Duplicate from phospho-app/so100_strawberry_grape-08sel8rxz4

Co-authored-by: Frédéric Legrand <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,26 @@
+
+---
+tags:
+- phosphobot
+- gr00t
+- replicate
+task_categories:
+- robotics                                               
+---
+
+# Gr00t Model - phospho Replication Pipeline
+
+This model was trained using **phospho's Replicate pipeline** for **gr00t models**.
+
+Training parameters:
+- **Dataset**: [youliangtan/so100_strawberry_grape](https://huggingface.co/datasets/youliangtan/so100_strawberry_grape)
+- **Wandb run URL**: None
+- **Epochs**: 10
+- **Batch size**: 64
+- **Training steps**: 5099
+
+📖 **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=replicate_groot_training_pipeline)
+
+🤖 **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=replicate_groot_training_pipeline)
+
+🔗 **Explore on Replicate**: [Replicate](https://replicate.com/phospho-app/gr00t-policy)

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/32e1fd2507f7739fad443e6b449c8188e0e02fcb",
+  "action_dim": 32,
+  "action_head_cfg": {
+    "action_dim": 32,
+    "action_horizon": 16,
+    "add_pos_embed": true,
+    "diffusion_model_cfg": {
+      "attention_head_dim": 48,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "interleave_self_attention": true,
+      "norm_type": "ada_norm",
+      "num_attention_heads": 32,
+      "num_layers": 16,
+      "output_dim": 1024,
+      "positional_embeddings": null
+    },
+    "freeze_decode_layer": false,
+    "hidden_size": 1024,
+    "input_embedding_dim": 1536,
+    "load_pretrained_det_decode_layer_path": null,
+    "max_action_dim": 32,
+    "max_state_dim": 64,
+    "model_dtype": "float32",
+    "noise_beta_alpha": 1.5,
+    "noise_beta_beta": 1.0,
+    "noise_s": 0.999,
+    "num_inference_timesteps": 16,
+    "num_timestep_buckets": 1000,
+    "tune_diffusion_model": true,
+    "tune_projector": true
+  },
+  "action_horizon": 16,
+  "architectures": [
+    "GR00T_N1"
+  ],
+  "attn_implementation": null,
+  "backbone_cfg": {
+    "allow_reshape_visual": true,
+    "load_pretrained_det_eagle_path": null,
+    "model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
+    "processor_cfg": {
+      "max_input_tiles": 1,
+      "model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
+      "model_spec": {
+        "num_image_token": 64,
+        "template": "qwen2-chat"
+      }
+    },
+    "projector_dim": 2048,
+    "remove_llm": false,
+    "reproject_vision": false,
+    "scale_image_resolution": 1,
+    "select_layer": 12,
+    "tune_llm": false,
+    "tune_visual": true
+  },
+  "compute_dtype": "bfloat16",
+  "hidden_size": 1536,
+  "model_dtype": "float32",
+  "model_type": "gr00t_n1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2"
+}

experiment_cfg/metadata.json

@@ -0,0 +1,187 @@
+{
+    "new_embodiment": {
+        "statistics": {
+            "state": {
+                "single_arm": {
+                    "max": [
+                        160.927734375,
+                        189.228515625,
+                        173.583984375,
+                        110.478515625,
+                        61.435546875
+                    ],
+                    "min": [
+                        38.056640625,
+                        42.802734375,
+                        22.412109375,
+                        -5.185546875,
+                        -137.021484375
+                    ],
+                    "mean": [
+                        94.10661315917969,
+                        93.80464935302734,
+                        104.91960906982422,
+                        57.34180450439453,
+                        -53.90055465698242
+                    ],
+                    "std": [
+                        16.860620498657227,
+                        27.817033767700195,
+                        29.3829345703125,
+                        16.53359031677246,
+                        35.19451141357422
+                    ],
+                    "q01": [
+                        52.20703125,
+                        50.44921875,
+                        45.5748046875,
+                        15.8203125,
+                        -125.5078125
+                    ],
+                    "q99": [
+                        135.52734375,
+                        176.572265625,
+                        168.134765625,
+                        92.4609375,
+                        41.91679687499985
+                    ]
+                },
+                "gripper": {
+                    "max": [
+                        57.46003723144531
+                    ],
+                    "min": [
+                        -2.575488567352295
+                    ],
+                    "mean": [
+                        24.326099395751953
+                    ],
+                    "std": [
+                        14.310999870300293
+                    ],
+                    "q01": [
+                        -0.7104795575141907
+                    ],
+                    "q99": [
+                        51.6873893737793
+                    ]
+                }
+            },
+            "action": {
+                "single_arm": {
+                    "max": [
+                        161.455078125,
+                        189.66796875,
+                        174.990234375,
+                        112.236328125,
+                        62.75390625
+                    ],
+                    "min": [
+                        38.84765625,
+                        43.330078125,
+                        20.91796875,
+                        -7.20703125,
+                        -137.98828125
+                    ],
+                    "mean": [
+                        94.57371520996094,
+                        95.25252532958984,
+                        104.53071594238281,
+                        57.791255950927734,
+                        -54.3458366394043
+                    ],
+                    "std": [
+                        16.85411834716797,
+                        27.58999252319336,
+                        29.793941497802734,
+                        16.753890991210938,
+                        35.37184143066406
+                    ],
+                    "q01": [
+                        52.646484375,
+                        51.943359375,
+                        45.287402343749996,
+                        15.64453125,
+                        -126.123046875
+                    ],
+                    "q99": [
+                        135.966796875,
+                        177.626953125,
+                        168.22265625,
+                        93.66767578124995,
+                        42.643652343749885
+                    ]
+                },
+                "gripper": {
+                    "max": [
+                        58.67697525024414
+                    ],
+                    "min": [
+                        -5.756013870239258
+                    ],
+                    "mean": [
+                        23.897945404052734
+                    ],
+                    "std": [
+                        16.041561126708984
+                    ],
+                    "q01": [
+                        -2.92096209526062
+                    ],
+                    "q99": [
+                        52.40549850463867
+                    ]
+                }
+            }
+        },
+        "modalities": {
+            "video": {
+                "ego_view": {
+                    "resolution": [
+                        640,
+                        480
+                    ],
+                    "channels": 3,
+                    "fps": 30.0
+                }
+            },
+            "state": {
+                "single_arm": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        5
+                    ],
+                    "continuous": true
+                },
+                "gripper": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                }
+            },
+            "action": {
+                "single_arm": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        5
+                    ],
+                    "continuous": true
+                },
+                "gripper": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                }
+            }
+        },
+        "embodiment_tag": "new_embodiment"
+    }
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f8ccfcbb992bd78357486d5debc31e68a3980b6aba07c8c30898482c81c753c
+size 4938446392

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1680c88f31b76535902d3312e89c7a99a174636e01ad047ab19b8c974d8b8f
+size 3821736024

model.safetensors.index.json

@@ -0,0 +1,809 @@
+{
+  "metadata": {
+    "total_size": 8760067008
+  },
+  "weight_map": {
+    "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
+    "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
+    "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
+    "action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
+    "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
+    "backbone.linear.bias": "model-00002-of-00002.safetensors",
+    "backbone.linear.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
+    "backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}

trainer_state.json

@@ -0,0 +1,3605 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4995098039215686,
+  "eval_steps": 500,
+  "global_step": 5099,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004901960784313725,
+      "grad_norm": 4.5476274490356445,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.6369,
+      "step": 10
+    },
+    {
+      "epoch": 0.00980392156862745,
+      "grad_norm": 2.52302885055542,
+      "learning_rate": 1.568627450980392e-05,
+      "loss": 0.484,
+      "step": 20
+    },
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 3.1443543434143066,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 0.3252,
+      "step": 30
+    },
+    {
+      "epoch": 0.0196078431372549,
+      "grad_norm": 2.1440389156341553,
+      "learning_rate": 3.137254901960784e-05,
+      "loss": 0.2779,
+      "step": 40
+    },
+    {
+      "epoch": 0.024509803921568627,
+      "grad_norm": 1.7569645643234253,
+      "learning_rate": 3.9215686274509805e-05,
+      "loss": 0.2387,
+      "step": 50
+    },
+    {
+      "epoch": 0.029411764705882353,
+      "grad_norm": 1.7137173414230347,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 0.2146,
+      "step": 60
+    },
+    {
+      "epoch": 0.03431372549019608,
+      "grad_norm": 1.0686582326889038,
+      "learning_rate": 5.490196078431373e-05,
+      "loss": 0.1638,
+      "step": 70
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 1.834192156791687,
+      "learning_rate": 6.274509803921569e-05,
+      "loss": 0.1594,
+      "step": 80
+    },
+    {
+      "epoch": 0.04411764705882353,
+      "grad_norm": 2.2320666313171387,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 0.156,
+      "step": 90
+    },
+    {
+      "epoch": 0.049019607843137254,
+      "grad_norm": 1.2987866401672363,
+      "learning_rate": 7.843137254901961e-05,
+      "loss": 0.1447,
+      "step": 100
+    },
+    {
+      "epoch": 0.05392156862745098,
+      "grad_norm": 1.5711545944213867,
+      "learning_rate": 8.627450980392158e-05,
+      "loss": 0.1449,
+      "step": 110
+    },
+    {
+      "epoch": 0.058823529411764705,
+      "grad_norm": 0.8892576098442078,
+      "learning_rate": 9.411764705882353e-05,
+      "loss": 0.1513,
+      "step": 120
+    },
+    {
+      "epoch": 0.06372549019607843,
+      "grad_norm": 1.1401337385177612,
+      "learning_rate": 0.00010196078431372549,
+      "loss": 0.1128,
+      "step": 130
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 1.375543475151062,
+      "learning_rate": 0.00010980392156862746,
+      "loss": 0.1186,
+      "step": 140
+    },
+    {
+      "epoch": 0.07352941176470588,
+      "grad_norm": 1.6076676845550537,
+      "learning_rate": 0.00011764705882352942,
+      "loss": 0.1396,
+      "step": 150
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 1.2637161016464233,
+      "learning_rate": 0.00012549019607843137,
+      "loss": 0.1187,
+      "step": 160
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.5812987685203552,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.1155,
+      "step": 170
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 0.7302483916282654,
+      "learning_rate": 0.0001411764705882353,
+      "loss": 0.1068,
+      "step": 180
