": 1.5712428092956543,
+      "learning_rate": 2.2274133194904076e-07,
+      "loss": 2.1019,
+      "step": 5150
+    },
+    {
+      "epoch": 0.01349686165522137,
+      "grad_norm": 1.0301058292388916,
+      "learning_rate": 2.2490428914411784e-07,
+      "loss": 2.0985,
+      "step": 5200
+    },
+    {
+      "epoch": 0.013626639171136962,
+      "grad_norm": 1.1751989126205444,
+      "learning_rate": 2.2706724633919495e-07,
+      "loss": 2.1023,
+      "step": 5250
+    },
+    {
+      "epoch": 0.01375641668705255,
+      "grad_norm": 2.097857713699341,
+      "learning_rate": 2.2923020353427208e-07,
+      "loss": 2.1226,
+      "step": 5300
+    },
+    {
+      "epoch": 0.013886194202968142,
+      "grad_norm": 1.0331202745437622,
+      "learning_rate": 2.3139316072934916e-07,
+      "loss": 2.1205,
+      "step": 5350
+    },
+    {
+      "epoch": 0.014015971718883732,
+      "grad_norm": 1.0770936012268066,
+      "learning_rate": 2.335561179244263e-07,
+      "loss": 2.1037,
+      "step": 5400
+    },
+    {
+      "epoch": 0.014145749234799321,
+      "grad_norm": 1.1082065105438232,
+      "learning_rate": 2.357190751195034e-07,
+      "loss": 2.1027,
+      "step": 5450
+    },
+    {
+      "epoch": 0.014275526750714912,
+      "grad_norm": 1.2101250886917114,
+      "learning_rate": 2.378820323145805e-07,
+      "loss": 2.1103,
+      "step": 5500
+    },
+    {
+      "epoch": 0.014405304266630501,
+      "grad_norm": 1.163560152053833,
+      "learning_rate": 2.400449895096576e-07,
+      "loss": 2.1035,
+      "step": 5550
+    },
+    {
+      "epoch": 0.014535081782546092,
+      "grad_norm": 1.1837356090545654,
+      "learning_rate": 2.4220794670473476e-07,
+      "loss": 2.0891,
+      "step": 5600
+    },
+    {
+      "epoch": 0.014664859298461683,
+      "grad_norm": 1.2113701105117798,
+      "learning_rate": 2.4437090389981184e-07,
+      "loss": 2.1096,
+      "step": 5650
+    },
+    {
+      "epoch": 0.014794636814377272,
+      "grad_norm": 1.1284654140472412,
+      "learning_rate": 2.4653386109488897e-07,
+      "loss": 2.0948,
+      "step": 5700
+    },
+    {
+      "epoch": 0.014924414330292863,
+      "grad_norm": 1.4470899105072021,
+      "learning_rate": 2.4869681828996605e-07,
+      "loss": 2.0954,
+      "step": 5750
+    },
+    {
+      "epoch": 0.015054191846208452,
+      "grad_norm": 1.0791606903076172,
+      "learning_rate": 2.5085977548504314e-07,
+      "loss": 2.1022,
+      "step": 5800
+    },
+    {
+      "epoch": 0.015183969362124043,
+      "grad_norm": 1.1813191175460815,
+      "learning_rate": 2.5302273268012027e-07,
+      "loss": 2.1102,
+      "step": 5850
+    },
+    {
+      "epoch": 0.015313746878039632,
+      "grad_norm": 1.1993714570999146,
+      "learning_rate": 2.551856898751974e-07,
+      "loss": 2.0967,
+      "step": 5900
+    },
+    {
+      "epoch": 0.015443524393955223,
+      "grad_norm": 1.1809765100479126,
+      "learning_rate": 2.573486470702745e-07,
+      "loss": 2.1054,
+      "step": 5950
+    },
+    {
+      "epoch": 0.015573301909870814,
+      "grad_norm": 1.0799180269241333,
+      "learning_rate": 2.595116042653516e-07,
+      "loss": 2.1144,
+      "step": 6000
+    },
+    {
+      "epoch": 0.015703079425786404,
+      "grad_norm": 1.0349640846252441,
+      "learning_rate": 2.6167456146042875e-07,
+      "loss": 2.0978,
+      "step": 6050
+    },
+    {
+      "epoch": 0.015832856941701993,
+      "grad_norm": 0.9997969269752502,
+      "learning_rate": 2.6383751865550584e-07,
+      "loss": 2.1274,
+      "step": 6100
+    },
