diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/resolved_config.yaml b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/resolved_config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..21b9af428aadcb60902e3a3c7de7672c5ca9b7ab
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/resolved_config.yaml
@@ -0,0 +1,28 @@
+experiment_name: fewshot_39tasks_5shot_from_baseline26_fullactionhead_seed0_5k
+policy_type: baseline
+base_model_path: ${HOME}/groot_robocasa/Atomic26_baseline/checkpoint-120000
+output_root: ${HOME}/groot_robocasa/robocasa_v2/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0
+dataset:
+  dataset_soup: fewshot_heldout_atomic39_human_5shot
+training:
+  num_gpus: 1
+  batch_size: 64
+  seed: 42
+  filter_key_seed: 0
+  manifest_path: ${HOME}/clvla/benchmarks/robocasa_v2/my_scripts/Fewshot/manifests/fewshot_heldout_atomic39/shot5_seed0.json
+  save_total_limit: 4
+phases:
+- name: train_5shot_seed0_fullactionhead_5k
+  max_steps: 5000
+  save_steps: 0
+  save_step_list:
+  - 1000
+  - 3000
+  - 5000
+  save_final_model: false
+  trainable:
+    tune_llm: false
+    tune_visual: false
+    tune_projector: true
+    tune_diffusion_model: true
+resolved_sweep: {}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/seed0_5k.yaml b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/seed0_5k.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..7dec189e22ad0a68635e7157878809efdb975a89
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/seed0_5k.yaml
@@ -0,0 +1,27 @@
+experiment_name: fewshot_39tasks_5shot_from_baseline26_fullactionhead_seed0_5k
+policy_type: baseline
+base_model_path: ${HOME}/groot_robocasa/Atomic26_baseline/checkpoint-120000
+output_root: ${HOME}/groot_robocasa/robocasa_v2/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0
+dataset:
+  dataset_soup: fewshot_heldout_atomic39_human_5shot
+training:
+  num_gpus: 1
+  batch_size: 64
+  seed: 42
+  filter_key_seed: 0
+  manifest_path: ${HOME}/clvla/benchmarks/robocasa_v2/my_scripts/Fewshot/manifests/fewshot_heldout_atomic39/shot5_seed0.json
+  save_total_limit: 4
+phases:
+- name: train_5shot_seed0_fullactionhead_5k
+  max_steps: 5000
+  save_steps: 0
+  save_step_list:
+  - 1000
+  - 3000
+  - 5000
+  save_final_model: false
+  trainable:
+    tune_llm: false
+    tune_visual: false
+    tune_projector: true
+    tune_diffusion_model: true
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b06ee3aaea89953051ee0fb13b0934a646c05634
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61046d6d7e9c58345891562a0fe071dd9475ab479c8ad61ed6d04127525d516c
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5cb91781cd23ce592e156076092143c18a8604b
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1710a8ef3e45be4a163c4f962d41466205343411de6f144fc6a83a28b8f503bf
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e59959a3badb3e44084639ee594b80925a2929e8
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf47a3b7290c0b108a84d6a1be53d7485caf86c3052476f4f13b3b4f8067bef
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cddb85352b4d053450624108786800cbad81d6cb
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19ead5779e3f8f2f666b7793de3a03d118f57f1b16a97eeb87bd732d18b445
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/config.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/config.json
@@ -0,0 +1,64 @@
+{
+  "action_dim": 32,
+  "action_head_cfg": {
+    "action_dim": 32,
+    "action_horizon": 16,
+    "add_pos_embed": true,
+    "backbone_embedding_dim": 2048,
+    "diffusion_model_cfg": {
+      "attention_head_dim": 48,
+      "cross_attention_dim": 2048,
+      "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
+    },
+    "hidden_size": 1024,
+    "input_embedding_dim": 1536,
+    "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": 4,
+    "num_target_vision_tokens": 32,
+    "num_timestep_buckets": 1000,
+    "tune_diffusion_model": true,
+    "tune_projector": true,
+    "use_vlln": true,
+    "vl_self_attention_cfg": {
+      "attention_head_dim": 64,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "num_attention_heads": 32,
+      "num_layers": 4,
+      "positional_embeddings": null
+    }
+  },
+  "action_horizon": 16,
+  "architectures": [
+    "GR00T_N1_5"
+  ],
+  "attn_implementation": null,
+  "backbone_cfg": {
+    "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
+    "load_bf16": false,
+    "project_to_dim": null,
+    "reproject_vision": false,
+    "select_layer": 12,
+    "tune_llm": false,
+    "tune_visual": true,
+    "use_flash_attention": true
+  },
+  "compute_dtype": "bfloat16",
+  "hidden_size": 2048,
+  "model_dtype": "float32",
+  "model_type": "gr00t_n1_5",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..11e7573e87819713aa14336d6276457412786937
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25f0b02d749bea2cca2fdfc5adf54ab4d1ebc771d7dee2a89d0784d30c57367
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a9b2bf998ecd9cd48acd9a4ce64df52bfd7125e7
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bb2f052e8c73380d13c16d9797f5516bcfbe2b88b40b1b94885f5ac80b6e0e6
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0a8d88210a849e66e284fd4cd4d247f2b03ee0ad
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfb9120e2de97798d6ff37a711f2ac1f7397b57a59789d33d9833d2d22d5cab
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de4e41c4a6949df056e028b10a18e7f8cd7b7580
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d8e6d8e53e6b837084d0cc18fdd63ca9e40bd44a65d38eb52695647a8e84e8
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/trainer_state.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4da60235b75b3d11b5eb6833ebf3b45ff6dee5e7
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/checkpoint-3000/trainer_state.json
@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.033557046979865,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016778523489932886,
+      "grad_norm": 1.0388541221618652,
+      "learning_rate": 1.08e-06,
+      "loss": 0.2251,
+      "step": 10
+    },
+    {
+      "epoch": 0.03355704697986577,
+      "grad_norm": 2.1458616256713867,
+      "learning_rate": 2.28e-06,
+      "loss": 0.2286,
+      "step": 20
+    },
+    {
+      "epoch": 0.050335570469798654,
+      "grad_norm": 1.0232809782028198,
+      "learning_rate": 3.48e-06,
+      "loss": 0.1901,
+      "step": 30
+    },
+    {
+      "epoch": 0.06711409395973154,
+      "grad_norm": 0.6550730466842651,
+      "learning_rate": 4.68e-06,
+      "loss": 0.1701,
+      "step": 40
+    },
+    {
+      "epoch": 0.08389261744966443,
+      "grad_norm": 0.6718728542327881,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 0.1338,
+      "step": 50
+    },
+    {
+      "epoch": 0.10067114093959731,
+      "grad_norm": 0.5689961910247803,
+      "learning_rate": 7.08e-06,
+      "loss": 0.1274,
+      "step": 60
+    },
+    {
+      "epoch": 0.1174496644295302,
+      "grad_norm": 0.4747137129306793,
+      "learning_rate": 8.28e-06,
+      "loss": 0.1026,
+      "step": 70
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "grad_norm": 0.3482891023159027,
+      "learning_rate": 9.48e-06,
+      "loss": 0.0929,
+      "step": 80
+    },
+    {
+      "epoch": 0.15100671140939598,
+      "grad_norm": 0.3731693923473358,
+      "learning_rate": 1.068e-05,
+      "loss": 0.0835,
+      "step": 90
+    },
+    {
+      "epoch": 0.16778523489932887,
+      "grad_norm": 0.3104197680950165,
+      "learning_rate": 1.1880000000000001e-05,
+      "loss": 0.0756,
+      "step": 100
+    },
+    {
+      "epoch": 0.18456375838926176,
+      "grad_norm": 0.2531762421131134,
+      "learning_rate": 1.308e-05,
+      "loss": 0.0726,
+      "step": 110
+    },
+    {
+      "epoch": 0.20134228187919462,
+      "grad_norm": 0.29734447598457336,
+      "learning_rate": 1.428e-05,
+      "loss": 0.0666,
+      "step": 120
+    },
+    {
+      "epoch": 0.2181208053691275,
+      "grad_norm": 0.24068564176559448,
+      "learning_rate": 1.548e-05,
+      "loss": 0.0632,
+      "step": 130
+    },
+    {
+      "epoch": 0.2348993288590604,
+      "grad_norm": 0.3159964382648468,
+      "learning_rate": 1.6680000000000003e-05,
+      "loss": 0.0647,
+      "step": 140
+    },
+    {
+      "epoch": 0.2516778523489933,
+      "grad_norm": 0.23858052492141724,
+      "learning_rate": 1.7879999999999998e-05,
+      "loss": 0.065,
+      "step": 150
+    },
+    {
+      "epoch": 0.2684563758389262,
+      "grad_norm": 0.2374449223279953,
+      "learning_rate": 1.908e-05,
+      "loss": 0.0601,
+      "step": 160
+    },
+    {
+      "epoch": 0.28523489932885904,
+      "grad_norm": 0.20790916681289673,
+      "learning_rate": 2.0280000000000002e-05,
+      "loss": 0.0593,
+      "step": 170
+    },
+    {
+      "epoch": 0.30201342281879195,
+      "grad_norm": 0.1952684223651886,
+      "learning_rate": 2.148e-05,
+      "loss": 0.0527,
+      "step": 180
+    },
+    {
+      "epoch": 0.3187919463087248,
+      "grad_norm": 0.3542490601539612,
+      "learning_rate": 2.268e-05,
+      "loss": 0.0583,
+      "step": 190
+    },
+    {
+      "epoch": 0.33557046979865773,
+      "grad_norm": 0.28306496143341064,
+      "learning_rate": 2.3880000000000002e-05,
+      "loss": 0.057,
+      "step": 200
+    },
+    {
+      "epoch": 0.3523489932885906,
+      "grad_norm": 0.2882148325443268,
+      "learning_rate": 2.508e-05,
+      "loss": 0.0541,
+      "step": 210
+    },
+    {
+      "epoch": 0.3691275167785235,
+      "grad_norm": 0.19627629220485687,
+      "learning_rate": 2.628e-05,
+      "loss": 0.0552,
+      "step": 220
+    },
+    {
+      "epoch": 0.3859060402684564,
+      "grad_norm": 0.1990572214126587,
+      "learning_rate": 2.748e-05,
+      "loss": 0.0506,
+      "step": 230
+    },
+    {
+      "epoch": 0.40268456375838924,
+      "grad_norm": 0.24517984688282013,
+      "learning_rate": 2.868e-05,
+      "loss": 0.0528,
+      "step": 240
+    },
+    {
+      "epoch": 0.41946308724832215,
+      "grad_norm": 0.2502721846103668,
+      "learning_rate": 2.9880000000000002e-05,
+      "loss": 0.0494,
+      "step": 250
+    },
+    {
+      "epoch": 0.436241610738255,
+      "grad_norm": 0.18276523053646088,
+      "learning_rate": 2.9999734259635676e-05,
+      "loss": 0.0451,
+      "step": 260
+    },
+    {
+      "epoch": 0.45302013422818793,
+      "grad_norm": 0.2971280813217163,
+      "learning_rate": 2.9998815663057245e-05,
+      "loss": 0.0488,
+      "step": 270
+    },
+    {
+      "epoch": 0.4697986577181208,
+      "grad_norm": 0.20258396863937378,
+      "learning_rate": 2.999724096969228e-05,
+      "loss": 0.0454,
+      "step": 280
+    },
+    {
+      "epoch": 0.4865771812080537,
+      "grad_norm": 0.27414819598197937,
+      "learning_rate": 2.9995010248422984e-05,
+      "loss": 0.0436,
+      "step": 290
+    },
+    {
+      "epoch": 0.5033557046979866,
+      "grad_norm": 0.2332964837551117,
+      "learning_rate": 2.999212359682832e-05,
+      "loss": 0.0459,
+      "step": 300
+    },
+    {
+      "epoch": 0.5201342281879194,
+      "grad_norm": 0.23066847026348114,
+      "learning_rate": 2.9988581141179787e-05,
+      "loss": 0.0446,
+      "step": 310
+    },
+    {
+      "epoch": 0.5369127516778524,
+      "grad_norm": 0.21959786117076874,
+      "learning_rate": 2.998438303643587e-05,
+      "loss": 0.0401,
+      "step": 320
+    },
+    {
+      "epoch": 0.5536912751677853,
+      "grad_norm": 0.1958390325307846,
+      "learning_rate": 2.997952946623527e-05,
+      "loss": 0.0418,
+      "step": 330
+    },
+    {
+      "epoch": 0.5704697986577181,
+      "grad_norm": 0.23207500576972961,
+      "learning_rate": 2.9974020642888875e-05,
+      "loss": 0.0455,
+      "step": 340
+    },
+    {
+      "epoch": 0.587248322147651,
+      "grad_norm": 0.1922421157360077,
+      "learning_rate": 2.9967856807370458e-05,
+      "loss": 0.0413,
+      "step": 350
+    },
+    {
+      "epoch": 0.6040268456375839,
+      "grad_norm": 0.20857904851436615,
+      "learning_rate": 2.996103822930615e-05,
+      "loss": 0.0445,
+      "step": 360
+    },
+    {
+      "epoch": 0.6208053691275168,
+      "grad_norm": 0.20092910528182983,
+      "learning_rate": 2.9953565206962653e-05,
+      "loss": 0.0376,
+      "step": 370
+    },
+    {
+      "epoch": 0.6375838926174496,
+      "grad_norm": 0.17054688930511475,
+      "learning_rate": 2.9945438067234172e-05,
+      "loss": 0.039,
+      "step": 380
+    },
+    {
+      "epoch": 0.6543624161073825,
+      "grad_norm": 0.18088215589523315,
+      "learning_rate": 2.9936657165628124e-05,
+      "loss": 0.0385,
+      "step": 390
+    },
+    {
+      "epoch": 0.6711409395973155,
+      "grad_norm": 0.22038601338863373,
+      "learning_rate": 2.992722288624959e-05,
+      "loss": 0.0381,
+      "step": 400
+    },
+    {
+      "epoch": 0.6879194630872483,
+      "grad_norm": 0.16217142343521118,
+      "learning_rate": 2.9917135641784515e-05,
+      "loss": 0.0384,
+      "step": 410
+    },
+    {
+      "epoch": 0.7046979865771812,
+      "grad_norm": 0.1879982352256775,
+      "learning_rate": 2.9906395873481655e-05,
+      "loss": 0.0375,
+      "step": 420
+    },
+    {
+      "epoch": 0.7214765100671141,
+      "grad_norm": 0.1811523288488388,
+      "learning_rate": 2.989500405113326e-05,
+      "loss": 0.0391,
+      "step": 430
+    },
+    {
+      "epoch": 0.738255033557047,
+      "grad_norm": 0.15471374988555908,
+      "learning_rate": 2.9882960673054547e-05,
+      "loss": 0.0347,
+      "step": 440
+    },
+    {
+      "epoch": 0.7550335570469798,
+      "grad_norm": 0.20345190167427063,
+      "learning_rate": 2.9870266266061886e-05,
+      "loss": 0.034,
+      "step": 450
+    },
+    {
+      "epoch": 0.7718120805369127,
+      "grad_norm": 0.22297805547714233,
+      "learning_rate": 2.9856921385449766e-05,
+      "loss": 0.0364,
+      "step": 460
+    },
+    {
+      "epoch": 0.7885906040268457,
+      "grad_norm": 0.18335476517677307,
+      "learning_rate": 2.9842926614966502e-05,
+      "loss": 0.0355,
+      "step": 470
+    },
+    {
+      "epoch": 0.8053691275167785,
+      "grad_norm": 0.21670755743980408,
+      "learning_rate": 2.982828256678868e-05,
+      "loss": 0.0356,
+      "step": 480
+    },
+    {
+      "epoch": 0.8221476510067114,
+      "grad_norm": 0.22311744093894958,
+      "learning_rate": 2.9812989881494412e-05,
+      "loss": 0.0345,
+      "step": 490
+    },
+    {
+      "epoch": 0.8389261744966443,
+      "grad_norm": 0.1998075544834137,
+      "learning_rate": 2.9797049228035296e-05,
+      "loss": 0.0377,
+      "step": 500
+    },
+    {
+      "epoch": 0.8557046979865772,
+      "grad_norm": 0.19125983119010925,
+      "learning_rate": 2.978046130370715e-05,
+      "loss": 0.0334,
+      "step": 510
+    },
+    {
+      "epoch": 0.87248322147651,
+      "grad_norm": 0.2721741497516632,
+      "learning_rate": 2.9763226834119535e-05,
+      "loss": 0.0355,
+      "step": 520
+    },
+    {
+      "epoch": 0.889261744966443,
+      "grad_norm": 0.20220515131950378,
+      "learning_rate": 2.9745346573163963e-05,
+      "loss": 0.0345,
+      "step": 530
+    },
+    {
+      "epoch": 0.9060402684563759,
+      "grad_norm": 0.29605722427368164,
+      "learning_rate": 2.9726821302980987e-05,
+      "loss": 0.0338,
+      "step": 540
+    },
+    {
+      "epoch": 0.9228187919463087,
+      "grad_norm": 0.1908901482820511,
+      "learning_rate": 2.9707651833925935e-05,
+      "loss": 0.0306,
+      "step": 550
+    },
+    {
+      "epoch": 0.9395973154362416,
+      "grad_norm": 0.18491318821907043,
+      "learning_rate": 2.968783900453348e-05,
+      "loss": 0.034,
+      "step": 560
+    },
+    {
+      "epoch": 0.9563758389261745,
+      "grad_norm": 0.15446802973747253,
+      "learning_rate": 2.9667383681480968e-05,
+      "loss": 0.0365,
+      "step": 570
+    },
+    {
+      "epoch": 0.9731543624161074,
+      "grad_norm": 0.18752741813659668,
+      "learning_rate": 2.9646286759550493e-05,
+      "loss": 0.032,
+      "step": 580
+    },
+    {
+      "epoch": 0.9899328859060402,
+      "grad_norm": 0.4135258197784424,
+      "learning_rate": 2.9624549161589764e-05,
+      "loss": 0.031,
+      "step": 590
+    },
+    {
+      "epoch": 1.0067114093959733,
+      "grad_norm": 0.19306783378124237,
+      "learning_rate": 2.9602171838471745e-05,
+      "loss": 0.0314,
+      "step": 600
+    },
+    {
+      "epoch": 1.023489932885906,
+      "grad_norm": 0.1685028225183487,
+      "learning_rate": 2.957915576905303e-05,
+      "loss": 0.03,
+      "step": 610
+    },
+    {
+      "epoch": 1.0402684563758389,
+      "grad_norm": 0.15813031792640686,
+      "learning_rate": 2.9555501960131058e-05,
+      "loss": 0.0287,
+      "step": 620
+    },
+    {
+      "epoch": 1.0570469798657718,
+      "grad_norm": 0.16480985283851624,
+      "learning_rate": 2.9531211446400068e-05,
+      "loss": 0.0326,
+      "step": 630
+    },
+    {
+      "epoch": 1.0738255033557047,
+      "grad_norm": 0.16310042142868042,
+      "learning_rate": 2.9506285290405813e-05,
+      "loss": 0.0319,
+      "step": 640
+    },
+    {
+      "epoch": 1.0906040268456376,
+      "grad_norm": 0.28549784421920776,
+      "learning_rate": 2.948072458249911e-05,
+      "loss": 0.0308,
+      "step": 650
+    },
+    {
+      "epoch": 1.1073825503355705,
+      "grad_norm": 0.4056604206562042,
+      "learning_rate": 2.9454530440788125e-05,
+      "loss": 0.0298,
+      "step": 660
+    },
+    {
+      "epoch": 1.1241610738255035,
+      "grad_norm": 0.24711917340755463,
+      "learning_rate": 2.9427704011089474e-05,
+      "loss": 0.0287,
+      "step": 670
+    },
+    {
+      "epoch": 1.1409395973154361,
+      "grad_norm": 0.2376968264579773,
+      "learning_rate": 2.94002464668781e-05,
+      "loss": 0.0281,
+      "step": 680
+    },
+    {
+      "epoch": 1.157718120805369,
+      "grad_norm": 0.1800604611635208,
+      "learning_rate": 2.9372159009235936e-05,
+      "loss": 0.0269,
+      "step": 690
+    },
+    {
+      "epoch": 1.174496644295302,
+      "grad_norm": 0.15358570218086243,
+      "learning_rate": 2.9343442866799365e-05,
+      "loss": 0.0277,
+      "step": 700
+    },
+    {
+      "epoch": 1.191275167785235,
+      "grad_norm": 0.28675392270088196,
+      "learning_rate": 2.9314099295705495e-05,
+      "loss": 0.0297,
+      "step": 710
+    },
+    {
+      "epoch": 1.2080536912751678,
+      "grad_norm": 0.20398671925067902,
+      "learning_rate": 2.928412957953718e-05,
+      "loss": 0.0275,
+      "step": 720
+    },
+    {
+      "epoch": 1.2248322147651007,
+      "grad_norm": 0.2259288877248764,
+      "learning_rate": 2.925353502926689e-05,
+      "loss": 0.0296,
+      "step": 730
+    },
+    {
+      "epoch": 1.2416107382550337,
+      "grad_norm": 0.16415706276893616,
+      "learning_rate": 2.922231698319937e-05,
+      "loss": 0.0291,
+      "step": 740
+    },
+    {
+      "epoch": 1.2583892617449663,
+      "grad_norm": 0.19491496682167053,
+      "learning_rate": 2.9190476806913088e-05,
+      "loss": 0.0295,
+      "step": 750
+    },
+    {
+      "epoch": 1.2751677852348993,
+      "grad_norm": 0.18139910697937012,
+      "learning_rate": 2.9158015893200504e-05,
+      "loss": 0.0285,
+      "step": 760
+    },
+    {
+      "epoch": 1.2919463087248322,
+      "grad_norm": 0.18600593507289886,
+      "learning_rate": 2.9124935662007137e-05,
+      "loss": 0.0307,
+      "step": 770
+    },
+    {
+      "epoch": 1.308724832214765,
+      "grad_norm": 0.16569755971431732,
+      "learning_rate": 2.9091237560369467e-05,
+      "loss": 0.0289,
+      "step": 780
+    },
+    {
+      "epoch": 1.325503355704698,
+      "grad_norm": 0.1949482262134552,
+      "learning_rate": 2.905692306235163e-05,
+      "loss": 0.0283,
+      "step": 790
+    },
+    {
+      "epoch": 1.342281879194631,
+      "grad_norm": 0.2368042767047882,
+      "learning_rate": 2.9021993668980925e-05,
+      "loss": 0.0279,
+      "step": 800
+    },
+    {
+      "epoch": 1.3590604026845639,
+      "grad_norm": 0.21733024716377258,
+      "learning_rate": 2.8986450908182185e-05,
+      "loss": 0.0257,
+      "step": 810
+    },
+    {
+      "epoch": 1.3758389261744965,
+      "grad_norm": 0.16328634321689606,
+      "learning_rate": 2.8950296334710902e-05,
+      "loss": 0.0281,
+      "step": 820
+    },
+    {
+      "epoch": 1.3926174496644295,
+      "grad_norm": 0.20662836730480194,
+      "learning_rate": 2.8913531530085248e-05,
+      "loss": 0.0272,
+      "step": 830
+    },
+    {
+      "epoch": 1.4093959731543624,
+      "grad_norm": 0.17186735570430756,
+      "learning_rate": 2.887615810251687e-05,
+      "loss": 0.0286,
+      "step": 840
+    },
+    {
+      "epoch": 1.4261744966442953,
+      "grad_norm": 0.187661275267601,
+      "learning_rate": 2.8838177686840577e-05,
+      "loss": 0.0284,
+      "step": 850
+    },
+    {
+      "epoch": 1.4429530201342282,
+      "grad_norm": 0.18711018562316895,
+      "learning_rate": 2.8799591944442776e-05,
+      "loss": 0.0289,
+      "step": 860
+    },
+    {
+      "epoch": 1.4597315436241611,
+      "grad_norm": 0.2038484513759613,
+      "learning_rate": 2.8760402563188848e-05,
+      "loss": 0.0279,
+      "step": 870
+    },
+    {
+      "epoch": 1.476510067114094,
+      "grad_norm": 0.20940718054771423,
+      "learning_rate": 2.8720611257349285e-05,
+      "loss": 0.0269,
+      "step": 880
+    },
+    {
+      "epoch": 1.4932885906040267,
+      "grad_norm": 0.19567424058914185,
+      "learning_rate": 2.868021976752471e-05,
+      "loss": 0.027,
+      "step": 890
+    },
+    {
+      "epoch": 1.5100671140939599,
+      "grad_norm": 0.16011153161525726,
+      "learning_rate": 2.8639229860569738e-05,
+      "loss": 0.0293,
+      "step": 900
+    },
+    {
+      "epoch": 1.5268456375838926,
+      "grad_norm": 0.13916991651058197,
+      "learning_rate": 2.8597643329515688e-05,
+      "loss": 0.0253,
+      "step": 910
+    },
+    {
+      "epoch": 1.5436241610738255,
+      "grad_norm": 0.12822005152702332,
+      "learning_rate": 2.855546199349214e-05,
+      "loss": 0.025,
+      "step": 920
+    },
+    {
+      "epoch": 1.5604026845637584,
+      "grad_norm": 0.18722663819789886,
+      "learning_rate": 2.85126876976474e-05,
+      "loss": 0.0277,
+      "step": 930
+    },
+    {
+      "epoch": 1.5771812080536913,
+      "grad_norm": 0.1512211114168167,
+      "learning_rate": 2.8469322313067726e-05,
+      "loss": 0.0253,
+      "step": 940
+    },
+    {
+      "epoch": 1.5939597315436242,
+      "grad_norm": 0.20754490792751312,
+      "learning_rate": 2.8425367736695522e-05,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 1.610738255033557,
+      "grad_norm": 0.238246351480484,
+      "learning_rate": 2.838082589124636e-05,
+      "loss": 0.028,
+      "step": 960
+    },
+    {
+      "epoch": 1.62751677852349,
+      "grad_norm": 0.14989012479782104,
+      "learning_rate": 2.8335698725124843e-05,
+      "loss": 0.0261,
+      "step": 970
+    },
+    {
+      "epoch": 1.6442953020134228,
+      "grad_norm": 0.15159383416175842,
+      "learning_rate": 2.8289988212339422e-05,
+      "loss": 0.0232,
+      "step": 980
+    },
+    {
+      "epoch": 1.6610738255033557,
+      "grad_norm": 0.17884178459644318,
+      "learning_rate": 2.8243696352415997e-05,
+      "loss": 0.0303,
+      "step": 990
+    },
+    {
+      "epoch": 1.6778523489932886,
+      "grad_norm": 0.1455809772014618,
+      "learning_rate": 2.8196825170310495e-05,
+      "loss": 0.0239,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6946308724832215,
+      "grad_norm": 0.15527848899364471,
+      "learning_rate": 2.8149376716320256e-05,
+      "loss": 0.0255,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7114093959731544,
+      "grad_norm": 0.16052792966365814,
+      "learning_rate": 2.8101353065994373e-05,
+      "loss": 0.0276,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7281879194630871,
+      "grad_norm": 0.12123282998800278,
+      "learning_rate": 2.8052756320042885e-05,
+      "loss": 0.025,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7449664429530203,
+      "grad_norm": 0.16650134325027466,
+      "learning_rate": 2.8003588604244893e-05,
+      "loss": 0.0232,
+      "step": 1040
+    },
+    {
+      "epoch": 1.761744966442953,
+      "grad_norm": 0.14930953085422516,
+      "learning_rate": 2.7953852069355565e-05,
+      "loss": 0.0225,
+      "step": 1050
+    },
+    {
+      "epoch": 1.778523489932886,
+      "grad_norm": 0.21071627736091614,
+      "learning_rate": 2.790354889101206e-05,
+      "loss": 0.0212,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7953020134228188,
+      "grad_norm": 0.1896669566631317,
+      "learning_rate": 2.7852681269638366e-05,
+      "loss": 0.0259,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8120805369127517,
+      "grad_norm": 0.15259258449077606,
+      "learning_rate": 2.780125143034902e-05,
+      "loss": 0.0263,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8288590604026846,
+      "grad_norm": 0.14170797169208527,
+      "learning_rate": 2.7749261622851812e-05,
+      "loss": 0.0228,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8456375838926173,
+      "grad_norm": 0.14577420055866241,
+      "learning_rate": 2.7696714121349335e-05,
+      "loss": 0.0233,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8624161073825505,
+      "grad_norm": 0.1250564157962799,
+      "learning_rate": 2.764361122443954e-05,
+      "loss": 0.0218,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8791946308724832,
+      "grad_norm": 0.16452714800834656,
+      "learning_rate": 2.758995525501517e-05,
+      "loss": 0.023,
+      "step": 1120
+    },
+    {
+      "epoch": 1.895973154362416,
+      "grad_norm": 0.17396444082260132,
+      "learning_rate": 2.753574856016215e-05,
+      "loss": 0.0231,
+      "step": 1130
+    },
+    {
+      "epoch": 1.912751677852349,
+      "grad_norm": 0.15328766405582428,
+      "learning_rate": 2.7480993511056913e-05,
+      "loss": 0.024,
+      "step": 1140
+    },
+    {
+      "epoch": 1.929530201342282,
+      "grad_norm": 0.1501884162425995,
+      "learning_rate": 2.7425692502862684e-05,
+      "loss": 0.0211,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9463087248322148,
+      "grad_norm": 0.1589355766773224,
+      "learning_rate": 2.7369847954624728e-05,
+      "loss": 0.0232,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9630872483221475,
+      "grad_norm": 0.12628960609436035,
+      "learning_rate": 2.731346230916448e-05,
+      "loss": 0.0254,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9798657718120807,
+      "grad_norm": 0.14850759506225586,
+      "learning_rate": 2.7256538032972746e-05,
+      "loss": 0.0231,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9966442953020134,
+      "grad_norm": 0.12806259095668793,
+      "learning_rate": 2.7199077616101773e-05,
+      "loss": 0.0209,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0134228187919465,
+      "grad_norm": 0.19582599401474,
+      "learning_rate": 2.714108357205634e-05,
+      "loss": 0.0238,
+      "step": 1200
+    },
+    {
+      "epoch": 2.030201342281879,
+      "grad_norm": 0.41255050897598267,
+      "learning_rate": 2.7082558437683803e-05,
+      "loss": 0.0218,
+      "step": 1210
+    },
+    {
+      "epoch": 2.046979865771812,
+      "grad_norm": 0.15883375704288483,
+      "learning_rate": 2.702350477306315e-05,
+      "loss": 0.0217,
+      "step": 1220
+    },
+    {
+      "epoch": 2.063758389261745,
+      "grad_norm": 0.21646834909915924,
+      "learning_rate": 2.6963925161392963e-05,
+      "loss": 0.0229,
+      "step": 1230
+    },
+    {
+      "epoch": 2.0805369127516777,
+      "grad_norm": 0.14378032088279724,
+      "learning_rate": 2.6903822208878476e-05,
+      "loss": 0.0225,
+      "step": 1240
+    },
+    {
+      "epoch": 2.097315436241611,
+      "grad_norm": 0.15373851358890533,
+      "learning_rate": 2.6843198544617535e-05,
+      "loss": 0.0241,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1140939597315436,
+      "grad_norm": 0.1561702936887741,
+      "learning_rate": 2.6782056820485612e-05,
+      "loss": 0.0228,
+      "step": 1260
+    },
+    {
+      "epoch": 2.1308724832214767,
+      "grad_norm": 0.15469935536384583,
+      "learning_rate": 2.672039971101979e-05,
+      "loss": 0.021,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1476510067114094,
+      "grad_norm": 0.11616158485412598,
+      "learning_rate": 2.665822991330178e-05,
+      "loss": 0.0244,
+      "step": 1280
+    },
+    {
+      "epoch": 2.164429530201342,
+      "grad_norm": 0.18575182557106018,
+      "learning_rate": 2.6595550146839934e-05,
+      "loss": 0.0233,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1812080536912752,
+      "grad_norm": 0.1657201200723648,
+      "learning_rate": 2.6532363153450287e-05,
+      "loss": 0.0219,
+      "step": 1300
+    },
+    {
+      "epoch": 2.197986577181208,
+      "grad_norm": 0.17577281594276428,
+      "learning_rate": 2.6468671697136634e-05,
+      "loss": 0.0206,
+      "step": 1310
+    },
+    {
+      "epoch": 2.214765100671141,
+      "grad_norm": 0.16942515969276428,
+      "learning_rate": 2.640447856396961e-05,
+      "loss": 0.0202,
+      "step": 1320
+    },
+    {
+      "epoch": 2.2315436241610738,
+      "grad_norm": 0.12942443788051605,
+      "learning_rate": 2.6339786561964805e-05,
+      "loss": 0.0235,
+      "step": 1330
+    },
+    {
+      "epoch": 2.248322147651007,
+      "grad_norm": 0.10895993560552597,
+      "learning_rate": 2.6274598520959966e-05,
+      "loss": 0.0217,
+      "step": 1340
+    },
+    {
+      "epoch": 2.2651006711409396,
+      "grad_norm": 0.16702544689178467,
+      "learning_rate": 2.6208917292491185e-05,
+      "loss": 0.0229,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2818791946308723,
+      "grad_norm": 0.14049775898456573,