+    },
+    {
+      "epoch": 0.09313725490196079,
+      "grad_norm": 0.6003187894821167,
+      "learning_rate": 0.00014901960784313728,
+      "loss": 0.1084,
+      "step": 190
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 1.3157514333724976,
+      "learning_rate": 0.00015686274509803922,
+      "loss": 0.1127,
+      "step": 200
+    },
+    {
+      "epoch": 0.10294117647058823,
+      "grad_norm": 0.8480639457702637,
+      "learning_rate": 0.0001647058823529412,
+      "loss": 0.1025,
+      "step": 210
+    },
+    {
+      "epoch": 0.10784313725490197,
+      "grad_norm": 1.0640238523483276,
+      "learning_rate": 0.00017254901960784316,
+      "loss": 0.1214,
+      "step": 220
+    },
+    {
+      "epoch": 0.11274509803921569,
+      "grad_norm": 0.7853420972824097,
+      "learning_rate": 0.0001803921568627451,
+      "loss": 0.1103,
+      "step": 230
+    },
+    {
+      "epoch": 0.11764705882352941,
+      "grad_norm": 0.760675847530365,
+      "learning_rate": 0.00018823529411764707,
+      "loss": 0.1071,
+      "step": 240
+    },
+    {
+      "epoch": 0.12254901960784313,
+      "grad_norm": 1.1404098272323608,
+      "learning_rate": 0.000196078431372549,
+      "loss": 0.1004,
+      "step": 250
+    },
+    {
+      "epoch": 0.12745098039215685,
+      "grad_norm": 0.6359620690345764,
+      "learning_rate": 0.0001999994742235753,
+      "loss": 0.1065,
+      "step": 260
+    },
+    {
+      "epoch": 0.1323529411764706,
+      "grad_norm": 0.7933241724967957,
+      "learning_rate": 0.00019999526804535039,
+      "loss": 0.0943,
+      "step": 270
+    },
+    {
+      "epoch": 0.13725490196078433,
+      "grad_norm": 1.599077582359314,
+      "learning_rate": 0.00019998685586582082,
+      "loss": 0.1304,
+      "step": 280
+    },
+    {
+      "epoch": 0.14215686274509803,
+      "grad_norm": 0.8844221234321594,
+      "learning_rate": 0.00019997423803881975,
+      "loss": 0.0917,
+      "step": 290
+    },
+    {
+      "epoch": 0.14705882352941177,
+      "grad_norm": 1.2456647157669067,
+      "learning_rate": 0.00019995741509507825,
+      "loss": 0.111,
+      "step": 300
+    },
+    {
+      "epoch": 0.15196078431372548,
+      "grad_norm": 0.6590626239776611,
+      "learning_rate": 0.00019993638774220307,
+      "loss": 0.1022,
+      "step": 310
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 0.7061448693275452,
+      "learning_rate": 0.00019991115686464675,
+      "loss": 0.0938,
+      "step": 320
+    },
+    {
+      "epoch": 0.16176470588235295,
+      "grad_norm": 1.0512727499008179,
+      "learning_rate": 0.00019988172352367056,
+      "loss": 0.1059,
+      "step": 330
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.6884363889694214,
+      "learning_rate": 0.00019984808895729978,
+      "loss": 0.0801,
+      "step": 340
+    },
+    {
+      "epoch": 0.1715686274509804,
+      "grad_norm": 0.8961064219474792,
+      "learning_rate": 0.00019981025458027169,
+      "loss": 0.0872,
+      "step": 350
+    },
+    {
+      "epoch": 0.17647058823529413,
+      "grad_norm": 0.7410668730735779,
+      "learning_rate": 0.00019976822198397595,
+      "loss": 0.0935,
+      "step": 360
+    },
+    {
+      "epoch": 0.18137254901960784,
+      "grad_norm": 0.8089532256126404,
+      "learning_rate": 0.00019972199293638777,
+      "loss": 0.0806,
+      "step": 370
+    },
+    {
+      "epoch": 0.18627450980392157,
+      "grad_norm": 0.6644020676612854,
+      "learning_rate": 0.00019967156938199355,
+      "loss": 0.0885,
+      "step": 380
+    },
+    {
+      "epoch": 0.19117647058823528,
+      "grad_norm": 0.8422799110412598,
+      "learning_rate": 0.00019961695344170895,
+      "loss": 0.0952,
+      "step": 390
+    },
+    {
+      "epoch": 0.19607843137254902,
+      "grad_norm": 0.8162615299224854,
+      "learning_rate": 0.00019955814741278986,
+      "loss": 0.0802,
+      "step": 400
+    },
+    {
+      "epoch": 0.20098039215686275,
+      "grad_norm": 0.7302709221839905,
+      "learning_rate": 0.0001994951537687357,
+      "loss": 0.0884,
+      "step": 410
+    },
+    {
+      "epoch": 0.20588235294117646,
+      "grad_norm": 0.7032344937324524,
+      "learning_rate": 0.00019942797515918527,
+      "loss": 0.0896,
+      "step": 420
+    },
+    {
+      "epoch": 0.2107843137254902,
+      "grad_norm": 0.8042428493499756,
+      "learning_rate": 0.00019935661440980554,
+      "loss": 0.0811,
+      "step": 430
+    },
+    {
+      "epoch": 0.21568627450980393,
+      "grad_norm": 0.6656658053398132,
+      "learning_rate": 0.00019928107452217255,
+      "loss": 0.0856,
+      "step": 440
+    },
+    {
+      "epoch": 0.22058823529411764,
+      "grad_norm": 1.2202825546264648,
+      "learning_rate": 0.00019920135867364534,
+      "loss": 0.0895,
+      "step": 450
+    },
+    {
+      "epoch": 0.22549019607843138,
+      "grad_norm": 0.8210168480873108,
+      "learning_rate": 0.00019911747021723216,
+      "loss": 0.0807,
+      "step": 460
+    },
+    {
+      "epoch": 0.23039215686274508,
+      "grad_norm": 0.7217456102371216,
+      "learning_rate": 0.0001990294126814496,
+      "loss": 0.0814,
+      "step": 470
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 0.743126392364502,
+      "learning_rate": 0.00019893718977017402,
+      "loss": 0.0887,
+      "step": 480
+    },
+    {
+      "epoch": 0.24019607843137256,
+      "grad_norm": 0.7190248370170593,
+      "learning_rate": 0.00019884080536248578,
+      "loss": 0.0859,
+      "step": 490
+    },
+    {
+      "epoch": 0.24509803921568626,
+      "grad_norm": 0.5253967046737671,
+      "learning_rate": 0.00019874026351250623,
+      "loss": 0.0678,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8271141052246094,
+      "learning_rate": 0.00019863556844922696,
+      "loss": 0.0762,
+      "step": 510
+    },
+    {
+      "epoch": 0.2549019607843137,
+      "grad_norm": 0.7656545639038086,
+      "learning_rate": 0.0001985267245763321,
+      "loss": 0.0724,
+      "step": 520
+    },
+    {
+      "epoch": 0.25980392156862747,
+      "grad_norm": 0.6673869490623474,
+      "learning_rate": 0.00019841373647201297,
+      "loss": 0.0817,
+      "step": 530
+    },
+    {
+      "epoch": 0.2647058823529412,
+      "grad_norm": 0.880395770072937,
+      "learning_rate": 0.00019829660888877565,
+      "loss": 0.0897,
+      "step": 540
+    },
+    {
+      "epoch": 0.2696078431372549,
+      "grad_norm": 0.7278539538383484,
+      "learning_rate": 0.00019817534675324093,
+      "loss": 0.0808,
+      "step": 550
+    },
+    {
+      "epoch": 0.27450980392156865,
+      "grad_norm": 0.5380986928939819,
+      "learning_rate": 0.00019804995516593712,
+      "loss": 0.077,
+      "step": 560
+    },
+    {
+      "epoch": 0.27941176470588236,
+      "grad_norm": 0.9306485652923584,
+      "learning_rate": 0.00019792043940108564,
+      "loss": 0.0883,
+      "step": 570
+    },
+    {
+      "epoch": 0.28431372549019607,
+      "grad_norm": 0.9304268956184387,
+      "learning_rate": 0.00019778680490637902,
+      "loss": 0.0899,
+      "step": 580
+    },
+    {
+      "epoch": 0.28921568627450983,
+      "grad_norm": 0.7331838607788086,
+      "learning_rate": 0.00019764905730275184,
+      "loss": 0.0709,
+      "step": 590
+    },
+    {
+      "epoch": 0.29411764705882354,
+      "grad_norm": 0.47580260038375854,
+      "learning_rate": 0.00019750720238414425,
+      "loss": 0.0857,
+      "step": 600
+    },
+    {
+      "epoch": 0.29901960784313725,
+      "grad_norm": 0.5752102732658386,
+      "learning_rate": 0.0001973612461172583,
+      "loss": 0.0838,
+      "step": 610
+    },
+    {
+      "epoch": 0.30392156862745096,
+      "grad_norm": 0.4644894599914551,
+      "learning_rate": 0.00019721119464130707,
+      "loss": 0.0851,
+      "step": 620
+    },
+    {
+      "epoch": 0.3088235294117647,
+      "grad_norm": 0.7036497592926025,
+      "learning_rate": 0.00019705705426775616,
+      "loss": 0.0741,
+      "step": 630
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 0.499897301197052,
+      "learning_rate": 0.0001968988314800585,
+      "loss": 0.0718,
+      "step": 640
+    },
+    {
+      "epoch": 0.31862745098039214,
+      "grad_norm": 0.7211794853210449,
+      "learning_rate": 0.0001967365329333816,
+      "loss": 0.0798,
+      "step": 650
+    },
+    {
+      "epoch": 0.3235294117647059,
+      "grad_norm": 0.6176502108573914,
+      "learning_rate": 0.0001965701654543274,
+      "loss": 0.0695,
+      "step": 660
+    },
+    {
+      "epoch": 0.3284313725490196,
+      "grad_norm": 0.7395395636558533,
+      "learning_rate": 0.0001963997360406454,
+      "loss": 0.0581,
+      "step": 670
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5304160714149475,
+      "learning_rate": 0.00019622525186093818,
+      "loss": 0.0826,
+      "step": 680
+    },
+    {
+      "epoch": 0.3382352941176471,
+      "grad_norm": 0.46235349774360657,
+      "learning_rate": 0.0001960467202543599,
+      "loss": 0.056,
+      "step": 690
+    },
+    {
+      "epoch": 0.3431372549019608,
+      "grad_norm": 0.5242049098014832,
+      "learning_rate": 0.00019586414873030758,
+      "loss": 0.0728,
+      "step": 700
+    },
+    {
+      "epoch": 0.3480392156862745,
+      "grad_norm": 0.552486777305603,
+      "learning_rate": 0.00019567754496810534,
+      "loss": 0.0806,
+      "step": 710
+    },
+    {
+      "epoch": 0.35294117647058826,
+      "grad_norm": 0.5002785325050354,
+      "learning_rate": 0.0001954869168166812,
+      "loss": 0.0643,
+      "step": 720
+    },
+    {
+      "epoch": 0.35784313725490197,
+      "grad_norm": 0.47353097796440125,
+      "learning_rate": 0.00019529227229423717,
+      "loss": 0.0838,
+      "step": 730
+    },
+    {
+      "epoch": 0.3627450980392157,
+      "grad_norm": 0.4200286865234375,
+      "learning_rate": 0.00019509361958791174,
+      "loss": 0.0776,
+      "step": 740
+    },
+    {
+      "epoch": 0.36764705882352944,
+      "grad_norm": 0.6603316068649292,
+      "learning_rate": 0.00019489096705343578,
+      "loss": 0.0705,
+      "step": 750
+    },
+    {
+      "epoch": 0.37254901960784315,
+      "grad_norm": 0.37562692165374756,
+      "learning_rate": 0.0001946843232147809,
+      "loss": 0.072,
+      "step": 760
+    },
+    {
+      "epoch": 0.37745098039215685,
+      "grad_norm": 0.6199838519096375,
+      "learning_rate": 0.0001944736967638009,
+      "loss": 0.0649,
+      "step": 770
+    },
+    {
+      "epoch": 0.38235294117647056,
+      "grad_norm": 0.7614375948905945,
+      "learning_rate": 0.0001942590965598663,
+      "loss": 0.0735,
+      "step": 780
+    },
+    {
+      "epoch": 0.3872549019607843,
+      "grad_norm": 0.671489953994751,
+      "learning_rate": 0.00019404053162949155,
+      "loss": 0.065,
+      "step": 790
+    },
+    {
+      "epoch": 0.39215686274509803,
+      "grad_norm": 0.5170246362686157,
+      "learning_rate": 0.0001938180111659556,
+      "loss": 0.078,
+      "step": 800
+    },
+    {
+      "epoch": 0.39705882352941174,
+      "grad_norm": 0.5392031073570251,
+      "learning_rate": 0.00019359154452891483,
+      "loss": 0.063,
+      "step": 810
+    },
+    {
+      "epoch": 0.4019607843137255,
+      "grad_norm": 0.6858069896697998,
+      "learning_rate": 0.00019336114124400978,
+      "loss": 0.0783,
+      "step": 820
+    },
+    {
+      "epoch": 0.4068627450980392,
+      "grad_norm": 0.7257099151611328,
+      "learning_rate": 0.0001931268110024642,
+      "loss": 0.0798,
+      "step": 830
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 0.7296270132064819,
+      "learning_rate": 0.00019288856366067746,
+      "loss": 0.0619,
+      "step": 840
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.6048017740249634,
+      "learning_rate": 0.0001926464092398101,
+      "loss": 0.0634,
+      "step": 850
+    },
+    {
+      "epoch": 0.4215686274509804,
+      "grad_norm": 0.3223126232624054,
+      "learning_rate": 0.00019240035792536216,
+      "loss": 0.0755,
+      "step": 860
+    },
+    {
+      "epoch": 0.4264705882352941,
+      "grad_norm": 0.45046138763427734,
+      "learning_rate": 0.0001921504200667449,
+      "loss": 0.0661,
+      "step": 870
+    },
+    {
+      "epoch": 0.43137254901960786,
+      "grad_norm": 0.609027624130249,
+      "learning_rate": 0.00019189660617684537,
+      "loss": 0.0711,
+      "step": 880
+    },
+    {
+      "epoch": 0.4362745098039216,
+      "grad_norm": 0.4166688323020935,
+      "learning_rate": 0.00019163892693158425,