+    {
+      "epoch": 0.015962634457617583,
+      "grad_norm": 1.3014293909072876,
+      "learning_rate": 2.660004758505829e-07,
+      "loss": 2.0857,
+      "step": 6150
+    },
+    {
+      "epoch": 0.016092411973533175,
+      "grad_norm": 1.1863785982131958,
+      "learning_rate": 2.6816343304566005e-07,
+      "loss": 2.1051,
+      "step": 6200
+    },
+    {
+      "epoch": 0.016222189489448764,
+      "grad_norm": 1.6769137382507324,
+      "learning_rate": 2.7032639024073713e-07,
+      "loss": 2.0934,
+      "step": 6250
+    },
+    {
+      "epoch": 0.016351967005364353,
+      "grad_norm": 1.0514180660247803,
+      "learning_rate": 2.7248934743581427e-07,
+      "loss": 2.0948,
+      "step": 6300
+    },
+    {
+      "epoch": 0.016481744521279942,
+      "grad_norm": 1.0475189685821533,
+      "learning_rate": 2.746523046308914e-07,
+      "loss": 2.088,
+      "step": 6350
+    },
+    {
+      "epoch": 0.016611522037195535,
+      "grad_norm": 2.3959105014801025,
+      "learning_rate": 2.768152618259685e-07,
+      "loss": 2.1053,
+      "step": 6400
+    },
+    {
+      "epoch": 0.016741299553111124,
+      "grad_norm": 1.291269302368164,
+      "learning_rate": 2.789782190210456e-07,
+      "loss": 2.0576,
+      "step": 6450
+    },
+    {
+      "epoch": 0.016871077069026713,
+      "grad_norm": 3.1083991527557373,
+      "learning_rate": 2.811411762161227e-07,
+      "loss": 2.103,
+      "step": 6500
+    },
+    {
+      "epoch": 0.017000854584942306,
+      "grad_norm": 1.2403531074523926,
+      "learning_rate": 2.833041334111998e-07,
+      "loss": 2.1099,
+      "step": 6550
+    },
+    {
+      "epoch": 0.017130632100857895,
+      "grad_norm": 1.0552589893341064,
+      "learning_rate": 2.854670906062769e-07,
+      "loss": 2.1089,
+      "step": 6600
+    },
+    {
+      "epoch": 0.017260409616773484,
+      "grad_norm": 1.15003502368927,
+      "learning_rate": 2.8763004780135405e-07,
+      "loss": 2.1039,
+      "step": 6650
+    },
+    {
+      "epoch": 0.017390187132689073,
+      "grad_norm": 1.0832091569900513,
+      "learning_rate": 2.8979300499643113e-07,
+      "loss": 2.1084,
+      "step": 6700
+    },
+    {
+      "epoch": 0.017519964648604665,
+      "grad_norm": 1.3141324520111084,
+      "learning_rate": 2.9195596219150826e-07,
+      "loss": 2.1135,
+      "step": 6750
+    },
+    {
+      "epoch": 0.017649742164520255,
+      "grad_norm": 1.1030374765396118,
+      "learning_rate": 2.941189193865854e-07,
+      "loss": 2.1015,
+      "step": 6800
+    },
+    {
+      "epoch": 0.017779519680435844,
+      "grad_norm": 1.1264283657073975,
+      "learning_rate": 2.962818765816625e-07,
+      "loss": 2.1046,
+      "step": 6850
+    },
+    {
+      "epoch": 0.017909297196351436,
+      "grad_norm": 1.0352332592010498,
+      "learning_rate": 2.9844483377673956e-07,
+      "loss": 2.1123,
+      "step": 6900
+    },
+    {
+      "epoch": 0.018039074712267025,
+      "grad_norm": 1.6451269388198853,
+      "learning_rate": 3.006077909718167e-07,
+      "loss": 2.0875,
+      "step": 6950
+    },
+    {
+      "epoch": 0.018168852228182614,
+      "grad_norm": 1.0955110788345337,
+      "learning_rate": 3.027707481668938e-07,
+      "loss": 2.0838,
+      "step": 7000
+    },
+    {
+      "epoch": 0.018298629744098207,
+      "grad_norm": 1.128531813621521,
+      "learning_rate": 3.049337053619709e-07,
+      "loss": 2.1029,
+      "step": 7050
+    },
+    {
+      "epoch": 0.018428407260013796,
+      "grad_norm": 1.0489044189453125,
+      "learning_rate": 3.0709666255704805e-07,