+      "learning_rate": 2.6142745749668176e-05,
+      "loss": 0.0213,
+      "step": 1360
+    },
+    {
+      "epoch": 2.2986577181208054,
+      "grad_norm": 0.17712368071079254,
+      "learning_rate": 2.607608678704859e-05,
+      "loss": 0.0222,
+      "step": 1370
+    },
+    {
+      "epoch": 2.315436241610738,
+      "grad_norm": 0.17040906846523285,
+      "learning_rate": 2.600894332051139e-05,
+      "loss": 0.0191,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3322147651006713,
+      "grad_norm": 0.1793813854455948,
+      "learning_rate": 2.594131828712932e-05,
+      "loss": 0.0226,
+      "step": 1390
+    },
+    {
+      "epoch": 2.348993288590604,
+      "grad_norm": 0.17199549078941345,
+      "learning_rate": 2.5873214645040414e-05,
+      "loss": 0.0205,
+      "step": 1400
+    },
+    {
+      "epoch": 2.365771812080537,
+      "grad_norm": 0.2560262680053711,
+      "learning_rate": 2.5804635373318604e-05,
+      "loss": 0.0194,
+      "step": 1410
+    },
+    {
+      "epoch": 2.38255033557047,
+      "grad_norm": 0.15049883723258972,
+      "learning_rate": 2.57355834718434e-05,
+      "loss": 0.0225,
+      "step": 1420
+    },
+    {
+      "epoch": 2.3993288590604025,
+      "grad_norm": 0.10687083005905151,
+      "learning_rate": 2.566606196116867e-05,
+      "loss": 0.0201,
+      "step": 1430
+    },
+    {
+      "epoch": 2.4161073825503356,
+      "grad_norm": 0.21092043817043304,
+      "learning_rate": 2.559607388239051e-05,
+      "loss": 0.0203,
+      "step": 1440
+    },
+    {
+      "epoch": 2.4328859060402683,
+      "grad_norm": 0.1304531693458557,
+      "learning_rate": 2.552562229701422e-05,
+      "loss": 0.0207,
+      "step": 1450
+    },
+    {
+      "epoch": 2.4496644295302015,
+      "grad_norm": 0.17584650218486786,
+      "learning_rate": 2.545471028682036e-05,
+      "loss": 0.0225,
+      "step": 1460
+    },
+    {
+      "epoch": 2.466442953020134,
+      "grad_norm": 0.28326791524887085,
+      "learning_rate": 2.538334095373e-05,
+      "loss": 0.0199,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4832214765100673,
+      "grad_norm": 0.2687714695930481,
+      "learning_rate": 2.531151741966896e-05,
+      "loss": 0.021,
+      "step": 1480
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.12673330307006836,
+      "learning_rate": 2.5239242826431302e-05,
+      "loss": 0.0212,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5167785234899327,
+      "grad_norm": 0.14194728434085846,
+      "learning_rate": 2.5166520335541865e-05,
+      "loss": 0.0202,
+      "step": 1500
+    },
+    {
+      "epoch": 2.533557046979866,
+      "grad_norm": 0.2310604751110077,
+      "learning_rate": 2.5093353128117996e-05,
+      "loss": 0.0213,
+      "step": 1510
+    },
+    {
+      "epoch": 2.5503355704697985,
+      "grad_norm": 0.13804496824741364,
+      "learning_rate": 2.501974440473037e-05,
+      "loss": 0.0193,
+      "step": 1520
+    },
+    {
+      "epoch": 2.5671140939597317,
+      "grad_norm": 0.14828719198703766,
+      "learning_rate": 2.4945697385263015e-05,
+      "loss": 0.0222,
+      "step": 1530
+    },
+    {
+      "epoch": 2.5838926174496644,
+      "grad_norm": 0.1583152413368225,
+      "learning_rate": 2.487121530877243e-05,
+      "loss": 0.0218,
+      "step": 1540
+    },
+    {
+      "epoch": 2.600671140939597,
+      "grad_norm": 0.1458803117275238,
+      "learning_rate": 2.4796301433345943e-05,
+      "loss": 0.0226,
+      "step": 1550
+    },
+    {
+      "epoch": 2.61744966442953,
+      "grad_norm": 0.15886026620864868,
+      "learning_rate": 2.4720959035959148e-05,
+      "loss": 0.0226,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6342281879194633,
+      "grad_norm": 0.15409216284751892,
+      "learning_rate": 2.464519141233257e-05,
+      "loss": 0.0206,
+      "step": 1570
+    },
+    {
+      "epoch": 2.651006711409396,
+      "grad_norm": 0.13891032338142395,
+      "learning_rate": 2.456900187678754e-05,
+      "loss": 0.0183,
+      "step": 1580
+    },
+    {
+      "epoch": 2.6677852348993287,
+      "grad_norm": 0.13419780135154724,
+      "learning_rate": 2.4492393762101147e-05,
+      "loss": 0.0221,
+      "step": 1590
+    },
+    {
+      "epoch": 2.684563758389262,
+      "grad_norm": 0.124265655875206,
+      "learning_rate": 2.4415370419360508e-05,
+      "loss": 0.0216,
+      "step": 1600
+    },
+    {
+      "epoch": 2.7013422818791946,
+      "grad_norm": 0.1302771270275116,
+      "learning_rate": 2.4337935217816157e-05,
+      "loss": 0.0201,
+      "step": 1610
+    },
+    {
+      "epoch": 2.7181208053691277,
+      "grad_norm": 0.16515520215034485,
+      "learning_rate": 2.4260091544734665e-05,
+      "loss": 0.019,
+      "step": 1620
+    },
+    {
+      "epoch": 2.7348993288590604,
+      "grad_norm": 0.13658763468265533,
+      "learning_rate": 2.4181842805250466e-05,
+      "loss": 0.0205,
+      "step": 1630
+    },
+    {
+      "epoch": 2.751677852348993,
+      "grad_norm": 0.11953597515821457,
+      "learning_rate": 2.4103192422216923e-05,
+      "loss": 0.0199,
+      "step": 1640
+    },
+    {
+      "epoch": 2.7684563758389262,
+      "grad_norm": 0.16735540330410004,
+      "learning_rate": 2.402414383605658e-05,
+      "loss": 0.0192,
+      "step": 1650
+    },
+    {
+      "epoch": 2.785234899328859,
+      "grad_norm": 0.14770597219467163,
+      "learning_rate": 2.3944700504610674e-05,
+      "loss": 0.0197,
+      "step": 1660
+    },
+    {
+      "epoch": 2.802013422818792,
+      "grad_norm": 0.14873377978801727,
+      "learning_rate": 2.3864865902987883e-05,
+      "loss": 0.0186,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8187919463087248,
+      "grad_norm": 0.22620314359664917,
+      "learning_rate": 2.378464352341231e-05,
+      "loss": 0.0214,
+      "step": 1680
+    },
+    {
+      "epoch": 2.8355704697986575,
+      "grad_norm": 0.20077335834503174,
+      "learning_rate": 2.3704036875070728e-05,
+      "loss": 0.0233,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8523489932885906,
+      "grad_norm": 0.18293912708759308,
+      "learning_rate": 2.362304948395906e-05,
+      "loss": 0.0244,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8691275167785237,
+      "grad_norm": 0.17799849808216095,
+      "learning_rate": 2.3541684892728157e-05,
+      "loss": 0.0195,
+      "step": 1710
+    },
+    {
+      "epoch": 2.8859060402684564,
+      "grad_norm": 0.15650226175785065,
+      "learning_rate": 2.345994666052883e-05,
+      "loss": 0.0183,
+      "step": 1720
+    },
+    {
+      "epoch": 2.902684563758389,
+      "grad_norm": 0.14934243261814117,
+      "learning_rate": 2.337783836285614e-05,
+      "loss": 0.0212,
+      "step": 1730
+    },
+    {
+      "epoch": 2.9194630872483223,
+      "grad_norm": 0.19469675421714783,
+      "learning_rate": 2.3295363591393026e-05,
+      "loss": 0.0191,
+      "step": 1740
+    },
+    {
+      "epoch": 2.936241610738255,
+      "grad_norm": 0.20920106768608093,
+      "learning_rate": 2.3212525953853174e-05,
+      "loss": 0.0202,
+      "step": 1750
+    },
+    {
+      "epoch": 2.953020134228188,
+      "grad_norm": 0.1367284506559372,
+      "learning_rate": 2.3129329073823206e-05,
+      "loss": 0.0204,
+      "step": 1760
+    },
+    {
+      "epoch": 2.969798657718121,
+      "grad_norm": 0.15733259916305542,
+      "learning_rate": 2.3045776590604175e-05,
+      "loss": 0.0192,
+      "step": 1770
+    },
+    {
+      "epoch": 2.9865771812080535,
+      "grad_norm": 0.1706557273864746,
+      "learning_rate": 2.296187215905237e-05,
+      "loss": 0.0206,
+      "step": 1780
+    },
+    {
+      "epoch": 3.0033557046979866,
+      "grad_norm": 0.20850840210914612,
+      "learning_rate": 2.2877619449419437e-05,
+      "loss": 0.022,
+      "step": 1790
+    },
+    {
+      "epoch": 3.0201342281879193,
+      "grad_norm": 0.21721336245536804,
+      "learning_rate": 2.2793022147191843e-05,
+      "loss": 0.0201,
+      "step": 1800
+    },
+    {
+      "epoch": 3.0369127516778525,
+      "grad_norm": 0.16258729994297028,
+      "learning_rate": 2.2708083952929634e-05,
+      "loss": 0.0185,
+      "step": 1810
+    },
+    {
+      "epoch": 3.053691275167785,
+      "grad_norm": 0.18179331719875336,
+      "learning_rate": 2.2622808582104594e-05,
+      "loss": 0.0215,
+      "step": 1820
+    },
+    {
+      "epoch": 3.0704697986577183,
+      "grad_norm": 0.11735052615404129,
+      "learning_rate": 2.2537199764937703e-05,
+      "loss": 0.019,
+      "step": 1830
+    },
+    {
+      "epoch": 3.087248322147651,
+      "grad_norm": 0.15188120305538177,
+      "learning_rate": 2.245126124623595e-05,
+      "loss": 0.0196,
+      "step": 1840
+    },
+    {
+      "epoch": 3.1040268456375837,
+      "grad_norm": 0.14142458140850067,
+      "learning_rate": 2.2364996785228547e-05,
+      "loss": 0.0188,
+      "step": 1850
+    },
+    {
+      "epoch": 3.120805369127517,
+      "grad_norm": 0.15011872351169586,
+      "learning_rate": 2.227841015540248e-05,
+      "loss": 0.0211,
+      "step": 1860
+    },
+    {
+      "epoch": 3.1375838926174495,
+      "grad_norm": 0.13913294672966003,
+      "learning_rate": 2.2191505144337433e-05,
+      "loss": 0.0203,
+      "step": 1870
+    },
+    {
+      "epoch": 3.1543624161073827,
+      "grad_norm": 0.1547662764787674,
+      "learning_rate": 2.210428555354013e-05,
+      "loss": 0.0198,
+      "step": 1880
+    },
+    {
+      "epoch": 3.1711409395973154,
+      "grad_norm": 0.16952672600746155,
+      "learning_rate": 2.201675519827802e-05,
+      "loss": 0.0207,
+      "step": 1890
+    },
+    {
+      "epoch": 3.1879194630872485,
+      "grad_norm": 0.16245362162590027,
+      "learning_rate": 2.1928917907412403e-05,
+      "loss": 0.0191,
+      "step": 1900
+    },
+    {
+      "epoch": 3.204697986577181,
+      "grad_norm": 0.20379698276519775,
+      "learning_rate": 2.1840777523230937e-05,
+      "loss": 0.0201,
+      "step": 1910
+    },
+    {
+      "epoch": 3.221476510067114,
+      "grad_norm": 0.12898804247379303,
+      "learning_rate": 2.1752337901279552e-05,
+      "loss": 0.0189,
+      "step": 1920
+    },
+    {
+      "epoch": 3.238255033557047,
+      "grad_norm": 0.22864995896816254,
+      "learning_rate": 2.166360291019383e-05,
+      "loss": 0.0189,
+      "step": 1930
+    },
+    {
+      "epoch": 3.2550335570469797,
+      "grad_norm": 0.10070180147886276,
+      "learning_rate": 2.157457643152973e-05,
+      "loss": 0.0191,
+      "step": 1940
+    },
+    {
+      "epoch": 3.271812080536913,
+      "grad_norm": 0.12235262989997864,
+      "learning_rate": 2.148526235959385e-05,
+      "loss": 0.0189,
+      "step": 1950
+    },
+    {
+      "epoch": 3.2885906040268456,
+      "grad_norm": 0.17240414023399353,
+      "learning_rate": 2.1395664601273016e-05,
+      "loss": 0.0185,
+      "step": 1960
+    },
+    {
+      "epoch": 3.3053691275167787,
+      "grad_norm": 0.1916498988866806,
+      "learning_rate": 2.130578707586345e-05,
+      "loss": 0.0204,
+      "step": 1970
+    },
+    {
+      "epoch": 3.3221476510067114,
+      "grad_norm": 0.13949474692344666,
+      "learning_rate": 2.1215633714899264e-05,
+      "loss": 0.0194,
+      "step": 1980
+    },
+    {
+      "epoch": 3.3389261744966445,
+      "grad_norm": 0.148747980594635,
+      "learning_rate": 2.112520846198053e-05,
+      "loss": 0.0187,
+      "step": 1990
+    },
+    {
+      "epoch": 3.3557046979865772,
+      "grad_norm": 0.14247365295886993,
+      "learning_rate": 2.103451527260074e-05,
+      "loss": 0.0179,
+      "step": 2000
+    },
+    {
+      "epoch": 3.37248322147651,
+      "grad_norm": 0.1270933598279953,
+      "learning_rate": 2.094355811397381e-05,
+      "loss": 0.0193,
+      "step": 2010
+    },
+    {
+      "epoch": 3.389261744966443,
+      "grad_norm": 0.16048407554626465,
+      "learning_rate": 2.0852340964860522e-05,
+      "loss": 0.0228,
+      "step": 2020
+    },
+    {
+      "epoch": 3.4060402684563758,
+      "grad_norm": 0.19520506262779236,
+      "learning_rate": 2.076086781539447e-05,
+      "loss": 0.0183,
+      "step": 2030
+    },
+    {
+      "epoch": 3.422818791946309,
+      "grad_norm": 0.1389211118221283,
+      "learning_rate": 2.066914266690755e-05,
+      "loss": 0.0187,
+      "step": 2040
+    },
+    {
+      "epoch": 3.4395973154362416,
+      "grad_norm": 0.15584081411361694,
+      "learning_rate": 2.0577169531754906e-05,
+      "loss": 0.0187,
+      "step": 2050
+    },
+    {
+      "epoch": 3.4563758389261743,
+      "grad_norm": 0.1802147477865219,
+      "learning_rate": 2.048495243313942e-05,
+      "loss": 0.0197,
+      "step": 2060
+    },
+    {
+      "epoch": 3.4731543624161074,
+      "grad_norm": 0.12090757489204407,
+      "learning_rate": 2.039249540493572e-05,
+      "loss": 0.0194,
+      "step": 2070
+    },
+    {
+      "epoch": 3.48993288590604,
+      "grad_norm": 0.18710780143737793,
+      "learning_rate": 2.0299802491513755e-05,
+      "loss": 0.0175,
+      "step": 2080
+    },
+    {
+      "epoch": 3.5067114093959733,
+      "grad_norm": 0.10997475683689117,
+      "learning_rate": 2.0206877747561828e-05,
+      "loss": 0.0195,
+      "step": 2090
+    },
+    {
+      "epoch": 3.523489932885906,
+      "grad_norm": 0.13992996513843536,
+      "learning_rate": 2.011372523790927e-05,
+      "loss": 0.0202,
+      "step": 2100
+    },
+    {
+      "epoch": 3.540268456375839,
+      "grad_norm": 0.11927074193954468,
+      "learning_rate": 2.0020349037348643e-05,
+      "loss": 0.0178,
+      "step": 2110
+    },
+    {
+      "epoch": 3.557046979865772,
+      "grad_norm": 0.18657186627388,
+      "learning_rate": 1.9926753230457443e-05,
+      "loss": 0.0182,
+      "step": 2120
+    },
+    {
+      "epoch": 3.573825503355705,
+      "grad_norm": 0.12504293024539948,
+      "learning_rate": 1.983294191141948e-05,
+      "loss": 0.0198,
+      "step": 2130
+    },
+    {
+      "epoch": 3.5906040268456376,
+      "grad_norm": 0.1450442671775818,
+      "learning_rate": 1.973891918384575e-05,
+      "loss": 0.0172,
+      "step": 2140
+    },
+    {
+      "epoch": 3.6073825503355703,
+      "grad_norm": 0.14081084728240967,
+      "learning_rate": 1.9644689160594945e-05,
+      "loss": 0.018,
+      "step": 2150
+    },
+    {
+      "epoch": 3.6241610738255035,
+      "grad_norm": 0.09649883955717087,
+      "learning_rate": 1.9550255963593553e-05,
+      "loss": 0.0156,
+      "step": 2160
+    },
+    {
+      "epoch": 3.640939597315436,
+      "grad_norm": 0.1074327751994133,
+      "learning_rate": 1.9455623723655524e-05,
+      "loss": 0.0157,
+      "step": 2170
+    },
+    {
+      "epoch": 3.6577181208053693,
+      "grad_norm": 0.1782575249671936,
+      "learning_rate": 1.9360796580301606e-05,
+      "loss": 0.0168,
+      "step": 2180
+    },
+    {
+      "epoch": 3.674496644295302,
+      "grad_norm": 0.16483958065509796,
+      "learning_rate": 1.9265778681578245e-05,
+      "loss": 0.0172,
+      "step": 2190
+    },
+    {
+      "epoch": 3.6912751677852347,
+      "grad_norm": 0.14613379538059235,
+      "learning_rate": 1.9170574183876143e-05,
+      "loss": 0.0204,
+      "step": 2200
+    },
+    {
+      "epoch": 3.708053691275168,
+      "grad_norm": 0.2648290693759918,
+      "learning_rate": 1.9075187251748452e-05,
+      "loss": 0.0202,
+      "step": 2210
+    },
+    {
+      "epoch": 3.7248322147651005,
+      "grad_norm": 0.15106196701526642,
+      "learning_rate": 1.8979622057728596e-05,
+      "loss": 0.0187,
+      "step": 2220
+    },
+    {
+      "epoch": 3.7416107382550337,
+      "grad_norm": 0.11246120184659958,
+      "learning_rate": 1.8883882782147748e-05,
+      "loss": 0.0169,
+      "step": 2230
+    },
+    {
+      "epoch": 3.7583892617449663,
+      "grad_norm": 0.1419929713010788,
+      "learning_rate": 1.8787973612951967e-05,
+      "loss": 0.0172,
+      "step": 2240
+    },
+    {
+      "epoch": 3.7751677852348995,
+      "grad_norm": 0.12565530836582184,
+      "learning_rate": 1.8691898745519028e-05,
+      "loss": 0.0192,
+      "step": 2250
+    },
+    {
+      "epoch": 3.791946308724832,
+      "grad_norm": 0.13186733424663544,
+      "learning_rate": 1.8595662382474863e-05,
+      "loss": 0.0206,
+      "step": 2260
+    },
+    {
+      "epoch": 3.8087248322147653,
+      "grad_norm": 0.16787581145763397,
+      "learning_rate": 1.8499268733509766e-05,
+      "loss": 0.0181,
+      "step": 2270
+    },
+    {
+      "epoch": 3.825503355704698,
+      "grad_norm": 0.1428891271352768,
+      "learning_rate": 1.84027220151942e-05,
+      "loss": 0.016,
+      "step": 2280
+    },
+    {
+      "epoch": 3.8422818791946307,
+      "grad_norm": 0.16047702729701996,
+      "learning_rate": 1.83060264507944e-05,
+      "loss": 0.0169,
+      "step": 2290
+    },
+    {
+      "epoch": 3.859060402684564,
+      "grad_norm": 0.13212737441062927,
+      "learning_rate": 1.82091862700876e-05,
+      "loss": 0.0168,
+      "step": 2300
+    },
+    {
+      "epoch": 3.8758389261744965,
+      "grad_norm": 0.10623549669981003,
+      "learning_rate": 1.8112205709177023e-05,
+      "loss": 0.0185,
+      "step": 2310
+    },
+    {
+      "epoch": 3.8926174496644297,
+      "grad_norm": 0.19981749355793,
+      "learning_rate": 1.8015089010306585e-05,
+      "loss": 0.0155,
+      "step": 2320
+    },
+    {
+      "epoch": 3.9093959731543624,
+      "grad_norm": 0.18881696462631226,
+      "learning_rate": 1.7917840421675298e-05,
+      "loss": 0.0209,
+      "step": 2330
+    },
+    {
+      "epoch": 3.926174496644295,
+      "grad_norm": 0.10692999511957169,
+      "learning_rate": 1.7820464197251474e-05,
+      "loss": 0.0161,
+      "step": 2340
+    },
+    {
+      "epoch": 3.942953020134228,
+      "grad_norm": 0.21753492951393127,
+      "learning_rate": 1.7722964596586627e-05,
+      "loss": 0.0189,
+      "step": 2350
+    },
+    {
+      "epoch": 3.959731543624161,
+      "grad_norm": 0.18070799112319946,
+      "learning_rate": 1.7625345884629144e-05,
+      "loss": 0.0184,
+      "step": 2360
+    },
+    {
+      "epoch": 3.976510067114094,
+      "grad_norm": 0.15308111906051636,
+      "learning_rate": 1.7527612331537722e-05,
+      "loss": 0.0156,
+      "step": 2370
+    },
+    {
+      "epoch": 3.9932885906040267,
+      "grad_norm": 0.14668720960617065,
+      "learning_rate": 1.7429768212494593e-05,
+      "loss": 0.0178,
+      "step": 2380
+    },
+    {
+      "epoch": 4.010067114093959,
+      "grad_norm": 0.3539591431617737,
+      "learning_rate": 1.7331817807518497e-05,
+      "loss": 0.0185,
+      "step": 2390
+    },
+    {
+      "epoch": 4.026845637583893,
+      "grad_norm": 0.1322038173675537,
+      "learning_rate": 1.723376540127745e-05,
+      "loss": 0.0171,
+      "step": 2400
+    },
+    {
+      "epoch": 4.043624161073826,
+      "grad_norm": 0.11787392944097519,
+      "learning_rate": 1.7135615282901357e-05,
+      "loss": 0.0163,
+      "step": 2410
+    },
+    {
+      "epoch": 4.060402684563758,
+      "grad_norm": 0.1422634720802307,
+      "learning_rate": 1.7037371745794358e-05,
+      "loss": 0.0206,
+      "step": 2420
+    },
+    {
+      "epoch": 4.077181208053691,
+      "grad_norm": 0.1516404151916504,
+      "learning_rate": 1.6939039087447026e-05,
+      "loss": 0.0166,
+      "step": 2430
+    },
+    {
+      "epoch": 4.093959731543624,
+      "grad_norm": 0.14106018841266632,
+      "learning_rate": 1.6840621609248397e-05,
+      "loss": 0.0197,
+      "step": 2440
+    },
+    {
+      "epoch": 4.110738255033557,
+      "grad_norm": 0.12483642995357513,
+      "learning_rate": 1.6742123616297794e-05,
+      "loss": 0.0175,
+      "step": 2450
+    },
+    {
+      "epoch": 4.12751677852349,
+      "grad_norm": 0.16260197758674622,
+      "learning_rate": 1.664354941721651e-05,
+      "loss": 0.0166,
+      "step": 2460
+    },
+    {
+      "epoch": 4.144295302013423,
+      "grad_norm": 0.1442679613828659,
+      "learning_rate": 1.6544903323959355e-05,
+      "loss": 0.016,
+      "step": 2470
+    },
+    {
+      "epoch": 4.1610738255033555,
+      "grad_norm": 0.11389831453561783,
+      "learning_rate": 1.6446189651626023e-05,
+      "loss": 0.0183,
+      "step": 2480
+    },
+    {
+      "epoch": 4.177852348993288,
+      "grad_norm": 0.14809614419937134,
+      "learning_rate": 1.6347412718272316e-05,
+      "loss": 0.0205,
+      "step": 2490
+    },
+    {
+      "epoch": 4.194630872483222,
+      "grad_norm": 0.17286059260368347,
+      "learning_rate": 1.624857684472131e-05,
+      "loss": 0.0168,
+      "step": 2500
+    },
+    {
+      "epoch": 4.2114093959731544,
+      "grad_norm": 0.14666445553302765,
+      "learning_rate": 1.6149686354374283e-05,
+      "loss": 0.0177,
+      "step": 2510
+    },
+    {
+      "epoch": 4.228187919463087,
+      "grad_norm": 0.15864591300487518,
+      "learning_rate": 1.605074557302165e-05,
+      "loss": 0.0175,
+      "step": 2520
+    },
+    {
+      "epoch": 4.24496644295302,
+      "grad_norm": 0.177460715174675,
+      "learning_rate": 1.59517588286537e-05,
+      "loss": 0.0175,
+      "step": 2530
+    },
+    {
+      "epoch": 4.261744966442953,
+      "grad_norm": 0.14390940964221954,
+      "learning_rate": 1.5852730451271324e-05,
+      "loss": 0.0156,
+      "step": 2540
+    },
+    {
+      "epoch": 4.278523489932886,
+      "grad_norm": 0.15486080944538116,
+      "learning_rate": 1.5753664772696546e-05,
+      "loss": 0.0182,
+      "step": 2550
+    },
+    {
+      "epoch": 4.295302013422819,
+      "grad_norm": 0.15260493755340576,
+      "learning_rate": 1.565456612638307e-05,
+      "loss": 0.0182,
+      "step": 2560
+    },
+    {
+      "epoch": 4.3120805369127515,
+      "grad_norm": 0.12060414999723434,
+      "learning_rate": 1.5555438847226732e-05,
+      "loss": 0.0167,
+      "step": 2570
+    },
+    {
+      "epoch": 4.328859060402684,
+      "grad_norm": 0.1500580757856369,
+      "learning_rate": 1.545628727137584e-05,
+      "loss": 0.0164,
+      "step": 2580
+    },
+    {
+      "epoch": 4.345637583892618,
+      "grad_norm": 0.15014661848545074,
+      "learning_rate": 1.535711573604153e-05,
+      "loss": 0.0161,
+      "step": 2590
+    },
+    {
+      "epoch": 4.3624161073825505,
+      "grad_norm": 0.16664306819438934,
+      "learning_rate": 1.5257928579308032e-05,
+      "loss": 0.0189,
+      "step": 2600
+    },
+    {
+      "epoch": 4.379194630872483,
+      "grad_norm": 0.155680850148201,
+      "learning_rate": 1.5158730139942902e-05,
+      "loss": 0.019,
+      "step": 2610
+    },
+    {
+      "epoch": 4.395973154362416,
+      "grad_norm": 0.16779354214668274,
+      "learning_rate": 1.5059524757207239e-05,
+      "loss": 0.0179,
+      "step": 2620
+    },
+    {
+      "epoch": 4.412751677852349,
+      "grad_norm": 0.1292392611503601,
+      "learning_rate": 1.4960316770665866e-05,
+      "loss": 0.0157,
+      "step": 2630
+    },
+    {
+      "epoch": 4.429530201342282,
+      "grad_norm": 0.1438266485929489,
+      "learning_rate": 1.4861110519997495e-05,
+      "loss": 0.0177,
+      "step": 2640
+    },
+    {
+      "epoch": 4.446308724832215,
+      "grad_norm": 0.15133166313171387,
+      "learning_rate": 1.4761910344804913e-05,
+      "loss": 0.0162,
+      "step": 2650
+    },
+    {
+      "epoch": 4.4630872483221475,
+      "grad_norm": 0.1657615602016449,
+      "learning_rate": 1.466272058442516e-05,
+      "loss": 0.0165,
+      "step": 2660
+    },
+    {
+      "epoch": 4.47986577181208,
+      "grad_norm": 0.1509656012058258,
+      "learning_rate": 1.4563545577739676e-05,
+      "loss": 0.0177,
+      "step": 2670
+    },
+    {
+      "epoch": 4.496644295302014,
+      "grad_norm": 0.1461293250322342,
+      "learning_rate": 1.4464389662984543e-05,
+      "loss": 0.0164,
+      "step": 2680
+    },
+    {
+      "epoch": 4.5134228187919465,
+      "grad_norm": 0.18428373336791992,
+      "learning_rate": 1.4365257177560684e-05,
+      "loss": 0.017,
+      "step": 2690
+    },
+    {
+      "epoch": 4.530201342281879,
+      "grad_norm": 0.13298265635967255,
+      "learning_rate": 1.426615245784416e-05,
+      "loss": 0.0158,
+      "step": 2700
+    },
+    {
+      "epoch": 4.546979865771812,
+      "grad_norm": 0.10208632797002792,
+      "learning_rate": 1.4167079838996468e-05,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 4.563758389261745,
+      "grad_norm": 0.16623789072036743,
+      "learning_rate": 1.4068043654774897e-05,
+      "loss": 0.0156,
+      "step": 2720
+    },
+    {
+      "epoch": 4.580536912751678,
+      "grad_norm": 0.14804600179195404,
+      "learning_rate": 1.3969048237342992e-05,
+      "loss": 0.0177,
+      "step": 2730
+    },
+    {
+      "epoch": 4.597315436241611,
+      "grad_norm": 0.16890902817249298,
+      "learning_rate": 1.3870097917081011e-05,
+      "loss": 0.0147,
+      "step": 2740
+    },
+    {
+      "epoch": 4.614093959731544,
+      "grad_norm": 0.21568931639194489,
+      "learning_rate": 1.3771197022396508e-05,
+      "loss": 0.0155,
+      "step": 2750
+    },
+    {
+      "epoch": 4.630872483221476,
+      "grad_norm": 0.14996445178985596,
+      "learning_rate": 1.3672349879535015e-05,
+      "loss": 0.0147,
+      "step": 2760
+    },
+    {
+      "epoch": 4.64765100671141,
+      "grad_norm": 0.10208549350500107,
+      "learning_rate": 1.3573560812390781e-05,
+      "loss": 0.0166,
+      "step": 2770
+    },
+    {
+      "epoch": 4.6644295302013425,
+      "grad_norm": 0.11123307049274445,
+      "learning_rate": 1.3474834142317635e-05,
+      "loss": 0.0151,
+      "step": 2780
+    },
+    {
+      "epoch": 4.681208053691275,
+      "grad_norm": 0.11926154792308807,
+      "learning_rate": 1.3376174187939955e-05,
+      "loss": 0.0157,
+      "step": 2790
+    },
+    {
+      "epoch": 4.697986577181208,
+      "grad_norm": 0.12520945072174072,
+      "learning_rate": 1.3277585264963761e-05,
+      "loss": 0.0164,
+      "step": 2800
+    },
+    {
+      "epoch": 4.714765100671141,
+      "grad_norm": 0.15269853174686432,
+      "learning_rate": 1.3179071685987928e-05,
+      "loss": 0.0187,
+      "step": 2810
+    },
+    {
+      "epoch": 4.731543624161074,
+      "grad_norm": 0.11586833000183105,
+      "learning_rate": 1.308063776031554e-05,
+      "loss": 0.0153,
+      "step": 2820
+    },
+    {
+      "epoch": 4.748322147651007,
+      "grad_norm": 0.23391515016555786,
+      "learning_rate": 1.2982287793765389e-05,
+      "loss": 0.0158,
+      "step": 2830
+    },
+    {
+      "epoch": 4.76510067114094,
+      "grad_norm": 0.13222748041152954,
+      "learning_rate": 1.2884026088483616e-05,
+      "loss": 0.0145,
+      "step": 2840
+    },
+    {
+      "epoch": 4.781879194630872,
+      "grad_norm": 0.1492713987827301,
+      "learning_rate": 1.2785856942755543e-05,
+      "loss": 0.0168,
+      "step": 2850
+    },
+    {
+      "epoch": 4.798657718120805,
+      "grad_norm": 0.13140155375003815,
+      "learning_rate": 1.2687784650817616e-05,
+      "loss": 0.0172,
+      "step": 2860
+    },
+    {
+      "epoch": 4.815436241610739,
+      "grad_norm": 0.11021384596824646,
+      "learning_rate": 1.2589813502669603e-05,
+      "loss": 0.0172,
+      "step": 2870
+    },
+    {
+      "epoch": 4.832214765100671,
+      "grad_norm": 0.15835842490196228,
+      "learning_rate": 1.2491947783886907e-05,
+      "loss": 0.016,
+      "step": 2880
+    },
+    {
+      "epoch": 4.848993288590604,
+      "grad_norm": 0.13786916434764862,
+      "learning_rate": 1.2394191775433106e-05,
+      "loss": 0.0158,
+      "step": 2890
+    },
+    {
+      "epoch": 4.865771812080537,
+      "grad_norm": 0.1657201498746872,
+      "learning_rate": 1.2296549753472696e-05,
+      "loss": 0.0157,
+      "step": 2900
+    },
+    {
+      "epoch": 4.882550335570469,
+      "grad_norm": 0.18127189576625824,
+      "learning_rate": 1.2199025989184032e-05,
+      "loss": 0.0143,
+      "step": 2910
+    },
+    {
+      "epoch": 4.899328859060403,
+      "grad_norm": 0.14471322298049927,
+      "learning_rate": 1.21016247485725e-05,
+      "loss": 0.0171,
+      "step": 2920
+    },
+    {
+      "epoch": 4.916107382550336,
+      "grad_norm": 0.15776599943637848,
+      "learning_rate": 1.2004350292283897e-05,
+      "loss": 0.0175,
+      "step": 2930
+    },
+    {
+      "epoch": 4.932885906040268,
+      "grad_norm": 0.12908852100372314,
+      "learning_rate": 1.1907206875418068e-05,
+      "loss": 0.0171,
+      "step": 2940
+    },
+    {
+      "epoch": 4.949664429530201,
+      "grad_norm": 0.19710037112236023,
+      "learning_rate": 1.1810198747342769e-05,
+      "loss": 0.0162,
+      "step": 2950
+    },
+    {
+      "epoch": 4.966442953020135,
+      "grad_norm": 0.1662857085466385,
+      "learning_rate": 1.1713330151507786e-05,
+      "loss": 0.016,
+      "step": 2960
+    },
+    {
+      "epoch": 4.983221476510067,
+      "grad_norm": 0.1350361704826355,
+      "learning_rate": 1.161660532525931e-05,
+      "loss": 0.0156,
+      "step": 2970
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.15521599352359772,
+      "learning_rate": 1.1520028499654584e-05,
+      "loss": 0.0134,
+      "step": 2980
+    },
+    {
+      "epoch": 5.016778523489933,
+      "grad_norm": 0.14748677611351013,
+      "learning_rate": 1.1423603899276833e-05,
+      "loss": 0.0143,
+      "step": 2990
+    },
+    {
+      "epoch": 5.033557046979865,
+      "grad_norm": 0.11525747179985046,
+      "learning_rate": 1.1327335742050442e-05,
+      "loss": 0.0158,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 5001,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/experiment_cfg/metadata.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/experiment_cfg/metadata.json
new file mode 100644
index 0000000000000000000000000000000000000000..6f73f8489294c58acc82d1351a17e5e3ff316e18