+      "loss": 0.0644,
+      "step": 890
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 0.6250641345977783,
+      "learning_rate": 0.00019137739316946685,
+      "loss": 0.0674,
+      "step": 900
+    },
+    {
+      "epoch": 0.44607843137254904,
+      "grad_norm": 0.6781248450279236,
+      "learning_rate": 0.00019111201589112718,
+      "loss": 0.0657,
+      "step": 910
+    },
+    {
+      "epoch": 0.45098039215686275,
+      "grad_norm": 0.9098891615867615,
+      "learning_rate": 0.00019084280625886516,
+      "loss": 0.0765,
+      "step": 920
+    },
+    {
+      "epoch": 0.45588235294117646,
+      "grad_norm": 0.5926252603530884,
+      "learning_rate": 0.00019056977559617731,
+      "loss": 0.0896,
+      "step": 930
+    },
+    {
+      "epoch": 0.46078431372549017,
+      "grad_norm": 0.6467915773391724,
+      "learning_rate": 0.0001902929353872803,
+      "loss": 0.0595,
+      "step": 940
+    },
+    {
+      "epoch": 0.46568627450980393,
+      "grad_norm": 0.4950433671474457,
+      "learning_rate": 0.0001900122972766279,
+      "loss": 0.0651,
+      "step": 950
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.6317784190177917,
+      "learning_rate": 0.0001897278730684213,
+      "loss": 0.08,
+      "step": 960
+    },
+    {
+      "epoch": 0.47549019607843135,
+      "grad_norm": 0.47558578848838806,
+      "learning_rate": 0.0001894396747261125,
+      "loss": 0.0622,
+      "step": 970
+    },
+    {
+      "epoch": 0.4803921568627451,
+      "grad_norm": 0.5610472559928894,
+      "learning_rate": 0.0001891477143719012,
+      "loss": 0.0667,
+      "step": 980
+    },
+    {
+      "epoch": 0.4852941176470588,
+      "grad_norm": 0.7227151989936829,
+      "learning_rate": 0.00018885200428622474,
+      "loss": 0.0648,
+      "step": 990
+    },
+    {
+      "epoch": 0.49019607843137253,
+      "grad_norm": 0.49453797936439514,
+      "learning_rate": 0.0001885525569072418,
+      "loss": 0.0663,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4950980392156863,
+      "grad_norm": 0.4297734200954437,
+      "learning_rate": 0.000188249384830309,
+      "loss": 0.0779,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.39416739344596863,
+      "learning_rate": 0.00018794250080745136,
+      "loss": 0.0577,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5049019607843137,
+      "grad_norm": 0.6955050230026245,
+      "learning_rate": 0.0001876319177468256,
+      "loss": 0.0579,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5098039215686274,
+      "grad_norm": 0.5533928871154785,
+      "learning_rate": 0.00018731764871217753,
+      "loss": 0.0583,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5147058823529411,
+      "grad_norm": 0.4718644618988037,
+      "learning_rate": 0.00018699970692229233,
+      "loss": 0.0609,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5196078431372549,
+      "grad_norm": 0.39921796321868896,
+      "learning_rate": 0.00018667810575043864,
+      "loss": 0.0612,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5245098039215687,
+      "grad_norm": 0.34913963079452515,
+      "learning_rate": 0.0001863528587238061,
+      "loss": 0.0522,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5294117647058824,
+      "grad_norm": 0.5829554796218872,
+      "learning_rate": 0.00018602397952293618,
+      "loss": 0.0651,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5343137254901961,
+      "grad_norm": 0.7142338156700134,
+      "learning_rate": 0.00018569148198114695,
+      "loss": 0.0643,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5392156862745098,
+      "grad_norm": 0.24581728875637054,
+      "learning_rate": 0.00018535538008395124,
+      "loss": 0.0537,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5441176470588235,
+      "grad_norm": 0.41139382123947144,
+      "learning_rate": 0.0001850156879684681,
+      "loss": 0.0631,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5490196078431373,
+      "grad_norm": 0.4532317519187927,
+      "learning_rate": 0.00018467241992282843,
+      "loss": 0.0573,
+      "step": 1120
+    },
+    {
+      "epoch": 0.553921568627451,
+      "grad_norm": 0.45865532755851746,
+      "learning_rate": 0.00018432559038557397,
+      "loss": 0.053,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5588235294117647,
+      "grad_norm": 0.3976840078830719,
+      "learning_rate": 0.00018397521394504995,
+      "loss": 0.0529,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5637254901960784,
+      "grad_norm": 0.47105035185813904,
+      "learning_rate": 0.00018362130533879133,
+      "loss": 0.0671,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5686274509803921,
+      "grad_norm": 0.5433268547058105,
+      "learning_rate": 0.00018326387945290313,
+      "loss": 0.0529,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5735294117647058,
+      "grad_norm": 0.6220820546150208,
+      "learning_rate": 0.00018290295132143415,
+      "loss": 0.0697,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5784313725490197,
+      "grad_norm": 0.38451075553894043,
+      "learning_rate": 0.00018253853612574473,
+      "loss": 0.0621,
+      "step": 1180
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.49342110753059387,
+      "learning_rate": 0.00018217064919386807,
+      "loss": 0.0603,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.5240128636360168,
+      "learning_rate": 0.00018179930599986554,
+      "loss": 0.0614,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5931372549019608,
+      "grad_norm": 0.5015797019004822,
+      "learning_rate": 0.0001814245221631758,
+      "loss": 0.0651,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5980392156862745,
+      "grad_norm": 0.7029892802238464,
+      "learning_rate": 0.0001810463134479579,
+      "loss": 0.0598,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6029411764705882,
+      "grad_norm": 0.3569225072860718,
+      "learning_rate": 0.00018066469576242806,
+      "loss": 0.0479,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6078431372549019,
+      "grad_norm": 0.4940333068370819,
+      "learning_rate": 0.00018027968515819072,
+      "loss": 0.055,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6127450980392157,
+      "grad_norm": 0.5233299732208252,
+      "learning_rate": 0.00017989129782956323,
+      "loss": 0.0555,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6176470588235294,
+      "grad_norm": 0.35107848048210144,
+      "learning_rate": 0.00017949955011289465,
+      "loss": 0.0472,
+      "step": 1260
+    },
+    {
+      "epoch": 0.6225490196078431,
+      "grad_norm": 0.42003870010375977,
+      "learning_rate": 0.00017910445848587885,
+      "loss": 0.0454,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.24233393371105194,
+      "learning_rate": 0.00017870603956686117,
+      "loss": 0.0631,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6323529411764706,
+      "grad_norm": 0.5557372570037842,
+      "learning_rate": 0.0001783043101141395,
+      "loss": 0.0628,
+      "step": 1290
+    },
+    {
+      "epoch": 0.6372549019607843,
+      "grad_norm": 0.33980950713157654,
+      "learning_rate": 0.00017789928702525952,
+      "loss": 0.0591,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6421568627450981,
+      "grad_norm": 0.2716699242591858,
+      "learning_rate": 0.00017749098733630368,
+      "loss": 0.0584,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6470588235294118,
+      "grad_norm": 0.42181700468063354,
+      "learning_rate": 0.00017707942822117495,
+      "loss": 0.0572,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6519607843137255,
+      "grad_norm": 0.46250826120376587,
+      "learning_rate": 0.00017666462699087422,
+      "loss": 0.0614,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6568627450980392,
+      "grad_norm": 0.7147281169891357,
+      "learning_rate": 0.00017624660109277223,
+      "loss": 0.0666,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6617647058823529,
+      "grad_norm": 0.6105577945709229,
+      "learning_rate": 0.00017582536810987576,
+      "loss": 0.0508,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.5564696788787842,
+      "learning_rate": 0.00017540094576008796,
+      "loss": 0.0581,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6715686274509803,
+      "grad_norm": 0.4955359399318695,
+      "learning_rate": 0.00017497335189546308,
+      "loss": 0.0569,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6764705882352942,
+      "grad_norm": 0.40812528133392334,
+      "learning_rate": 0.0001745426045014558,
+      "loss": 0.065,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6813725490196079,
+      "grad_norm": 0.31670013070106506,
+      "learning_rate": 0.00017410872169616447,
+      "loss": 0.0632,
+      "step": 1390
+    },
+    {
+      "epoch": 0.6862745098039216,
+      "grad_norm": 0.5076479911804199,
+      "learning_rate": 0.00017367172172956906,
+      "loss": 0.0558,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6911764705882353,
+      "grad_norm": 0.5511890053749084,
+      "learning_rate": 0.0001732316229827637,
+      "loss": 0.0669,
+      "step": 1410
+    },
+    {
+      "epoch": 0.696078431372549,
+      "grad_norm": 0.32073989510536194,
+      "learning_rate": 0.00017278844396718336,
+      "loss": 0.0543,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7009803921568627,
+      "grad_norm": 0.5955519080162048,
+      "learning_rate": 0.00017234220332382528,
+      "loss": 0.0594,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 0.5735410451889038,
+      "learning_rate": 0.00017189291982246493,
+      "loss": 0.0498,
+      "step": 1440
+    },
+    {
+      "epoch": 0.7107843137254902,
+      "grad_norm": 0.4336249530315399,
+      "learning_rate": 0.0001714406123608665,
+      "loss": 0.0577,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7156862745098039,
+      "grad_norm": 0.2760525047779083,
+      "learning_rate": 0.00017098529996398796,
+      "loss": 0.05,
+      "step": 1460
+    },
+    {
+      "epoch": 0.7205882352941176,
+      "grad_norm": 0.466795951128006,
+      "learning_rate": 0.00017052700178318088,
+      "loss": 0.0435,
+      "step": 1470
+    },
+    {
+      "epoch": 0.7254901960784313,
+      "grad_norm": 0.2780659794807434,
+      "learning_rate": 0.00017006573709538492,
+      "loss": 0.0516,
+      "step": 1480
+    },
+    {
+      "epoch": 0.7303921568627451,
+      "grad_norm": 0.31002551317214966,
+      "learning_rate": 0.00016960152530231696,
+      "loss": 0.0494,
+      "step": 1490
+    },
+    {
+      "epoch": 0.7352941176470589,
+      "grad_norm": 0.4070112407207489,
+      "learning_rate": 0.00016913438592965497,
+      "loss": 0.0594,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7401960784313726,
+      "grad_norm": 0.5858240127563477,
+      "learning_rate": 0.00016866433862621692,
+      "loss": 0.0421,
+      "step": 1510
+    },
+    {
+      "epoch": 0.7450980392156863,
+      "grad_norm": 0.2468300759792328,
+      "learning_rate": 0.00016819140316313397,
+      "loss": 0.0499,
+      "step": 1520
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.4881417155265808,
+      "learning_rate": 0.00016771559943301926,
+      "loss": 0.0557,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7549019607843137,
+      "grad_norm": 0.428586483001709,
+      "learning_rate": 0.00016723694744913087,
+      "loss": 0.0547,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7598039215686274,
+      "grad_norm": 0.4626677334308624,
+      "learning_rate": 0.0001667554673445302,
+      "loss": 0.0577,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7647058823529411,
+      "grad_norm": 0.44555196166038513,
+      "learning_rate": 0.000166271179371235,
+      "loss": 0.0498,
+      "step": 1560
+    },
+    {
+      "epoch": 0.7696078431372549,
+      "grad_norm": 0.4426194131374359,
+      "learning_rate": 0.0001657841038993677,
+      "loss": 0.0491,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7745098039215687,
+      "grad_norm": 0.3198953866958618,
+      "learning_rate": 0.00016529426141629843,
+      "loss": 0.0472,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7794117647058824,
+      "grad_norm": 0.2759292423725128,
+      "learning_rate": 0.0001648016725257834,
+      "loss": 0.0508,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.33216890692710876,
+      "learning_rate": 0.00016430635794709817,
+      "loss": 0.0516,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7892156862745098,