+      "loss": 2.0908,
+      "step": 7100
+    },
+    {
+      "epoch": 0.018558184775929385,
+      "grad_norm": 1.0876027345657349,
+      "learning_rate": 3.0925961975212513e-07,
+      "loss": 2.0817,
+      "step": 7150
+    },
+    {
+      "epoch": 0.018687962291844974,
+      "grad_norm": 1.025060772895813,
+      "learning_rate": 3.1142257694720226e-07,
+      "loss": 2.0924,
+      "step": 7200
+    },
+    {
+      "epoch": 0.018817739807760567,
+      "grad_norm": 1.3133209943771362,
+      "learning_rate": 3.1358553414227934e-07,
+      "loss": 2.0848,
+      "step": 7250
+    },
+    {
+      "epoch": 0.018947517323676156,
+      "grad_norm": 1.159995436668396,
+      "learning_rate": 3.157484913373565e-07,
+      "loss": 2.0938,
+      "step": 7300
+    },
+    {
+      "epoch": 0.019077294839591745,
+      "grad_norm": 1.151329755783081,
+      "learning_rate": 3.1791144853243356e-07,
+      "loss": 2.1002,
+      "step": 7350
+    },
+    {
+      "epoch": 0.019207072355507337,
+      "grad_norm": 1.123695731163025,
+      "learning_rate": 3.200744057275107e-07,
+      "loss": 2.0951,
+      "step": 7400
+    },
+    {
+      "epoch": 0.019336849871422927,
+      "grad_norm": 1.143547534942627,
+      "learning_rate": 3.222373629225878e-07,
+      "loss": 2.1034,
+      "step": 7450
+    },
+    {
+      "epoch": 0.019466627387338516,
+      "grad_norm": 1.093329906463623,
+      "learning_rate": 3.2440032011766486e-07,
+      "loss": 2.0921,
+      "step": 7500
+    },
+    {
+      "epoch": 0.019596404903254105,
+      "grad_norm": 1.3572251796722412,
+      "learning_rate": 3.2656327731274204e-07,
+      "loss": 2.0902,
+      "step": 7550
+    },
+    {
+      "epoch": 0.019726182419169697,
+      "grad_norm": 1.146531343460083,
+      "learning_rate": 3.287262345078191e-07,
+      "loss": 2.0899,
+      "step": 7600
+    },
+    {
+      "epoch": 0.019855959935085286,
+      "grad_norm": 1.0585743188858032,
+      "learning_rate": 3.308891917028962e-07,
+      "loss": 2.108,
+      "step": 7650
+    },
+    {
+      "epoch": 0.019985737451000875,
+      "grad_norm": 1.1923290491104126,
+      "learning_rate": 3.3305214889797334e-07,
+      "loss": 2.098,
+      "step": 7700
+    },
+    {
+      "epoch": 0.020115514966916468,
+      "grad_norm": 1.1357568502426147,
+      "learning_rate": 3.352151060930504e-07,
+      "loss": 2.1021,
+      "step": 7750
+    },
+    {
+      "epoch": 0.020245292482832057,
+      "grad_norm": 1.2182716131210327,
+      "learning_rate": 3.373780632881275e-07,
+      "loss": 2.0816,
+      "step": 7800
+    },
+    {
+      "epoch": 0.020375069998747646,
+      "grad_norm": 1.1091363430023193,
+      "learning_rate": 3.395410204832047e-07,
+      "loss": 2.0832,
+      "step": 7850
+    },
+    {
+      "epoch": 0.02050484751466324,
+      "grad_norm": 1.1325336694717407,
+      "learning_rate": 3.4170397767828177e-07,
+      "loss": 2.0872,
+      "step": 7900
+    },
+    {
+      "epoch": 0.020634625030578828,
+      "grad_norm": 1.020922064781189,
+      "learning_rate": 3.4386693487335885e-07,
+      "loss": 2.0798,
+      "step": 7950
+    },
+    {
+      "epoch": 0.020764402546494417,
+      "grad_norm": 1.1414934396743774,
+      "learning_rate": 3.46029892068436e-07,
+      "loss": 2.0745,
+      "step": 8000
+    },
+    {
+      "epoch": 0.020894180062410006,
+      "grad_norm": 1.1155861616134644,
+      "learning_rate": 3.481928492635131e-07,
+      "loss": 2.0975,
+      "step": 8050
+    },
+    {
+      "epoch": 0.0210239575783256,
+      "grad_norm": 0.9747071266174316,