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed0/default/train_5shot_seed0_fullactionhead_5k/experiment_cfg/metadata.json
@@ -0,0 +1,431 @@
+{
+    "new_embodiment": {
+        "statistics": {
+            "state": {
+                "base_position": {
+                    "max": [
+                        7.778976917266846,
+                        0.33403685688972473,
+                        0.7223060727119446
+                    ],
+                    "min": [
+                        -4.821934223175049,
+                        -6.785110950469971,
+                        0.6994727253913879
+                    ],
+                    "mean": [
+                        2.5886094736594543,
+                        -2.1559664577316586,
+                        0.7003580854548973
+                    ],
+                    "std": [
+                        1.6717149343420803,
+                        1.3743695399555862,
+                        0.000940069542359506
+                    ],
+                    "q01": [
+                        -0.7517815060249613,
+                        -5.497849509089705,
+                        0.6999776914424374
+                    ],
+                    "q99": [
+                        6.060945690807028,
+                        -0.5331499932493624,
+                        0.7028864260472257
+                    ]
+                },
+                "base_rotation": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.24488939171811902,
+                        0.5968549204077488
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.6659970734507764,
+                        0.37443298392262264
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        -0.9999999999999999,
+                        4.149924358336069e-06
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        0.9999999999999999,
+                        0.9999999999999999
+                    ]
+                },
+                "end_effector_position_relative": {
+                    "max": [
+                        0.8848381638526917,
+                        0.8569459915161133,
+                        1.053884744644165
+                    ],
+                    "min": [
+                        -0.5828549861907959,
+                        -0.8486236333847046,
+                        -0.3446122705936432
+                    ],
+                    "mean": [
+                        0.25087486209693133,
+                        -0.005738920462036393,
+                        0.43643948866361787
+                    ],
+                    "std": [
+                        0.15741544532518012,
+                        0.2547603106793105,
+                        0.2050434492495558
+                    ],
+                    "q01": [
+                        -0.013990057288082561,
+                        -0.4824599092623036,
+                        0.18825220353500022
+                    ],
+                    "q99": [
+                        0.5411989642841469,
+                        0.4754923657245658,
+                        0.6912323747882034
+                    ]
+                },
+                "end_effector_rotation_relative": {
+                    "max": [
+                        0.9999949932098389,
+                        0.9997354745864868,
+                        0.9900747537612915,
+                        0.9735639095306396
+                    ],
+                    "min": [
+                        -0.9999914169311523,
+                        -0.9999884366989136,
+                        -0.9975369572639465,
+                        6.754255821306288e-08
+                    ],
+                    "mean": [
+                        -0.22290331318740714,
+                        0.04579037037503981,
+                        -0.05804094906527823,
+                        0.12347219024917105
+                    ],
+                    "std": [
+                        0.8519267931761344,
+                        0.2949394732270141,
+                        0.30026078832556913,
+                        0.16333086331829588
+                    ],
+                    "q01": [
+                        -0.9957959450418518,
+                        -0.5678869493126506,
+                        -0.5318135475761875,
+                        0.0014160465686576505
+                    ],
+                    "q99": [
+                        0.9900692296898317,
+                        0.6357358195673684,
+                        0.5009847868015971,
+                        0.4287044482210845
+                    ]
+                },
+                "gripper_qpos": {
+                    "max": [
+                        0.05289580300450325,
+                        0.00937709677964449
+                    ],
+                    "min": [
+                        -0.011669117026031017,
+                        -0.06307756155729294
+                    ],
+                    "mean": [
+                        0.03203268930378034,
+                        -0.032331639271968075
+                    ],
+                    "std": [
+                        0.011607049173153697,
+                        0.011306286745872529
+                    ],
+                    "q01": [
+                        0.006429109393656672,
+                        -0.04056586943958638
+                    ],
+                    "q99": [
+                        0.040377860142451545,
+                        -0.006593889698673258
+                    ]
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0,
+                        0.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.006050336852760097,
+                        0.002728916466628117,
+                        -0.0017236811393598838,
+                        0.0
+                    ],
+                    "std": [
+                        0.11032167711449951,
+                        0.09824140301615687,
+                        0.07825208047515658,
+                        0.0
+                    ],
+                    "q01": [
+                        -0.154721262094005,
+                        -0.18955302988697728,
+                        -0.14454065867754942,
+                        0.0
+                    ],
+                    "q99": [
+                        0.24492955247744197,
+                        0.2496797822190429,
+                        0.11966742325336034,
+                        0.0
+                    ]
+                },
+                "control_mode": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.9294448715752568
+                    ],
+                    "std": [
+                        0.36897903503358326
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        -0.21627562513311385
+                    ]
+                },
+                "end_effector_position": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.00826780165926883,
+                        0.003161997359379232,
+                        -0.08157453651841007
+                    ],
+                    "std": [
+                        0.4545430944464769,
+                        0.41040151434986594,
+                        0.4102644251536544
+                    ],
+                    "q01": [
+                        -0.9653185255999107,
+                        -0.9255635199318754,
+                        -0.8208437313341718
+                    ],
+                    "q99": [
+                        0.7987781084592441,
+                        0.9260844232330088,
+                        0.8357421812622201
+                    ]
+                },
+                "end_effector_rotation": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        0.007367024641295137,
+                        -0.02060756343728361,
+                        -0.001884833075998489
+                    ],
+                    "std": [
+                        0.1116768956941076,
+                        0.13249042272165212,
+                        0.12338908364725322
+                    ],
+                    "q01": [
+                        -0.26894658663246845,
+                        -0.39865607740339326,
+                        -0.34393735191302655
+                    ],
+                    "q99": [
+                        0.3191674780171587,
+                        0.31133630397431267,
+                        0.33968476423051097
+                    ]
+                },
+                "gripper_close": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.3098994894722959
+                    ],
+                    "std": [
+                        0.9507718287498876
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        0.7545620899936146
+                    ]
+                }
+            }
+        },
+        "modalities": {
+            "video": {
+                "robot0_eye_in_hand": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_left": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_right": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                }
+            },
+            "state": {
+                "base_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "base_rotation": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position_relative": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation_relative": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "gripper_qpos": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        2
+                    ],
+                    "continuous": true
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "control_mode": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation": {
+                    "absolute": true,
+                    "rotation_type": "axis_angle",
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "gripper_close": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                }
+            }
+        },
+        "embodiment_tag": "new_embodiment"
+    }
+}
\ No newline at end of file
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/resolved_config.yaml b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/resolved_config.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..af1b524a714cb17611800134efea109692a8f4cc
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/resolved_config.yaml
@@ -0,0 +1,28 @@
+experiment_name: fewshot_39tasks_5shot_from_baseline26_fullactionhead_seed1_5k
+policy_type: baseline
+base_model_path: ${HOME}/groot_robocasa/Atomic26_baseline/checkpoint-120000
+output_root: ${HOME}/groot_robocasa/robocasa_v2/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1
+dataset:
+  dataset_soup: fewshot_heldout_atomic39_human_5shot
+training:
+  num_gpus: 1
+  batch_size: 64
+  seed: 42
+  filter_key_seed: 1
+  manifest_path: ${HOME}/clvla/benchmarks/robocasa_v2/my_scripts/Fewshot/manifests/fewshot_heldout_atomic39/shot5_seed1.json
+  save_total_limit: 4
+phases:
+- name: train_5shot_seed1_fullactionhead_5k
+  max_steps: 5000
+  save_steps: 0
+  save_step_list:
+  - 1000
+  - 3000
+  - 5000
+  save_final_model: false
+  trainable:
+    tune_llm: false
+    tune_visual: false
+    tune_projector: true
+    tune_diffusion_model: true
+resolved_sweep: {}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/seed1_5k.yaml b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/seed1_5k.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..7a1cab8916bb35644789c61f7d219ae2883e988e
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/seed1_5k.yaml
@@ -0,0 +1,27 @@
+experiment_name: fewshot_39tasks_5shot_from_baseline26_fullactionhead_seed1_5k
+policy_type: baseline
+base_model_path: ${HOME}/groot_robocasa/Atomic26_baseline/checkpoint-120000
+output_root: ${HOME}/groot_robocasa/robocasa_v2/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1
+dataset:
+  dataset_soup: fewshot_heldout_atomic39_human_5shot
+training:
+  num_gpus: 1
+  batch_size: 64
+  seed: 42
+  filter_key_seed: 1
+  manifest_path: ${HOME}/clvla/benchmarks/robocasa_v2/my_scripts/Fewshot/manifests/fewshot_heldout_atomic39/shot5_seed1.json
+  save_total_limit: 4
+phases:
+- name: train_5shot_seed1_fullactionhead_5k
+  max_steps: 5000
+  save_steps: 0
+  save_step_list:
+  - 1000
+  - 3000
+  - 5000
+  save_final_model: false
+  trainable:
+    tune_llm: false
+    tune_visual: false
+    tune_projector: true
+    tune_diffusion_model: true
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/config.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/config.json
@@ -0,0 +1,64 @@
+{
+  "action_dim": 32,
+  "action_head_cfg": {
+    "action_dim": 32,
+    "action_horizon": 16,
+    "add_pos_embed": true,
+    "backbone_embedding_dim": 2048,
+    "diffusion_model_cfg": {
+      "attention_head_dim": 48,
+      "cross_attention_dim": 2048,
+      "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
+    },
+    "hidden_size": 1024,
+    "input_embedding_dim": 1536,
+    "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": 4,
+    "num_target_vision_tokens": 32,
+    "num_timestep_buckets": 1000,
+    "tune_diffusion_model": true,
+    "tune_projector": true,
+    "use_vlln": true,
+    "vl_self_attention_cfg": {
+      "attention_head_dim": 64,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "num_attention_heads": 32,
+      "num_layers": 4,
+      "positional_embeddings": null
+    }
+  },
+  "action_horizon": 16,
+  "architectures": [
+    "GR00T_N1_5"
+  ],
+  "attn_implementation": null,
+  "backbone_cfg": {
+    "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
+    "load_bf16": false,
+    "project_to_dim": null,
+    "reproject_vision": false,
+    "select_layer": 12,
+    "tune_llm": false,
+    "tune_visual": true,
+    "use_flash_attention": true
+  },
+  "compute_dtype": "bfloat16",
+  "hidden_size": 2048,
+  "model_dtype": "float32",
+  "model_type": "gr00t_n1_5",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/experiment_cfg/metadata.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/experiment_cfg/metadata.json
new file mode 100644
index 0000000000000000000000000000000000000000..27700cac5d292d4d42897b3c2e80bdc58e55c60e
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/experiment_cfg/metadata.json
@@ -0,0 +1,431 @@
+{
+    "new_embodiment": {
+        "statistics": {
+            "state": {
+                "base_position": {
+                    "max": [
+                        7.778976917266846,
+                        0.33403685688972473,
+                        0.7223060727119446
+                    ],
+                    "min": [
+                        -4.821934223175049,
+                        -6.785110950469971,
+                        0.6994727253913879
+                    ],
+                    "mean": [
+                        2.5719731235192254,
+                        -2.1489371002267235,
+                        0.7003612741268546
+                    ],
+                    "std": [
+                        1.669945884010784,
+                        1.3739411381361726,
+                        0.0009413282367754987
+                    ],
+                    "q01": [
+                        -0.7944286339399775,
+                        -5.486611518471242,
+                        0.699977555971739
+                    ],
+                    "q99": [
+                        6.019886905263648,
+                        -0.5229184210026855,
+                        0.702930326282967
+                    ]
+                },
+                "base_rotation": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.248543484335273,
+                        0.5959317405459531
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.6655550240074092,
+                        0.374283995143559
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        -1.0000000000000002,
+                        4.503254968910557e-06
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        1.0000000000000002,
+                        1.0000000000000002
+                    ]
+                },
+                "end_effector_position_relative": {
+                    "max": [
+                        0.8848381638526917,
+                        0.8569459915161133,
+                        1.053884744644165
+                    ],
+                    "min": [
+                        -0.5828549861907959,
+                        -0.8486236333847046,
+                        -0.3446122705936432
+                    ],
+                    "mean": [
+                        0.2465490874130862,
+                        -0.004711658908481467,
+                        0.43463835464312073
+                    ],
+                    "std": [
+                        0.15798784670671595,
+                        0.25624102400497073,
+                        0.20836028727974915
+                    ],
+                    "q01": [
+                        -0.020752051134640608,
+                        -0.4837933887347875,
+                        0.1802942952289915
+                    ],
+                    "q99": [
+                        0.5386784714844007,
+                        0.4801424212024721,
+                        0.695095732975766
+                    ]
+                },
+                "end_effector_rotation_relative": {
+                    "max": [
+                        0.9999949932098389,
+                        0.9997354745864868,
+                        0.9900747537612915,
+                        0.9735639095306396
+                    ],
+                    "min": [
+                        -0.9999914169311523,
+                        -0.9999884366989136,
+                        -0.9975369572639465,
+                        6.754255821306288e-08
+                    ],
+                    "mean": [
+                        -0.22531859714056926,
+                        0.046973702821026614,
+                        -0.0568176967878771,
+                        0.12364307042955697
+                    ],
+                    "std": [
+                        0.8502144333612052,
+                        0.29591250318147405,
+                        0.30218053156837016,
+                        0.1636031353412931
+                    ],
+                    "q01": [
+                        -0.9959057387172566,
+                        -0.5665384745573048,
+                        -0.5329334620834977,
+                        0.0014372279999397553
+                    ],
+                    "q99": [
+                        0.9904107951565839,
+                        0.6359623612021396,
+                        0.5026076022439377,
+                        0.42955559234879914
+                    ]
+                },
+                "gripper_qpos": {
+                    "max": [
+                        0.05289580300450325,
+                        0.00937709677964449
+                    ],
+                    "min": [
+                        -0.011669117026031017,
+                        -0.06307756155729294
+                    ],
+                    "mean": [
+                        0.03188757060429838,
+                        -0.0321793333086053
+                    ],
+                    "std": [
+                        0.01171052313737148,
+                        0.011427336801203189
+                    ],
+                    "q01": [
+                        0.006462901319459925,
+                        -0.040557140599419166
+                    ],
+                    "q99": [
+                        0.04037619335388386,
+                        -0.006523947835993347
+                    ]
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0,
+                        0.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.006639007355857881,
+                        0.0027330421795561874,
+                        -0.0017774441970214892,
+                        0.0
+                    ],
+                    "std": [
+                        0.11841528114040736,
+                        0.1041359083946544,
+                        0.08346265521208351,
+                        0.0
+                    ],
+                    "q01": [
+                        -0.17562359675270237,
+                        -0.21706402321529558,
+                        -0.16273392585723104,
+                        0.0
+                    ],
+                    "q99": [
+                        0.2572918701644887,
+                        0.27022325575787115,
+                        0.1369626751049278,
+                        0.0
+                    ]
+                },
+                "control_mode": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.9205539608927732
+                    ],
+                    "std": [
+                        0.39063657242534666
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        -0.17711863866562935
+                    ]
+                },
+                "end_effector_position": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.00924803964621179,
+                        0.004053841761390575,
+                        -0.08385115578460103
+                    ],
+                    "std": [
+                        0.45413072518223824,
+                        0.40158612714634856,
+                        0.41068634292849304
+                    ],
+                    "q01": [
+                        -0.9669817145875343,
+                        -0.9241307799783718,
+                        -0.8264079503068825
+                    ],
+                    "q99": [
+                        0.8021511975722166,
+                        0.9241346582748478,
+                        0.8348116781502298
+                    ]
+                },
+                "end_effector_rotation": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        0.007644157504353809,
+                        -0.019962543093886335,
+                        -0.002047110452602617
+                    ],
+                    "std": [
+                        0.11076012154791087,
+                        0.13176735140285795,
+                        0.12286528665895614
+                    ],
+                    "q01": [
+                        -0.2659105439401192,
+                        -0.3961694033813533,
+                        -0.3434870832468936
+                    ],
+                    "q99": [
+                        0.3145786959266369,
+                        0.31309430361227547,
+                        0.34107754401942986
+                    ]
+                },
+                "gripper_close": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.29870612267533575
+                    ],
+                    "std": [
+                        0.9543487555375691
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        0.7610674802484976
+                    ]
+                }
+            }
+        },
+        "modalities": {
+            "video": {
+                "robot0_eye_in_hand": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_left": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_right": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                }
+            },
+            "state": {
+                "base_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "base_rotation": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position_relative": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation_relative": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "gripper_qpos": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        2
+                    ],
+                    "continuous": true
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "control_mode": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation": {
+                    "absolute": true,
+                    "rotation_type": "axis_angle",
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "gripper_close": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                }
+            }
+        },
+        "embodiment_tag": "new_embodiment"
+    }
+}
\ No newline at end of file
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d5e0e2eeb776b6d4bb042e0ba6405390c78eaa01
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cad739162e0ee8414ba4511b7fcaa0c2ddb8fe047d46496aa03423aeaeee6e4
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0e9bf3b0d7508b7ca1d30a9276f203b5d1d0b720
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b7fd8ca7c5411df32b3e3aca2c478b6ba6fb382b541607e176c33f60b106a0
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model.safetensors.index.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/model.safetensors.index.json
@@ -0,0 +1,906 @@
+{
+  "metadata": {
+    "total_size": 7585939328
+  },
+  "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.future_tokens.weight": "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-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-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",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vlln.bias": "model-00002-of-00002.safetensors",
+    "action_head.vlln.weight": "model-00002-of-00002.safetensors",
+    "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c024d982916986a23a0cf8819e819e8126fd07f9
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d26d43acc5ab7bea94836e04a88ec871c236de452bb39c79dfe60e17ed0674
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cddb85352b4d053450624108786800cbad81d6cb
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19ead5779e3f8f2f666b7793de3a03d118f57f1b16a97eeb87bd732d18b445
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/trainer_state.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5bd7049e1cb72e73723b20cd8df2951a6ce155a1
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-1000/trainer_state.json
@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.675041876046901,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01675041876046901,
+      "grad_norm": 1.3394557237625122,
+      "learning_rate": 1.08e-06,
+      "loss": 0.2322,
+      "step": 10
+    },
+    {
+      "epoch": 0.03350083752093802,
+      "grad_norm": 1.0503181219100952,
+      "learning_rate": 2.28e-06,
+      "loss": 0.2236,
+      "step": 20
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 0.8409915566444397,
+      "learning_rate": 3.48e-06,
+      "loss": 0.1834,
+      "step": 30
+    },
+    {
+      "epoch": 0.06700167504187604,
+      "grad_norm": 1.0835442543029785,
+      "learning_rate": 4.68e-06,
+      "loss": 0.1607,
+      "step": 40
+    },
+    {
+      "epoch": 0.08375209380234507,
+      "grad_norm": 0.6771818399429321,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 0.1415,
+      "step": 50
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 0.690451443195343,
+      "learning_rate": 7.08e-06,
+      "loss": 0.137,
+      "step": 60
+    },
+    {
+      "epoch": 0.11725293132328309,
+      "grad_norm": 0.3838907480239868,
+      "learning_rate": 8.28e-06,
+      "loss": 0.1083,
+      "step": 70
+    },
+    {
+      "epoch": 0.13400335008375208,
+      "grad_norm": 0.3522876799106598,
+      "learning_rate": 9.48e-06,
+      "loss": 0.0972,
+      "step": 80
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 0.2768699526786804,
+      "learning_rate": 1.068e-05,
+      "loss": 0.0842,
+      "step": 90
+    },
+    {
+      "epoch": 0.16750418760469013,
+      "grad_norm": 0.27654263377189636,
+      "learning_rate": 1.1880000000000001e-05,
+      "loss": 0.0762,
+      "step": 100
+    },
+    {
+      "epoch": 0.18425460636515914,
+      "grad_norm": 0.33774033188819885,
+      "learning_rate": 1.308e-05,
+      "loss": 0.0713,
+      "step": 110
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 0.2147975116968155,
+      "learning_rate": 1.428e-05,
+      "loss": 0.0672,
+      "step": 120
+    },
+    {
+      "epoch": 0.21775544388609716,
+      "grad_norm": 0.25137603282928467,
+      "learning_rate": 1.548e-05,
+      "loss": 0.0625,
+      "step": 130
+    },
+    {
+      "epoch": 0.23450586264656617,
+      "grad_norm": 0.3030863404273987,
+      "learning_rate": 1.6680000000000003e-05,
+      "loss": 0.0694,
+      "step": 140
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 0.2430053949356079,
+      "learning_rate": 1.7879999999999998e-05,
+      "loss": 0.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.26800670016750416,
+      "grad_norm": 0.24571731686592102,
+      "learning_rate": 1.908e-05,
+      "loss": 0.0658,
+      "step": 160
+    },
+    {
+      "epoch": 0.2847571189279732,
+      "grad_norm": 0.27303019165992737,
+      "learning_rate": 2.0280000000000002e-05,
+      "loss": 0.0633,
+      "step": 170
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 0.23230038583278656,
+      "learning_rate": 2.148e-05,
+      "loss": 0.0564,
+      "step": 180
+    },
+    {
+      "epoch": 0.31825795644891125,
+      "grad_norm": 0.2652761936187744,
+      "learning_rate": 2.268e-05,
+      "loss": 0.0579,
+      "step": 190
+    },
+    {
+      "epoch": 0.33500837520938026,
+      "grad_norm": 0.3008716106414795,
+      "learning_rate": 2.3880000000000002e-05,
+      "loss": 0.0581,
+      "step": 200
+    },
+    {
+      "epoch": 0.35175879396984927,
+      "grad_norm": 0.25785622000694275,
+      "learning_rate": 2.508e-05,
+      "loss": 0.0614,
+      "step": 210
+    },
+    {
+      "epoch": 0.3685092127303183,
+      "grad_norm": 0.26564037799835205,
+      "learning_rate": 2.628e-05,
+      "loss": 0.0522,
+      "step": 220
+    },
+    {
+      "epoch": 0.3852596314907873,
+      "grad_norm": 0.2962818741798401,
+      "learning_rate": 2.748e-05,
+      "loss": 0.0521,
+      "step": 230
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 0.28678590059280396,
+      "learning_rate": 2.868e-05,
+      "loss": 0.0555,
+      "step": 240
+    },
+    {
+      "epoch": 0.4187604690117253,
+      "grad_norm": 0.29701972007751465,