+      "grad_norm": 0.40735071897506714,
+      "learning_rate": 0.0001638083385141662,
+      "loss": 0.0549,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7941176470588235,
+      "grad_norm": 0.3739156424999237,
+      "learning_rate": 0.0001633076351746827,
+      "loss": 0.0543,
+      "step": 1620
+    },
+    {
+      "epoch": 0.7990196078431373,
+      "grad_norm": 0.2865970730781555,
+      "learning_rate": 0.0001628042689892331,
+      "loss": 0.0557,
+      "step": 1630
+    },
+    {
+      "epoch": 0.803921568627451,
+      "grad_norm": 0.6009504795074463,
+      "learning_rate": 0.00016229826113040767,
+      "loss": 0.0481,
+      "step": 1640
+    },
+    {
+      "epoch": 0.8088235294117647,
+      "grad_norm": 0.2973253130912781,
+      "learning_rate": 0.00016178963288191072,
+      "loss": 0.0465,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8137254901960784,
+      "grad_norm": 0.36205539107322693,
+      "learning_rate": 0.00016127840563766527,
+      "loss": 0.0676,
+      "step": 1660
+    },
+    {
+      "epoch": 0.8186274509803921,
+      "grad_norm": 0.41221827268600464,
+      "learning_rate": 0.0001607646009009135,
+      "loss": 0.0544,
+      "step": 1670
+    },
+    {
+      "epoch": 0.8235294117647058,
+      "grad_norm": 0.7448700666427612,
+      "learning_rate": 0.00016024824028331195,
+      "loss": 0.0544,
+      "step": 1680
+    },
+    {
+      "epoch": 0.8284313725490197,
+      "grad_norm": 0.5625671744346619,
+      "learning_rate": 0.0001597293455040227,
+      "loss": 0.0659,
+      "step": 1690
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.5039217472076416,
+      "learning_rate": 0.00015920793838879966,
+      "loss": 0.0522,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8382352941176471,
+      "grad_norm": 0.6583822965621948,
+      "learning_rate": 0.00015868404086907077,
+      "loss": 0.0473,
+      "step": 1710
+    },
+    {
+      "epoch": 0.8431372549019608,
+      "grad_norm": 0.4799802899360657,
+      "learning_rate": 0.00015815767498101522,
+      "loss": 0.0502,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8480392156862745,
+      "grad_norm": 0.38270649313926697,
+      "learning_rate": 0.00015762886286463683,
+      "loss": 0.0488,
+      "step": 1730
+    },
+    {
+      "epoch": 0.8529411764705882,
+      "grad_norm": 0.5844431519508362,
+      "learning_rate": 0.0001570976267628326,
+      "loss": 0.0506,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8578431372549019,
+      "grad_norm": 0.3698306977748871,
+      "learning_rate": 0.00015656398902045727,
+      "loss": 0.0474,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8627450980392157,
+      "grad_norm": 0.4788702428340912,
+      "learning_rate": 0.00015602797208338337,
+      "loss": 0.0452,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8676470588235294,
+      "grad_norm": 0.47195127606391907,
+      "learning_rate": 0.00015548959849755715,
+      "loss": 0.0497,
+      "step": 1770
+    },
+    {
+      "epoch": 0.8725490196078431,
+      "grad_norm": 0.3890342712402344,
+      "learning_rate": 0.00015494889090805018,
+      "loss": 0.0466,
+      "step": 1780
+    },
+    {
+      "epoch": 0.8774509803921569,
+      "grad_norm": 0.24695785343647003,
+      "learning_rate": 0.00015440587205810692,
+      "loss": 0.0525,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": 0.41040509939193726,
+      "learning_rate": 0.00015386056478818814,
+      "loss": 0.0556,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8872549019607843,
+      "grad_norm": 0.5128910541534424,
+      "learning_rate": 0.00015331299203501,
+      "loss": 0.0485,
+      "step": 1810
+    },
+    {
+      "epoch": 0.8921568627450981,
+      "grad_norm": 0.3270062804222107,
+      "learning_rate": 0.0001527631768305796,
+      "loss": 0.0423,
+      "step": 1820
+    },
+    {
+      "epoch": 0.8970588235294118,
+      "grad_norm": 0.43017369508743286,
+      "learning_rate": 0.00015221114230122584,
+      "loss": 0.0461,
+      "step": 1830
+    },
+    {
+      "epoch": 0.9019607843137255,
+      "grad_norm": 0.501888632774353,
+      "learning_rate": 0.00015165691166662705,
+      "loss": 0.0472,
+      "step": 1840
+    },
+    {
+      "epoch": 0.9068627450980392,
+      "grad_norm": 0.286864310503006,
+      "learning_rate": 0.00015110050823883406,
+      "loss": 0.0418,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9117647058823529,
+      "grad_norm": 0.5109400153160095,
+      "learning_rate": 0.00015054195542128968,
+      "loss": 0.0426,
+      "step": 1860
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.32924002408981323,
+      "learning_rate": 0.00014998127670784448,
+      "loss": 0.0389,
+      "step": 1870
+    },
+    {
+      "epoch": 0.9215686274509803,
+      "grad_norm": 0.21681684255599976,
+      "learning_rate": 0.0001494184956817684,
+      "loss": 0.0487,
+      "step": 1880
+    },
+    {
+      "epoch": 0.9264705882352942,
+      "grad_norm": 0.20006486773490906,
+      "learning_rate": 0.00014885363601475888,
+      "loss": 0.0521,
+      "step": 1890
+    },
+    {
+      "epoch": 0.9313725490196079,
+      "grad_norm": 0.6207095980644226,
+      "learning_rate": 0.00014828672146594511,
+      "loss": 0.0542,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9362745098039216,
+      "grad_norm": 0.5559191703796387,
+      "learning_rate": 0.00014771777588088884,
+      "loss": 0.0446,
+      "step": 1910
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.3139231503009796,
+      "learning_rate": 0.00014714682319058112,
+      "loss": 0.0403,
+      "step": 1920
+    },
+    {
+      "epoch": 0.946078431372549,
+      "grad_norm": 0.3132689893245697,
+      "learning_rate": 0.00014657388741043606,
+      "loss": 0.0398,
+      "step": 1930
+    },
+    {
+      "epoch": 0.9509803921568627,
+      "grad_norm": 0.2745281457901001,
+      "learning_rate": 0.00014599899263928028,
+      "loss": 0.0358,
+      "step": 1940
+    },
+    {
+      "epoch": 0.9558823529411765,
+      "grad_norm": 0.2483411729335785,
+      "learning_rate": 0.00014542216305833968,
+      "loss": 0.0506,
+      "step": 1950
+    },
+    {
+      "epoch": 0.9607843137254902,
+      "grad_norm": 0.3583033084869385,
+      "learning_rate": 0.000144843422930222,
+      "loss": 0.0442,
+      "step": 1960
+    },
+    {
+      "epoch": 0.9656862745098039,
+      "grad_norm": 0.2526845932006836,
+      "learning_rate": 0.00014426279659789651,
+      "loss": 0.0458,
+      "step": 1970
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": 0.3186612129211426,
+      "learning_rate": 0.00014368030848367,
+      "loss": 0.052,
+      "step": 1980
+    },
+    {
+      "epoch": 0.9754901960784313,
+      "grad_norm": 0.3088064193725586,
+      "learning_rate": 0.00014309598308815945,
+      "loss": 0.0453,
+      "step": 1990
+    },
+    {
+      "epoch": 0.9803921568627451,
+      "grad_norm": 0.44008663296699524,
+      "learning_rate": 0.00014250984498926167,
+      "loss": 0.0449,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9852941176470589,
+      "grad_norm": 0.5169370174407959,
+      "learning_rate": 0.0001419219188411194,
+      "loss": 0.0411,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9901960784313726,
+      "grad_norm": 0.32191041111946106,
+      "learning_rate": 0.0001413322293730842,
+      "loss": 0.0406,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9950980392156863,
+      "grad_norm": 0.300047904253006,
+      "learning_rate": 0.00014074080138867654,
+      "loss": 0.0432,
+      "step": 2030
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6571453809738159,
+      "learning_rate": 0.00014014765976454231,
+      "loss": 0.0421,
+      "step": 2040
+    },
+    {
+      "epoch": 1.0049019607843137,
+      "grad_norm": 0.43792489171028137,
+      "learning_rate": 0.00013955282944940652,
+      "loss": 0.0389,
+      "step": 2050
+    },
+    {
+      "epoch": 1.0098039215686274,
+      "grad_norm": 0.40551769733428955,
+      "learning_rate": 0.0001389563354630239,
+      "loss": 0.0418,
+      "step": 2060
+    },
+    {
+      "epoch": 1.0147058823529411,
+      "grad_norm": 0.3299430012702942,
+      "learning_rate": 0.0001383582028951265,
+      "loss": 0.0465,
+      "step": 2070
+    },
+    {
+      "epoch": 1.0196078431372548,
+      "grad_norm": 0.2800670266151428,
+      "learning_rate": 0.00013775845690436848,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 1.0245098039215685,
+      "grad_norm": 0.49185529351234436,
+      "learning_rate": 0.00013715712271726772,
+      "loss": 0.0415,
+      "step": 2090
+    },
+    {
+      "epoch": 1.0294117647058822,
+      "grad_norm": 0.6726065278053284,
+      "learning_rate": 0.0001365542256271448,
+      "loss": 0.038,
+      "step": 2100
+    },
+    {
+      "epoch": 1.0343137254901962,
+      "grad_norm": 0.5443005561828613,
+      "learning_rate": 0.00013594979099305928,
+      "loss": 0.0407,
+      "step": 2110
+    },
+    {
+      "epoch": 1.0392156862745099,
+      "grad_norm": 0.3882359564304352,
+      "learning_rate": 0.00013534384423874272,
+      "loss": 0.0479,
+      "step": 2120
+    },
+    {
+      "epoch": 1.0441176470588236,
+      "grad_norm": 0.3460078239440918,
+      "learning_rate": 0.00013473641085152957,
+      "loss": 0.0472,
+      "step": 2130
+    },
+    {
+      "epoch": 1.0490196078431373,
+      "grad_norm": 0.3264780342578888,
+      "learning_rate": 0.00013412751638128503,
+      "loss": 0.0374,
+      "step": 2140
+    },
+    {
+      "epoch": 1.053921568627451,
+      "grad_norm": 0.28663188219070435,
+      "learning_rate": 0.0001335171864393304,
+      "loss": 0.0386,
+      "step": 2150
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": 0.22994215786457062,
+      "learning_rate": 0.00013290544669736576,
+      "loss": 0.0492,
+      "step": 2160
+    },
+    {
+      "epoch": 1.0637254901960784,
+      "grad_norm": 0.2018628716468811,
+      "learning_rate": 0.0001322923228863902,
+      "loss": 0.0367,
+      "step": 2170
+    },
+    {
+      "epoch": 1.0686274509803921,
+      "grad_norm": 0.20426690578460693,
+      "learning_rate": 0.0001316778407956196,
+      "loss": 0.0322,
+      "step": 2180
+    },
+    {
+      "epoch": 1.0735294117647058,
+      "grad_norm": 0.32902026176452637,
+      "learning_rate": 0.00013106202627140163,
+      "loss": 0.0321,
+      "step": 2190
+    },
+    {
+      "epoch": 1.0784313725490196,
+      "grad_norm": 0.3210899233818054,
+      "learning_rate": 0.00013044490521612904,
+      "loss": 0.0405,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.23476989567279816,
+      "learning_rate": 0.00012982650358714967,
+      "loss": 0.0416,
+      "step": 2210
+    },
+    {
+      "epoch": 1.088235294117647,
+      "grad_norm": 0.3046343922615051,
+      "learning_rate": 0.000129206847395675,
+      "loss": 0.0394,
+      "step": 2220
+    },
+    {
+      "epoch": 1.093137254901961,
+      "grad_norm": 0.27315208315849304,
+      "learning_rate": 0.0001285859627056858,
+      "loss": 0.0439,
+      "step": 2230
+    },
+    {
+      "epoch": 1.0980392156862746,
+      "grad_norm": 0.34966346621513367,
+      "learning_rate": 0.00012796387563283605,
+      "loss": 0.0387,
+      "step": 2240
+    },
+    {
+      "epoch": 1.1029411764705883,
+      "grad_norm": 0.24096551537513733,
+      "learning_rate": 0.00012734061234335434,
+      "loss": 0.0412,
+      "step": 2250
+    },
+    {
+      "epoch": 1.107843137254902,
+      "grad_norm": 0.26461055874824524,
+      "learning_rate": 0.00012671619905294326,
+      "loss": 0.0494,
+      "step": 2260
+    },
+    {
+      "epoch": 1.1127450980392157,
+      "grad_norm": 0.24669981002807617,
+      "learning_rate": 0.0001260906620256767,
+      "loss": 0.0396,
+      "step": 2270
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": 0.37667712569236755,
+      "learning_rate": 0.00012546402757289532,
+      "loss": 0.0426,
+      "step": 2280
+    },
+    {
+      "epoch": 1.1225490196078431,
+      "grad_norm": 0.3720461130142212,
+      "learning_rate": 0.00012483632205209953,
+      "loss": 0.042,
+      "step": 2290
+    },
+    {
+      "epoch": 1.1274509803921569,
+      "grad_norm": 0.3975540101528168,
+      "learning_rate": 0.0001242075718658411,
+      "loss": 0.0464,
+      "step": 2300
+    },
+    {
+      "epoch": 1.1323529411764706,
+      "grad_norm": 0.34910279512405396,
+      "learning_rate": 0.00012357780346061256,
+      "loss": 0.0412,
+      "step": 2310
+    },
+    {