+      "learning_rate": 3.503558064585902e-07,
+      "loss": 2.0796,
+      "step": 8100
+    },
+    {
+      "epoch": 0.021153735094241188,
+      "grad_norm": 1.2895739078521729,
+      "learning_rate": 3.5251876365366734e-07,
+      "loss": 2.0951,
+      "step": 8150
+    },
+    {
+      "epoch": 0.021283512610156777,
+      "grad_norm": 1.147414207458496,
+      "learning_rate": 3.546817208487444e-07,
+      "loss": 2.0955,
+      "step": 8200
+    },
+    {
+      "epoch": 0.02141329012607237,
+      "grad_norm": 1.1811184883117676,
+      "learning_rate": 3.568446780438215e-07,
+      "loss": 2.0895,
+      "step": 8250
+    },
+    {
+      "epoch": 0.02154306764198796,
+      "grad_norm": 1.2630963325500488,
+      "learning_rate": 3.590076352388987e-07,
+      "loss": 2.0668,
+      "step": 8300
+    },
+    {
+      "epoch": 0.021672845157903547,
+      "grad_norm": 1.0883618593215942,
+      "learning_rate": 3.6117059243397577e-07,
+      "loss": 2.0981,
+      "step": 8350
+    },
+    {
+      "epoch": 0.021802622673819137,
+      "grad_norm": 1.2500261068344116,
+      "learning_rate": 3.6333354962905285e-07,
+      "loss": 2.0911,
+      "step": 8400
+    },
+    {
+      "epoch": 0.02193240018973473,
+      "grad_norm": 1.133091926574707,
+      "learning_rate": 3.6549650682413e-07,
+      "loss": 2.082,
+      "step": 8450
+    },
+    {
+      "epoch": 0.022062177705650318,
+      "grad_norm": 1.1500440835952759,
+      "learning_rate": 3.6765946401920707e-07,
+      "loss": 2.091,
+      "step": 8500
+    },
+    {
+      "epoch": 0.022191955221565907,
+      "grad_norm": 1.1573790311813354,
+      "learning_rate": 3.6982242121428415e-07,
+      "loss": 2.091,
+      "step": 8550
+    },
+    {
+      "epoch": 0.0223217327374815,
+      "grad_norm": 1.0022162199020386,
+      "learning_rate": 3.7198537840936134e-07,
+      "loss": 2.0734,
+      "step": 8600
+    },
+    {
+      "epoch": 0.02245151025339709,
+      "grad_norm": 1.2101961374282837,
+      "learning_rate": 3.741483356044384e-07,
+      "loss": 2.0976,
+      "step": 8650
+    },
+    {
+      "epoch": 0.022581287769312678,
+      "grad_norm": 1.1183929443359375,
+      "learning_rate": 3.763112927995155e-07,
+      "loss": 2.0742,
+      "step": 8700
+    },
+    {
+      "epoch": 0.02271106528522827,
+      "grad_norm": 1.1698428392410278,
+      "learning_rate": 3.784742499945927e-07,
+      "loss": 2.1189,
+      "step": 8750
+    },
+    {
+      "epoch": 0.02284084280114386,
+      "grad_norm": 1.238348126411438,
+      "learning_rate": 3.8063720718966977e-07,
+      "loss": 2.0864,
+      "step": 8800
+    },
+    {
+      "epoch": 0.02297062031705945,
+      "grad_norm": 1.0891568660736084,
+      "learning_rate": 3.8280016438474685e-07,
+      "loss": 2.071,
+      "step": 8850
+    },
+    {
+      "epoch": 0.023100397832975038,
+      "grad_norm": 1.0950003862380981,
+      "learning_rate": 3.84963121579824e-07,
+      "loss": 2.0944,
+      "step": 8900
+    },
+    {
+      "epoch": 0.02323017534889063,
+      "grad_norm": 1.0031663179397583,
+      "learning_rate": 3.8712607877490106e-07,
+      "loss": 2.0688,
+      "step": 8950
+    },
+    {
+      "epoch": 0.02335995286480622,
+      "grad_norm": 1.1025946140289307,
+      "learning_rate": 3.8928903596997815e-07,
+      "loss": 2.0853,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1155822,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.939629947120517e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a39d525f4bbbda65b3707c6ec9f3b1d46c81edf25bce482861401bbeb02da405
+size 5880