+      "learning_rate": 2.9880000000000002e-05,
+      "loss": 0.0517,
+      "step": 250
+    },
+    {
+      "epoch": 0.4355108877721943,
+      "grad_norm": 0.2258671224117279,
+      "learning_rate": 2.9999734259635676e-05,
+      "loss": 0.0523,
+      "step": 260
+    },
+    {
+      "epoch": 0.45226130653266333,
+      "grad_norm": 0.2276943176984787,
+      "learning_rate": 2.9998815663057245e-05,
+      "loss": 0.0491,
+      "step": 270
+    },
+    {
+      "epoch": 0.46901172529313234,
+      "grad_norm": 0.367814838886261,
+      "learning_rate": 2.999724096969228e-05,
+      "loss": 0.0472,
+      "step": 280
+    },
+    {
+      "epoch": 0.48576214405360135,
+      "grad_norm": 0.19225119054317474,
+      "learning_rate": 2.9995010248422984e-05,
+      "loss": 0.0452,
+      "step": 290
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 0.3076336681842804,
+      "learning_rate": 2.999212359682832e-05,
+      "loss": 0.0478,
+      "step": 300
+    },
+    {
+      "epoch": 0.5192629815745393,
+      "grad_norm": 0.2448616325855255,
+      "learning_rate": 2.9988581141179787e-05,
+      "loss": 0.0471,
+      "step": 310
+    },
+    {
+      "epoch": 0.5360134003350083,
+      "grad_norm": 0.20978757739067078,
+      "learning_rate": 2.998438303643587e-05,
+      "loss": 0.0383,
+      "step": 320
+    },
+    {
+      "epoch": 0.5527638190954773,
+      "grad_norm": 0.24052295088768005,
+      "learning_rate": 2.997952946623527e-05,
+      "loss": 0.0435,
+      "step": 330
+    },
+    {
+      "epoch": 0.5695142378559463,
+      "grad_norm": 0.22263383865356445,
+      "learning_rate": 2.9974020642888875e-05,
+      "loss": 0.0467,
+      "step": 340
+    },
+    {
+      "epoch": 0.5862646566164154,
+      "grad_norm": 0.25700053572654724,
+      "learning_rate": 2.9967856807370458e-05,
+      "loss": 0.0448,
+      "step": 350
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 0.19276398420333862,
+      "learning_rate": 2.996103822930615e-05,
+      "loss": 0.0436,
+      "step": 360
+    },
+    {
+      "epoch": 0.6197654941373534,
+      "grad_norm": 0.19240586459636688,
+      "learning_rate": 2.9953565206962653e-05,
+      "loss": 0.0406,
+      "step": 370
+    },
+    {
+      "epoch": 0.6365159128978225,
+      "grad_norm": 0.23333503305912018,
+      "learning_rate": 2.9945438067234172e-05,
+      "loss": 0.0397,
+      "step": 380
+    },
+    {
+      "epoch": 0.6532663316582915,
+      "grad_norm": 0.26178690791130066,
+      "learning_rate": 2.9936657165628124e-05,
+      "loss": 0.0394,
+      "step": 390
+    },
+    {
+      "epoch": 0.6700167504187605,
+      "grad_norm": 0.16855783760547638,
+      "learning_rate": 2.992722288624959e-05,
+      "loss": 0.0385,
+      "step": 400
+    },
+    {
+      "epoch": 0.6867671691792295,
+      "grad_norm": 0.1688416302204132,
+      "learning_rate": 2.9917135641784515e-05,
+      "loss": 0.0422,
+      "step": 410
+    },
+    {
+      "epoch": 0.7035175879396985,
+      "grad_norm": 0.18370051681995392,
+      "learning_rate": 2.9906395873481655e-05,
+      "loss": 0.0371,
+      "step": 420
+    },
+    {
+      "epoch": 0.7202680067001676,
+      "grad_norm": 0.2349836379289627,
+      "learning_rate": 2.989500405113326e-05,
+      "loss": 0.0413,
+      "step": 430
+    },
+    {
+      "epoch": 0.7370184254606366,
+      "grad_norm": 0.20748260617256165,
+      "learning_rate": 2.9882960673054547e-05,
+      "loss": 0.0367,
+      "step": 440
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 0.1702982783317566,
+      "learning_rate": 2.9870266266061886e-05,
+      "loss": 0.0379,
+      "step": 450
+    },
+    {
+      "epoch": 0.7705192629815746,
+      "grad_norm": 0.26680412888526917,
+      "learning_rate": 2.9856921385449766e-05,
+      "loss": 0.0367,
+      "step": 460
+    },
+    {
+      "epoch": 0.7872696817420436,
+      "grad_norm": 0.21671664714813232,
+      "learning_rate": 2.9842926614966502e-05,
+      "loss": 0.0367,
+      "step": 470
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 0.20597104728221893,
+      "learning_rate": 2.982828256678868e-05,
+      "loss": 0.0377,
+      "step": 480
+    },
+    {
+      "epoch": 0.8207705192629816,
+      "grad_norm": 0.25721216201782227,
+      "learning_rate": 2.9812989881494412e-05,
+      "loss": 0.0376,
+      "step": 490
+    },
+    {
+      "epoch": 0.8375209380234506,
+      "grad_norm": 0.20260390639305115,
+      "learning_rate": 2.9797049228035296e-05,
+      "loss": 0.0353,
+      "step": 500
+    },
+    {
+      "epoch": 0.8542713567839196,
+      "grad_norm": 0.18940532207489014,
+      "learning_rate": 2.978046130370715e-05,
+      "loss": 0.0326,
+      "step": 510
+    },
+    {
+      "epoch": 0.8710217755443886,
+      "grad_norm": 0.14810627698898315,
+      "learning_rate": 2.9763226834119535e-05,
+      "loss": 0.0359,
+      "step": 520
+    },
+    {
+      "epoch": 0.8877721943048577,
+      "grad_norm": 0.21682192385196686,
+      "learning_rate": 2.9745346573163963e-05,
+      "loss": 0.0343,
+      "step": 530
+    },
+    {
+      "epoch": 0.9045226130653267,
+      "grad_norm": 0.2462719827890396,
+      "learning_rate": 2.9726821302980987e-05,
+      "loss": 0.0344,
+      "step": 540
+    },
+    {
+      "epoch": 0.9212730318257957,
+      "grad_norm": 0.20271016657352448,
+      "learning_rate": 2.9707651833925935e-05,
+      "loss": 0.0295,
+      "step": 550
+    },
+    {
+      "epoch": 0.9380234505862647,
+      "grad_norm": 0.18994300067424774,
+      "learning_rate": 2.968783900453348e-05,
+      "loss": 0.0331,
+      "step": 560
+    },
+    {
+      "epoch": 0.9547738693467337,
+      "grad_norm": 0.1817820817232132,
+      "learning_rate": 2.9667383681480968e-05,
+      "loss": 0.0344,
+      "step": 570
+    },
+    {
+      "epoch": 0.9715242881072027,
+      "grad_norm": 0.20372416079044342,
+      "learning_rate": 2.9646286759550493e-05,
+      "loss": 0.0333,
+      "step": 580
+    },
+    {
+      "epoch": 0.9882747068676717,
+      "grad_norm": 0.22303369641304016,
+      "learning_rate": 2.9624549161589764e-05,
+      "loss": 0.0316,
+      "step": 590
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 0.15984657406806946,
+      "learning_rate": 2.9602171838471745e-05,
+      "loss": 0.0325,
+      "step": 600
+    },
+    {
+      "epoch": 1.0217755443886096,
+      "grad_norm": 0.18722732365131378,
+      "learning_rate": 2.957915576905303e-05,
+      "loss": 0.0304,
+      "step": 610
+    },
+    {
+      "epoch": 1.0385259631490786,
+      "grad_norm": 0.18170492351055145,
+      "learning_rate": 2.9555501960131058e-05,
+      "loss": 0.0314,
+      "step": 620
+    },
+    {
+      "epoch": 1.0552763819095476,
+      "grad_norm": 0.19419005513191223,
+      "learning_rate": 2.9531211446400068e-05,
+      "loss": 0.0336,
+      "step": 630
+    },
+    {
+      "epoch": 1.0720268006700167,
+      "grad_norm": 0.21015776693820953,
+      "learning_rate": 2.9506285290405813e-05,
+      "loss": 0.0312,
+      "step": 640
+    },
+    {
+      "epoch": 1.0887772194304857,
+      "grad_norm": 0.13695307075977325,
+      "learning_rate": 2.948072458249911e-05,
+      "loss": 0.0341,
+      "step": 650
+    },
+    {
+      "epoch": 1.1055276381909547,
+      "grad_norm": 0.16071368753910065,
+      "learning_rate": 2.9454530440788125e-05,
+      "loss": 0.0295,
+      "step": 660
+    },
+    {
+      "epoch": 1.1222780569514237,
+      "grad_norm": 0.18829545378684998,
+      "learning_rate": 2.9427704011089474e-05,
+      "loss": 0.0303,
+      "step": 670
+    },
+    {
+      "epoch": 1.1390284757118927,
+      "grad_norm": 0.1615035980939865,
+      "learning_rate": 2.94002464668781e-05,
+      "loss": 0.0294,
+      "step": 680
+    },
+    {
+      "epoch": 1.1557788944723617,
+      "grad_norm": 0.1708756685256958,
+      "learning_rate": 2.9372159009235936e-05,
+      "loss": 0.0278,
+      "step": 690
+    },
+    {
+      "epoch": 1.1725293132328307,
+      "grad_norm": 0.1325443536043167,
+      "learning_rate": 2.9343442866799365e-05,
+      "loss": 0.0289,
+      "step": 700
+    },
+    {
+      "epoch": 1.1892797319932997,
+      "grad_norm": 0.18041647970676422,
+      "learning_rate": 2.9314099295705495e-05,
+      "loss": 0.0316,
+      "step": 710
+    },
+    {
+      "epoch": 1.2060301507537687,
+      "grad_norm": 0.15595586597919464,
+      "learning_rate": 2.928412957953718e-05,
+      "loss": 0.0294,
+      "step": 720
+    },
+    {
+      "epoch": 1.2227805695142377,
+      "grad_norm": 0.18720653653144836,
+      "learning_rate": 2.925353502926689e-05,
+      "loss": 0.0292,
+      "step": 730
+    },
+    {
+      "epoch": 1.2395309882747068,
+      "grad_norm": 0.1344250738620758,
+      "learning_rate": 2.922231698319937e-05,
+      "loss": 0.0299,
+      "step": 740
+    },
+    {
+      "epoch": 1.2562814070351758,
+      "grad_norm": 0.18409386277198792,
+      "learning_rate": 2.9190476806913088e-05,
+      "loss": 0.0305,
+      "step": 750
+    },
+    {
+      "epoch": 1.2730318257956448,
+      "grad_norm": 0.16554060578346252,
+      "learning_rate": 2.9158015893200504e-05,
+      "loss": 0.0292,
+      "step": 760
+    },
+    {
+      "epoch": 1.2897822445561138,
+      "grad_norm": 0.1602775752544403,
+      "learning_rate": 2.9124935662007137e-05,
+      "loss": 0.03,
+      "step": 770
+    },
+    {
+      "epoch": 1.3065326633165828,
+      "grad_norm": 0.1876162886619568,
+      "learning_rate": 2.9091237560369467e-05,
+      "loss": 0.0284,
+      "step": 780
+    },
+    {
+      "epoch": 1.3232830820770518,
+      "grad_norm": 0.24121980369091034,
+      "learning_rate": 2.905692306235163e-05,
+      "loss": 0.0282,
+      "step": 790
+    },
+    {
+      "epoch": 1.3400335008375208,
+      "grad_norm": 0.15151315927505493,
+      "learning_rate": 2.9021993668980925e-05,
+      "loss": 0.0288,
+      "step": 800
+    },
+    {
+      "epoch": 1.3567839195979898,
+      "grad_norm": 0.32094353437423706,
+      "learning_rate": 2.8986450908182185e-05,
+      "loss": 0.0265,
+      "step": 810
+    },
+    {
+      "epoch": 1.3735343383584588,
+      "grad_norm": 0.20612798631191254,
+      "learning_rate": 2.8950296334710902e-05,
+      "loss": 0.0281,
+      "step": 820
+    },
+    {
+      "epoch": 1.3902847571189278,
+      "grad_norm": 0.16587623953819275,
+      "learning_rate": 2.8913531530085248e-05,
+      "loss": 0.0272,
+      "step": 830
+    },
+    {
+      "epoch": 1.4070351758793969,
+      "grad_norm": 0.1658754050731659,
+      "learning_rate": 2.887615810251687e-05,
+      "loss": 0.0279,
+      "step": 840
+    },
+    {
+      "epoch": 1.4237855946398659,
+      "grad_norm": 0.155488982796669,
+      "learning_rate": 2.8838177686840577e-05,
+      "loss": 0.0266,
+      "step": 850
+    },
+    {
+      "epoch": 1.4405360134003349,
+      "grad_norm": 0.2229546457529068,
+      "learning_rate": 2.8799591944442776e-05,
+      "loss": 0.0292,
+      "step": 860
+    },
+    {
+      "epoch": 1.457286432160804,
+      "grad_norm": 0.36190536618232727,
+      "learning_rate": 2.8760402563188848e-05,
+      "loss": 0.0277,
+      "step": 870
+    },
+    {
+      "epoch": 1.474036850921273,
+      "grad_norm": 0.18090955913066864,
+      "learning_rate": 2.8720611257349285e-05,
+      "loss": 0.0297,
+      "step": 880
+    },
+    {
+      "epoch": 1.490787269681742,
+      "grad_norm": 0.17235404253005981,
+      "learning_rate": 2.868021976752471e-05,
+      "loss": 0.0265,
+      "step": 890
+    },
+    {
+      "epoch": 1.507537688442211,
+      "grad_norm": 0.1455887258052826,
+      "learning_rate": 2.8639229860569738e-05,
+      "loss": 0.0298,
+      "step": 900
+    },
+    {
+      "epoch": 1.52428810720268,
+      "grad_norm": 0.1774197816848755,
+      "learning_rate": 2.8597643329515688e-05,
+      "loss": 0.0263,
+      "step": 910
+    },
+    {
+      "epoch": 1.541038525963149,
+      "grad_norm": 0.15991894900798798,
+      "learning_rate": 2.855546199349214e-05,
+      "loss": 0.0259,
+      "step": 920
+    },
+    {
+      "epoch": 1.557788944723618,
+      "grad_norm": 0.30203819274902344,
+      "learning_rate": 2.85126876976474e-05,
+      "loss": 0.0276,
+      "step": 930
+    },
+    {
+      "epoch": 1.574539363484087,
+      "grad_norm": 0.13825957477092743,
+      "learning_rate": 2.8469322313067726e-05,
+      "loss": 0.0262,
+      "step": 940
+    },
+    {
+      "epoch": 1.591289782244556,
+      "grad_norm": 0.19100086390972137,
+      "learning_rate": 2.8425367736695522e-05,
+      "loss": 0.0257,
+      "step": 950
+    },
+    {
+      "epoch": 1.608040201005025,
+      "grad_norm": 0.16253994405269623,
+      "learning_rate": 2.838082589124636e-05,
+      "loss": 0.0282,
+      "step": 960
+    },
+    {
+      "epoch": 1.624790619765494,
+      "grad_norm": 0.21166931092739105,
+      "learning_rate": 2.8335698725124843e-05,
+      "loss": 0.0278,
+      "step": 970
+    },
+    {
+      "epoch": 1.641541038525963,
+      "grad_norm": 0.13361522555351257,
+      "learning_rate": 2.8289988212339422e-05,
+      "loss": 0.0254,
+      "step": 980
+    },
+    {
+      "epoch": 1.658291457286432,
+      "grad_norm": 0.20177683234214783,
+      "learning_rate": 2.8243696352415997e-05,
+      "loss": 0.0317,
+      "step": 990
+    },
+    {
+      "epoch": 1.675041876046901,
+      "grad_norm": 0.17741645872592926,
+      "learning_rate": 2.8196825170310495e-05,
+      "loss": 0.0254,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 5001,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/config.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/config.json
@@ -0,0 +1,64 @@
+{
+  "action_dim": 32,
+  "action_head_cfg": {
+    "action_dim": 32,
+    "action_horizon": 16,
+    "add_pos_embed": true,
+    "backbone_embedding_dim": 2048,
+    "diffusion_model_cfg": {
+      "attention_head_dim": 48,
+      "cross_attention_dim": 2048,
+      "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
+    },
+    "hidden_size": 1024,
+    "input_embedding_dim": 1536,
+    "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": 4,
+    "num_target_vision_tokens": 32,
+    "num_timestep_buckets": 1000,
+    "tune_diffusion_model": true,
+    "tune_projector": true,
+    "use_vlln": true,
+    "vl_self_attention_cfg": {
+      "attention_head_dim": 64,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "num_attention_heads": 32,
+      "num_layers": 4,
+      "positional_embeddings": null
+    }
+  },
+  "action_horizon": 16,
+  "architectures": [
+    "GR00T_N1_5"
+  ],
+  "attn_implementation": null,
+  "backbone_cfg": {
+    "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
+    "load_bf16": false,
+    "project_to_dim": null,
+    "reproject_vision": false,
+    "select_layer": 12,
+    "tune_llm": false,
+    "tune_visual": true,
+    "use_flash_attention": true
+  },
+  "compute_dtype": "bfloat16",
+  "hidden_size": 2048,
+  "model_dtype": "float32",
+  "model_type": "gr00t_n1_5",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/experiment_cfg/metadata.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/experiment_cfg/metadata.json
new file mode 100644
index 0000000000000000000000000000000000000000..27700cac5d292d4d42897b3c2e80bdc58e55c60e
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/experiment_cfg/metadata.json
@@ -0,0 +1,431 @@
+{
+    "new_embodiment": {
+        "statistics": {
+            "state": {
+                "base_position": {
+                    "max": [
+                        7.778976917266846,
+                        0.33403685688972473,
+                        0.7223060727119446
+                    ],
+                    "min": [
+                        -4.821934223175049,
+                        -6.785110950469971,
+                        0.6994727253913879
+                    ],
+                    "mean": [
+                        2.5719731235192254,
+                        -2.1489371002267235,
+                        0.7003612741268546
+                    ],
+                    "std": [
+                        1.669945884010784,
+                        1.3739411381361726,
+                        0.0009413282367754987
+                    ],
+                    "q01": [
+                        -0.7944286339399775,
+                        -5.486611518471242,
+                        0.699977555971739
+                    ],
+                    "q99": [
+                        6.019886905263648,
+                        -0.5229184210026855,
+                        0.702930326282967
+                    ]
+                },
+                "base_rotation": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.248543484335273,
+                        0.5959317405459531
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.6655550240074092,
+                        0.374283995143559
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        -1.0000000000000002,
+                        4.503254968910557e-06
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        1.0000000000000002,
+                        1.0000000000000002
+                    ]
+                },
+                "end_effector_position_relative": {
+                    "max": [
+                        0.8848381638526917,
+                        0.8569459915161133,
+                        1.053884744644165
+                    ],
+                    "min": [
+                        -0.5828549861907959,
+                        -0.8486236333847046,
+                        -0.3446122705936432
+                    ],
+                    "mean": [
+                        0.2465490874130862,
+                        -0.004711658908481467,
+                        0.43463835464312073
+                    ],
+                    "std": [
+                        0.15798784670671595,
+                        0.25624102400497073,
+                        0.20836028727974915
+                    ],
+                    "q01": [
+                        -0.020752051134640608,
+                        -0.4837933887347875,
+                        0.1802942952289915
+                    ],
+                    "q99": [
+                        0.5386784714844007,
+                        0.4801424212024721,
+                        0.695095732975766
+                    ]
+                },
+                "end_effector_rotation_relative": {
+                    "max": [
+                        0.9999949932098389,
+                        0.9997354745864868,
+                        0.9900747537612915,
+                        0.9735639095306396
+                    ],
+                    "min": [
+                        -0.9999914169311523,
+                        -0.9999884366989136,
+                        -0.9975369572639465,
+                        6.754255821306288e-08
+                    ],
+                    "mean": [
+                        -0.22531859714056926,
+                        0.046973702821026614,
+                        -0.0568176967878771,
+                        0.12364307042955697
+                    ],
+                    "std": [
+                        0.8502144333612052,
+                        0.29591250318147405,
+                        0.30218053156837016,
+                        0.1636031353412931
+                    ],
+                    "q01": [
+                        -0.9959057387172566,
+                        -0.5665384745573048,
+                        -0.5329334620834977,
+                        0.0014372279999397553
+                    ],
+                    "q99": [
+                        0.9904107951565839,
+                        0.6359623612021396,
+                        0.5026076022439377,
+                        0.42955559234879914
+                    ]
+                },
+                "gripper_qpos": {
+                    "max": [
+                        0.05289580300450325,
+                        0.00937709677964449
+                    ],
+                    "min": [
+                        -0.011669117026031017,
+                        -0.06307756155729294
+                    ],
+                    "mean": [
+                        0.03188757060429838,
+                        -0.0321793333086053
+                    ],
+                    "std": [
+                        0.01171052313737148,
+                        0.011427336801203189
+                    ],
+                    "q01": [
+                        0.006462901319459925,
+                        -0.040557140599419166
+                    ],
+                    "q99": [
+                        0.04037619335388386,
+                        -0.006523947835993347
+                    ]
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0,
+                        0.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.006639007355857881,
+                        0.0027330421795561874,
+                        -0.0017774441970214892,
+                        0.0
+                    ],
+                    "std": [
+                        0.11841528114040736,
+                        0.1041359083946544,
+                        0.08346265521208351,
+                        0.0
+                    ],
+                    "q01": [
+                        -0.17562359675270237,
+                        -0.21706402321529558,
+                        -0.16273392585723104,
+                        0.0
+                    ],
+                    "q99": [
+                        0.2572918701644887,
+                        0.27022325575787115,
+                        0.1369626751049278,
+                        0.0
+                    ]
+                },
+                "control_mode": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.9205539608927732
+                    ],
+                    "std": [
+                        0.39063657242534666
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        -0.17711863866562935
+                    ]
+                },
+                "end_effector_position": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.00924803964621179,
+                        0.004053841761390575,
+                        -0.08385115578460103
+                    ],
+                    "std": [
+                        0.45413072518223824,
+                        0.40158612714634856,
+                        0.41068634292849304
+                    ],
+                    "q01": [
+                        -0.9669817145875343,
+                        -0.9241307799783718,
+                        -0.8264079503068825
+                    ],
+                    "q99": [
+                        0.8021511975722166,
+                        0.9241346582748478,
+                        0.8348116781502298
+                    ]
+                },
+                "end_effector_rotation": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        0.007644157504353809,
+                        -0.019962543093886335,
+                        -0.002047110452602617
+                    ],
+                    "std": [
+                        0.11076012154791087,
+                        0.13176735140285795,
+                        0.12286528665895614
+                    ],
+                    "q01": [
+                        -0.2659105439401192,
+                        -0.3961694033813533,
+                        -0.3434870832468936
+                    ],
+                    "q99": [
+                        0.3145786959266369,
+                        0.31309430361227547,
+                        0.34107754401942986
+                    ]
+                },
+                "gripper_close": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.29870612267533575
+                    ],
+                    "std": [
+                        0.9543487555375691
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        0.7610674802484976
+                    ]
+                }
+            }
+        },
+        "modalities": {
+            "video": {
+                "robot0_eye_in_hand": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_left": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_right": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                }
+            },
+            "state": {
+                "base_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "base_rotation": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position_relative": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation_relative": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "gripper_qpos": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        2
+                    ],
+                    "continuous": true
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "control_mode": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation": {
+                    "absolute": true,
+                    "rotation_type": "axis_angle",
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "gripper_close": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                }
+            }
+        },
+        "embodiment_tag": "new_embodiment"
+    }
+}
\ No newline at end of file
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..706733a813efd5c0d04295e659be470462677472
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:198273fb376d0ef6bf0de2576f81b6e5621cfaa0811f0315876056eb703889b5
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f82dd438ca6ae3372df2c762b5fbe1706b913a35
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1fc016c68b2a0b15538d66fc764cd9d97818706db8fdc808bc880466fd1ab1
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model.safetensors.index.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/model.safetensors.index.json
@@ -0,0 +1,906 @@
+{
+  "metadata": {
+    "total_size": 7585939328
+  },
+  "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.future_tokens.weight": "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-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-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",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vlln.bias": "model-00002-of-00002.safetensors",
+    "action_head.vlln.weight": "model-00002-of-00002.safetensors",
+    "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2f794ccb867814532d52224f3c3fa2912e97d5b0
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c92d34f806bd357292f6ef538c5846496ee7354432a4e1a4328334bd4b95bc43
+size 8550719959
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7969d0c75ecf6a45378fd552390a1416459c488d
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85cf750ef17be819e7281f7355fdb6fe24e17d7b2f3f773c8f182329ad9e5dc9
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de4e41c4a6949df056e028b10a18e7f8cd7b7580
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d8e6d8e53e6b837084d0cc18fdd63ca9e40bd44a65d38eb52695647a8e84e8
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/trainer_state.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..303f847338a6a930a54761db25662d4df1e5f750
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/checkpoint-3000/trainer_state.json
@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.025125628140704,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01675041876046901,
+      "grad_norm": 1.3394557237625122,
+      "learning_rate": 1.08e-06,
+      "loss": 0.2322,
+      "step": 10
+    },
+    {
+      "epoch": 0.03350083752093802,
+      "grad_norm": 1.0503181219100952,
+      "learning_rate": 2.28e-06,
+      "loss": 0.2236,
+      "step": 20
+    },
+    {
+      "epoch": 0.05025125628140704,
+      "grad_norm": 0.8409915566444397,
+      "learning_rate": 3.48e-06,
+      "loss": 0.1834,
+      "step": 30
+    },
+    {
+      "epoch": 0.06700167504187604,
+      "grad_norm": 1.0835442543029785,
+      "learning_rate": 4.68e-06,
+      "loss": 0.1607,
+      "step": 40
+    },
+    {
+      "epoch": 0.08375209380234507,
+      "grad_norm": 0.6771818399429321,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 0.1415,
+      "step": 50
+    },
+    {
+      "epoch": 0.10050251256281408,
+      "grad_norm": 0.690451443195343,
+      "learning_rate": 7.08e-06,
+      "loss": 0.137,
+      "step": 60
+    },
+    {
+      "epoch": 0.11725293132328309,
+      "grad_norm": 0.3838907480239868,
+      "learning_rate": 8.28e-06,
+      "loss": 0.1083,
+      "step": 70
+    },
+    {
+      "epoch": 0.13400335008375208,
+      "grad_norm": 0.3522876799106598,
+      "learning_rate": 9.48e-06,
+      "loss": 0.0972,
+      "step": 80
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 0.2768699526786804,
+      "learning_rate": 1.068e-05,
+      "loss": 0.0842,
+      "step": 90
+    },
+    {
+      "epoch": 0.16750418760469013,
+      "grad_norm": 0.27654263377189636,
+      "learning_rate": 1.1880000000000001e-05,
+      "loss": 0.0762,
+      "step": 100
+    },
+    {
+      "epoch": 0.18425460636515914,
+      "grad_norm": 0.33774033188819885,
+      "learning_rate": 1.308e-05,
+      "loss": 0.0713,
+      "step": 110
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 0.2147975116968155,
+      "learning_rate": 1.428e-05,
+      "loss": 0.0672,
+      "step": 120
+    },
+    {
+      "epoch": 0.21775544388609716,
+      "grad_norm": 0.25137603282928467,
+      "learning_rate": 1.548e-05,
+      "loss": 0.0625,
+      "step": 130
+    },
+    {
+      "epoch": 0.23450586264656617,
+      "grad_norm": 0.3030863404273987,
+      "learning_rate": 1.6680000000000003e-05,
+      "loss": 0.0694,
+      "step": 140
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 0.2430053949356079,
+      "learning_rate": 1.7879999999999998e-05,
+      "loss": 0.0638,
+      "step": 150
+    },
+    {
+      "epoch": 0.26800670016750416,
+      "grad_norm": 0.24571731686592102,