+      "epoch": 1.1372549019607843,
+      "grad_norm": 0.34874585270881653,
+      "learning_rate": 0.00012294704332573462,
+      "loss": 0.0458,
+      "step": 2320
+    },
+    {
+      "epoch": 1.142156862745098,
+      "grad_norm": 0.24936801195144653,
+      "learning_rate": 0.0001223153179922423,
+      "loss": 0.0437,
+      "step": 2330
+    },
+    {
+      "epoch": 1.1470588235294117,
+      "grad_norm": 0.39299267530441284,
+      "learning_rate": 0.00012168265403176864,
+      "loss": 0.0419,
+      "step": 2340
+    },
+    {
+      "epoch": 1.1519607843137254,
+      "grad_norm": 0.44494786858558655,
+      "learning_rate": 0.0001210490780554274,
+      "loss": 0.0391,
+      "step": 2350
+    },
+    {
+      "epoch": 1.156862745098039,
+      "grad_norm": 0.26526331901550293,
+      "learning_rate": 0.00012041461671269337,
+      "loss": 0.0338,
+      "step": 2360
+    },
+    {
+      "epoch": 1.161764705882353,
+      "grad_norm": 0.4189550280570984,
+      "learning_rate": 0.00011977929669028174,
+      "loss": 0.0441,
+      "step": 2370
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.2872006595134735,
+      "learning_rate": 0.00011914314471102545,
+      "loss": 0.0427,
+      "step": 2380
+    },
+    {
+      "epoch": 1.1715686274509804,
+      "grad_norm": 0.2823413908481598,
+      "learning_rate": 0.0001185061875327512,
+      "loss": 0.0443,
+      "step": 2390
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.26944294571876526,
+      "learning_rate": 0.00011786845194715403,
+      "loss": 0.0387,
+      "step": 2400
+    },
+    {
+      "epoch": 1.1813725490196079,
+      "grad_norm": 0.3672547936439514,
+      "learning_rate": 0.00011722996477867026,
+      "loss": 0.0397,
+      "step": 2410
+    },
+    {
+      "epoch": 1.1862745098039216,
+      "grad_norm": 0.2237931340932846,
+      "learning_rate": 0.00011659075288334938,
+      "loss": 0.0444,
+      "step": 2420
+    },
+    {
+      "epoch": 1.1911764705882353,
+      "grad_norm": 0.2790263295173645,
+      "learning_rate": 0.00011595084314772429,
+      "loss": 0.0358,
+      "step": 2430
+    },
+    {
+      "epoch": 1.196078431372549,
+      "grad_norm": 0.2825845777988434,
+      "learning_rate": 0.00011531026248768048,
+      "loss": 0.0368,
+      "step": 2440
+    },
+    {
+      "epoch": 1.2009803921568627,
+      "grad_norm": 0.27560582756996155,
+      "learning_rate": 0.00011466903784732381,
+      "loss": 0.0474,
+      "step": 2450
+    },
+    {
+      "epoch": 1.2058823529411764,
+      "grad_norm": 0.4237360656261444,
+      "learning_rate": 0.00011402719619784734,
+      "loss": 0.0375,
+      "step": 2460
+    },
+    {
+      "epoch": 1.2107843137254901,
+      "grad_norm": 0.3769036531448364,
+      "learning_rate": 0.00011338476453639666,
+      "loss": 0.0308,
+      "step": 2470
+    },
+    {
+      "epoch": 1.215686274509804,
+      "grad_norm": 0.32824084162712097,
+      "learning_rate": 0.00011274176988493454,
+      "loss": 0.0386,
+      "step": 2480
+    },
+    {
+      "epoch": 1.2205882352941178,
+      "grad_norm": 0.30048561096191406,
+      "learning_rate": 0.0001120982392891042,
+      "loss": 0.0391,
+      "step": 2490
+    },
+    {
+      "epoch": 1.2254901960784315,
+      "grad_norm": 0.30690962076187134,
+      "learning_rate": 0.00011145419981709169,
+      "loss": 0.0443,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2303921568627452,
+      "grad_norm": 0.4496728479862213,
+      "learning_rate": 0.00011080967855848755,
+      "loss": 0.0447,
+      "step": 2510
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": 0.25722137093544006,
+      "learning_rate": 0.00011016470262314707,
+      "loss": 0.0333,
+      "step": 2520
+    },
+    {
+      "epoch": 1.2401960784313726,
+      "grad_norm": 0.32415884733200073,
+      "learning_rate": 0.00010951929914005033,
+      "loss": 0.0375,
+      "step": 2530
+    },
+    {
+      "epoch": 1.2450980392156863,
+      "grad_norm": 0.33738696575164795,
+      "learning_rate": 0.00010887349525616075,
+      "loss": 0.0408,
+      "step": 2540
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.3490372896194458,
+      "learning_rate": 0.00010822731813528354,
+      "loss": 0.0337,
+      "step": 2550
+    },
+    {
+      "epoch": 1.2549019607843137,
+      "grad_norm": 0.42863723635673523,
+      "learning_rate": 0.00010758079495692294,
+      "loss": 0.0442,
+      "step": 2560
+    },
+    {
+      "epoch": 1.2598039215686274,
+      "grad_norm": 0.29293495416641235,
+      "learning_rate": 0.00010693395291513908,
+      "loss": 0.0408,
+      "step": 2570
+    },
+    {
+      "epoch": 1.2647058823529411,
+      "grad_norm": 0.27024197578430176,
+      "learning_rate": 0.00010628681921740414,
+      "loss": 0.0377,
+      "step": 2580
+    },
+    {
+      "epoch": 1.2696078431372548,
+      "grad_norm": 0.35880324244499207,
+      "learning_rate": 0.00010563942108345785,
+      "loss": 0.0364,
+      "step": 2590
+    },
+    {
+      "epoch": 1.2745098039215685,
+      "grad_norm": 0.3253026306629181,
+      "learning_rate": 0.0001049917857441628,
+      "loss": 0.0374,
+      "step": 2600
+    },
+    {
+      "epoch": 1.2794117647058822,
+      "grad_norm": 0.33250367641448975,
+      "learning_rate": 0.00010434394044035878,
+      "loss": 0.0384,
+      "step": 2610
+    },
+    {
+      "epoch": 1.284313725490196,
+      "grad_norm": 0.34700486063957214,
+      "learning_rate": 0.00010369591242171719,
+      "loss": 0.0369,
+      "step": 2620
+    },
+    {
+      "epoch": 1.2892156862745099,
+      "grad_norm": 0.3287598788738251,
+      "learning_rate": 0.00010304772894559475,
+      "loss": 0.0419,
+      "step": 2630
+    },
+    {
+      "epoch": 1.2941176470588236,
+      "grad_norm": 0.3363092243671417,
+      "learning_rate": 0.00010239941727588707,
+      "loss": 0.0419,
+      "step": 2640
+    },
+    {
+      "epoch": 1.2990196078431373,
+      "grad_norm": 0.32619622349739075,
+      "learning_rate": 0.0001017510046818817,
+      "loss": 0.0353,
+      "step": 2650
+    },
+    {
+      "epoch": 1.303921568627451,
+      "grad_norm": 0.28630563616752625,
+      "learning_rate": 0.00010110251843711149,
+      "loss": 0.0317,
+      "step": 2660
+    },
+    {
+      "epoch": 1.3088235294117647,
+      "grad_norm": 0.470198392868042,
+      "learning_rate": 0.00010045398581820702,
+      "loss": 0.0397,
+      "step": 2670
+    },
+    {
+      "epoch": 1.3137254901960784,
+      "grad_norm": 0.34590962529182434,
+      "learning_rate": 9.98054341037495e-05,
+      "loss": 0.0336,
+      "step": 2680
+    },
+    {
+      "epoch": 1.3186274509803921,
+      "grad_norm": 0.18714579939842224,
+      "learning_rate": 9.91568905731234e-05,
+      "loss": 0.0268,
+      "step": 2690
+    },
+    {
+      "epoch": 1.3235294117647058,
+      "grad_norm": 0.3055776357650757,
+      "learning_rate": 9.850838250536885e-05,
+      "loss": 0.0384,
+      "step": 2700
+    },
+    {
+      "epoch": 1.3284313725490196,
+      "grad_norm": 0.33092889189720154,
+      "learning_rate": 9.785993717803445e-05,
+      "loss": 0.0323,
+      "step": 2710
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.26138371229171753,
+      "learning_rate": 9.721158186602979e-05,
+      "loss": 0.0391,
+      "step": 2720
+    },
+    {
+      "epoch": 1.3382352941176472,
+      "grad_norm": 0.2703782320022583,
+      "learning_rate": 9.656334384047812e-05,
+      "loss": 0.0268,
+      "step": 2730
+    },
+    {
+      "epoch": 1.343137254901961,
+      "grad_norm": 0.24206914007663727,
+      "learning_rate": 9.591525036756952e-05,
+      "loss": 0.032,
+      "step": 2740
+    },
+    {
+      "epoch": 1.3480392156862746,
+      "grad_norm": 0.3793281018733978,
+      "learning_rate": 9.526732870741386e-05,
+      "loss": 0.0399,
+      "step": 2750
+    },
+    {
+      "epoch": 1.3529411764705883,
+      "grad_norm": 0.3143618404865265,
+      "learning_rate": 9.46196061128942e-05,
+      "loss": 0.0365,
+      "step": 2760
+    },
+    {
+      "epoch": 1.357843137254902,
+      "grad_norm": 0.23540951311588287,
+      "learning_rate": 9.397210982852053e-05,
+      "loss": 0.0328,
+      "step": 2770
+    },
+    {
+      "epoch": 1.3627450980392157,
+      "grad_norm": 0.2023368775844574,
+      "learning_rate": 9.332486708928373e-05,
+      "loss": 0.0316,
+      "step": 2780
+    },
+    {
+      "epoch": 1.3676470588235294,
+      "grad_norm": 0.26689231395721436,
+      "learning_rate": 9.267790511951015e-05,
+      "loss": 0.0326,
+      "step": 2790
+    },
+    {
+      "epoch": 1.3725490196078431,
+      "grad_norm": 0.2792396545410156,
+      "learning_rate": 9.203125113171631e-05,
+      "loss": 0.0336,
+      "step": 2800
+    },
+    {
+      "epoch": 1.3774509803921569,
+      "grad_norm": 0.21045692265033722,
+      "learning_rate": 9.13849323254645e-05,
+      "loss": 0.0296,
+      "step": 2810
+    },
+    {
+      "epoch": 1.3823529411764706,
+      "grad_norm": 0.26224854588508606,
+      "learning_rate": 9.073897588621853e-05,
+      "loss": 0.0311,
+      "step": 2820
+    },
+    {
+      "epoch": 1.3872549019607843,
+      "grad_norm": 0.30219170451164246,
+      "learning_rate": 9.009340898420029e-05,
+      "loss": 0.0379,
+      "step": 2830
+    },
+    {
+      "epoch": 1.392156862745098,
+      "grad_norm": 0.19660678505897522,
+      "learning_rate": 8.944825877324708e-05,
+      "loss": 0.035,
+      "step": 2840
+    },
+    {
+      "epoch": 1.3970588235294117,
+      "grad_norm": 0.2348472774028778,
+      "learning_rate": 8.880355238966923e-05,
+      "loss": 0.0366,
+      "step": 2850
+    },
+    {
+      "epoch": 1.4019607843137254,
+      "grad_norm": 0.44347622990608215,
+      "learning_rate": 8.815931695110885e-05,
+      "loss": 0.0333,
+      "step": 2860
+    },
+    {
+      "epoch": 1.406862745098039,
+      "grad_norm": 0.34309887886047363,
+      "learning_rate": 8.751557955539915e-05,
+      "loss": 0.0394,
+      "step": 2870
+    },
+    {
+      "epoch": 1.4117647058823528,
+      "grad_norm": 0.3023855984210968,
+      "learning_rate": 8.687236727942465e-05,
+      "loss": 0.0308,
+      "step": 2880
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.25127673149108887,
+      "learning_rate": 8.622970717798227e-05,
+      "loss": 0.0384,
+      "step": 2890
+    },
+    {
+      "epoch": 1.4215686274509804,
+      "grad_norm": 0.17014305293560028,
+      "learning_rate": 8.558762628264345e-05,
+      "loss": 0.0331,
+      "step": 2900
+    },
+    {
+      "epoch": 1.4264705882352942,
+      "grad_norm": 0.32725852727890015,
+      "learning_rate": 8.494615160061694e-05,
+      "loss": 0.0326,
+      "step": 2910
+    },
+    {
+      "epoch": 1.4313725490196079,
+      "grad_norm": 0.2895604968070984,
+      "learning_rate": 8.430531011361298e-05,
+      "loss": 0.0319,
+      "step": 2920
+    },
+    {
+      "epoch": 1.4362745098039216,
+      "grad_norm": 0.3882890045642853,
+      "learning_rate": 8.366512877670842e-05,
+      "loss": 0.0331,
+      "step": 2930
+    },
+    {
+      "epoch": 1.4411764705882353,
+      "grad_norm": 0.27492624521255493,
+      "learning_rate": 8.302563451721282e-05,
+      "loss": 0.0384,
+      "step": 2940
+    },
+    {
+      "epoch": 1.446078431372549,
+      "grad_norm": 0.23316094279289246,
+      "learning_rate": 8.238685423353588e-05,
+      "loss": 0.0426,
+      "step": 2950
+    },
+    {
+      "epoch": 1.4509803921568627,
+      "grad_norm": 0.395353227853775,
+      "learning_rate": 8.174881479405607e-05,
+      "loss": 0.0347,
+      "step": 2960
+    },
+    {
+      "epoch": 1.4558823529411764,
+      "grad_norm": 0.5179559588432312,
+      "learning_rate": 8.111154303599049e-05,
+      "loss": 0.0371,
+      "step": 2970
+    },
+    {
+      "epoch": 1.4607843137254901,
+      "grad_norm": 0.22947251796722412,
+      "learning_rate": 8.047506576426596e-05,
+      "loss": 0.03,
+      "step": 2980
+    },
+    {
+      "epoch": 1.465686274509804,
+      "grad_norm": 0.3831785023212433,
+      "learning_rate": 7.983940975039166e-05,
+      "loss": 0.0346,
+      "step": 2990
+    },
+    {
+      "epoch": 1.4705882352941178,
+      "grad_norm": 0.34753093123435974,
+      "learning_rate": 7.920460173133304e-05,
+      "loss": 0.0464,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4754901960784315,
+      "grad_norm": 0.24026577174663544,
+      "learning_rate": 7.85706684083871e-05,
+      "loss": 0.0334,
+      "step": 3010
+    },
+    {
+      "epoch": 1.4803921568627452,
+      "grad_norm": 0.32264992594718933,
+      "learning_rate": 7.793763644605947e-05,
+      "loss": 0.0329,
+      "step": 3020
+    },
+    {
+      "epoch": 1.4852941176470589,
+      "grad_norm": 0.25292444229125977,
+      "learning_rate": 7.730553247094266e-05,
+      "loss": 0.0306,
+      "step": 3030
+    },
+    {
+      "epoch": 1.4901960784313726,
+      "grad_norm": 0.21395047008991241,
+      "learning_rate": 7.667438307059627e-05,
+      "loss": 0.0346,
+      "step": 3040
+    },
+    {
+      "epoch": 1.4950980392156863,
+      "grad_norm": 0.29967001080513,
+      "learning_rate": 7.604421479242846e-05,
+      "loss": 0.0403,
+      "step": 3050
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.2828430235385895,
+      "learning_rate": 7.541505414257959e-05,
+      "loss": 0.0327,
+      "step": 3060
+    },
+    {
+      "epoch": 1.5049019607843137,
+      "grad_norm": 0.43027809262275696,
+      "learning_rate": 7.478692758480698e-05,
+      "loss": 0.0331,
+      "step": 3070
+    },
+    {
+      "epoch": 1.5098039215686274,
+      "grad_norm": 0.34473538398742676,
+      "learning_rate": 7.415986153937202e-05,
+      "loss": 0.0444,
+      "step": 3080
+    },
+    {
+      "epoch": 1.5147058823529411,
+      "grad_norm": 0.3717981278896332,
+      "learning_rate": 7.353388238192892e-05,
+      "loss": 0.042,
+      "step": 3090
+    },
+    {
+      "epoch": 1.5196078431372548,
+      "grad_norm": 0.15127846598625183,
+      "learning_rate": 7.29090164424151e-05,
+      "loss": 0.0296,
+      "step": 3100
+    },
+    {
+      "epoch": 1.5245098039215685,
+      "grad_norm": 0.33397403359413147,
+      "learning_rate": 7.22852900039438e-05,
+      "loss": 0.0314,
+      "step": 3110
+    },
+    {
+      "epoch": 1.5294117647058822,
+      "grad_norm": 0.25943371653556824,
+      "learning_rate": 7.166272930169861e-05,
+      "loss": 0.0342,
+      "step": 3120
+    },
+    {
+      "epoch": 1.534313725490196,
+      "grad_norm": 0.3120077848434448,
+      "learning_rate": 7.104136052182992e-05,
+      "loss": 0.0317,
+      "step": 3130
+    },
+    {
+      "epoch": 1.5392156862745097,
+      "grad_norm": 0.24377594888210297,
+      "learning_rate": 7.042120980035346e-05,
+      "loss": 0.0284,
+      "step": 3140
+    },
+    {
+      "epoch": 1.5441176470588234,
+      "grad_norm": 0.19070957601070404,
+      "learning_rate": 6.980230322205099e-05,
+      "loss": 0.0343,
+      "step": 3150
+    },
+    {
+      "epoch": 1.5490196078431373,
+      "grad_norm": 0.22296807169914246,
+      "learning_rate": 6.918466681937308e-05,
+      "loss": 0.0299,
+      "step": 3160
+    },
+    {
+      "epoch": 1.553921568627451,
+      "grad_norm": 0.2279416173696518,
+      "learning_rate": 6.856832657134424e-05,
+      "loss": 0.0333,
+      "step": 3170
+    },
+    {
+      "epoch": 1.5588235294117647,
+      "grad_norm": 0.2242182493209839,
+      "learning_rate": 6.795330840247006e-05,
+      "loss": 0.0331,
+      "step": 3180
+    },
+    {
+      "epoch": 1.5637254901960784,
+      "grad_norm": 0.2774062752723694,
+      "learning_rate": 6.733963818164686e-05,
+      "loss": 0.0266,
+      "step": 3190
+    },
+    {
+      "epoch": 1.5686274509803921,
+      "grad_norm": 0.37312522530555725,
+      "learning_rate": 6.672734172107354e-05,
+      "loss": 0.0376,
+      "step": 3200
+    },
+    {
+      "epoch": 1.5735294117647058,
+      "grad_norm": 0.23322941362857819,
+      "learning_rate": 6.611644477516595e-05,
+      "loss": 0.0282,
+      "step": 3210
+    },
+    {
+      "epoch": 1.5784313725490198,
+      "grad_norm": 0.32735109329223633,
+      "learning_rate": 6.550697303947345e-05,
+      "loss": 0.0294,
+      "step": 3220
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.21853038668632507,
+      "learning_rate": 6.489895214959828e-05,
+      "loss": 0.0259,
+      "step": 3230
+    },
+    {
+      "epoch": 1.5882352941176472,
+      "grad_norm": 0.3016158640384674,
+      "learning_rate": 6.429240768011719e-05,
+      "loss": 0.028,
+      "step": 3240
+    },
+    {
+      "epoch": 1.593137254901961,
+      "grad_norm": 0.20449745655059814,
+      "learning_rate": 6.368736514350568e-05,
+      "loss": 0.0303,
+      "step": 3250
+    },
+    {
+      "epoch": 1.5980392156862746,
+      "grad_norm": 0.2439008206129074,
+      "learning_rate": 6.308384998906506e-05,
+      "loss": 0.027,
+      "step": 3260
+    },
+    {
+      "epoch": 1.6029411764705883,
+      "grad_norm": 0.28377825021743774,
+      "learning_rate": 6.248188760185173e-05,
+      "loss": 0.0302,
+      "step": 3270
+    },
+    {
+      "epoch": 1.607843137254902,
+      "grad_norm": 0.32138168811798096,
+      "learning_rate": 6.188150330160971e-05,
+      "loss": 0.0255,
+      "step": 3280
+    },
+    {
+      "epoch": 1.6127450980392157,
+      "grad_norm": 0.23931661248207092,
+      "learning_rate": 6.128272234170547e-05,
+      "loss": 0.0284,
+      "step": 3290
+    },
+    {
+      "epoch": 1.6176470588235294,
+      "grad_norm": 0.26550066471099854,
+      "learning_rate": 6.068556990806579e-05,
+      "loss": 0.039,
+      "step": 3300
+    },
+    {
+      "epoch": 1.6225490196078431,
+      "grad_norm": 0.20831480622291565,
+      "learning_rate": 6.0090071118118355e-05,
+      "loss": 0.0248,
+      "step": 3310
+    },
+    {
+      "epoch": 1.6274509803921569,
+      "grad_norm": 0.26879703998565674,
+      "learning_rate": 5.949625101973527e-05,
+      "loss": 0.0303,
+      "step": 3320
+    },
+    {
+      "epoch": 1.6323529411764706,
+      "grad_norm": 0.34190261363983154,
+      "learning_rate": 5.890413459017958e-05,
+      "loss": 0.0296,
+      "step": 3330
+    },
+    {
+      "epoch": 1.6372549019607843,
+      "grad_norm": 0.3451369106769562,
+      "learning_rate": 5.8313746735054544e-05,
+      "loss": 0.0274,
+      "step": 3340
+    },
+    {
+      "epoch": 1.642156862745098,
+      "grad_norm": 0.2692447304725647,
+      "learning_rate": 5.77251122872561e-05,
+      "loss": 0.0303,
+      "step": 3350
+    },
+    {
+      "epoch": 1.6470588235294117,
+      "grad_norm": 0.28057631850242615,
+      "learning_rate": 5.713825600592841e-05,
+      "loss": 0.0335,
+      "step": 3360
+    },
+    {
+      "epoch": 1.6519607843137254,
+      "grad_norm": 0.20118731260299683,
+      "learning_rate": 5.6553202575422385e-05,
+      "loss": 0.0339,
+      "step": 3370
+    },
+    {
+      "epoch": 1.656862745098039,
+      "grad_norm": 0.27384528517723083,
+      "learning_rate": 5.596997660425746e-05,
+      "loss": 0.0296,
+      "step": 3380
+    },
+    {
+      "epoch": 1.6617647058823528,
+      "grad_norm": 0.27839264273643494,
+      "learning_rate": 5.538860262408632e-05,
+      "loss": 0.0306,
+      "step": 3390
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.26187360286712646,
+      "learning_rate": 5.480910508866333e-05,
+      "loss": 0.0327,
+      "step": 3400
+    },
+    {
+      "epoch": 1.6715686274509802,
+      "grad_norm": 0.16635389626026154,
+      "learning_rate": 5.423150837281585e-05,
+      "loss": 0.0268,
+      "step": 3410
+    },
+    {
+      "epoch": 1.6764705882352942,
+      "grad_norm": 0.3123128414154053,
+      "learning_rate": 5.365583677141883e-05,
+      "loss": 0.0345,
+      "step": 3420
+    },
+    {
+      "epoch": 1.6813725490196079,
+      "grad_norm": 0.30305176973342896,
+      "learning_rate": 5.308211449837315e-05,
+      "loss": 0.0264,
+      "step": 3430
+    },
+    {
+      "epoch": 1.6862745098039216,
+      "grad_norm": 0.19436487555503845,
+      "learning_rate": 5.2510365685587026e-05,
+      "loss": 0.0318,
+      "step": 3440
+    },
+    {
+      "epoch": 1.6911764705882353,
+      "grad_norm": 0.2048874795436859,
+      "learning_rate": 5.1940614381961004e-05,
+      "loss": 0.0296,
+      "step": 3450
+    },
+    {
+      "epoch": 1.696078431372549,
+      "grad_norm": 0.32843217253685,
+      "learning_rate": 5.137288455237627e-05,
+      "loss": 0.0288,
+      "step": 3460
+    },
+    {
+      "epoch": 1.7009803921568627,
+      "grad_norm": 0.26734060049057007,
+      "learning_rate": 5.080720007668689e-05,
+      "loss": 0.0309,
+      "step": 3470
+    },
+    {
+      "epoch": 1.7058823529411766,
+      "grad_norm": 0.2050999402999878,
+      "learning_rate": 5.0243584748715235e-05,
+      "loss": 0.0283,
+      "step": 3480
+    },
+    {
+      "epoch": 1.7107843137254903,
+      "grad_norm": 0.32800912857055664,
+      "learning_rate": 4.968206227525111e-05,
+      "loss": 0.0356,
+      "step": 3490
+    },
+    {
+      "epoch": 1.715686274509804,
+      "grad_norm": 0.2212320864200592,
+      "learning_rate": 4.912265627505468e-05,
+      "loss": 0.0278,
+      "step": 3500
+    },
+    {
+      "epoch": 1.7205882352941178,
+      "grad_norm": 0.22088485956192017,
+      "learning_rate": 4.856539027786305e-05,
+      "loss": 0.0315,
+      "step": 3510
+    },
+    {
+      "epoch": 1.7254901960784315,
+      "grad_norm": 0.2626785635948181,
+      "learning_rate": 4.8010287723400494e-05,
+      "loss": 0.0395,
+      "step": 3520
+    },
+    {
+      "epoch": 1.7303921568627452,
+      "grad_norm": 0.343022882938385,
+      "learning_rate": 4.745737196039259e-05,
+      "loss": 0.0235,
+      "step": 3530
+    },
+    {
+      "epoch": 1.7352941176470589,
+      "grad_norm": 0.4321844279766083,
+      "learning_rate": 4.6906666245583965e-05,
+      "loss": 0.0393,
+      "step": 3540
+    },
+    {
+      "epoch": 1.7401960784313726,
+      "grad_norm": 0.34605053067207336,
+      "learning_rate": 4.6358193742760305e-05,
+      "loss": 0.0214,
+      "step": 3550
+    },
+    {
+      "epoch": 1.7450980392156863,
+      "grad_norm": 0.2320283055305481,
+      "learning_rate": 4.5811977521773906e-05,
+      "loss": 0.0331,
+      "step": 3560
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21285474300384521,
+      "learning_rate": 4.526804055757328e-05,
+      "loss": 0.0333,
+      "step": 3570
+    },
+    {
+      "epoch": 1.7549019607843137,
+      "grad_norm": 0.185288667678833,
+      "learning_rate": 4.472640572923687e-05,
+      "loss": 0.0269,
+      "step": 3580
+    },
+    {
+      "epoch": 1.7598039215686274,
+      "grad_norm": 0.2527756989002228,
+      "learning_rate": 4.4187095819010674e-05,
+      "loss": 0.0296,
+      "step": 3590
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.1697828769683838,
+      "learning_rate": 4.365013351135001e-05,
+      "loss": 0.0272,
+      "step": 3600
+    },
+    {
+      "epoch": 1.7696078431372548,
+      "grad_norm": 0.215946227312088,
+      "learning_rate": 4.311554139196522e-05,
+      "loss": 0.0262,
+      "step": 3610
+    },
+    {
+      "epoch": 1.7745098039215685,
+      "grad_norm": 0.41971561312675476,
+      "learning_rate": 4.258334194687188e-05,
+      "loss": 0.0282,
+      "step": 3620
+    },
+    {
+      "epoch": 1.7794117647058822,
+      "grad_norm": 0.18381306529045105,
+      "learning_rate": 4.205355756144489e-05,
+      "loss": 0.0293,
+      "step": 3630
+    },
+    {
+      "epoch": 1.784313725490196,
+      "grad_norm": 0.24697428941726685,
+      "learning_rate": 4.152621051947682e-05,
+      "loss": 0.0205,
+      "step": 3640
+    },
+    {
+      "epoch": 1.7892156862745097,
+      "grad_norm": 0.23640835285186768,
+      "learning_rate": 4.1001323002240754e-05,
+      "loss": 0.0304,
+      "step": 3650
+    },
+    {
+      "epoch": 1.7941176470588234,
+      "grad_norm": 0.21955536305904388,
+      "learning_rate": 4.047891708755724e-05,
+      "loss": 0.0281,
+      "step": 3660
+    },
+    {
+      "epoch": 1.7990196078431373,
+      "grad_norm": 0.34594038128852844,
+      "learning_rate": 3.995901474886568e-05,
+      "loss": 0.0344,
+      "step": 3670
+    },
+    {
+      "epoch": 1.803921568627451,
+      "grad_norm": 0.4010615646839142,
+      "learning_rate": 3.944163785429992e-05,
+      "loss": 0.0241,
+      "step": 3680
+    },
+    {
+      "epoch": 1.8088235294117647,
+      "grad_norm": 0.24570715427398682,
+      "learning_rate": 3.8926808165768715e-05,
+      "loss": 0.0269,
+      "step": 3690
+    },
+    {
+      "epoch": 1.8137254901960784,
+      "grad_norm": 0.2714114785194397,
+      "learning_rate": 3.841454733804016e-05,
+      "loss": 0.0287,
+      "step": 3700
+    },
+    {
+      "epoch": 1.8186274509803921,
+      "grad_norm": 0.29776889085769653,
+      "learning_rate": 3.790487691783099e-05,
+      "loss": 0.0325,
+      "step": 3710
+    },
+    {
+      "epoch": 1.8235294117647058,
+      "grad_norm": 0.20955297350883484,