+      "learning_rate": 1.908e-05,
+      "loss": 0.0658,
+      "step": 160
+    },
+    {
+      "epoch": 0.2847571189279732,
+      "grad_norm": 0.27303019165992737,
+      "learning_rate": 2.0280000000000002e-05,
+      "loss": 0.0633,
+      "step": 170
+    },
+    {
+      "epoch": 0.3015075376884422,
+      "grad_norm": 0.23230038583278656,
+      "learning_rate": 2.148e-05,
+      "loss": 0.0564,
+      "step": 180
+    },
+    {
+      "epoch": 0.31825795644891125,
+      "grad_norm": 0.2652761936187744,
+      "learning_rate": 2.268e-05,
+      "loss": 0.0579,
+      "step": 190
+    },
+    {
+      "epoch": 0.33500837520938026,
+      "grad_norm": 0.3008716106414795,
+      "learning_rate": 2.3880000000000002e-05,
+      "loss": 0.0581,
+      "step": 200
+    },
+    {
+      "epoch": 0.35175879396984927,
+      "grad_norm": 0.25785622000694275,
+      "learning_rate": 2.508e-05,
+      "loss": 0.0614,
+      "step": 210
+    },
+    {
+      "epoch": 0.3685092127303183,
+      "grad_norm": 0.26564037799835205,
+      "learning_rate": 2.628e-05,
+      "loss": 0.0522,
+      "step": 220
+    },
+    {
+      "epoch": 0.3852596314907873,
+      "grad_norm": 0.2962818741798401,
+      "learning_rate": 2.748e-05,
+      "loss": 0.0521,
+      "step": 230
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 0.28678590059280396,
+      "learning_rate": 2.868e-05,
+      "loss": 0.0555,
+      "step": 240
+    },
+    {
+      "epoch": 0.4187604690117253,
+      "grad_norm": 0.29701972007751465,
+      "learning_rate": 2.9880000000000002e-05,
+      "loss": 0.0517,
+      "step": 250
+    },
+    {
+      "epoch": 0.4355108877721943,
+      "grad_norm": 0.2258671224117279,
+      "learning_rate": 2.9999734259635676e-05,
+      "loss": 0.0523,
+      "step": 260
+    },
+    {
+      "epoch": 0.45226130653266333,
+      "grad_norm": 0.2276943176984787,
+      "learning_rate": 2.9998815663057245e-05,
+      "loss": 0.0491,
+      "step": 270
+    },
+    {
+      "epoch": 0.46901172529313234,
+      "grad_norm": 0.367814838886261,
+      "learning_rate": 2.999724096969228e-05,
+      "loss": 0.0472,
+      "step": 280
+    },
+    {
+      "epoch": 0.48576214405360135,
+      "grad_norm": 0.19225119054317474,
+      "learning_rate": 2.9995010248422984e-05,
+      "loss": 0.0452,
+      "step": 290
+    },
+    {
+      "epoch": 0.5025125628140703,
+      "grad_norm": 0.3076336681842804,
+      "learning_rate": 2.999212359682832e-05,
+      "loss": 0.0478,
+      "step": 300
+    },
+    {
+      "epoch": 0.5192629815745393,
+      "grad_norm": 0.2448616325855255,
+      "learning_rate": 2.9988581141179787e-05,
+      "loss": 0.0471,
+      "step": 310
+    },
+    {
+      "epoch": 0.5360134003350083,
+      "grad_norm": 0.20978757739067078,
+      "learning_rate": 2.998438303643587e-05,
+      "loss": 0.0383,
+      "step": 320
+    },
+    {
+      "epoch": 0.5527638190954773,
+      "grad_norm": 0.24052295088768005,
+      "learning_rate": 2.997952946623527e-05,
+      "loss": 0.0435,
+      "step": 330
+    },
+    {
+      "epoch": 0.5695142378559463,
+      "grad_norm": 0.22263383865356445,
+      "learning_rate": 2.9974020642888875e-05,
+      "loss": 0.0467,
+      "step": 340
+    },
+    {
+      "epoch": 0.5862646566164154,
+      "grad_norm": 0.25700053572654724,
+      "learning_rate": 2.9967856807370458e-05,
+      "loss": 0.0448,
+      "step": 350
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 0.19276398420333862,
+      "learning_rate": 2.996103822930615e-05,
+      "loss": 0.0436,
+      "step": 360
+    },
+    {
+      "epoch": 0.6197654941373534,
+      "grad_norm": 0.19240586459636688,
+      "learning_rate": 2.9953565206962653e-05,
+      "loss": 0.0406,
+      "step": 370
+    },
+    {
+      "epoch": 0.6365159128978225,
+      "grad_norm": 0.23333503305912018,
+      "learning_rate": 2.9945438067234172e-05,
+      "loss": 0.0397,
+      "step": 380
+    },
+    {
+      "epoch": 0.6532663316582915,
+      "grad_norm": 0.26178690791130066,
+      "learning_rate": 2.9936657165628124e-05,
+      "loss": 0.0394,
+      "step": 390
+    },
+    {
+      "epoch": 0.6700167504187605,
+      "grad_norm": 0.16855783760547638,
+      "learning_rate": 2.992722288624959e-05,
+      "loss": 0.0385,
+      "step": 400
+    },
+    {
+      "epoch": 0.6867671691792295,
+      "grad_norm": 0.1688416302204132,
+      "learning_rate": 2.9917135641784515e-05,
+      "loss": 0.0422,
+      "step": 410
+    },
+    {
+      "epoch": 0.7035175879396985,
+      "grad_norm": 0.18370051681995392,
+      "learning_rate": 2.9906395873481655e-05,
+      "loss": 0.0371,
+      "step": 420
+    },
+    {
+      "epoch": 0.7202680067001676,
+      "grad_norm": 0.2349836379289627,
+      "learning_rate": 2.989500405113326e-05,
+      "loss": 0.0413,
+      "step": 430
+    },
+    {
+      "epoch": 0.7370184254606366,
+      "grad_norm": 0.20748260617256165,
+      "learning_rate": 2.9882960673054547e-05,
+      "loss": 0.0367,
+      "step": 440
+    },
+    {
+      "epoch": 0.7537688442211056,
+      "grad_norm": 0.1702982783317566,
+      "learning_rate": 2.9870266266061886e-05,
+      "loss": 0.0379,
+      "step": 450
+    },
+    {
+      "epoch": 0.7705192629815746,
+      "grad_norm": 0.26680412888526917,
+      "learning_rate": 2.9856921385449766e-05,
+      "loss": 0.0367,
+      "step": 460
+    },
+    {
+      "epoch": 0.7872696817420436,
+      "grad_norm": 0.21671664714813232,
+      "learning_rate": 2.9842926614966502e-05,
+      "loss": 0.0367,
+      "step": 470
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 0.20597104728221893,
+      "learning_rate": 2.982828256678868e-05,
+      "loss": 0.0377,
+      "step": 480
+    },
+    {
+      "epoch": 0.8207705192629816,
+      "grad_norm": 0.25721216201782227,
+      "learning_rate": 2.9812989881494412e-05,
+      "loss": 0.0376,
+      "step": 490
+    },
+    {
+      "epoch": 0.8375209380234506,
+      "grad_norm": 0.20260390639305115,
+      "learning_rate": 2.9797049228035296e-05,
+      "loss": 0.0353,
+      "step": 500
+    },
+    {
+      "epoch": 0.8542713567839196,
+      "grad_norm": 0.18940532207489014,
+      "learning_rate": 2.978046130370715e-05,
+      "loss": 0.0326,
+      "step": 510
+    },
+    {
+      "epoch": 0.8710217755443886,
+      "grad_norm": 0.14810627698898315,
+      "learning_rate": 2.9763226834119535e-05,
+      "loss": 0.0359,
+      "step": 520
+    },
+    {
+      "epoch": 0.8877721943048577,
+      "grad_norm": 0.21682192385196686,
+      "learning_rate": 2.9745346573163963e-05,
+      "loss": 0.0343,
+      "step": 530
+    },
+    {
+      "epoch": 0.9045226130653267,
+      "grad_norm": 0.2462719827890396,
+      "learning_rate": 2.9726821302980987e-05,
+      "loss": 0.0344,
+      "step": 540
+    },
+    {
+      "epoch": 0.9212730318257957,
+      "grad_norm": 0.20271016657352448,
+      "learning_rate": 2.9707651833925935e-05,
+      "loss": 0.0295,
+      "step": 550
+    },
+    {
+      "epoch": 0.9380234505862647,
+      "grad_norm": 0.18994300067424774,
+      "learning_rate": 2.968783900453348e-05,
+      "loss": 0.0331,
+      "step": 560
+    },
+    {
+      "epoch": 0.9547738693467337,
+      "grad_norm": 0.1817820817232132,
+      "learning_rate": 2.9667383681480968e-05,
+      "loss": 0.0344,
+      "step": 570
+    },
+    {
+      "epoch": 0.9715242881072027,
+      "grad_norm": 0.20372416079044342,
+      "learning_rate": 2.9646286759550493e-05,
+      "loss": 0.0333,
+      "step": 580
+    },
+    {
+      "epoch": 0.9882747068676717,
+      "grad_norm": 0.22303369641304016,
+      "learning_rate": 2.9624549161589764e-05,
+      "loss": 0.0316,
+      "step": 590
+    },
+    {
+      "epoch": 1.0050251256281406,
+      "grad_norm": 0.15984657406806946,
+      "learning_rate": 2.9602171838471745e-05,
+      "loss": 0.0325,
+      "step": 600
+    },
+    {
+      "epoch": 1.0217755443886096,
+      "grad_norm": 0.18722732365131378,
+      "learning_rate": 2.957915576905303e-05,
+      "loss": 0.0304,
+      "step": 610
+    },
+    {
+      "epoch": 1.0385259631490786,
+      "grad_norm": 0.18170492351055145,
+      "learning_rate": 2.9555501960131058e-05,
+      "loss": 0.0314,
+      "step": 620
+    },
+    {
+      "epoch": 1.0552763819095476,
+      "grad_norm": 0.19419005513191223,
+      "learning_rate": 2.9531211446400068e-05,
+      "loss": 0.0336,
+      "step": 630
+    },
+    {
+      "epoch": 1.0720268006700167,
+      "grad_norm": 0.21015776693820953,
+      "learning_rate": 2.9506285290405813e-05,
+      "loss": 0.0312,
+      "step": 640
+    },
+    {
+      "epoch": 1.0887772194304857,
+      "grad_norm": 0.13695307075977325,
+      "learning_rate": 2.948072458249911e-05,
+      "loss": 0.0341,
+      "step": 650
+    },
+    {
+      "epoch": 1.1055276381909547,
+      "grad_norm": 0.16071368753910065,
+      "learning_rate": 2.9454530440788125e-05,
+      "loss": 0.0295,
+      "step": 660
+    },
+    {
+      "epoch": 1.1222780569514237,
+      "grad_norm": 0.18829545378684998,
+      "learning_rate": 2.9427704011089474e-05,
+      "loss": 0.0303,
+      "step": 670
+    },
+    {
+      "epoch": 1.1390284757118927,
+      "grad_norm": 0.1615035980939865,
+      "learning_rate": 2.94002464668781e-05,
+      "loss": 0.0294,
+      "step": 680
+    },
+    {
+      "epoch": 1.1557788944723617,
+      "grad_norm": 0.1708756685256958,
+      "learning_rate": 2.9372159009235936e-05,
+      "loss": 0.0278,
+      "step": 690
+    },
+    {
+      "epoch": 1.1725293132328307,
+      "grad_norm": 0.1325443536043167,
+      "learning_rate": 2.9343442866799365e-05,
+      "loss": 0.0289,
+      "step": 700
+    },
+    {
+      "epoch": 1.1892797319932997,
+      "grad_norm": 0.18041647970676422,
+      "learning_rate": 2.9314099295705495e-05,
+      "loss": 0.0316,
+      "step": 710
+    },
+    {
+      "epoch": 1.2060301507537687,
+      "grad_norm": 0.15595586597919464,
+      "learning_rate": 2.928412957953718e-05,
+      "loss": 0.0294,
+      "step": 720
+    },
+    {
+      "epoch": 1.2227805695142377,
+      "grad_norm": 0.18720653653144836,
+      "learning_rate": 2.925353502926689e-05,
+      "loss": 0.0292,
+      "step": 730
+    },
+    {
+      "epoch": 1.2395309882747068,
+      "grad_norm": 0.1344250738620758,
+      "learning_rate": 2.922231698319937e-05,
+      "loss": 0.0299,
+      "step": 740
+    },
+    {
+      "epoch": 1.2562814070351758,
+      "grad_norm": 0.18409386277198792,
+      "learning_rate": 2.9190476806913088e-05,
+      "loss": 0.0305,
+      "step": 750
+    },
+    {
+      "epoch": 1.2730318257956448,
+      "grad_norm": 0.16554060578346252,
+      "learning_rate": 2.9158015893200504e-05,
+      "loss": 0.0292,
+      "step": 760
+    },
+    {
+      "epoch": 1.2897822445561138,
+      "grad_norm": 0.1602775752544403,
+      "learning_rate": 2.9124935662007137e-05,
+      "loss": 0.03,
+      "step": 770
+    },
+    {
+      "epoch": 1.3065326633165828,
+      "grad_norm": 0.1876162886619568,
+      "learning_rate": 2.9091237560369467e-05,
+      "loss": 0.0284,
+      "step": 780
+    },
+    {
+      "epoch": 1.3232830820770518,
+      "grad_norm": 0.24121980369091034,
+      "learning_rate": 2.905692306235163e-05,
+      "loss": 0.0282,
+      "step": 790
+    },
+    {
+      "epoch": 1.3400335008375208,
+      "grad_norm": 0.15151315927505493,
+      "learning_rate": 2.9021993668980925e-05,
+      "loss": 0.0288,
+      "step": 800
+    },
+    {
+      "epoch": 1.3567839195979898,
+      "grad_norm": 0.32094353437423706,
+      "learning_rate": 2.8986450908182185e-05,
+      "loss": 0.0265,
+      "step": 810
+    },
+    {
+      "epoch": 1.3735343383584588,
+      "grad_norm": 0.20612798631191254,
+      "learning_rate": 2.8950296334710902e-05,
+      "loss": 0.0281,
+      "step": 820
+    },
+    {
+      "epoch": 1.3902847571189278,
+      "grad_norm": 0.16587623953819275,
+      "learning_rate": 2.8913531530085248e-05,
+      "loss": 0.0272,
+      "step": 830
+    },
+    {
+      "epoch": 1.4070351758793969,
+      "grad_norm": 0.1658754050731659,
+      "learning_rate": 2.887615810251687e-05,
+      "loss": 0.0279,
+      "step": 840
+    },
+    {
+      "epoch": 1.4237855946398659,
+      "grad_norm": 0.155488982796669,
+      "learning_rate": 2.8838177686840577e-05,
+      "loss": 0.0266,
+      "step": 850
+    },
+    {
+      "epoch": 1.4405360134003349,
+      "grad_norm": 0.2229546457529068,
+      "learning_rate": 2.8799591944442776e-05,
+      "loss": 0.0292,
+      "step": 860
+    },
+    {
+      "epoch": 1.457286432160804,
+      "grad_norm": 0.36190536618232727,
+      "learning_rate": 2.8760402563188848e-05,
+      "loss": 0.0277,
+      "step": 870
+    },
+    {
+      "epoch": 1.474036850921273,
+      "grad_norm": 0.18090955913066864,
+      "learning_rate": 2.8720611257349285e-05,
+      "loss": 0.0297,
+      "step": 880
+    },
+    {
+      "epoch": 1.490787269681742,
+      "grad_norm": 0.17235404253005981,
+      "learning_rate": 2.868021976752471e-05,
+      "loss": 0.0265,
+      "step": 890
+    },
+    {
+      "epoch": 1.507537688442211,
+      "grad_norm": 0.1455887258052826,
+      "learning_rate": 2.8639229860569738e-05,
+      "loss": 0.0298,
+      "step": 900
+    },
+    {
+      "epoch": 1.52428810720268,
+      "grad_norm": 0.1774197816848755,
+      "learning_rate": 2.8597643329515688e-05,
+      "loss": 0.0263,
+      "step": 910
+    },
+    {
+      "epoch": 1.541038525963149,
+      "grad_norm": 0.15991894900798798,
+      "learning_rate": 2.855546199349214e-05,
+      "loss": 0.0259,
+      "step": 920
+    },
+    {
+      "epoch": 1.557788944723618,
+      "grad_norm": 0.30203819274902344,
+      "learning_rate": 2.85126876976474e-05,
+      "loss": 0.0276,
+      "step": 930
+    },
+    {
+      "epoch": 1.574539363484087,
+      "grad_norm": 0.13825957477092743,
+      "learning_rate": 2.8469322313067726e-05,
+      "loss": 0.0262,
+      "step": 940
+    },
+    {
+      "epoch": 1.591289782244556,
+      "grad_norm": 0.19100086390972137,
+      "learning_rate": 2.8425367736695522e-05,
+      "loss": 0.0257,
+      "step": 950
+    },
+    {
+      "epoch": 1.608040201005025,
+      "grad_norm": 0.16253994405269623,
+      "learning_rate": 2.838082589124636e-05,
+      "loss": 0.0282,
+      "step": 960
+    },
+    {
+      "epoch": 1.624790619765494,
+      "grad_norm": 0.21166931092739105,
+      "learning_rate": 2.8335698725124843e-05,
+      "loss": 0.0278,
+      "step": 970
+    },
+    {
+      "epoch": 1.641541038525963,
+      "grad_norm": 0.13361522555351257,
+      "learning_rate": 2.8289988212339422e-05,
+      "loss": 0.0254,
+      "step": 980
+    },
+    {
+      "epoch": 1.658291457286432,
+      "grad_norm": 0.20177683234214783,
+      "learning_rate": 2.8243696352415997e-05,
+      "loss": 0.0317,
+      "step": 990
+    },
+    {
+      "epoch": 1.675041876046901,
+      "grad_norm": 0.17741645872592926,
+      "learning_rate": 2.8196825170310495e-05,
+      "loss": 0.0254,
+      "step": 1000
+    },
+    {
+      "epoch": 1.69179229480737,
+      "grad_norm": 0.1586075723171234,
+      "learning_rate": 2.8149376716320256e-05,
+      "loss": 0.0264,
+      "step": 1010
+    },
+    {
+      "epoch": 1.708542713567839,
+      "grad_norm": 0.18498659133911133,
+      "learning_rate": 2.8101353065994373e-05,
+      "loss": 0.0289,
+      "step": 1020
+    },
+    {
+      "epoch": 1.725293132328308,
+      "grad_norm": 0.16134566068649292,
+      "learning_rate": 2.8052756320042885e-05,
+      "loss": 0.0262,
+      "step": 1030
+    },
+    {
+      "epoch": 1.742043551088777,
+      "grad_norm": 0.18623295426368713,
+      "learning_rate": 2.8003588604244893e-05,
+      "loss": 0.0242,
+      "step": 1040
+    },
+    {
+      "epoch": 1.758793969849246,
+      "grad_norm": 0.1394229531288147,
+      "learning_rate": 2.7953852069355565e-05,
+      "loss": 0.0236,
+      "step": 1050
+    },
+    {
+      "epoch": 1.775544388609715,
+      "grad_norm": 0.15025576949119568,
+      "learning_rate": 2.790354889101206e-05,
+      "loss": 0.0222,
+      "step": 1060
+    },
+    {
+      "epoch": 1.792294807370184,
+      "grad_norm": 0.13321664929389954,
+      "learning_rate": 2.7852681269638366e-05,
+      "loss": 0.0259,
+      "step": 1070
+    },
+    {
+      "epoch": 1.809045226130653,
+      "grad_norm": 0.16647320985794067,
+      "learning_rate": 2.780125143034902e-05,
+      "loss": 0.0268,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8257956448911221,
+      "grad_norm": 0.21666789054870605,
+      "learning_rate": 2.7749261622851812e-05,
+      "loss": 0.0242,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8425460636515911,
+      "grad_norm": 0.18027998507022858,
+      "learning_rate": 2.7696714121349335e-05,
+      "loss": 0.0253,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8592964824120601,
+      "grad_norm": 0.17092131078243256,
+      "learning_rate": 2.764361122443954e-05,
+      "loss": 0.0236,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8760469011725294,
+      "grad_norm": 0.1665954291820526,
+      "learning_rate": 2.758995525501517e-05,
+      "loss": 0.0226,
+      "step": 1120
+    },
+    {
+      "epoch": 1.8927973199329984,
+      "grad_norm": 0.1582082360982895,
+      "learning_rate": 2.753574856016215e-05,
+      "loss": 0.0257,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9095477386934674,
+      "grad_norm": 0.18370600044727325,
+      "learning_rate": 2.7480993511056913e-05,
+      "loss": 0.0252,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9262981574539364,
+      "grad_norm": 0.14998869597911835,
+      "learning_rate": 2.7425692502862684e-05,
+      "loss": 0.022,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9430485762144054,
+      "grad_norm": 0.13657869398593903,
+      "learning_rate": 2.7369847954624728e-05,
+      "loss": 0.0248,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9597989949748744,
+      "grad_norm": 0.15892188251018524,
+      "learning_rate": 2.731346230916448e-05,
+      "loss": 0.026,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9765494137353434,
+      "grad_norm": 0.15034610033035278,
+      "learning_rate": 2.7256538032972746e-05,
+      "loss": 0.0232,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9932998324958124,
+      "grad_norm": 0.1602204591035843,
+      "learning_rate": 2.7199077616101773e-05,
+      "loss": 0.0231,
+      "step": 1190
+    },
+    {
+      "epoch": 2.0100502512562812,
+      "grad_norm": 0.12914741039276123,
+      "learning_rate": 2.714108357205634e-05,
+      "loss": 0.0239,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0268006700167502,
+      "grad_norm": 0.1998392939567566,
+      "learning_rate": 2.7082558437683803e-05,
+      "loss": 0.0224,
+      "step": 1210
+    },
+    {
+      "epoch": 2.0435510887772192,
+      "grad_norm": 0.18535244464874268,
+      "learning_rate": 2.702350477306315e-05,
+      "loss": 0.0233,
+      "step": 1220
+    },
+    {
+      "epoch": 2.0603015075376883,
+      "grad_norm": 0.14260677993297577,
+      "learning_rate": 2.6963925161392963e-05,
+      "loss": 0.0245,
+      "step": 1230
+    },
+    {
+      "epoch": 2.0770519262981573,
+      "grad_norm": 0.201503187417984,
+      "learning_rate": 2.6903822208878476e-05,
+      "loss": 0.0235,
+      "step": 1240
+    },
+    {
+      "epoch": 2.0938023450586263,
+      "grad_norm": 0.16170263290405273,
+      "learning_rate": 2.6843198544617535e-05,
+      "loss": 0.0242,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1105527638190953,
+      "grad_norm": 0.14339309930801392,
+      "learning_rate": 2.6782056820485612e-05,
+      "loss": 0.0229,
+      "step": 1260
+    },
+    {
+      "epoch": 2.1273031825795643,
+      "grad_norm": 0.23185782134532928,
+      "learning_rate": 2.672039971101979e-05,
+      "loss": 0.0229,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1440536013400333,
+      "grad_norm": 0.2018624097108841,
+      "learning_rate": 2.665822991330178e-05,
+      "loss": 0.0263,
+      "step": 1280
+    },
+    {
+      "epoch": 2.1608040201005023,
+      "grad_norm": 0.22470778226852417,
+      "learning_rate": 2.6595550146839934e-05,
+      "loss": 0.0244,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1775544388609713,
+      "grad_norm": 0.1919565051794052,
+      "learning_rate": 2.6532363153450287e-05,
+      "loss": 0.023,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1943048576214403,
+      "grad_norm": 0.16625232994556427,
+      "learning_rate": 2.6468671697136634e-05,
+      "loss": 0.022,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2110552763819094,
+      "grad_norm": 0.16590924561023712,
+      "learning_rate": 2.640447856396961e-05,
+      "loss": 0.0211,
+      "step": 1320
+    },
+    {
+      "epoch": 2.2278056951423784,
+      "grad_norm": 0.1491633653640747,
+      "learning_rate": 2.6339786561964805e-05,
+      "loss": 0.0265,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2445561139028474,
+      "grad_norm": 0.16424474120140076,
+      "learning_rate": 2.6274598520959966e-05,
+      "loss": 0.0235,
+      "step": 1340
+    },
+    {
+      "epoch": 2.2613065326633164,
+      "grad_norm": 0.18205176293849945,
+      "learning_rate": 2.6208917292491185e-05,
+      "loss": 0.0242,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2780569514237854,
+      "grad_norm": 0.1608763039112091,
+      "learning_rate": 2.6142745749668176e-05,
+      "loss": 0.0225,
+      "step": 1360
+    },
+    {
+      "epoch": 2.2948073701842544,
+      "grad_norm": 0.1522231101989746,
+      "learning_rate": 2.607608678704859e-05,
+      "loss": 0.0229,
+      "step": 1370
+    },
+    {
+      "epoch": 2.3115577889447234,
+      "grad_norm": 0.16214381158351898,
+      "learning_rate": 2.600894332051139e-05,
+      "loss": 0.0201,
+      "step": 1380
+    },
+    {
+      "epoch": 2.3283082077051924,
+      "grad_norm": 0.1418379843235016,
+      "learning_rate": 2.594131828712932e-05,
+      "loss": 0.0232,
+      "step": 1390
+    },
+    {
+      "epoch": 2.3450586264656614,
+      "grad_norm": 0.1545649766921997,
+      "learning_rate": 2.5873214645040414e-05,
+      "loss": 0.0224,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3618090452261304,
+      "grad_norm": 0.16949930787086487,
+      "learning_rate": 2.5804635373318604e-05,
+      "loss": 0.0209,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3785594639865995,
+      "grad_norm": 0.1950673907995224,
+      "learning_rate": 2.57355834718434e-05,
+      "loss": 0.0235,
+      "step": 1420
+    },
+    {
+      "epoch": 2.3953098827470685,
+      "grad_norm": 0.15320082008838654,
+      "learning_rate": 2.566606196116867e-05,
+      "loss": 0.0209,
+      "step": 1430
+    },
+    {
+      "epoch": 2.4120603015075375,
+      "grad_norm": 0.14742597937583923,
+      "learning_rate": 2.559607388239051e-05,
+      "loss": 0.0206,
+      "step": 1440
+    },
+    {
+      "epoch": 2.4288107202680065,
+      "grad_norm": 0.15421146154403687,
+      "learning_rate": 2.552562229701422e-05,
+      "loss": 0.0228,
+      "step": 1450
+    },
+    {
+      "epoch": 2.4455611390284755,
+      "grad_norm": 0.16883830726146698,
+      "learning_rate": 2.545471028682036e-05,
+      "loss": 0.0252,
+      "step": 1460
+    },
+    {
+      "epoch": 2.4623115577889445,
+      "grad_norm": 0.143342524766922,
+      "learning_rate": 2.538334095373e-05,
+      "loss": 0.0207,
+      "step": 1470
+    },
+    {
+      "epoch": 2.4790619765494135,
+      "grad_norm": 0.17817887663841248,
+      "learning_rate": 2.531151741966896e-05,
+      "loss": 0.0212,
+      "step": 1480
+    },
+    {
+      "epoch": 2.4958123953098825,
+      "grad_norm": 0.1521480828523636,
+      "learning_rate": 2.5239242826431302e-05,
+      "loss": 0.0208,
+      "step": 1490
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 0.14518405497074127,
+      "learning_rate": 2.5166520335541865e-05,
+      "loss": 0.0204,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5293132328308205,
+      "grad_norm": 0.11578862369060516,
+      "learning_rate": 2.5093353128117996e-05,
+      "loss": 0.0237,
+      "step": 1510
+    },
+    {
+      "epoch": 2.5460636515912896,
+      "grad_norm": 0.1930747777223587,
+      "learning_rate": 2.501974440473037e-05,
+      "loss": 0.0205,
+      "step": 1520
+    },
+    {
+      "epoch": 2.5628140703517586,
+      "grad_norm": 0.1401190161705017,
+      "learning_rate": 2.4945697385263015e-05,
+      "loss": 0.0217,
+      "step": 1530
+    },
+    {
+      "epoch": 2.5795644891122276,
+      "grad_norm": 0.1486596018075943,
+      "learning_rate": 2.487121530877243e-05,
+      "loss": 0.0242,
+      "step": 1540
+    },
+    {
+      "epoch": 2.5963149078726966,
+      "grad_norm": 0.16599705815315247,
+      "learning_rate": 2.4796301433345943e-05,
+      "loss": 0.0219,
+      "step": 1550
+    },
+    {
+      "epoch": 2.6130653266331656,
+      "grad_norm": 0.1955460160970688,
+      "learning_rate": 2.4720959035959148e-05,
+      "loss": 0.022,
+      "step": 1560
+    },
+    {
+      "epoch": 2.6298157453936346,
+      "grad_norm": 0.16018950939178467,
+      "learning_rate": 2.464519141233257e-05,
+      "loss": 0.0219,
+      "step": 1570
+    },
+    {
+      "epoch": 2.6465661641541036,
+      "grad_norm": 0.15230196714401245,
+      "learning_rate": 2.456900187678754e-05,
+      "loss": 0.0211,
+      "step": 1580
+    },
+    {
+      "epoch": 2.6633165829145726,
+      "grad_norm": 0.1539147049188614,
+      "learning_rate": 2.4492393762101147e-05,
+      "loss": 0.0224,
+      "step": 1590
+    },
+    {
+      "epoch": 2.6800670016750416,
+      "grad_norm": 0.2199530005455017,
+      "learning_rate": 2.4415370419360508e-05,
+      "loss": 0.0216,
+      "step": 1600
+    },
+    {
+      "epoch": 2.6968174204355106,
+      "grad_norm": 0.11828820407390594,
+      "learning_rate": 2.4337935217816157e-05,
+      "loss": 0.0191,
+      "step": 1610
+    },
+    {
+      "epoch": 2.7135678391959797,
+      "grad_norm": 0.11301644891500473,
+      "learning_rate": 2.4260091544734665e-05,
+      "loss": 0.0209,
+      "step": 1620
+    },
+    {
+      "epoch": 2.7303182579564487,
+      "grad_norm": 0.13908027112483978,
+      "learning_rate": 2.4181842805250466e-05,
+      "loss": 0.0219,
+      "step": 1630
+    },
+    {
+      "epoch": 2.7470686767169177,
+      "grad_norm": 0.14333346486091614,
+      "learning_rate": 2.4103192422216923e-05,
+      "loss": 0.0179,
+      "step": 1640
+    },
+    {
+      "epoch": 2.7638190954773867,
+      "grad_norm": 0.15043054521083832,
+      "learning_rate": 2.402414383605658e-05,
+      "loss": 0.0209,
+      "step": 1650
+    },
+    {
+      "epoch": 2.7805695142378557,
+      "grad_norm": 0.1858556866645813,
+      "learning_rate": 2.3944700504610674e-05,
+      "loss": 0.0185,
+      "step": 1660
+    },
+    {
+      "epoch": 2.7973199329983247,
+      "grad_norm": 0.13898970186710358,
+      "learning_rate": 2.3864865902987883e-05,
+      "loss": 0.0206,
+      "step": 1670
+    },
+    {
+      "epoch": 2.8140703517587937,
+      "grad_norm": 0.17943225800991058,
+      "learning_rate": 2.378464352341231e-05,
+      "loss": 0.0212,
+      "step": 1680
+    },
+    {
+      "epoch": 2.8308207705192627,
+      "grad_norm": 0.1789410412311554,
+      "learning_rate": 2.3704036875070728e-05,
+      "loss": 0.0234,
+      "step": 1690
+    },
+    {
+      "epoch": 2.8475711892797317,
+      "grad_norm": 0.16943080723285675,
+      "learning_rate": 2.362304948395906e-05,
+      "loss": 0.0238,
+      "step": 1700
+    },
+    {
+      "epoch": 2.8643216080402008,
+      "grad_norm": 0.182373046875,
+      "learning_rate": 2.3541684892728157e-05,
+      "loss": 0.022,
+      "step": 1710
+    },
+    {
+      "epoch": 2.8810720268006698,
+      "grad_norm": 0.1499493569135666,
+      "learning_rate": 2.345994666052883e-05,
+      "loss": 0.02,
+      "step": 1720
+    },
+    {
+      "epoch": 2.8978224455611388,
+      "grad_norm": 0.17924560606479645,
+      "learning_rate": 2.337783836285614e-05,
+      "loss": 0.0208,
+      "step": 1730
+    },
+    {
+      "epoch": 2.914572864321608,
+      "grad_norm": 0.17541290819644928,
+      "learning_rate": 2.3295363591393026e-05,
+      "loss": 0.0183,
+      "step": 1740
+    },
+    {
+      "epoch": 2.931323283082077,
+      "grad_norm": 0.14497047662734985,
+      "learning_rate": 2.3212525953853174e-05,
+      "loss": 0.0219,
+      "step": 1750
+    },
+    {
+      "epoch": 2.948073701842546,
+      "grad_norm": 0.1496923714876175,
+      "learning_rate": 2.3129329073823206e-05,
+      "loss": 0.0196,
+      "step": 1760
+    },
+    {
+      "epoch": 2.964824120603015,
+      "grad_norm": 0.18601380288600922,
+      "learning_rate": 2.3045776590604175e-05,
+      "loss": 0.0228,
+      "step": 1770
+    },
+    {
+      "epoch": 2.981574539363484,
+      "grad_norm": 0.16404607892036438,
+      "learning_rate": 2.296187215905237e-05,
+      "loss": 0.0201,
+      "step": 1780
+    },
+    {
+      "epoch": 2.998324958123953,
+      "grad_norm": 0.16068114340305328,
+      "learning_rate": 2.2877619449419437e-05,
+      "loss": 0.0222,
+      "step": 1790
+    },
+    {
+      "epoch": 3.0150753768844223,
+      "grad_norm": 0.22023139894008636,
+      "learning_rate": 2.2793022147191843e-05,
+      "loss": 0.0196,
+      "step": 1800
+    },
+    {
+      "epoch": 3.0318257956448913,
+      "grad_norm": 0.22863224148750305,
+      "learning_rate": 2.2708083952929634e-05,
+      "loss": 0.0175,
+      "step": 1810
+    },
+    {
+      "epoch": 3.0485762144053603,
+      "grad_norm": 0.1506689339876175,
+      "learning_rate": 2.2622808582104594e-05,
+      "loss": 0.0195,
+      "step": 1820
+    },
+    {
+      "epoch": 3.0653266331658293,
+      "grad_norm": 0.12392555922269821,
+      "learning_rate": 2.2537199764937703e-05,
+      "loss": 0.0203,
+      "step": 1830
+    },
+    {
+      "epoch": 3.0820770519262983,
+      "grad_norm": 0.13800229132175446,
+      "learning_rate": 2.245126124623595e-05,
+      "loss": 0.0209,
+      "step": 1840
+    },
+    {
+      "epoch": 3.0988274706867673,
+      "grad_norm": 0.12618660926818848,
+      "learning_rate": 2.2364996785228547e-05,
+      "loss": 0.0206,
+      "step": 1850
+    },
+    {
+      "epoch": 3.1155778894472363,
+      "grad_norm": 0.1612847000360489,
+      "learning_rate": 2.227841015540248e-05,
+      "loss": 0.0212,
+      "step": 1860
+    },
+    {
+      "epoch": 3.1323283082077054,
+      "grad_norm": 0.11662063002586365,
+      "learning_rate": 2.2191505144337433e-05,
+      "loss": 0.0208,
+      "step": 1870
+    },
+    {
+      "epoch": 3.1490787269681744,
+      "grad_norm": 0.14581643044948578,
+      "learning_rate": 2.210428555354013e-05,
+      "loss": 0.0202,
+      "step": 1880
+    },
+    {
+      "epoch": 3.1658291457286434,
+      "grad_norm": 0.16268415749073029,
+      "learning_rate": 2.201675519827802e-05,
+      "loss": 0.0205,
+      "step": 1890
+    },
+    {
+      "epoch": 3.1825795644891124,
+      "grad_norm": 0.1655290424823761,
+      "learning_rate": 2.1928917907412403e-05,
+      "loss": 0.0188,
+      "step": 1900
+    },
+    {
+      "epoch": 3.1993299832495814,
+      "grad_norm": 0.1120857372879982,
+      "learning_rate": 2.1840777523230937e-05,
+      "loss": 0.0202,
+      "step": 1910
+    },
+    {
+      "epoch": 3.2160804020100504,
+      "grad_norm": 0.12592901289463043,
+      "learning_rate": 2.1752337901279552e-05,
+      "loss": 0.0192,
+      "step": 1920
+    },
+    {
+      "epoch": 3.2328308207705194,
+      "grad_norm": 0.22475941479206085,
+      "learning_rate": 2.166360291019383e-05,
+      "loss": 0.0198,
+      "step": 1930
+    },
+    {
+      "epoch": 3.2495812395309884,
+      "grad_norm": 0.11940304934978485,
+      "learning_rate": 2.157457643152973e-05,
+      "loss": 0.019,
+      "step": 1940
+    },
+    {
+      "epoch": 3.2663316582914574,
+      "grad_norm": 0.14816822111606598,
+      "learning_rate": 2.148526235959385e-05,
+      "loss": 0.0186,
+      "step": 1950
+    },
+    {
+      "epoch": 3.2830820770519265,
+      "grad_norm": 0.1205066591501236,
+      "learning_rate": 2.1395664601273016e-05,
+      "loss": 0.02,
+      "step": 1960
+    },
+    {
+      "epoch": 3.2998324958123955,
+      "grad_norm": 0.13585013151168823,
+      "learning_rate": 2.130578707586345e-05,
+      "loss": 0.0194,
+      "step": 1970
+    },
+    {
+      "epoch": 3.3165829145728645,
+      "grad_norm": 0.13307107985019684,
+      "learning_rate": 2.1215633714899264e-05,
+      "loss": 0.0205,
+      "step": 1980
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.1215062215924263,
+      "learning_rate": 2.112520846198053e-05,
+      "loss": 0.0202,
+      "step": 1990
+    },
+    {
+      "epoch": 3.3500837520938025,
+      "grad_norm": 0.14667080342769623,
+      "learning_rate": 2.103451527260074e-05,
+      "loss": 0.0205,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3668341708542715,
+      "grad_norm": 0.19008496403694153,
+      "learning_rate": 2.094355811397381e-05,
+      "loss": 0.0196,
+      "step": 2010
+    },
+    {
+      "epoch": 3.3835845896147405,
+      "grad_norm": 0.1476626843214035,
+      "learning_rate": 2.0852340964860522e-05,
+      "loss": 0.0227,
+      "step": 2020
+    },
+    {
+      "epoch": 3.4003350083752095,
+      "grad_norm": 0.17680875957012177,
+      "learning_rate": 2.076086781539447e-05,
+      "loss": 0.0193,
+      "step": 2030
+    },
+    {
+      "epoch": 3.4170854271356785,
+      "grad_norm": 0.1655515730381012,
+      "learning_rate": 2.066914266690755e-05,
+      "loss": 0.0191,
+      "step": 2040
+    },
+    {
+      "epoch": 3.4338358458961475,
+      "grad_norm": 0.18550711870193481,
+      "learning_rate": 2.0577169531754906e-05,
+      "loss": 0.0198,
+      "step": 2050
+    },
+    {
+      "epoch": 3.4505862646566166,
+      "grad_norm": 0.11140353232622147,
+      "learning_rate": 2.048495243313942e-05,
+      "loss": 0.0186,
+      "step": 2060
+    },
+    {
+      "epoch": 3.4673366834170856,
+      "grad_norm": 0.15830710530281067,
+      "learning_rate": 2.039249540493572e-05,
+      "loss": 0.0208,
+      "step": 2070
+    },
+    {
+      "epoch": 3.4840871021775546,
+      "grad_norm": 0.15438948571681976,
+      "learning_rate": 2.0299802491513755e-05,
+      "loss": 0.017,
+      "step": 2080
+    },
+    {
+      "epoch": 3.5008375209380236,
+      "grad_norm": 0.17817939817905426,
+      "learning_rate": 2.0206877747561828e-05,
+      "loss": 0.0203,
+      "step": 2090
+    },
+    {
+      "epoch": 3.5175879396984926,
+      "grad_norm": 0.1366434544324875,
+      "learning_rate": 2.011372523790927e-05,
+      "loss": 0.0212,
+      "step": 2100
+    },
+    {
+      "epoch": 3.5343383584589616,
+      "grad_norm": 0.13273486495018005,
+      "learning_rate": 2.0020349037348643e-05,
+      "loss": 0.016,
+      "step": 2110
+    },
+    {
+      "epoch": 3.5510887772194306,
+      "grad_norm": 0.15586011111736298,
+      "learning_rate": 1.9926753230457443e-05,
+      "loss": 0.0192,
+      "step": 2120
+    },
+    {
+      "epoch": 3.5678391959798996,
+      "grad_norm": 0.10179942101240158,
+      "learning_rate": 1.983294191141948e-05,
+      "loss": 0.0194,
+      "step": 2130
+    },
+    {
+      "epoch": 3.5845896147403686,
+      "grad_norm": 0.18417240679264069,
+      "learning_rate": 1.973891918384575e-05,
+      "loss": 0.0186,
+      "step": 2140
+    },
+    {
+      "epoch": 3.6013400335008376,
+      "grad_norm": 0.14377598464488983,
+      "learning_rate": 1.9644689160594945e-05,
+      "loss": 0.0181,
+      "step": 2150
+    },
+    {
+      "epoch": 3.6180904522613067,
+      "grad_norm": 0.18220196664333344,
+      "learning_rate": 1.9550255963593553e-05,
+      "loss": 0.018,
+      "step": 2160
+    },
+    {
+      "epoch": 3.6348408710217757,
+      "grad_norm": 0.22227473556995392,
+      "learning_rate": 1.9455623723655524e-05,
+      "loss": 0.018,
+      "step": 2170
+    },
+    {
+      "epoch": 3.6515912897822447,
+      "grad_norm": 0.10854306817054749,
+      "learning_rate": 1.9360796580301606e-05,
+      "loss": 0.0171,
+      "step": 2180
+    },
+    {
+      "epoch": 3.6683417085427137,
+      "grad_norm": 0.15350358188152313,
+      "learning_rate": 1.9265778681578245e-05,
+      "loss": 0.0187,
+      "step": 2190
+    },
+    {
+      "epoch": 3.6850921273031827,
+      "grad_norm": 0.1715448796749115,
+      "learning_rate": 1.9170574183876143e-05,
+      "loss": 0.0211,
+      "step": 2200
+    },
+    {
+      "epoch": 3.7018425460636517,
+      "grad_norm": 0.15281938016414642,
+      "learning_rate": 1.9075187251748452e-05,
+      "loss": 0.0205,
+      "step": 2210
+    },
+    {
+      "epoch": 3.7185929648241207,
+      "grad_norm": 0.1549525409936905,
+      "learning_rate": 1.8979622057728596e-05,
+      "loss": 0.0193,
+      "step": 2220
+    },
+    {
+      "epoch": 3.7353433835845897,
+      "grad_norm": 0.1523311883211136,
+      "learning_rate": 1.8883882782147748e-05,
+      "loss": 0.0184,
+      "step": 2230
+    },
+    {
+      "epoch": 3.7520938023450587,
+      "grad_norm": 0.18689101934432983,
+      "learning_rate": 1.8787973612951967e-05,
+      "loss": 0.0183,
+      "step": 2240
+    },
+    {
+      "epoch": 3.7688442211055277,
+      "grad_norm": 0.16317549347877502,
+      "learning_rate": 1.8691898745519028e-05,
+      "loss": 0.0189,
+      "step": 2250
+    },
+    {
+      "epoch": 3.7855946398659968,
+      "grad_norm": 0.12337777763605118,
+      "learning_rate": 1.8595662382474863e-05,
+      "loss": 0.0197,
+      "step": 2260
+    },
+    {
+      "epoch": 3.8023450586264658,
+      "grad_norm": 0.1409161388874054,
+      "learning_rate": 1.8499268733509766e-05,
+      "loss": 0.0181,
+      "step": 2270
+    },
+    {
+      "epoch": 3.819095477386935,
+      "grad_norm": 0.15133973956108093,
+      "learning_rate": 1.84027220151942e-05,
+      "loss": 0.0158,
+      "step": 2280
+    },
+    {
+      "epoch": 3.835845896147404,
+      "grad_norm": 0.13350911438465118,
+      "learning_rate": 1.83060264507944e-05,
+      "loss": 0.0184,
+      "step": 2290
+    },
+    {
+      "epoch": 3.852596314907873,
+      "grad_norm": 0.1512780487537384,
+      "learning_rate": 1.82091862700876e-05,
+      "loss": 0.0174,
+      "step": 2300
+    },
+    {
+      "epoch": 3.869346733668342,
+      "grad_norm": 0.14480029046535492,
+      "learning_rate": 1.8112205709177023e-05,
+      "loss": 0.0209,
+      "step": 2310
+    },
+    {
+      "epoch": 3.886097152428811,
+      "grad_norm": 0.11316472291946411,
+      "learning_rate": 1.8015089010306585e-05,
+      "loss": 0.0177,
+      "step": 2320
+    },
+    {
+      "epoch": 3.90284757118928,
+      "grad_norm": 0.18374566733837128,
+      "learning_rate": 1.7917840421675298e-05,
+      "loss": 0.0211,
+      "step": 2330
+    },
+    {
+      "epoch": 3.919597989949749,
+      "grad_norm": 0.14135697484016418,
+      "learning_rate": 1.7820464197251474e-05,
+      "loss": 0.0187,
+      "step": 2340
+    },
+    {
+      "epoch": 3.936348408710218,
+      "grad_norm": 0.13300488889217377,
+      "learning_rate": 1.7722964596586627e-05,
+      "loss": 0.0188,
+      "step": 2350
+    },
+    {
+      "epoch": 3.953098827470687,
+      "grad_norm": 0.17664390802383423,
+      "learning_rate": 1.7625345884629144e-05,
+      "loss": 0.0189,
+      "step": 2360
+    },
+    {
+      "epoch": 3.969849246231156,
+      "grad_norm": 0.11432985216379166,
+      "learning_rate": 1.7527612331537722e-05,
+      "loss": 0.0168,
+      "step": 2370
+    },
+    {
+      "epoch": 3.986599664991625,
+      "grad_norm": 0.16970939934253693,
+      "learning_rate": 1.7429768212494593e-05,
+      "loss": 0.0194,
+      "step": 2380
+    },
+    {
+      "epoch": 4.0033500837520934,
+      "grad_norm": 0.21405430138111115,
+      "learning_rate": 1.7331817807518497e-05,
+      "loss": 0.021,
+      "step": 2390
+    },
+    {
+      "epoch": 4.0201005025125625,
+      "grad_norm": 0.14571137726306915,
+      "learning_rate": 1.723376540127745e-05,
+      "loss": 0.0189,
+      "step": 2400
+    },
+    {
+      "epoch": 4.0368509212730315,
+      "grad_norm": 0.14875146746635437,
+      "learning_rate": 1.7135615282901357e-05,
+      "loss": 0.0166,
+      "step": 2410
+    },
+    {
+      "epoch": 4.0536013400335005,
+      "grad_norm": 0.1627630889415741,
+      "learning_rate": 1.7037371745794358e-05,
+      "loss": 0.0206,
+      "step": 2420
+    },
+    {
+      "epoch": 4.0703517587939695,
+      "grad_norm": 0.1687653660774231,
+      "learning_rate": 1.6939039087447026e-05,
+      "loss": 0.0188,
+      "step": 2430
+    },
+    {
+      "epoch": 4.0871021775544385,
+      "grad_norm": 0.13051913678646088,
+      "learning_rate": 1.6840621609248397e-05,
+      "loss": 0.0172,
+      "step": 2440
+    },
+    {
+      "epoch": 4.1038525963149075,
+      "grad_norm": 0.1474522203207016,
+      "learning_rate": 1.6742123616297794e-05,
+      "loss": 0.0181,
+      "step": 2450
+    },
+    {
+      "epoch": 4.1206030150753765,
+      "grad_norm": 0.11590561270713806,
+      "learning_rate": 1.664354941721651e-05,
+      "loss": 0.0161,
+      "step": 2460
+    },
+    {
+      "epoch": 4.1373534338358455,
+      "grad_norm": 0.12784413993358612,
+      "learning_rate": 1.6544903323959355e-05,
+      "loss": 0.0167,
+      "step": 2470
+    },
+    {
+      "epoch": 4.1541038525963145,
+      "grad_norm": 0.14732132852077484,
+      "learning_rate": 1.6446189651626023e-05,
+      "loss": 0.0186,
+      "step": 2480
+    },
+    {
+      "epoch": 4.1708542713567835,
+      "grad_norm": 0.15262089669704437,
+      "learning_rate": 1.6347412718272316e-05,
+      "loss": 0.0189,
+      "step": 2490
+    },
+    {
+      "epoch": 4.187604690117253,
+      "grad_norm": 0.12261030077934265,
+      "learning_rate": 1.624857684472131e-05,
+      "loss": 0.0166,
+      "step": 2500
+    },
+    {
+      "epoch": 4.204355108877722,
+      "grad_norm": 0.16570910811424255,
+      "learning_rate": 1.6149686354374283e-05,
+      "loss": 0.0175,
+      "step": 2510
+    },
+    {
+      "epoch": 4.221105527638191,
+      "grad_norm": 0.13071776926517487,
+      "learning_rate": 1.605074557302165e-05,
+      "loss": 0.017,
+      "step": 2520
+    },
+    {
+      "epoch": 4.23785594639866,
+      "grad_norm": 0.13835109770298004,
+      "learning_rate": 1.59517588286537e-05,
+      "loss": 0.0181,
+      "step": 2530
+    },
+    {
+      "epoch": 4.254606365159129,
+      "grad_norm": 0.13597555458545685,
+      "learning_rate": 1.5852730451271324e-05,
+      "loss": 0.0174,
+      "step": 2540
+    },
+    {
+      "epoch": 4.271356783919598,
+      "grad_norm": 0.11292872577905655,
+      "learning_rate": 1.5753664772696546e-05,
+      "loss": 0.0184,
+      "step": 2550
+    },
+    {
+      "epoch": 4.288107202680067,
+      "grad_norm": 0.18765822052955627,
+      "learning_rate": 1.565456612638307e-05,
+      "loss": 0.0192,
+      "step": 2560
+    },
+    {
+      "epoch": 4.304857621440536,
+      "grad_norm": 0.1113753542304039,
+      "learning_rate": 1.5555438847226732e-05,
+      "loss": 0.0155,
+      "step": 2570
+    },
+    {
+      "epoch": 4.321608040201005,
+      "grad_norm": 0.15917973220348358,
+      "learning_rate": 1.545628727137584e-05,
+      "loss": 0.0178,
+      "step": 2580
+    },
+    {
+      "epoch": 4.338358458961474,
+      "grad_norm": 0.1233622133731842,
+      "learning_rate": 1.535711573604153e-05,
+      "loss": 0.015,
+      "step": 2590
+    },
+    {
+      "epoch": 4.355108877721943,
+      "grad_norm": 0.12452328950166702,
+      "learning_rate": 1.5257928579308032e-05,
+      "loss": 0.0187,
+      "step": 2600
+    },
+    {
+      "epoch": 4.371859296482412,
+      "grad_norm": 0.13558247685432434,
+      "learning_rate": 1.5158730139942902e-05,
+      "loss": 0.0174,
+      "step": 2610
+    },
+    {
+      "epoch": 4.388609715242881,
+      "grad_norm": 0.15536141395568848,
+      "learning_rate": 1.5059524757207239e-05,
+      "loss": 0.0165,
+      "step": 2620
+    },
+    {
+      "epoch": 4.40536013400335,
+      "grad_norm": 0.1601993888616562,
+      "learning_rate": 1.4960316770665866e-05,
+      "loss": 0.0164,
+      "step": 2630
+    },
+    {
+      "epoch": 4.422110552763819,
+      "grad_norm": 0.13969165086746216,
+      "learning_rate": 1.4861110519997495e-05,
+      "loss": 0.0188,
+      "step": 2640
+    },
+    {
+      "epoch": 4.438860971524288,
+      "grad_norm": 0.11961787194013596,
+      "learning_rate": 1.4761910344804913e-05,
+      "loss": 0.016,
+      "step": 2650
+    },
+    {
+      "epoch": 4.455611390284757,
+      "grad_norm": 0.12037152051925659,
+      "learning_rate": 1.466272058442516e-05,
+      "loss": 0.0179,
+      "step": 2660
+    },
+    {
+      "epoch": 4.472361809045226,
+      "grad_norm": 0.15370553731918335,
+      "learning_rate": 1.4563545577739676e-05,
+      "loss": 0.0166,
+      "step": 2670
+    },
+    {
+      "epoch": 4.489112227805695,
+      "grad_norm": 0.11886673420667648,
+      "learning_rate": 1.4464389662984543e-05,
+      "loss": 0.0182,
+      "step": 2680
+    },
+    {
+      "epoch": 4.505862646566165,
+      "grad_norm": 0.13794168829917908,
+      "learning_rate": 1.4365257177560684e-05,
+      "loss": 0.0187,
+      "step": 2690
+    },
+    {
+      "epoch": 4.522613065326633,
+      "grad_norm": 0.16981415450572968,
+      "learning_rate": 1.426615245784416e-05,
+      "loss": 0.0161,
+      "step": 2700
+    },
+    {
+      "epoch": 4.539363484087103,
+      "grad_norm": 0.14231683313846588,
+      "learning_rate": 1.4167079838996468e-05,
+      "loss": 0.0164,
+      "step": 2710
+    },
+    {
+      "epoch": 4.556113902847571,
+      "grad_norm": 0.12874573469161987,
+      "learning_rate": 1.4068043654774897e-05,
+      "loss": 0.0165,
+      "step": 2720
+    },
+    {
+      "epoch": 4.572864321608041,
+      "grad_norm": 0.1743222177028656,
+      "learning_rate": 1.3969048237342992e-05,
+      "loss": 0.0179,
+      "step": 2730
+    },
+    {
+      "epoch": 4.589614740368509,
+      "grad_norm": 0.26698336005210876,
+      "learning_rate": 1.3870097917081011e-05,
+      "loss": 0.0169,
+      "step": 2740
+    },
+    {
+      "epoch": 4.606365159128979,
+      "grad_norm": 0.12284237146377563,
+      "learning_rate": 1.3771197022396508e-05,
+      "loss": 0.0146,
+      "step": 2750
+    },
+    {
+      "epoch": 4.623115577889447,
+      "grad_norm": 0.11153502017259598,
+      "learning_rate": 1.3672349879535015e-05,
+      "loss": 0.0153,
+      "step": 2760
+    },
+    {
+      "epoch": 4.639865996649917,
+      "grad_norm": 0.13498924672603607,
+      "learning_rate": 1.3573560812390781e-05,
+      "loss": 0.0185,
+      "step": 2770
+    },
+    {
+      "epoch": 4.656616415410385,
+      "grad_norm": 0.13696305453777313,
+      "learning_rate": 1.3474834142317635e-05,
+      "loss": 0.0149,
+      "step": 2780
+    },
+    {
+      "epoch": 4.673366834170855,
+      "grad_norm": 0.13542267680168152,
+      "learning_rate": 1.3376174187939955e-05,
+      "loss": 0.0147,
+      "step": 2790
+    },
+    {
+      "epoch": 4.690117252931323,
+      "grad_norm": 0.14426903426647186,
+      "learning_rate": 1.3277585264963761e-05,
+      "loss": 0.0176,
+      "step": 2800
+    },
+    {
+      "epoch": 4.706867671691793,
+      "grad_norm": 0.12668757140636444,
+      "learning_rate": 1.3179071685987928e-05,
+      "loss": 0.0179,
+      "step": 2810
+    },
+    {
+      "epoch": 4.723618090452261,
+      "grad_norm": 0.14874869585037231,
+      "learning_rate": 1.308063776031554e-05,
+      "loss": 0.0161,
+      "step": 2820
+    },
+    {
+      "epoch": 4.740368509212731,
+      "grad_norm": 0.1480618417263031,
+      "learning_rate": 1.2982287793765389e-05,
+      "loss": 0.0151,
+      "step": 2830
+    },
+    {
+      "epoch": 4.757118927973199,
+      "grad_norm": 0.1443120837211609,
+      "learning_rate": 1.2884026088483616e-05,
+      "loss": 0.0165,
+      "step": 2840
+    },
+    {
+      "epoch": 4.773869346733669,
+      "grad_norm": 0.16240982711315155,
+      "learning_rate": 1.2785856942755543e-05,
+      "loss": 0.0166,
+      "step": 2850
+    },
+    {
+      "epoch": 4.790619765494137,
+      "grad_norm": 0.1501774787902832,
+      "learning_rate": 1.2687784650817616e-05,
+      "loss": 0.0178,
+      "step": 2860
+    },
+    {
+      "epoch": 4.807370184254607,
+      "grad_norm": 0.12356068193912506,
+      "learning_rate": 1.2589813502669603e-05,
+      "loss": 0.019,
+      "step": 2870
+    },
+    {
+      "epoch": 4.824120603015075,
+      "grad_norm": 0.1650429666042328,
+      "learning_rate": 1.2491947783886907e-05,
+      "loss": 0.0172,
+      "step": 2880
+    },
+    {
+      "epoch": 4.840871021775545,
+      "grad_norm": 0.10088960081338882,
+      "learning_rate": 1.2394191775433106e-05,
+      "loss": 0.0159,
+      "step": 2890
+    },
+    {
+      "epoch": 4.857621440536013,
+      "grad_norm": 0.14617778360843658,
+      "learning_rate": 1.2296549753472696e-05,
+      "loss": 0.0169,
+      "step": 2900
+    },
+    {
+      "epoch": 4.874371859296483,
+      "grad_norm": 0.14807341992855072,
+      "learning_rate": 1.2199025989184032e-05,
+      "loss": 0.0155,
+      "step": 2910
+    },
+    {
+      "epoch": 4.891122278056951,
+      "grad_norm": 0.32588717341423035,
+      "learning_rate": 1.21016247485725e-05,
+      "loss": 0.0206,
+      "step": 2920
+    },
+    {
+      "epoch": 4.907872696817421,
+      "grad_norm": 0.12184573709964752,
+      "learning_rate": 1.2004350292283897e-05,
+      "loss": 0.0168,
+      "step": 2930
+    },
+    {
+      "epoch": 4.924623115577889,
+      "grad_norm": 0.20224563777446747,
+      "learning_rate": 1.1907206875418068e-05,
+      "loss": 0.0167,
+      "step": 2940
+    },
+    {
+      "epoch": 4.941373534338359,
+      "grad_norm": 0.1300506293773651,
+      "learning_rate": 1.1810198747342769e-05,
+      "loss": 0.0181,
+      "step": 2950
+    },
+    {
+      "epoch": 4.958123953098827,
+      "grad_norm": 0.15161874890327454,
+      "learning_rate": 1.1713330151507786e-05,
+      "loss": 0.0157,
+      "step": 2960
+    },
+    {
+      "epoch": 4.974874371859297,
+      "grad_norm": 0.14213404059410095,
+      "learning_rate": 1.161660532525931e-05,
+      "loss": 0.0167,
+      "step": 2970
+    },
+    {
+      "epoch": 4.991624790619765,
+      "grad_norm": 0.17077548801898956,
+      "learning_rate": 1.1520028499654584e-05,
+      "loss": 0.0162,
+      "step": 2980
+    },
+    {
+      "epoch": 5.008375209380235,
+      "grad_norm": 0.13322734832763672,
+      "learning_rate": 1.1423603899276833e-05,
+      "loss": 0.0144,
+      "step": 2990
+    },
+    {
+      "epoch": 5.025125628140704,
+      "grad_norm": 0.17589686810970306,
+      "learning_rate": 1.1327335742050442e-05,
+      "loss": 0.0163,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 5001,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/experiment_cfg/metadata.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/experiment_cfg/metadata.json
new file mode 100644
index 0000000000000000000000000000000000000000..27700cac5d292d4d42897b3c2e80bdc58e55c60e
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed1/default/train_5shot_seed1_fullactionhead_5k/experiment_cfg/metadata.json
@@ -0,0 +1,431 @@
+{
+    "new_embodiment": {
+        "statistics": {
+            "state": {
+                "base_position": {
+                    "max": [
+                        7.778976917266846,
+                        0.33403685688972473,
+                        0.7223060727119446
+                    ],
+                    "min": [
+                        -4.821934223175049,
+                        -6.785110950469971,
+                        0.6994727253913879
+                    ],
+                    "mean": [
+                        2.5719731235192254,
+                        -2.1489371002267235,
+                        0.7003612741268546
+                    ],
+                    "std": [
+                        1.669945884010784,
+                        1.3739411381361726,
+                        0.0009413282367754987
+                    ],
+                    "q01": [
+                        -0.7944286339399775,
+                        -5.486611518471242,
+                        0.699977555971739
+                    ],
+                    "q99": [
+                        6.019886905263648,
+                        -0.5229184210026855,
+                        0.702930326282967
+                    ]
+                },
+                "base_rotation": {
+                    "max": [
+                        0.0,
+                        0.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        0.0,
+                        0.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.0,
+                        0.0,
+                        0.248543484335273,
+                        0.5959317405459531
+                    ],
+                    "std": [
+                        0.0,
+                        0.0,
+                        0.6655550240074092,
+                        0.374283995143559
+                    ],
+                    "q01": [
+                        0.0,
+                        0.0,
+                        -1.0000000000000002,
+                        4.503254968910557e-06
+                    ],
+                    "q99": [
+                        0.0,
+                        0.0,
+                        1.0000000000000002,
+                        1.0000000000000002
+                    ]
+                },
+                "end_effector_position_relative": {
+                    "max": [
+                        0.8848381638526917,
+                        0.8569459915161133,
+                        1.053884744644165
+                    ],
+                    "min": [
+                        -0.5828549861907959,
+                        -0.8486236333847046,
+                        -0.3446122705936432
+                    ],
+                    "mean": [
+                        0.2465490874130862,
+                        -0.004711658908481467,
+                        0.43463835464312073
+                    ],
+                    "std": [
+                        0.15798784670671595,
+                        0.25624102400497073,
+                        0.20836028727974915
+                    ],
+                    "q01": [
+                        -0.020752051134640608,
+                        -0.4837933887347875,
+                        0.1802942952289915
+                    ],
+                    "q99": [
+                        0.5386784714844007,
+                        0.4801424212024721,
+                        0.695095732975766
+                    ]
+                },
+                "end_effector_rotation_relative": {
+                    "max": [
+                        0.9999949932098389,
+                        0.9997354745864868,
+                        0.9900747537612915,
+                        0.9735639095306396
+                    ],
+                    "min": [
+                        -0.9999914169311523,
+                        -0.9999884366989136,
+                        -0.9975369572639465,
+                        6.754255821306288e-08
+                    ],
+                    "mean": [
+                        -0.22531859714056926,
+                        0.046973702821026614,
+                        -0.0568176967878771,
+                        0.12364307042955697
+                    ],
+                    "std": [
+                        0.8502144333612052,
+                        0.29591250318147405,
+                        0.30218053156837016,
+                        0.1636031353412931
+                    ],
+                    "q01": [
+                        -0.9959057387172566,
+                        -0.5665384745573048,
+                        -0.5329334620834977,
+                        0.0014372279999397553
+                    ],
+                    "q99": [
+                        0.9904107951565839,
+                        0.6359623612021396,
+                        0.5026076022439377,
+                        0.42955559234879914
+                    ]
+                },
+                "gripper_qpos": {
+                    "max": [
+                        0.05289580300450325,
+                        0.00937709677964449
+                    ],
+                    "min": [
+                        -0.011669117026031017,
+                        -0.06307756155729294
+                    ],
+                    "mean": [
+                        0.03188757060429838,
+                        -0.0321793333086053
+                    ],
+                    "std": [
+                        0.01171052313737148,
+                        0.011427336801203189
+                    ],
+                    "q01": [
+                        0.006462901319459925,
+                        -0.040557140599419166
+                    ],
+                    "q99": [
+                        0.04037619335388386,
+                        -0.006523947835993347
+                    ]
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0,
+                        0.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0,
+                        0.0
+                    ],
+                    "mean": [
+                        0.006639007355857881,
+                        0.0027330421795561874,
+                        -0.0017774441970214892,
+                        0.0
+                    ],
+                    "std": [
+                        0.11841528114040736,
+                        0.1041359083946544,
+                        0.08346265521208351,
+                        0.0
+                    ],
+                    "q01": [
+                        -0.17562359675270237,
+                        -0.21706402321529558,
+                        -0.16273392585723104,
+                        0.0
+                    ],
+                    "q99": [
+                        0.2572918701644887,
+                        0.27022325575787115,
+                        0.1369626751049278,
+                        0.0
+                    ]
+                },
+                "control_mode": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.9205539608927732
+                    ],
+                    "std": [
+                        0.39063657242534666
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        -0.17711863866562935
+                    ]
+                },
+                "end_effector_position": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.00924803964621179,
+                        0.004053841761390575,
+                        -0.08385115578460103
+                    ],
+                    "std": [
+                        0.45413072518223824,
+                        0.40158612714634856,
+                        0.41068634292849304
+                    ],
+                    "q01": [
+                        -0.9669817145875343,
+                        -0.9241307799783718,
+                        -0.8264079503068825
+                    ],
+                    "q99": [
+                        0.8021511975722166,
+                        0.9241346582748478,
+                        0.8348116781502298
+                    ]
+                },
+                "end_effector_rotation": {
+                    "max": [
+                        1.0,
+                        1.0,
+                        1.0
+                    ],
+                    "min": [
+                        -1.0,