+      "learning_rate": 3.739781834290006e-05,
+      "loss": 0.0319,
+      "step": 3720
+    },
+    {
+      "epoch": 1.8284313725490198,
+      "grad_norm": 0.2985910475254059,
+      "learning_rate": 3.689339294114692e-05,
+      "loss": 0.0244,
+      "step": 3730
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.33746784925460815,
+      "learning_rate": 3.639162192971457e-05,
+      "loss": 0.0272,
+      "step": 3740
+    },
+    {
+      "epoch": 1.8382352941176472,
+      "grad_norm": 0.2537771761417389,
+      "learning_rate": 3.5892526414096925e-05,
+      "loss": 0.0317,
+      "step": 3750
+    },
+    {
+      "epoch": 1.843137254901961,
+      "grad_norm": 0.30214208364486694,
+      "learning_rate": 3.53961273872513e-05,
+      "loss": 0.0207,
+      "step": 3760
+    },
+    {
+      "epoch": 1.8480392156862746,
+      "grad_norm": 0.3083361089229584,
+      "learning_rate": 3.490244572871524e-05,
+      "loss": 0.0216,
+      "step": 3770
+    },
+    {
+      "epoch": 1.8529411764705883,
+      "grad_norm": 0.24969086050987244,
+      "learning_rate": 3.44115022037284e-05,
+      "loss": 0.0254,
+      "step": 3780
+    },
+    {
+      "epoch": 1.857843137254902,
+      "grad_norm": 0.2084352970123291,
+      "learning_rate": 3.3923317462358905e-05,
+      "loss": 0.0305,
+      "step": 3790
+    },
+    {
+      "epoch": 1.8627450980392157,
+      "grad_norm": 0.21671414375305176,
+      "learning_rate": 3.3437912038635056e-05,
+      "loss": 0.0303,
+      "step": 3800
+    },
+    {
+      "epoch": 1.8676470588235294,
+      "grad_norm": 0.2956879436969757,
+      "learning_rate": 3.295530634968147e-05,
+      "loss": 0.0298,
+      "step": 3810
+    },
+    {
+      "epoch": 1.8725490196078431,
+      "grad_norm": 0.29368528723716736,
+      "learning_rate": 3.24755206948602e-05,
+      "loss": 0.0261,
+      "step": 3820
+    },
+    {
+      "epoch": 1.8774509803921569,
+      "grad_norm": 0.13201627135276794,
+      "learning_rate": 3.199857525491714e-05,
+      "loss": 0.0217,
+      "step": 3830
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.21656860411167145,
+      "learning_rate": 3.1524490091133e-05,
+      "loss": 0.0288,
+      "step": 3840
+    },
+    {
+      "epoch": 1.8872549019607843,
+      "grad_norm": 0.20571519434452057,
+      "learning_rate": 3.105328514447957e-05,
+      "loss": 0.0254,
+      "step": 3850
+    },
+    {
+      "epoch": 1.892156862745098,
+      "grad_norm": 0.2538784444332123,
+      "learning_rate": 3.0584980234780916e-05,
+      "loss": 0.0325,
+      "step": 3860
+    },
+    {
+      "epoch": 1.8970588235294117,
+      "grad_norm": 0.282520592212677,
+      "learning_rate": 3.0119595059879678e-05,
+      "loss": 0.0292,
+      "step": 3870
+    },
+    {
+      "epoch": 1.9019607843137254,
+      "grad_norm": 0.2727642357349396,
+      "learning_rate": 2.965714919480872e-05,
+      "loss": 0.0264,
+      "step": 3880
+    },
+    {
+      "epoch": 1.906862745098039,
+      "grad_norm": 0.1925729215145111,
+      "learning_rate": 2.9197662090967625e-05,
+      "loss": 0.0282,
+      "step": 3890
+    },
+    {
+      "epoch": 1.9117647058823528,
+      "grad_norm": 0.23374304175376892,
+      "learning_rate": 2.8741153075304438e-05,
+      "loss": 0.0266,
+      "step": 3900
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.24565072357654572,
+      "learning_rate": 2.828764134950297e-05,
+      "loss": 0.0198,
+      "step": 3910
+    },
+    {
+      "epoch": 1.9215686274509802,
+      "grad_norm": 0.1271701604127884,
+      "learning_rate": 2.7837145989174974e-05,
+      "loss": 0.0206,
+      "step": 3920
+    },
+    {
+      "epoch": 1.9264705882352942,
+      "grad_norm": 0.25117677450180054,
+      "learning_rate": 2.7389685943057852e-05,
+      "loss": 0.0249,
+      "step": 3930
+    },
+    {
+      "epoch": 1.9313725490196079,
+      "grad_norm": 0.33383405208587646,
+      "learning_rate": 2.6945280032217535e-05,
+      "loss": 0.0298,
+      "step": 3940
+    },
+    {
+      "epoch": 1.9362745098039216,
+      "grad_norm": 0.22882990539073944,
+      "learning_rate": 2.6503946949256974e-05,
+      "loss": 0.0273,
+      "step": 3950
+    },
+    {
+      "epoch": 1.9411764705882353,
+      "grad_norm": 0.2781018316745758,
+      "learning_rate": 2.6065705257529848e-05,
+      "loss": 0.0345,
+      "step": 3960
+    },
+    {
+      "epoch": 1.946078431372549,
+      "grad_norm": 0.23163281381130219,
+      "learning_rate": 2.5630573390359624e-05,
+      "loss": 0.024,
+      "step": 3970
+    },
+    {
+      "epoch": 1.9509803921568627,
+      "grad_norm": 0.30135810375213623,
+      "learning_rate": 2.5198569650264403e-05,
+      "loss": 0.0245,
+      "step": 3980
+    },
+    {
+      "epoch": 1.9558823529411766,
+      "grad_norm": 0.2169611006975174,
+      "learning_rate": 2.4769712208186967e-05,
+      "loss": 0.0217,
+      "step": 3990
+    },
+    {
+      "epoch": 1.9607843137254903,
+      "grad_norm": 0.2509106397628784,
+      "learning_rate": 2.4344019102730542e-05,
+      "loss": 0.0225,
+      "step": 4000
+    },
+    {
+      "epoch": 1.965686274509804,
+      "grad_norm": 0.3170604407787323,
+      "learning_rate": 2.3921508239399913e-05,
+      "loss": 0.027,
+      "step": 4010
+    },
+    {
+      "epoch": 1.9705882352941178,
+      "grad_norm": 0.1460844874382019,
+      "learning_rate": 2.350219738984849e-05,
+      "loss": 0.021,
+      "step": 4020
+    },
+    {
+      "epoch": 1.9754901960784315,
+      "grad_norm": 0.27143651247024536,
+      "learning_rate": 2.3086104191130643e-05,
+      "loss": 0.0262,
+      "step": 4030
+    },
+    {
+      "epoch": 1.9803921568627452,
+      "grad_norm": 0.2494950294494629,
+      "learning_rate": 2.2673246144959935e-05,
+      "loss": 0.0249,
+      "step": 4040
+    },
+    {
+      "epoch": 1.9852941176470589,
+      "grad_norm": 0.26637178659439087,
+      "learning_rate": 2.226364061697287e-05,
+      "loss": 0.0325,
+      "step": 4050
+    },
+    {
+      "epoch": 1.9901960784313726,
+      "grad_norm": 0.2871919274330139,
+      "learning_rate": 2.185730483599856e-05,
+      "loss": 0.0286,
+      "step": 4060
+    },
+    {
+      "epoch": 1.9950980392156863,
+      "grad_norm": 0.2098357230424881,
+      "learning_rate": 2.1454255893334064e-05,
+      "loss": 0.0332,
+      "step": 4070
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2278250902891159,
+      "learning_rate": 2.10545107420253e-05,
+      "loss": 0.0234,
+      "step": 4080
+    },
+    {
+      "epoch": 2.0049019607843137,
+      "grad_norm": 0.266368567943573,
+      "learning_rate": 2.0658086196154236e-05,
+      "loss": 0.0226,
+      "step": 4090
+    },
+    {
+      "epoch": 2.0098039215686274,
+      "grad_norm": 0.10192721337080002,
+      "learning_rate": 2.026499893013144e-05,
+      "loss": 0.0217,
+      "step": 4100
+    },
+    {
+      "epoch": 2.014705882352941,
+      "grad_norm": 0.2021161913871765,
+      "learning_rate": 1.9875265477994875e-05,
+      "loss": 0.0219,
+      "step": 4110
+    },
+    {
+      "epoch": 2.019607843137255,
+      "grad_norm": 0.18436592817306519,
+      "learning_rate": 1.9488902232714267e-05,
+      "loss": 0.0216,
+      "step": 4120
+    },
+    {
+      "epoch": 2.0245098039215685,
+      "grad_norm": 0.18808206915855408,
+      "learning_rate": 1.9105925445501794e-05,
+      "loss": 0.0184,
+      "step": 4130
+    },
+    {
+      "epoch": 2.0294117647058822,
+      "grad_norm": 0.2091018408536911,
+      "learning_rate": 1.87263512251284e-05,
+      "loss": 0.0237,
+      "step": 4140
+    },
+    {
+      "epoch": 2.034313725490196,
+      "grad_norm": 0.29868388175964355,
+      "learning_rate": 1.8350195537246184e-05,
+      "loss": 0.0251,
+      "step": 4150
+    },
+    {
+      "epoch": 2.0392156862745097,
+      "grad_norm": 0.15926848351955414,
+      "learning_rate": 1.797747420371699e-05,
+      "loss": 0.0214,
+      "step": 4160
+    },
+    {
+      "epoch": 2.0441176470588234,
+      "grad_norm": 0.24016976356506348,
+      "learning_rate": 1.7608202901946826e-05,
+      "loss": 0.0206,
+      "step": 4170
+    },
+    {
+      "epoch": 2.049019607843137,
+      "grad_norm": 0.18072175979614258,
+      "learning_rate": 1.7242397164226452e-05,
+      "loss": 0.0192,
+      "step": 4180
+    },
+    {
+      "epoch": 2.053921568627451,
+      "grad_norm": 0.21760503947734833,
+      "learning_rate": 1.6880072377078026e-05,
+      "loss": 0.0237,
+      "step": 4190
+    },
+    {
+      "epoch": 2.0588235294117645,
+      "grad_norm": 0.28834259510040283,
+      "learning_rate": 1.6521243780607974e-05,
+      "loss": 0.0185,
+      "step": 4200
+    },
+    {
+      "epoch": 2.063725490196078,
+      "grad_norm": 0.14096632599830627,
+      "learning_rate": 1.616592646786599e-05,
+      "loss": 0.0184,
+      "step": 4210
+    },
+    {
+      "epoch": 2.0686274509803924,
+      "grad_norm": 0.15555402636528015,
+      "learning_rate": 1.5814135384210026e-05,
+      "loss": 0.02,
+      "step": 4220
+    },
+    {
+      "epoch": 2.073529411764706,
+      "grad_norm": 0.09052202850580215,
+      "learning_rate": 1.5465885326677897e-05,
+      "loss": 0.019,
+      "step": 4230
+    },
+    {
+      "epoch": 2.0784313725490198,
+      "grad_norm": 0.1283917874097824,
+      "learning_rate": 1.512119094336466e-05,
+      "loss": 0.0194,
+      "step": 4240
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.268288791179657,
+      "learning_rate": 1.4780066732806663e-05,
+      "loss": 0.024,
+      "step": 4250
+    },
+    {
+      "epoch": 2.088235294117647,
+      "grad_norm": 0.1498635858297348,
+      "learning_rate": 1.4442527043371622e-05,
+      "loss": 0.0226,
+      "step": 4260
+    },
+    {
+      "epoch": 2.093137254901961,
+      "grad_norm": 0.31013911962509155,
+      "learning_rate": 1.4108586072655062e-05,
+      "loss": 0.0198,
+      "step": 4270
+    },
+    {
+      "epoch": 2.0980392156862746,
+      "grad_norm": 0.19611553847789764,
+      "learning_rate": 1.377825786688326e-05,
+      "loss": 0.029,
+      "step": 4280
+    },
+    {
+      "epoch": 2.1029411764705883,
+      "grad_norm": 0.15280510485172272,
+      "learning_rate": 1.3451556320322344e-05,
+      "loss": 0.0305,
+      "step": 4290
+    },
+    {
+      "epoch": 2.107843137254902,
+      "grad_norm": 0.1233508512377739,
+      "learning_rate": 1.3128495174693833e-05,
+      "loss": 0.0214,
+      "step": 4300
+    },
+    {
+      "epoch": 2.1127450980392157,
+      "grad_norm": 0.23667648434638977,
+      "learning_rate": 1.280908801859676e-05,
+      "loss": 0.017,
+      "step": 4310
+    },
+    {
+      "epoch": 2.1176470588235294,
+      "grad_norm": 0.2285485714673996,
+      "learning_rate": 1.2493348286936013e-05,
+      "loss": 0.019,
+      "step": 4320
+    },
+    {
+      "epoch": 2.122549019607843,
+      "grad_norm": 0.17249974608421326,
+      "learning_rate": 1.2181289260357265e-05,
+      "loss": 0.0233,
+      "step": 4330
+    },
+    {
+      "epoch": 2.127450980392157,
+      "grad_norm": 0.18264269828796387,
+      "learning_rate": 1.1872924064688328e-05,
+      "loss": 0.0176,
+      "step": 4340
+    },
+    {
+      "epoch": 2.1323529411764706,
+      "grad_norm": 0.23498280346393585,
+      "learning_rate": 1.1568265670387125e-05,
+      "loss": 0.0216,
+      "step": 4350
+    },
+    {
+      "epoch": 2.1372549019607843,
+      "grad_norm": 0.20697841048240662,
+      "learning_rate": 1.12673268919961e-05,
+      "loss": 0.0221,
+      "step": 4360
+    },
+    {
+      "epoch": 2.142156862745098,
+      "grad_norm": 0.20883601903915405,
+      "learning_rate": 1.0970120387603122e-05,
+      "loss": 0.0211,
+      "step": 4370
+    },
+    {
+      "epoch": 2.1470588235294117,
+      "grad_norm": 0.2525753676891327,
+      "learning_rate": 1.0676658658309225e-05,
+      "loss": 0.0182,
+      "step": 4380
+    },
+    {
+      "epoch": 2.1519607843137254,
+      "grad_norm": 0.20986422896385193,
+      "learning_rate": 1.0386954047702646e-05,
+      "loss": 0.0222,
+      "step": 4390
+    },
+    {
+      "epoch": 2.156862745098039,
+      "grad_norm": 0.18922965228557587,
+      "learning_rate": 1.010101874133973e-05,
+      "loss": 0.0215,
+      "step": 4400
+    },
+    {
+      "epoch": 2.161764705882353,
+      "grad_norm": 0.23508426547050476,
+      "learning_rate": 9.81886476623226e-06,
+      "loss": 0.0158,
+      "step": 4410
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.17150916159152985,
+      "learning_rate": 9.540503990341743e-06,