+                        -1.0,
+                        -1.0
+                    ],
+                    "mean": [
+                        0.007644157504353809,
+                        -0.019962543093886335,
+                        -0.002047110452602617
+                    ],
+                    "std": [
+                        0.11076012154791087,
+                        0.13176735140285795,
+                        0.12286528665895614
+                    ],
+                    "q01": [
+                        -0.2659105439401192,
+                        -0.3961694033813533,
+                        -0.3434870832468936
+                    ],
+                    "q99": [
+                        0.3145786959266369,
+                        0.31309430361227547,
+                        0.34107754401942986
+                    ]
+                },
+                "gripper_close": {
+                    "max": [
+                        1.0
+                    ],
+                    "min": [
+                        -1.0
+                    ],
+                    "mean": [
+                        -0.29870612267533575
+                    ],
+                    "std": [
+                        0.9543487555375691
+                    ],
+                    "q01": [
+                        -1.0
+                    ],
+                    "q99": [
+                        0.7610674802484976
+                    ]
+                }
+            }
+        },
+        "modalities": {
+            "video": {
+                "robot0_eye_in_hand": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_left": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                },
+                "robot0_agentview_right": {
+                    "resolution": [
+                        256,
+                        256
+                    ],
+                    "channels": 3,
+                    "fps": 20.0
+                }
+            },
+            "state": {
+                "base_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "base_rotation": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position_relative": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation_relative": {
+                    "absolute": true,
+                    "rotation_type": "quaternion",
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "gripper_qpos": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        2
+                    ],
+                    "continuous": true
+                }
+            },
+            "action": {
+                "base_motion": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        4
+                    ],
+                    "continuous": true
+                },
+                "control_mode": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                },
+                "end_effector_position": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "end_effector_rotation": {
+                    "absolute": true,
+                    "rotation_type": "axis_angle",
+                    "shape": [
+                        3
+                    ],
+                    "continuous": true
+                },
+                "gripper_close": {
+                    "absolute": true,
+                    "rotation_type": null,
+                    "shape": [
+                        1
+                    ],
+                    "continuous": true
+                }
+            }
+        },
+        "embodiment_tag": "new_embodiment"
+    }
+}
\ No newline at end of file
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/config.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..47d7b77e4255263f3803a4b6f94ca6831e459b70
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/config.json
@@ -0,0 +1,64 @@
+{
+  "action_dim": 32,
+  "action_head_cfg": {
+    "action_dim": 32,
+    "action_horizon": 16,
+    "add_pos_embed": true,
+    "backbone_embedding_dim": 2048,
+    "diffusion_model_cfg": {
+      "attention_head_dim": 48,
+      "cross_attention_dim": 2048,
+      "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
+    },
+    "hidden_size": 1024,
+    "input_embedding_dim": 1536,
+    "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": 4,
+    "num_target_vision_tokens": 32,
+    "num_timestep_buckets": 1000,
+    "tune_diffusion_model": true,
+    "tune_projector": true,
+    "use_vlln": true,
+    "vl_self_attention_cfg": {
+      "attention_head_dim": 64,
+      "dropout": 0.2,
+      "final_dropout": true,
+      "num_attention_heads": 32,
+      "num_layers": 4,
+      "positional_embeddings": null
+    }
+  },
+  "action_horizon": 16,
+  "architectures": [
+    "GR00T_N1_5"
+  ],
+  "attn_implementation": null,
+  "backbone_cfg": {
+    "eagle_path": "NVEagle/eagle_er-qwen3_1_7B-Siglip2_400M_stage1_5_128gpu_er_v7_1mlp_nops",
+    "load_bf16": false,
+    "project_to_dim": null,
+    "reproject_vision": false,
+    "select_layer": 12,
+    "tune_llm": false,
+    "tune_visual": true,
+    "use_flash_attention": true
+  },
+  "compute_dtype": "bfloat16",
+  "hidden_size": 2048,
+  "model_dtype": "float32",
+  "model_type": "gr00t_n1_5",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3"
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b834db9bc88251b04230218b1d9c2ce4079b7699
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6609af3d3bd3bf14cadbe66a91687968c154549621c5df35b9966992f230416a
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..43937b9dd79ce741b4d88eccb00e0bee61808def
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69171ad5963fab0bd3f27b20e600d60bafda65d5522e7dbf5c4619528f62628e
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model.safetensors.index.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..5ef5f247b61eb93e89601c7da8334fc087e19750
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/model.safetensors.index.json
@@ -0,0 +1,906 @@
+{
+  "metadata": {
+    "total_size": 7585939328
+  },
+  "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.future_tokens.weight": "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-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00001-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-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00001-of-00002.safetensors",
+    "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00001-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",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.0.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.1.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.2.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm3.bias": "model-00002-of-00002.safetensors",
+    "action_head.vl_self_attention.transformer_blocks.3.norm3.weight": "model-00002-of-00002.safetensors",
+    "action_head.vlln.bias": "model-00002-of-00002.safetensors",
+    "action_head.vlln.weight": "model-00002-of-00002.safetensors",
+    "backbone.eagle_model.language_model.lm_head.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.language_model.model.norm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.mlp1.0.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.mlp1.0.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.in_proj_weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.layernorm.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc1.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.mlp.fc2.weight": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.head.probe": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
+    "backbone.eagle_model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a51ac33d9d811ec399ae16cfc6fc02c91f20fc0e
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e5ea787a79065bd33196ddfc4a157aadd4974fe449cec2f580e807e4a9a2600
+size 8550719959
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a6309a815f0af96226d8a23de429f2deb60fd680
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b5547f9bceb2f4c2f2444aef8721d4c47e59d74bc07eb896351aab894daa96
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cddb85352b4d053450624108786800cbad81d6cb
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19ead5779e3f8f2f666b7793de3a03d118f57f1b16a97eeb87bd732d18b445
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3dc131ad0b2f6f09a4096306884ede3ade3e7050
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47267e3f9c5a3cc4eff7aa426660c1ccc906d211cac5b9561adc60dc7b62d4d5
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fa351abfbba4e5e926c6a71145a5a3b66f0fefb9
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:940b04c26d7de74a2e8db252b7ce90fac13dc3f4eb65005d3a43947ae267fcae
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aa300cc2402e4cb5ebe635a81f0843d0baa46040
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f3ef76c50e1cd0a2c91e4863b114c43241cc2cd478c6560d32cdc2ca6b23b8
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de4e41c4a6949df056e028b10a18e7f8cd7b7580
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d8e6d8e53e6b837084d0cc18fdd63ca9e40bd44a65d38eb52695647a8e84e8
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/trainer_state.json b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c1adae4ed5f308fdbffc2e98b3bbe1f8bf0db6e0
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_FullactionHead_5k/seed2/default/train_5shot_seed2_fullactionhead_5k/checkpoint-3000/trainer_state.json
@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.128205128205128,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017094017094017096,
+      "grad_norm": 1.2046294212341309,
+      "learning_rate": 1.08e-06,
+      "loss": 0.2224,
+      "step": 10
+    },
+    {
+      "epoch": 0.03418803418803419,
+      "grad_norm": 1.3672140836715698,
+      "learning_rate": 2.28e-06,
+      "loss": 0.2037,
+      "step": 20
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 1.2484416961669922,
+      "learning_rate": 3.48e-06,
+      "loss": 0.193,
+      "step": 30
+    },
+    {
+      "epoch": 0.06837606837606838,
+      "grad_norm": 0.7811980247497559,
+      "learning_rate": 4.68e-06,
+      "loss": 0.158,
+      "step": 40
+    },
+    {
+      "epoch": 0.08547008547008547,
+      "grad_norm": 1.1057628393173218,
+      "learning_rate": 5.8800000000000005e-06,
+      "loss": 0.1518,
+      "step": 50
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 0.6198669672012329,
+      "learning_rate": 7.08e-06,
+      "loss": 0.1235,
+      "step": 60
+    },
+    {
+      "epoch": 0.11965811965811966,
+      "grad_norm": 0.6399325728416443,
+      "learning_rate": 8.28e-06,
+      "loss": 0.1012,
+      "step": 70
+    },
+    {
+      "epoch": 0.13675213675213677,
+      "grad_norm": 0.34900981187820435,
+      "learning_rate": 9.48e-06,
+      "loss": 0.0894,
+      "step": 80
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.24374151229858398,
+      "learning_rate": 1.068e-05,
+      "loss": 0.0847,
+      "step": 90
+    },
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 0.3181402087211609,
+      "learning_rate": 1.1880000000000001e-05,
+      "loss": 0.076,
+      "step": 100
+    },
+    {
+      "epoch": 0.18803418803418803,
+      "grad_norm": 0.3558669984340668,
+      "learning_rate": 1.308e-05,
+      "loss": 0.0756,
+      "step": 110
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 0.25770920515060425,
+      "learning_rate": 1.428e-05,
+      "loss": 0.0678,
+      "step": 120
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.3094629645347595,
+      "learning_rate": 1.548e-05,
+      "loss": 0.0656,
+      "step": 130
+    },
+    {
+      "epoch": 0.23931623931623933,
+      "grad_norm": 0.31149178743362427,
+      "learning_rate": 1.6680000000000003e-05,
+      "loss": 0.0661,
+      "step": 140
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 0.28312113881111145,
+      "learning_rate": 1.7879999999999998e-05,
+      "loss": 0.0644,
+      "step": 150
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 0.32937219738960266,
+      "learning_rate": 1.908e-05,
+      "loss": 0.0634,
+      "step": 160
+    },
+    {
+      "epoch": 0.2905982905982906,
+      "grad_norm": 0.24805986881256104,
+      "learning_rate": 2.0280000000000002e-05,
+      "loss": 0.0604,
+      "step": 170
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.3144904673099518,
+      "learning_rate": 2.148e-05,
+      "loss": 0.0559,
+      "step": 180
+    },
+    {
+      "epoch": 0.3247863247863248,
+      "grad_norm": 0.22721275687217712,
+      "learning_rate": 2.268e-05,
+      "loss": 0.0559,
+      "step": 190
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 0.24481946229934692,
+      "learning_rate": 2.3880000000000002e-05,
+      "loss": 0.0563,
+      "step": 200
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 0.29072335362434387,
+      "learning_rate": 2.508e-05,
+      "loss": 0.0543,
+      "step": 210
+    },
+    {
+      "epoch": 0.37606837606837606,
+      "grad_norm": 0.2773635983467102,
+      "learning_rate": 2.628e-05,
+      "loss": 0.0533,
+      "step": 220
+    },
+    {
+      "epoch": 0.39316239316239315,
+      "grad_norm": 0.28752514719963074,
+      "learning_rate": 2.748e-05,
+      "loss": 0.0531,
+      "step": 230
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 0.2401578277349472,
+      "learning_rate": 2.868e-05,
+      "loss": 0.0543,
+      "step": 240
+    },
+    {
+      "epoch": 0.42735042735042733,
+      "grad_norm": 0.22457115352153778,
+      "learning_rate": 2.9880000000000002e-05,
+      "loss": 0.0498,
+      "step": 250
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.22619064152240753,
+      "learning_rate": 2.9999734259635676e-05,
+      "loss": 0.0495,
+      "step": 260
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.23179255425930023,
+      "learning_rate": 2.9998815663057245e-05,
+      "loss": 0.0463,
+      "step": 270
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 0.23389773070812225,
+      "learning_rate": 2.999724096969228e-05,
+      "loss": 0.0476,
+      "step": 280
+    },
+    {
+      "epoch": 0.49572649572649574,
+      "grad_norm": 0.24128898978233337,
+      "learning_rate": 2.9995010248422984e-05,
+      "loss": 0.0437,
+      "step": 290
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.2507748007774353,
+      "learning_rate": 2.999212359682832e-05,
+      "loss": 0.0474,
+      "step": 300
+    },
+    {
+      "epoch": 0.5299145299145299,
+      "grad_norm": 0.21490685641765594,
+      "learning_rate": 2.9988581141179787e-05,
+      "loss": 0.0434,
+      "step": 310
+    },
+    {
+      "epoch": 0.5470085470085471,
+      "grad_norm": 0.22923023998737335,
+      "learning_rate": 2.998438303643587e-05,
+      "loss": 0.044,
+      "step": 320
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 0.22642545402050018,
+      "learning_rate": 2.997952946623527e-05,
+      "loss": 0.0429,
+      "step": 330
+    },
+    {
+      "epoch": 0.5811965811965812,
+      "grad_norm": 0.221108540892601,
+      "learning_rate": 2.9974020642888875e-05,
+      "loss": 0.0465,
+      "step": 340
+    },
+    {
+      "epoch": 0.5982905982905983,
+      "grad_norm": 0.19173994660377502,
+      "learning_rate": 2.9967856807370458e-05,
+      "loss": 0.0433,
+      "step": 350
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.2417234629392624,
+      "learning_rate": 2.996103822930615e-05,
+      "loss": 0.0418,
+      "step": 360
+    },
+    {
+      "epoch": 0.6324786324786325,
+      "grad_norm": 0.22277653217315674,
+      "learning_rate": 2.9953565206962653e-05,
+      "loss": 0.0388,
+      "step": 370
+    },
+    {
+      "epoch": 0.6495726495726496,
+      "grad_norm": 0.16107745468616486,
+      "learning_rate": 2.9945438067234172e-05,
+      "loss": 0.0382,
+      "step": 380
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.15353648364543915,
+      "learning_rate": 2.9936657165628124e-05,
+      "loss": 0.0406,
+      "step": 390
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 0.18034681677818298,
+      "learning_rate": 2.992722288624959e-05,
+      "loss": 0.0415,
+      "step": 400
+    },
+    {
+      "epoch": 0.7008547008547008,
+      "grad_norm": 0.23336061835289001,
+      "learning_rate": 2.9917135641784515e-05,
+      "loss": 0.0414,
+      "step": 410
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 0.19218440353870392,
+      "learning_rate": 2.9906395873481655e-05,
+      "loss": 0.0392,
+      "step": 420
+    },
+    {
+      "epoch": 0.7350427350427351,
+      "grad_norm": 0.22765028476715088,
+      "learning_rate": 2.989500405113326e-05,
+      "loss": 0.0403,
+      "step": 430
+    },
+    {
+      "epoch": 0.7521367521367521,
+      "grad_norm": 0.20929336547851562,
+      "learning_rate": 2.9882960673054547e-05,
+      "loss": 0.0369,
+      "step": 440
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.17191247642040253,
+      "learning_rate": 2.9870266266061886e-05,
+      "loss": 0.0354,
+      "step": 450
+    },
+    {
+      "epoch": 0.7863247863247863,
+      "grad_norm": 0.2489067018032074,
+      "learning_rate": 2.9856921385449766e-05,
+      "loss": 0.0365,
+      "step": 460
+    },
+    {
+      "epoch": 0.8034188034188035,
+      "grad_norm": 0.25272417068481445,
+      "learning_rate": 2.9842926614966502e-05,
+      "loss": 0.0385,
+      "step": 470
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 0.19717201590538025,
+      "learning_rate": 2.982828256678868e-05,
+      "loss": 0.0339,
+      "step": 480
+    },
+    {
+      "epoch": 0.8376068376068376,
+      "grad_norm": 0.25095418095588684,
+      "learning_rate": 2.9812989881494412e-05,
+      "loss": 0.0352,
+      "step": 490
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 0.2102588564157486,
+      "learning_rate": 2.9797049228035296e-05,
+      "loss": 0.0369,
+      "step": 500
+    },
+    {
+      "epoch": 0.8717948717948718,
+      "grad_norm": 0.20112262666225433,
+      "learning_rate": 2.978046130370715e-05,
+      "loss": 0.0326,
+      "step": 510
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.19247573614120483,
+      "learning_rate": 2.9763226834119535e-05,
+      "loss": 0.0362,
+      "step": 520
+    },
+    {
+      "epoch": 0.905982905982906,
+      "grad_norm": 0.21424508094787598,
+      "learning_rate": 2.9745346573163963e-05,
+      "loss": 0.0359,
+      "step": 530
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.26557332277297974,
+      "learning_rate": 2.9726821302980987e-05,
+      "loss": 0.0345,
+      "step": 540
+    },
+    {
+      "epoch": 0.9401709401709402,
+      "grad_norm": 0.19497093558311462,
+      "learning_rate": 2.9707651833925935e-05,
+      "loss": 0.0298,
+      "step": 550
+    },
+    {
+      "epoch": 0.9572649572649573,
+      "grad_norm": 0.17632479965686798,
+      "learning_rate": 2.968783900453348e-05,
+      "loss": 0.0333,
+      "step": 560
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "grad_norm": 0.2774340808391571,
+      "learning_rate": 2.9667383681480968e-05,
+      "loss": 0.0351,
+      "step": 570
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "grad_norm": 0.17489512264728546,
+      "learning_rate": 2.9646286759550493e-05,
+      "loss": 0.0341,
+      "step": 580
+    },
+    {
+      "epoch": 1.0085470085470085,
+      "grad_norm": 0.18617698550224304,
+      "learning_rate": 2.9624549161589764e-05,
+      "loss": 0.031,
+      "step": 590
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.1862032115459442,
+      "learning_rate": 2.9602171838471745e-05,
+      "loss": 0.0327,
+      "step": 600
+    },
+    {
+      "epoch": 1.0427350427350428,
+      "grad_norm": 0.16319014132022858,
+      "learning_rate": 2.957915576905303e-05,
+      "loss": 0.0311,
+      "step": 610
+    },
+    {
+      "epoch": 1.0598290598290598,
+      "grad_norm": 0.18638090789318085,
+      "learning_rate": 2.9555501960131058e-05,
+      "loss": 0.0328,
+      "step": 620
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 0.159883052110672,
+      "learning_rate": 2.9531211446400068e-05,
+      "loss": 0.0319,
+      "step": 630
+    },
+    {
+      "epoch": 1.0940170940170941,
+      "grad_norm": 0.17638160288333893,
+      "learning_rate": 2.9506285290405813e-05,
+      "loss": 0.0324,
+      "step": 640
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.17149314284324646,
+      "learning_rate": 2.948072458249911e-05,
+      "loss": 0.033,
+      "step": 650
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": 0.1854614019393921,
+      "learning_rate": 2.9454530440788125e-05,
+      "loss": 0.0321,
+      "step": 660
+    },
+    {
+      "epoch": 1.1452991452991452,
+      "grad_norm": 0.18628022074699402,
+      "learning_rate": 2.9427704011089474e-05,
+      "loss": 0.0308,
+      "step": 670
+    },
+    {
+      "epoch": 1.1623931623931625,
+      "grad_norm": 0.15781794488430023,
+      "learning_rate": 2.94002464668781e-05,
+      "loss": 0.0289,
+      "step": 680
+    },
+    {
+      "epoch": 1.1794871794871795,
+      "grad_norm": 0.18502387404441833,
+      "learning_rate": 2.9372159009235936e-05,
+      "loss": 0.0285,
+      "step": 690
+    },
+    {
+      "epoch": 1.1965811965811965,
+      "grad_norm": 0.13340029120445251,
+      "learning_rate": 2.9343442866799365e-05,
+      "loss": 0.03,
+      "step": 700
+    },
+    {
+      "epoch": 1.2136752136752136,
+      "grad_norm": 0.16018730401992798,
+      "learning_rate": 2.9314099295705495e-05,
+      "loss": 0.0283,
+      "step": 710
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.1523085981607437,
+      "learning_rate": 2.928412957953718e-05,
+      "loss": 0.0276,
+      "step": 720
+    },
+    {
+      "epoch": 1.2478632478632479,
+      "grad_norm": 0.1537986546754837,
+      "learning_rate": 2.925353502926689e-05,
+      "loss": 0.0291,
+      "step": 730
+    },
+    {
+      "epoch": 1.264957264957265,
+      "grad_norm": 0.1516842246055603,
+      "learning_rate": 2.922231698319937e-05,
+      "loss": 0.0315,
+      "step": 740
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 0.1799113154411316,
+      "learning_rate": 2.9190476806913088e-05,
+      "loss": 0.03,
+      "step": 750
+    },
+    {
+      "epoch": 1.2991452991452992,
+      "grad_norm": 0.2539559304714203,
+      "learning_rate": 2.9158015893200504e-05,
+      "loss": 0.0288,
+      "step": 760
+    },
+    {
+      "epoch": 1.3162393162393162,
+      "grad_norm": 0.1597651243209839,
+      "learning_rate": 2.9124935662007137e-05,
+      "loss": 0.0303,
+      "step": 770
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.18849721550941467,
+      "learning_rate": 2.9091237560369467e-05,
+      "loss": 0.0295,
+      "step": 780
+    },
+    {
+      "epoch": 1.3504273504273505,
+      "grad_norm": 0.13707464933395386,
+      "learning_rate": 2.905692306235163e-05,
+      "loss": 0.0261,
+      "step": 790
+    },
+    {
+      "epoch": 1.3675213675213675,
+      "grad_norm": 0.1797618865966797,
+      "learning_rate": 2.9021993668980925e-05,
+      "loss": 0.0266,
+      "step": 800
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 0.18061158061027527,
+      "learning_rate": 2.8986450908182185e-05,
+      "loss": 0.0277,
+      "step": 810
+    },
+    {
+      "epoch": 1.4017094017094016,
+      "grad_norm": 0.14432664215564728,
+      "learning_rate": 2.8950296334710902e-05,
+      "loss": 0.0268,
+      "step": 820
+    },
+    {
+      "epoch": 1.4188034188034189,
+      "grad_norm": 0.19661664962768555,
+      "learning_rate": 2.8913531530085248e-05,
+      "loss": 0.0275,
+      "step": 830
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 0.16374897956848145,
+      "learning_rate": 2.887615810251687e-05,
+      "loss": 0.0272,
+      "step": 840
+    },
+    {
+      "epoch": 1.452991452991453,
+      "grad_norm": 0.16281157732009888,
+      "learning_rate": 2.8838177686840577e-05,
+      "loss": 0.0283,
+      "step": 850
+    },
+    {
+      "epoch": 1.4700854700854702,
+      "grad_norm": 0.1767149716615677,
+      "learning_rate": 2.8799591944442776e-05,
+      "loss": 0.0291,
+      "step": 860
+    },
+    {
+      "epoch": 1.4871794871794872,
+      "grad_norm": 0.2484145313501358,
+      "learning_rate": 2.8760402563188848e-05,
+      "loss": 0.0284,
+      "step": 870
+    },
+    {
+      "epoch": 1.5042735042735043,
+      "grad_norm": 0.21058519184589386,
+      "learning_rate": 2.8720611257349285e-05,
+      "loss": 0.0304,
+      "step": 880
+    },
+    {
+      "epoch": 1.5213675213675213,
+      "grad_norm": 0.19965742528438568,
+      "learning_rate": 2.868021976752471e-05,
+      "loss": 0.028,
+      "step": 890
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 0.1859794408082962,
+      "learning_rate": 2.8639229860569738e-05,
+      "loss": 0.0292,
+      "step": 900
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.18770064413547516,
+      "learning_rate": 2.8597643329515688e-05,
+      "loss": 0.0264,
+      "step": 910
+    },
+    {
+      "epoch": 1.5726495726495726,
+      "grad_norm": 0.18467789888381958,
+      "learning_rate": 2.855546199349214e-05,
+      "loss": 0.0253,
+      "step": 920
+    },
+    {
+      "epoch": 1.5897435897435899,
+      "grad_norm": 0.1546042114496231,
+      "learning_rate": 2.85126876976474e-05,
+      "loss": 0.0282,
+      "step": 930
+    },
+    {
+      "epoch": 1.606837606837607,
+      "grad_norm": 0.17473237216472626,
+      "learning_rate": 2.8469322313067726e-05,
+      "loss": 0.0262,
+      "step": 940
+    },
+    {
+      "epoch": 1.623931623931624,
+      "grad_norm": 0.17649267613887787,
+      "learning_rate": 2.8425367736695522e-05,
+      "loss": 0.026,
+      "step": 950
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.15947958827018738,
+      "learning_rate": 2.838082589124636e-05,
+      "loss": 0.0258,
+      "step": 960
+    },
+    {
+      "epoch": 1.658119658119658,
+      "grad_norm": 0.18516002595424652,
+      "learning_rate": 2.8335698725124843e-05,
+      "loss": 0.0277,
+      "step": 970
+    },
+    {
+      "epoch": 1.6752136752136753,
+      "grad_norm": 0.1311817169189453,
+      "learning_rate": 2.8289988212339422e-05,
+      "loss": 0.0253,
+      "step": 980
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 0.18864114582538605,
+      "learning_rate": 2.8243696352415997e-05,
+      "loss": 0.03,
+      "step": 990
+    },
+    {
+      "epoch": 1.7094017094017095,
+      "grad_norm": 0.1583152711391449,
+      "learning_rate": 2.8196825170310495e-05,
+      "loss": 0.024,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7264957264957266,
+      "grad_norm": 0.19438093900680542,
+      "learning_rate": 2.8149376716320256e-05,
+      "loss": 0.025,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7435897435897436,
+      "grad_norm": 0.17569419741630554,
+      "learning_rate": 2.8101353065994373e-05,
+      "loss": 0.0299,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7606837606837606,
+      "grad_norm": 0.1977061629295349,
+      "learning_rate": 2.8052756320042885e-05,
+      "loss": 0.0235,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.14877791702747345,
+      "learning_rate": 2.8003588604244893e-05,
+      "loss": 0.0241,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 0.18093445897102356,
+      "learning_rate": 2.7953852069355565e-05,
+      "loss": 0.0215,
+      "step": 1050
+    },
+    {
+      "epoch": 1.811965811965812,
+      "grad_norm": 0.13836748898029327,
+      "learning_rate": 2.790354889101206e-05,
+      "loss": 0.0219,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8290598290598292,
+      "grad_norm": 0.1955246478319168,
+      "learning_rate": 2.7852681269638366e-05,
+      "loss": 0.0262,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 0.13735222816467285,
+      "learning_rate": 2.780125143034902e-05,
+      "loss": 0.0234,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8632478632478633,
+      "grad_norm": 0.20777004957199097,
+      "learning_rate": 2.7749261622851812e-05,
+      "loss": 0.0225,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8803418803418803,
+      "grad_norm": 0.15912115573883057,
+      "learning_rate": 2.7696714121349335e-05,
+      "loss": 0.0235,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8974358974358974,
+      "grad_norm": 0.14222097396850586,
+      "learning_rate": 2.764361122443954e-05,
+      "loss": 0.0217,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9145299145299144,
+      "grad_norm": 0.12735839188098907,
+      "learning_rate": 2.758995525501517e-05,
+      "loss": 0.024,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9316239316239316,
+      "grad_norm": 0.13369329273700714,
+      "learning_rate": 2.753574856016215e-05,
+      "loss": 0.0259,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9487179487179487,
+      "grad_norm": 0.14417479932308197,
+      "learning_rate": 2.7480993511056913e-05,
+      "loss": 0.024,
+      "step": 1140
+    },
+    {
+      "epoch": 1.965811965811966,
+      "grad_norm": 0.13541226089000702,
+      "learning_rate": 2.7425692502862684e-05,
+      "loss": 0.021,
+      "step": 1150
+    },
+    {
+      "epoch": 1.982905982905983,
+      "grad_norm": 0.13426485657691956,
+      "learning_rate": 2.7369847954624728e-05,
+      "loss": 0.0249,
+      "step": 1160
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22447210550308228,
+      "learning_rate": 2.731346230916448e-05,
+      "loss": 0.0275,
+      "step": 1170
+    },
+    {
+      "epoch": 2.017094017094017,
+      "grad_norm": 0.1316627860069275,
+      "learning_rate": 2.7256538032972746e-05,
+      "loss": 0.0236,
+      "step": 1180
+    },
+    {
+      "epoch": 2.034188034188034,
+      "grad_norm": 0.1581067442893982,
+      "learning_rate": 2.7199077616101773e-05,
+      "loss": 0.0209,
+      "step": 1190
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 0.1645020693540573,
+      "learning_rate": 2.714108357205634e-05,