+      "loss": 0.0204,
+      "step": 4420
+    },
+    {
+      "epoch": 2.1715686274509802,
+      "grad_norm": 0.12821370363235474,
+      "learning_rate": 9.265948122080048e-06,
+      "loss": 0.0162,
+      "step": 4430
+    },
+    {
+      "epoch": 2.176470588235294,
+      "grad_norm": 0.14045512676239014,
+      "learning_rate": 8.995208709817071e-06,
+      "loss": 0.0231,
+      "step": 4440
+    },
+    {
+      "epoch": 2.1813725490196076,
+      "grad_norm": 0.24774880707263947,
+      "learning_rate": 8.728297141394858e-06,
+      "loss": 0.0205,
+      "step": 4450
+    },
+    {
+      "epoch": 2.186274509803922,
+      "grad_norm": 0.20708513259887695,
+      "learning_rate": 8.465224643648728e-06,
+      "loss": 0.0217,
+      "step": 4460
+    },
+    {
+      "epoch": 2.1911764705882355,
+      "grad_norm": 0.1988290697336197,
+      "learning_rate": 8.206002281934977e-06,
+      "loss": 0.0181,
+      "step": 4470
+    },
+    {
+      "epoch": 2.196078431372549,
+      "grad_norm": 0.24248534440994263,
+      "learning_rate": 7.950640959665457e-06,
+      "loss": 0.014,
+      "step": 4480
+    },
+    {
+      "epoch": 2.200980392156863,
+      "grad_norm": 0.199833944439888,
+      "learning_rate": 7.69915141784896e-06,
+      "loss": 0.0177,
+      "step": 4490
+    },
+    {
+      "epoch": 2.2058823529411766,
+      "grad_norm": 0.18880146741867065,
+      "learning_rate": 7.451544234639473e-06,
+      "loss": 0.0309,
+      "step": 4500
+    },
+    {
+      "epoch": 2.2107843137254903,
+      "grad_norm": 0.19817057251930237,
+      "learning_rate": 7.207829824891199e-06,
+      "loss": 0.0135,
+      "step": 4510
+    },
+    {
+      "epoch": 2.215686274509804,
+      "grad_norm": 0.22702986001968384,
+      "learning_rate": 6.968018439720414e-06,
+      "loss": 0.0242,
+      "step": 4520
+    },
+    {
+      "epoch": 2.2205882352941178,
+      "grad_norm": 0.23108519613742828,
+      "learning_rate": 6.732120166074441e-06,
+      "loss": 0.0266,
+      "step": 4530
+    },
+    {
+      "epoch": 2.2254901960784315,
+      "grad_norm": 0.2683473229408264,
+      "learning_rate": 6.500144926307295e-06,
+      "loss": 0.0138,
+      "step": 4540
+    },
+    {
+      "epoch": 2.230392156862745,
+      "grad_norm": 0.3906085193157196,
+      "learning_rate": 6.272102477762254e-06,
+      "loss": 0.0257,
+      "step": 4550
+    },
+    {
+      "epoch": 2.235294117647059,
+      "grad_norm": 0.16685569286346436,
+      "learning_rate": 6.048002412361598e-06,
+      "loss": 0.0197,
+      "step": 4560
+    },
+    {
+      "epoch": 2.2401960784313726,
+      "grad_norm": 0.19442564249038696,
+      "learning_rate": 5.827854156203017e-06,
+      "loss": 0.0183,
+      "step": 4570
+    },
+    {
+      "epoch": 2.2450980392156863,
+      "grad_norm": 0.22825686633586884,
+      "learning_rate": 5.611666969163243e-06,
+      "loss": 0.0192,
+      "step": 4580
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.13165044784545898,
+      "learning_rate": 5.399449944508439e-06,
+      "loss": 0.0181,
+      "step": 4590
+    },
+    {
+      "epoch": 2.2549019607843137,
+      "grad_norm": 0.32770487666130066,
+      "learning_rate": 5.1912120085118365e-06,
+      "loss": 0.0194,
+      "step": 4600
+    },
+    {
+      "epoch": 2.2598039215686274,
+      "grad_norm": 0.20789536833763123,
+      "learning_rate": 4.986961920078204e-06,
+      "loss": 0.0274,
+      "step": 4610
+    },
+    {
+      "epoch": 2.264705882352941,
+      "grad_norm": 0.3107619881629944,
+      "learning_rate": 4.786708270375462e-06,
+      "loss": 0.0244,
+      "step": 4620
+    },
+    {
+      "epoch": 2.269607843137255,
+      "grad_norm": 0.11234085261821747,
+      "learning_rate": 4.590459482473286e-06,
+      "loss": 0.0125,
+      "step": 4630
+    },
+    {
+      "epoch": 2.2745098039215685,
+      "grad_norm": 0.2838551700115204,
+      "learning_rate": 4.398223810988866e-06,
+      "loss": 0.0209,
+      "step": 4640
+    },
+    {
+      "epoch": 2.2794117647058822,
+      "grad_norm": 0.2697765529155731,
+      "learning_rate": 4.2100093417396845e-06,
+      "loss": 0.0245,
+      "step": 4650
+    },
+    {
+      "epoch": 2.284313725490196,
+      "grad_norm": 0.1846655011177063,
+      "learning_rate": 4.0258239914033765e-06,
+      "loss": 0.0271,
+      "step": 4660
+    },
+    {
+      "epoch": 2.2892156862745097,
+      "grad_norm": 0.20711906254291534,
+      "learning_rate": 3.8456755071847765e-06,
+      "loss": 0.0262,
+      "step": 4670
+    },
+    {
+      "epoch": 2.2941176470588234,
+      "grad_norm": 0.23577173054218292,
+      "learning_rate": 3.6695714664900293e-06,
+      "loss": 0.0147,
+      "step": 4680
+    },
+    {
+      "epoch": 2.299019607843137,
+      "grad_norm": 0.21056267619132996,
+      "learning_rate": 3.49751927660793e-06,
+      "loss": 0.0242,
+      "step": 4690
+    },
+    {
+      "epoch": 2.303921568627451,
+      "grad_norm": 0.1903896927833557,
+      "learning_rate": 3.329526174398223e-06,
+      "loss": 0.0199,
+      "step": 4700
+    },
+    {
+      "epoch": 2.3088235294117645,
+      "grad_norm": 0.1740642637014389,
+      "learning_rate": 3.165599225987381e-06,
+      "loss": 0.0241,
+      "step": 4710
+    },
+    {
+      "epoch": 2.313725490196078,
+      "grad_norm": 0.23523923754692078,
+      "learning_rate": 3.005745326471254e-06,
+      "loss": 0.0196,
+      "step": 4720
+    },
+    {
+      "epoch": 2.318627450980392,
+      "grad_norm": 0.17898762226104736,
+      "learning_rate": 2.849971199625112e-06,
+      "loss": 0.0178,
+      "step": 4730
+    },
+    {
+      "epoch": 2.323529411764706,
+      "grad_norm": 0.18050484359264374,
+      "learning_rate": 2.6982833976208043e-06,
+      "loss": 0.0264,
+      "step": 4740
+    },
+    {
+      "epoch": 2.3284313725490198,
+      "grad_norm": 0.14259324967861176,
+      "learning_rate": 2.5506883007511695e-06,
+      "loss": 0.0163,
+      "step": 4750
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.25935426354408264,
+      "learning_rate": 2.407192117161683e-06,
+      "loss": 0.0215,
+      "step": 4760
+    },
+    {
+      "epoch": 2.338235294117647,
+      "grad_norm": 0.24692723155021667,
+      "learning_rate": 2.2678008825893106e-06,
+      "loss": 0.0185,
+      "step": 4770
+    },
+    {
+      "epoch": 2.343137254901961,
+      "grad_norm": 0.22854046523571014,
+      "learning_rate": 2.1325204601086222e-06,
+      "loss": 0.0235,
+      "step": 4780
+    },
+    {
+      "epoch": 2.3480392156862746,
+      "grad_norm": 0.31760168075561523,
+      "learning_rate": 2.001356539885213e-06,
+      "loss": 0.0279,
+      "step": 4790
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 0.19233286380767822,
+      "learning_rate": 1.8743146389363474e-06,
+      "loss": 0.0174,
+      "step": 4800
+    },
+    {
+      "epoch": 2.357843137254902,
+      "grad_norm": 0.28652098774909973,
+      "learning_rate": 1.7514001008988923e-06,
+      "loss": 0.0193,
+      "step": 4810
+    },
+    {
+      "epoch": 2.3627450980392157,
+      "grad_norm": 0.16845420002937317,
+      "learning_rate": 1.6326180958045502e-06,
+      "loss": 0.0177,
+      "step": 4820
+    },
+    {
+      "epoch": 2.3676470588235294,
+      "grad_norm": 0.12303224951028824,
+      "learning_rate": 1.517973619862445e-06,
+      "loss": 0.0205,
+      "step": 4830
+    },
+    {
+      "epoch": 2.372549019607843,
+      "grad_norm": 0.1442280411720276,
+      "learning_rate": 1.4074714952489132e-06,
+      "loss": 0.0215,
+      "step": 4840
+    },
+    {
+      "epoch": 2.377450980392157,
+      "grad_norm": 0.18173760175704956,
+      "learning_rate": 1.3011163699046758e-06,
+      "loss": 0.0166,
+      "step": 4850
+    },
+    {
+      "epoch": 2.3823529411764706,
+      "grad_norm": 0.2543584406375885,
+      "learning_rate": 1.1989127173393955e-06,
+      "loss": 0.0195,
+      "step": 4860
+    },
+    {
+      "epoch": 2.3872549019607843,
+      "grad_norm": 0.14100182056427002,
+      "learning_rate": 1.1008648364434493e-06,
+      "loss": 0.0252,
+      "step": 4870
+    },
+    {
+      "epoch": 2.392156862745098,
+      "grad_norm": 0.22381238639354706,
+      "learning_rate": 1.0069768513071287e-06,
+      "loss": 0.0184,
+      "step": 4880
+    },
+    {
+      "epoch": 2.3970588235294117,
+      "grad_norm": 0.1522032916545868,
+      "learning_rate": 9.172527110472007e-07,
+      "loss": 0.0226,
+      "step": 4890
+    },
+    {
+      "epoch": 2.4019607843137254,
+      "grad_norm": 0.151298388838768,
+      "learning_rate": 8.316961896407293e-07,
+      "loss": 0.0161,
+      "step": 4900
+    },
+    {
+      "epoch": 2.406862745098039,
+      "grad_norm": 0.10205589234828949,
+      "learning_rate": 7.503108857664476e-07,
+      "loss": 0.0221,
+      "step": 4910
+    },
+    {
+      "epoch": 2.411764705882353,
+      "grad_norm": 0.29145070910453796,
+      "learning_rate": 6.731002226532557e-07,
+      "loss": 0.0256,
+      "step": 4920
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.11820173263549805,
+      "learning_rate": 6.000674479363366e-07,
+      "loss": 0.0192,
+      "step": 4930
+    },
+    {
+      "epoch": 2.4215686274509802,
+      "grad_norm": 0.34024494886398315,
+      "learning_rate": 5.312156335205098e-07,
+      "loss": 0.0184,
+      "step": 4940
+    },
+    {
+      "epoch": 2.426470588235294,
+      "grad_norm": 0.2437254935503006,
+      "learning_rate": 4.665476754510234e-07,
+      "loss": 0.0172,
+      "step": 4950
+    },
+    {
+      "epoch": 2.431372549019608,
+      "grad_norm": 0.22836612164974213,
+      "learning_rate": 4.0606629379175143e-07,
+      "loss": 0.0236,
+      "step": 4960
+    },
+    {
+      "epoch": 2.436274509803922,
+      "grad_norm": 0.30892133712768555,
+      "learning_rate": 3.497740325107746e-07,
+      "loss": 0.021,
+      "step": 4970
+    },
+    {
+      "epoch": 2.4411764705882355,
+      "grad_norm": 0.1466980129480362,
+      "learning_rate": 2.9767325937338775e-07,
+      "loss": 0.0158,
+      "step": 4980
+    },
+    {
+      "epoch": 2.446078431372549,
+      "grad_norm": 0.17119024693965912,
+      "learning_rate": 2.497661658424688e-07,
+      "loss": 0.0211,
+      "step": 4990
+    },
+    {
+      "epoch": 2.450980392156863,
+      "grad_norm": 0.24735775589942932,
+      "learning_rate": 2.0605476698636328e-07,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 2.4558823529411766,
+      "grad_norm": 0.22227314114570618,
+      "learning_rate": 1.6654090139408551e-07,
+      "loss": 0.0222,
+      "step": 5010
+    },
+    {
+      "epoch": 2.4607843137254903,
+      "grad_norm": 0.2925474941730499,
+      "learning_rate": 1.3122623109795839e-07,
+      "loss": 0.0212,
+      "step": 5020
+    },
+    {
+      "epoch": 2.465686274509804,
+      "grad_norm": 0.11938751488924026,
+      "learning_rate": 1.0011224150379139e-07,
+      "loss": 0.0206,
+      "step": 5030
+    },
+    {
+      "epoch": 2.4705882352941178,
+      "grad_norm": 0.18019632995128632,
+      "learning_rate": 7.320024132829729e-08,
+      "loss": 0.0175,
+      "step": 5040
+    },
+    {
+      "epoch": 2.4754901960784315,
+      "grad_norm": 0.1969996839761734,
+      "learning_rate": 5.049136254413611e-08,
+      "loss": 0.0196,
+      "step": 5050
+    },
+    {
+      "epoch": 2.480392156862745,
+      "grad_norm": 0.26969224214553833,
+      "learning_rate": 3.1986560332242234e-08,
+      "loss": 0.0159,
+      "step": 5060
+    },
+    {
+      "epoch": 2.485294117647059,
+      "grad_norm": 0.24808961153030396,
+      "learning_rate": 1.768661304166752e-08,
+      "loss": 0.0235,
+      "step": 5070
+    },
+    {
+      "epoch": 2.4901960784313726,
+      "grad_norm": 0.08070988208055496,
+      "learning_rate": 7.592122156829806e-09,
+      "loss": 0.0196,
+      "step": 5080
+    },
+    {
+      "epoch": 2.4950980392156863,
+      "grad_norm": 0.3003765642642975,
+      "learning_rate": 1.7035122722663943e-09,
+      "loss": 0.0214,
+      "step": 5090
+    },
+    {
+      "epoch": 2.4995098039215686,
+      "step": 5099,
+      "total_flos": 1.0010895665363712e+17,
+      "train_loss": 0.049077389520344766,
+      "train_runtime": 1734.3659,
+      "train_samples_per_second": 47.04,
+      "train_steps_per_second": 2.94
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5099,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0010895665363712e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975c0abb6e9f88f537854c00fe7683cd31d159345bd7f0b498bc9dfe0f157343
+size 5240