+      "loss": 0.0254,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0683760683760686,
+      "grad_norm": 0.15171298384666443,
+      "learning_rate": 2.7082558437683803e-05,
+      "loss": 0.0219,
+      "step": 1210
+    },
+    {
+      "epoch": 2.0854700854700856,
+      "grad_norm": 0.14786364138126373,
+      "learning_rate": 2.702350477306315e-05,
+      "loss": 0.0232,
+      "step": 1220
+    },
+    {
+      "epoch": 2.1025641025641026,
+      "grad_norm": 0.19275642931461334,
+      "learning_rate": 2.6963925161392963e-05,
+      "loss": 0.0261,
+      "step": 1230
+    },
+    {
+      "epoch": 2.1196581196581197,
+      "grad_norm": 0.21039193868637085,
+      "learning_rate": 2.6903822208878476e-05,
+      "loss": 0.0237,
+      "step": 1240
+    },
+    {
+      "epoch": 2.1367521367521367,
+      "grad_norm": 0.1635989099740982,
+      "learning_rate": 2.6843198544617535e-05,
+      "loss": 0.024,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 0.14116357266902924,
+      "learning_rate": 2.6782056820485612e-05,
+      "loss": 0.0233,
+      "step": 1260
+    },
+    {
+      "epoch": 2.1709401709401708,
+      "grad_norm": 0.1337611824274063,
+      "learning_rate": 2.672039971101979e-05,
+      "loss": 0.0223,
+      "step": 1270
+    },
+    {
+      "epoch": 2.1880341880341883,
+      "grad_norm": 0.12742610275745392,
+      "learning_rate": 2.665822991330178e-05,
+      "loss": 0.0233,
+      "step": 1280
+    },
+    {
+      "epoch": 2.2051282051282053,
+      "grad_norm": 0.16495631635189056,
+      "learning_rate": 2.6595550146839934e-05,
+      "loss": 0.0244,
+      "step": 1290
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.13133522868156433,
+      "learning_rate": 2.6532363153450287e-05,
+      "loss": 0.0236,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2393162393162394,
+      "grad_norm": 0.11399739980697632,
+      "learning_rate": 2.6468671697136634e-05,
+      "loss": 0.0222,
+      "step": 1310
+    },
+    {
+      "epoch": 2.2564102564102564,
+      "grad_norm": 0.12264499813318253,
+      "learning_rate": 2.640447856396961e-05,
+      "loss": 0.0205,
+      "step": 1320
+    },
+    {
+      "epoch": 2.2735042735042734,
+      "grad_norm": 0.1786639243364334,
+      "learning_rate": 2.6339786561964805e-05,
+      "loss": 0.0251,
+      "step": 1330
+    },
+    {
+      "epoch": 2.2905982905982905,
+      "grad_norm": 0.15574303269386292,
+      "learning_rate": 2.6274598520959966e-05,
+      "loss": 0.0226,
+      "step": 1340
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.15068724751472473,
+      "learning_rate": 2.6208917292491185e-05,
+      "loss": 0.0219,
+      "step": 1350
+    },
+    {
+      "epoch": 2.324786324786325,
+      "grad_norm": 0.16358910501003265,
+      "learning_rate": 2.6142745749668176e-05,
+      "loss": 0.0225,
+      "step": 1360
+    },
+    {
+      "epoch": 2.341880341880342,
+      "grad_norm": 0.21654905378818512,
+      "learning_rate": 2.607608678704859e-05,
+      "loss": 0.0232,
+      "step": 1370
+    },
+    {
+      "epoch": 2.358974358974359,
+      "grad_norm": 0.22834260761737823,
+      "learning_rate": 2.600894332051139e-05,
+      "loss": 0.0215,
+      "step": 1380
+    },
+    {
+      "epoch": 2.376068376068376,
+      "grad_norm": 0.17436617612838745,
+      "learning_rate": 2.594131828712932e-05,
+      "loss": 0.0217,
+      "step": 1390
+    },
+    {
+      "epoch": 2.393162393162393,
+      "grad_norm": 0.13975125551223755,
+      "learning_rate": 2.5873214645040414e-05,
+      "loss": 0.02,
+      "step": 1400
+    },
+    {
+      "epoch": 2.41025641025641,
+      "grad_norm": 0.18962903320789337,
+      "learning_rate": 2.5804635373318604e-05,
+      "loss": 0.0216,
+      "step": 1410
+    },
+    {
+      "epoch": 2.427350427350427,
+      "grad_norm": 0.1517896205186844,
+      "learning_rate": 2.57355834718434e-05,
+      "loss": 0.0221,
+      "step": 1420
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.1567123383283615,
+      "learning_rate": 2.566606196116867e-05,
+      "loss": 0.0218,
+      "step": 1430
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 0.2237260341644287,
+      "learning_rate": 2.559607388239051e-05,
+      "loss": 0.0205,
+      "step": 1440
+    },
+    {
+      "epoch": 2.4786324786324787,
+      "grad_norm": 0.1526583880186081,
+      "learning_rate": 2.552562229701422e-05,
+      "loss": 0.0215,
+      "step": 1450
+    },
+    {
+      "epoch": 2.4957264957264957,
+      "grad_norm": 0.14554832875728607,
+      "learning_rate": 2.545471028682036e-05,
+      "loss": 0.0235,
+      "step": 1460
+    },
+    {
+      "epoch": 2.5128205128205128,
+      "grad_norm": 0.14237725734710693,
+      "learning_rate": 2.538334095373e-05,
+      "loss": 0.0209,
+      "step": 1470
+    },
+    {
+      "epoch": 2.52991452991453,
+      "grad_norm": 0.17106768488883972,
+      "learning_rate": 2.531151741966896e-05,
+      "loss": 0.0215,
+      "step": 1480
+    },
+    {
+      "epoch": 2.547008547008547,
+      "grad_norm": 0.12999463081359863,
+      "learning_rate": 2.5239242826431302e-05,
+      "loss": 0.0207,
+      "step": 1490
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 0.23773175477981567,
+      "learning_rate": 2.5166520335541865e-05,
+      "loss": 0.0218,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5811965811965814,
+      "grad_norm": 0.11908961087465286,
+      "learning_rate": 2.5093353128117996e-05,
+      "loss": 0.0223,
+      "step": 1510
+    },
+    {
+      "epoch": 2.5982905982905984,
+      "grad_norm": 0.25520920753479004,
+      "learning_rate": 2.501974440473037e-05,
+      "loss": 0.0198,
+      "step": 1520
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.21974427998065948,
+      "learning_rate": 2.4945697385263015e-05,
+      "loss": 0.0223,
+      "step": 1530
+    },
+    {
+      "epoch": 2.6324786324786325,
+      "grad_norm": 0.1549292355775833,
+      "learning_rate": 2.487121530877243e-05,
+      "loss": 0.0208,
+      "step": 1540
+    },
+    {
+      "epoch": 2.6495726495726495,
+      "grad_norm": 0.17997530102729797,
+      "learning_rate": 2.4796301433345943e-05,
+      "loss": 0.0207,
+      "step": 1550
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.15226222574710846,
+      "learning_rate": 2.4720959035959148e-05,
+      "loss": 0.0218,
+      "step": 1560
+    },
+    {
+      "epoch": 2.683760683760684,
+      "grad_norm": 0.2047930359840393,
+      "learning_rate": 2.464519141233257e-05,
+      "loss": 0.0215,
+      "step": 1570
+    },
+    {
+      "epoch": 2.700854700854701,
+      "grad_norm": 0.16199080646038055,
+      "learning_rate": 2.456900187678754e-05,
+      "loss": 0.0214,
+      "step": 1580
+    },
+    {
+      "epoch": 2.717948717948718,
+      "grad_norm": 0.11895282566547394,
+      "learning_rate": 2.4492393762101147e-05,
+      "loss": 0.0202,
+      "step": 1590
+    },
+    {
+      "epoch": 2.735042735042735,
+      "grad_norm": 0.15882159769535065,
+      "learning_rate": 2.4415370419360508e-05,
+      "loss": 0.022,
+      "step": 1600
+    },
+    {
+      "epoch": 2.752136752136752,
+      "grad_norm": 0.14013583958148956,
+      "learning_rate": 2.4337935217816157e-05,
+      "loss": 0.022,
+      "step": 1610
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.20299099385738373,
+      "learning_rate": 2.4260091544734665e-05,
+      "loss": 0.0207,
+      "step": 1620
+    },
+    {
+      "epoch": 2.786324786324786,
+      "grad_norm": 0.21985934674739838,
+      "learning_rate": 2.4181842805250466e-05,
+      "loss": 0.0214,
+      "step": 1630
+    },
+    {
+      "epoch": 2.8034188034188032,
+      "grad_norm": 0.14461225271224976,
+      "learning_rate": 2.4103192422216923e-05,
+      "loss": 0.0195,
+      "step": 1640
+    },
+    {
+      "epoch": 2.8205128205128203,
+      "grad_norm": 0.10911990702152252,
+      "learning_rate": 2.402414383605658e-05,
+      "loss": 0.0204,
+      "step": 1650
+    },
+    {
+      "epoch": 2.8376068376068377,
+      "grad_norm": 0.13800372183322906,
+      "learning_rate": 2.3944700504610674e-05,
+      "loss": 0.0192,
+      "step": 1660
+    },
+    {
+      "epoch": 2.8547008547008548,
+      "grad_norm": 0.14190635085105896,
+      "learning_rate": 2.3864865902987883e-05,
+      "loss": 0.0204,
+      "step": 1670
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 0.14053791761398315,
+      "learning_rate": 2.378464352341231e-05,
+      "loss": 0.0199,
+      "step": 1680
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.1504385620355606,
+      "learning_rate": 2.3704036875070728e-05,
+      "loss": 0.0233,
+      "step": 1690
+    },
+    {
+      "epoch": 2.905982905982906,
+      "grad_norm": 0.18149782717227936,
+      "learning_rate": 2.362304948395906e-05,
+      "loss": 0.0235,
+      "step": 1700
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.17068181931972504,
+      "learning_rate": 2.3541684892728157e-05,
+      "loss": 0.0212,
+      "step": 1710
+    },
+    {
+      "epoch": 2.9401709401709404,
+      "grad_norm": 0.1624104231595993,
+      "learning_rate": 2.345994666052883e-05,
+      "loss": 0.0177,
+      "step": 1720
+    },
+    {
+      "epoch": 2.9572649572649574,
+      "grad_norm": 0.19329632818698883,
+      "learning_rate": 2.337783836285614e-05,
+      "loss": 0.0214,
+      "step": 1730
+    },
+    {
+      "epoch": 2.9743589743589745,
+      "grad_norm": 0.13297595083713531,
+      "learning_rate": 2.3295363591393026e-05,
+      "loss": 0.0184,
+      "step": 1740
+    },
+    {
+      "epoch": 2.9914529914529915,
+      "grad_norm": 0.12240353226661682,
+      "learning_rate": 2.3212525953853174e-05,
+      "loss": 0.0212,
+      "step": 1750
+    },
+    {
+      "epoch": 3.0085470085470085,
+      "grad_norm": 0.130058154463768,
+      "learning_rate": 2.3129329073823206e-05,
+      "loss": 0.0205,
+      "step": 1760
+    },
+    {
+      "epoch": 3.0256410256410255,
+      "grad_norm": 0.11880940198898315,
+      "learning_rate": 2.3045776590604175e-05,
+      "loss": 0.0193,
+      "step": 1770
+    },
+    {
+      "epoch": 3.0427350427350426,
+      "grad_norm": 0.12890465557575226,
+      "learning_rate": 2.296187215905237e-05,
+      "loss": 0.0212,
+      "step": 1780
+    },
+    {
+      "epoch": 3.0598290598290596,
+      "grad_norm": 0.1741575449705124,
+      "learning_rate": 2.2877619449419437e-05,
+      "loss": 0.0212,
+      "step": 1790
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 0.1907522976398468,
+      "learning_rate": 2.2793022147191843e-05,
+      "loss": 0.0203,
+      "step": 1800
+    },
+    {
+      "epoch": 3.094017094017094,
+      "grad_norm": 0.17696961760520935,
+      "learning_rate": 2.2708083952929634e-05,
+      "loss": 0.0181,
+      "step": 1810
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 0.1593712717294693,
+      "learning_rate": 2.2622808582104594e-05,
+      "loss": 0.0197,
+      "step": 1820
+    },
+    {
+      "epoch": 3.128205128205128,
+      "grad_norm": 0.12099262326955795,
+      "learning_rate": 2.2537199764937703e-05,
+      "loss": 0.0188,
+      "step": 1830
+    },
+    {
+      "epoch": 3.1452991452991452,
+      "grad_norm": 0.16116322576999664,
+      "learning_rate": 2.245126124623595e-05,
+      "loss": 0.0196,
+      "step": 1840
+    },
+    {
+      "epoch": 3.1623931623931623,
+      "grad_norm": 0.1666380614042282,
+      "learning_rate": 2.2364996785228547e-05,
+      "loss": 0.0203,
+      "step": 1850
+    },
+    {
+      "epoch": 3.1794871794871793,
+      "grad_norm": 0.13607926666736603,
+      "learning_rate": 2.227841015540248e-05,
+      "loss": 0.0212,
+      "step": 1860
+    },
+    {
+      "epoch": 3.1965811965811968,
+      "grad_norm": 0.1656973510980606,
+      "learning_rate": 2.2191505144337433e-05,
+      "loss": 0.0195,
+      "step": 1870
+    },
+    {
+      "epoch": 3.213675213675214,
+      "grad_norm": 0.13743546605110168,
+      "learning_rate": 2.210428555354013e-05,
+      "loss": 0.0213,
+      "step": 1880
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 0.15309397876262665,
+      "learning_rate": 2.201675519827802e-05,
+      "loss": 0.0215,
+      "step": 1890
+    },
+    {
+      "epoch": 3.247863247863248,
+      "grad_norm": 0.13153575360774994,
+      "learning_rate": 2.1928917907412403e-05,
+      "loss": 0.0189,
+      "step": 1900
+    },
+    {
+      "epoch": 3.264957264957265,
+      "grad_norm": 0.16302916407585144,
+      "learning_rate": 2.1840777523230937e-05,
+      "loss": 0.0189,
+      "step": 1910
+    },
+    {
+      "epoch": 3.282051282051282,
+      "grad_norm": 0.12375231087207794,
+      "learning_rate": 2.1752337901279552e-05,
+      "loss": 0.021,
+      "step": 1920
+    },
+    {
+      "epoch": 3.299145299145299,
+      "grad_norm": 0.18395335972309113,
+      "learning_rate": 2.166360291019383e-05,
+      "loss": 0.0187,
+      "step": 1930
+    },
+    {
+      "epoch": 3.316239316239316,
+      "grad_norm": 0.12572312355041504,
+      "learning_rate": 2.157457643152973e-05,
+      "loss": 0.0203,
+      "step": 1940
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.12790457904338837,
+      "learning_rate": 2.148526235959385e-05,
+      "loss": 0.0177,
+      "step": 1950
+    },
+    {
+      "epoch": 3.3504273504273505,
+      "grad_norm": 0.19870531558990479,
+      "learning_rate": 2.1395664601273016e-05,
+      "loss": 0.0204,
+      "step": 1960
+    },
+    {
+      "epoch": 3.3675213675213675,
+      "grad_norm": 0.18182598054409027,
+      "learning_rate": 2.130578707586345e-05,
+      "loss": 0.023,
+      "step": 1970
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 0.13019001483917236,
+      "learning_rate": 2.1215633714899264e-05,
+      "loss": 0.021,
+      "step": 1980
+    },
+    {
+      "epoch": 3.4017094017094016,
+      "grad_norm": 0.12526895105838776,
+      "learning_rate": 2.112520846198053e-05,
+      "loss": 0.0201,
+      "step": 1990
+    },
+    {
+      "epoch": 3.4188034188034186,
+      "grad_norm": 0.1366206407546997,
+      "learning_rate": 2.103451527260074e-05,
+      "loss": 0.0186,
+      "step": 2000
+    },
+    {
+      "epoch": 3.435897435897436,
+      "grad_norm": 0.13825932145118713,
+      "learning_rate": 2.094355811397381e-05,
+      "loss": 0.0193,
+      "step": 2010
+    },
+    {
+      "epoch": 3.452991452991453,
+      "grad_norm": 0.10611677914857864,
+      "learning_rate": 2.0852340964860522e-05,
+      "loss": 0.0203,
+      "step": 2020
+    },
+    {
+      "epoch": 3.47008547008547,
+      "grad_norm": 0.15153281390666962,
+      "learning_rate": 2.076086781539447e-05,
+      "loss": 0.02,
+      "step": 2030
+    },
+    {
+      "epoch": 3.4871794871794872,
+      "grad_norm": 0.12375279515981674,
+      "learning_rate": 2.066914266690755e-05,
+      "loss": 0.0182,
+      "step": 2040
+    },
+    {
+      "epoch": 3.5042735042735043,
+      "grad_norm": 0.12043378502130508,
+      "learning_rate": 2.0577169531754906e-05,
+      "loss": 0.0197,
+      "step": 2050
+    },
+    {
+      "epoch": 3.5213675213675213,
+      "grad_norm": 0.12067852169275284,
+      "learning_rate": 2.048495243313942e-05,
+      "loss": 0.0195,
+      "step": 2060
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 0.16918447613716125,
+      "learning_rate": 2.039249540493572e-05,
+      "loss": 0.0201,
+      "step": 2070
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.1681264340877533,
+      "learning_rate": 2.0299802491513755e-05,
+      "loss": 0.0172,
+      "step": 2080
+    },
+    {
+      "epoch": 3.5726495726495724,
+      "grad_norm": 0.14336660504341125,
+      "learning_rate": 2.0206877747561828e-05,
+      "loss": 0.0216,
+      "step": 2090
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 0.15480872988700867,
+      "learning_rate": 2.011372523790927e-05,
+      "loss": 0.02,
+      "step": 2100
+    },
+    {
+      "epoch": 3.606837606837607,
+      "grad_norm": 0.15778888761997223,
+      "learning_rate": 2.0020349037348643e-05,
+      "loss": 0.0178,
+      "step": 2110
+    },
+    {
+      "epoch": 3.623931623931624,
+      "grad_norm": 0.1326507329940796,
+      "learning_rate": 1.9926753230457443e-05,
+      "loss": 0.0193,
+      "step": 2120
+    },
+    {
+      "epoch": 3.641025641025641,
+      "grad_norm": 0.1321679651737213,
+      "learning_rate": 1.983294191141948e-05,
+      "loss": 0.0214,
+      "step": 2130
+    },
+    {
+      "epoch": 3.658119658119658,
+      "grad_norm": 0.12508369982242584,
+      "learning_rate": 1.973891918384575e-05,
+      "loss": 0.0167,
+      "step": 2140
+    },
+    {
+      "epoch": 3.6752136752136755,
+      "grad_norm": 0.17087364196777344,
+      "learning_rate": 1.9644689160594945e-05,
+      "loss": 0.0199,
+      "step": 2150
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 0.12470774352550507,
+      "learning_rate": 1.9550255963593553e-05,
+      "loss": 0.0174,
+      "step": 2160
+    },
+    {
+      "epoch": 3.7094017094017095,
+      "grad_norm": 0.12396084517240524,
+      "learning_rate": 1.9455623723655524e-05,
+      "loss": 0.015,
+      "step": 2170
+    },
+    {
+      "epoch": 3.7264957264957266,
+      "grad_norm": 0.11109942197799683,
+      "learning_rate": 1.9360796580301606e-05,
+      "loss": 0.0177,
+      "step": 2180
+    },
+    {
+      "epoch": 3.7435897435897436,
+      "grad_norm": 0.12820954620838165,
+      "learning_rate": 1.9265778681578245e-05,
+      "loss": 0.0172,
+      "step": 2190
+    },
+    {
+      "epoch": 3.7606837606837606,
+      "grad_norm": 0.16764280200004578,
+      "learning_rate": 1.9170574183876143e-05,
+      "loss": 0.0213,
+      "step": 2200
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 0.13727493584156036,
+      "learning_rate": 1.9075187251748452e-05,
+      "loss": 0.0202,
+      "step": 2210
+    },
+    {
+      "epoch": 3.7948717948717947,
+      "grad_norm": 0.1443384438753128,
+      "learning_rate": 1.8979622057728596e-05,
+      "loss": 0.0191,
+      "step": 2220
+    },
+    {
+      "epoch": 3.8119658119658117,
+      "grad_norm": 0.13722945749759674,
+      "learning_rate": 1.8883882782147748e-05,
+      "loss": 0.0189,
+      "step": 2230
+    },
+    {
+      "epoch": 3.8290598290598292,
+      "grad_norm": 0.15205898880958557,
+      "learning_rate": 1.8787973612951967e-05,
+      "loss": 0.0178,
+      "step": 2240
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 0.1548609435558319,
+      "learning_rate": 1.8691898745519028e-05,
+      "loss": 0.0194,
+      "step": 2250
+    },
+    {
+      "epoch": 3.8632478632478633,
+      "grad_norm": 0.1382390409708023,
+      "learning_rate": 1.8595662382474863e-05,
+      "loss": 0.0195,
+      "step": 2260
+    },
+    {
+      "epoch": 3.8803418803418803,
+      "grad_norm": 0.12302783131599426,
+      "learning_rate": 1.8499268733509766e-05,
+      "loss": 0.0187,
+      "step": 2270
+    },
+    {
+      "epoch": 3.8974358974358974,
+      "grad_norm": 0.1820244938135147,
+      "learning_rate": 1.84027220151942e-05,
+      "loss": 0.0165,
+      "step": 2280
+    },
+    {
+      "epoch": 3.9145299145299144,
+      "grad_norm": 0.1326133906841278,
+      "learning_rate": 1.83060264507944e-05,
+      "loss": 0.017,
+      "step": 2290
+    },
+    {
+      "epoch": 3.931623931623932,
+      "grad_norm": 0.12418877333402634,
+      "learning_rate": 1.82091862700876e-05,
+      "loss": 0.0173,
+      "step": 2300
+    },
+    {
+      "epoch": 3.948717948717949,
+      "grad_norm": 0.12344951182603836,
+      "learning_rate": 1.8112205709177023e-05,
+      "loss": 0.0204,
+      "step": 2310
+    },
+    {
+      "epoch": 3.965811965811966,
+      "grad_norm": 0.20541010797023773,
+      "learning_rate": 1.8015089010306585e-05,
+      "loss": 0.0169,
+      "step": 2320
+    },
+    {
+      "epoch": 3.982905982905983,
+      "grad_norm": 0.20820003747940063,
+      "learning_rate": 1.7917840421675298e-05,
+      "loss": 0.0222,
+      "step": 2330
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12587814033031464,
+      "learning_rate": 1.7820464197251474e-05,
+      "loss": 0.0168,
+      "step": 2340
+    },
+    {
+      "epoch": 4.017094017094017,
+      "grad_norm": 0.12032312154769897,
+      "learning_rate": 1.7722964596586627e-05,
+      "loss": 0.02,
+      "step": 2350
+    },
+    {
+      "epoch": 4.034188034188034,
+      "grad_norm": 0.16112498939037323,
+      "learning_rate": 1.7625345884629144e-05,
+      "loss": 0.0173,
+      "step": 2360
+    },
+    {
+      "epoch": 4.051282051282051,
+      "grad_norm": 0.11967416107654572,
+      "learning_rate": 1.7527612331537722e-05,
+      "loss": 0.0175,
+      "step": 2370
+    },
+    {
+      "epoch": 4.068376068376068,
+      "grad_norm": 0.12133967131376266,
+      "learning_rate": 1.7429768212494593e-05,
+      "loss": 0.0179,
+      "step": 2380
+    },
+    {
+      "epoch": 4.085470085470085,
+      "grad_norm": 0.16594752669334412,
+      "learning_rate": 1.7331817807518497e-05,
+      "loss": 0.0195,
+      "step": 2390
+    },
+    {
+      "epoch": 4.102564102564102,
+      "grad_norm": 0.15331916511058807,
+      "learning_rate": 1.723376540127745e-05,
+      "loss": 0.0156,
+      "step": 2400
+    },
+    {
+      "epoch": 4.119658119658119,
+      "grad_norm": 0.13228918612003326,
+      "learning_rate": 1.7135615282901357e-05,
+      "loss": 0.0169,
+      "step": 2410
+    },
+    {
+      "epoch": 4.136752136752137,
+      "grad_norm": 0.13137143850326538,
+      "learning_rate": 1.7037371745794358e-05,
+      "loss": 0.0221,
+      "step": 2420
+    },
+    {
+      "epoch": 4.153846153846154,
+      "grad_norm": 0.1315498948097229,
+      "learning_rate": 1.6939039087447026e-05,
+      "loss": 0.0186,
+      "step": 2430
+    },
+    {
+      "epoch": 4.170940170940171,
+      "grad_norm": 0.1358824223279953,
+      "learning_rate": 1.6840621609248397e-05,
+      "loss": 0.0182,
+      "step": 2440
+    },
+    {
+      "epoch": 4.188034188034188,
+      "grad_norm": 0.13738547265529633,
+      "learning_rate": 1.6742123616297794e-05,
+      "loss": 0.0167,
+      "step": 2450
+    },
+    {
+      "epoch": 4.205128205128205,
+      "grad_norm": 0.12346506863832474,
+      "learning_rate": 1.664354941721651e-05,
+      "loss": 0.0162,
+      "step": 2460
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 0.13007137179374695,
+      "learning_rate": 1.6544903323959355e-05,
+      "loss": 0.0166,
+      "step": 2470
+    },
+    {
+      "epoch": 4.239316239316239,
+      "grad_norm": 0.13907431066036224,
+      "learning_rate": 1.6446189651626023e-05,
+      "loss": 0.0174,
+      "step": 2480
+    },
+    {
+      "epoch": 4.256410256410256,
+      "grad_norm": 0.12497235089540482,
+      "learning_rate": 1.6347412718272316e-05,
+      "loss": 0.0193,
+      "step": 2490
+    },
+    {
+      "epoch": 4.273504273504273,
+      "grad_norm": 0.13083861768245697,
+      "learning_rate": 1.624857684472131e-05,
+      "loss": 0.0168,
+      "step": 2500
+    },
+    {
+      "epoch": 4.2905982905982905,
+      "grad_norm": 0.13517604768276215,
+      "learning_rate": 1.6149686354374283e-05,
+      "loss": 0.0197,
+      "step": 2510
+    },
+    {
+      "epoch": 4.3076923076923075,
+      "grad_norm": 0.15625643730163574,
+      "learning_rate": 1.605074557302165e-05,
+      "loss": 0.0177,
+      "step": 2520
+    },
+    {
+      "epoch": 4.3247863247863245,
+      "grad_norm": 0.20975004136562347,
+      "learning_rate": 1.59517588286537e-05,
+      "loss": 0.0189,
+      "step": 2530
+    },
+    {
+      "epoch": 4.3418803418803416,
+      "grad_norm": 0.16902174055576324,
+      "learning_rate": 1.5852730451271324e-05,
+      "loss": 0.0164,
+      "step": 2540
+    },
+    {
+      "epoch": 4.358974358974359,
+      "grad_norm": 0.14469504356384277,
+      "learning_rate": 1.5753664772696546e-05,
+      "loss": 0.0186,
+      "step": 2550
+    },
+    {
+      "epoch": 4.3760683760683765,
+      "grad_norm": 0.14689213037490845,
+      "learning_rate": 1.565456612638307e-05,
+      "loss": 0.0203,
+      "step": 2560
+    },
+    {
+      "epoch": 4.3931623931623935,
+      "grad_norm": 0.13142313063144684,
+      "learning_rate": 1.5555438847226732e-05,
+      "loss": 0.0163,
+      "step": 2570
+    },
+    {
+      "epoch": 4.410256410256411,
+      "grad_norm": 0.15418632328510284,
+      "learning_rate": 1.545628727137584e-05,
+      "loss": 0.0178,
+      "step": 2580
+    },
+    {
+      "epoch": 4.427350427350428,
+      "grad_norm": 0.15956638753414154,
+      "learning_rate": 1.535711573604153e-05,
+      "loss": 0.0144,
+      "step": 2590
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.1449543535709381,
+      "learning_rate": 1.5257928579308032e-05,
+      "loss": 0.0177,
+      "step": 2600
+    },
+    {
+      "epoch": 4.461538461538462,
+      "grad_norm": 0.1384369283914566,
+      "learning_rate": 1.5158730139942902e-05,
+      "loss": 0.0174,
+      "step": 2610
+    },
+    {
+      "epoch": 4.478632478632479,
+      "grad_norm": 0.13507409393787384,
+      "learning_rate": 1.5059524757207239e-05,
+      "loss": 0.0173,
+      "step": 2620
+    },
+    {
+      "epoch": 4.495726495726496,
+      "grad_norm": 0.14348851144313812,
+      "learning_rate": 1.4960316770665866e-05,
+      "loss": 0.017,
+      "step": 2630
+    },
+    {
+      "epoch": 4.512820512820513,
+      "grad_norm": 0.10914012789726257,
+      "learning_rate": 1.4861110519997495e-05,
+      "loss": 0.0178,
+      "step": 2640
+    },
+    {
+      "epoch": 4.52991452991453,
+      "grad_norm": 0.21071846783161163,
+      "learning_rate": 1.4761910344804913e-05,
+      "loss": 0.0168,
+      "step": 2650
+    },
+    {
+      "epoch": 4.547008547008547,
+      "grad_norm": 0.11937859654426575,
+      "learning_rate": 1.466272058442516e-05,
+      "loss": 0.0171,
+      "step": 2660
+    },
+    {
+      "epoch": 4.564102564102564,
+      "grad_norm": 0.09995169937610626,
+      "learning_rate": 1.4563545577739676e-05,
+      "loss": 0.0174,
+      "step": 2670
+    },
+    {
+      "epoch": 4.581196581196581,
+      "grad_norm": 0.1595757007598877,
+      "learning_rate": 1.4464389662984543e-05,
+      "loss": 0.0173,
+      "step": 2680
+    },
+    {
+      "epoch": 4.598290598290598,
+      "grad_norm": 0.13326671719551086,
+      "learning_rate": 1.4365257177560684e-05,
+      "loss": 0.0177,
+      "step": 2690
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 0.1444454789161682,
+      "learning_rate": 1.426615245784416e-05,
+      "loss": 0.0166,
+      "step": 2700
+    },
+    {
+      "epoch": 4.632478632478632,
+      "grad_norm": 0.11446025967597961,
+      "learning_rate": 1.4167079838996468e-05,
+      "loss": 0.0151,
+      "step": 2710
+    },
+    {
+      "epoch": 4.64957264957265,
+      "grad_norm": 0.13881082832813263,
+      "learning_rate": 1.4068043654774897e-05,
+      "loss": 0.0155,
+      "step": 2720
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.20510493218898773,
+      "learning_rate": 1.3969048237342992e-05,
+      "loss": 0.0185,
+      "step": 2730
+    },
+    {
+      "epoch": 4.683760683760684,
+      "grad_norm": 0.14961980283260345,
+      "learning_rate": 1.3870097917081011e-05,
+      "loss": 0.0166,
+      "step": 2740
+    },
+    {
+      "epoch": 4.700854700854701,
+      "grad_norm": 0.12033514678478241,
+      "learning_rate": 1.3771197022396508e-05,
+      "loss": 0.0146,
+      "step": 2750
+    },
+    {
+      "epoch": 4.717948717948718,
+      "grad_norm": 0.13812503218650818,
+      "learning_rate": 1.3672349879535015e-05,
+      "loss": 0.0172,
+      "step": 2760
+    },
+    {
+      "epoch": 4.735042735042735,
+      "grad_norm": 0.13671137392520905,
+      "learning_rate": 1.3573560812390781e-05,
+      "loss": 0.0177,
+      "step": 2770
+    },
+    {
+      "epoch": 4.752136752136752,
+      "grad_norm": 0.14928513765335083,
+      "learning_rate": 1.3474834142317635e-05,
+      "loss": 0.0142,
+      "step": 2780
+    },
+    {
+      "epoch": 4.769230769230769,
+      "grad_norm": 0.10949765145778656,
+      "learning_rate": 1.3376174187939955e-05,
+      "loss": 0.0161,
+      "step": 2790
+    },
+    {
+      "epoch": 4.786324786324786,
+      "grad_norm": 0.10777349025011063,
+      "learning_rate": 1.3277585264963761e-05,
+      "loss": 0.0168,
+      "step": 2800
+    },
+    {
+      "epoch": 4.803418803418803,
+      "grad_norm": 0.17750239372253418,
+      "learning_rate": 1.3179071685987928e-05,
+      "loss": 0.0182,
+      "step": 2810
+    },
+    {
+      "epoch": 4.82051282051282,
+      "grad_norm": 0.13401111960411072,
+      "learning_rate": 1.308063776031554e-05,
+      "loss": 0.0164,
+      "step": 2820
+    },
+    {
+      "epoch": 4.837606837606837,
+      "grad_norm": 0.1763419806957245,
+      "learning_rate": 1.2982287793765389e-05,
+      "loss": 0.0147,
+      "step": 2830
+    },
+    {
+      "epoch": 4.854700854700854,
+      "grad_norm": 0.13647712767124176,
+      "learning_rate": 1.2884026088483616e-05,
+      "loss": 0.0162,
+      "step": 2840
+    },
+    {
+      "epoch": 4.871794871794872,
+      "grad_norm": 0.1311454325914383,
+      "learning_rate": 1.2785856942755543e-05,
+      "loss": 0.0174,
+      "step": 2850
+    },
+    {
+      "epoch": 4.888888888888889,
+      "grad_norm": 0.12965312600135803,
+      "learning_rate": 1.2687784650817616e-05,
+      "loss": 0.0169,
+      "step": 2860
+    },
+    {
+      "epoch": 4.905982905982906,
+      "grad_norm": 0.14787934720516205,
+      "learning_rate": 1.2589813502669603e-05,
+      "loss": 0.0193,
+      "step": 2870
+    },
+    {
+      "epoch": 4.923076923076923,
+      "grad_norm": 0.1825832575559616,
+      "learning_rate": 1.2491947783886907e-05,
+      "loss": 0.0169,
+      "step": 2880
+    },
+    {
+      "epoch": 4.94017094017094,
+      "grad_norm": 0.1275591403245926,
+      "learning_rate": 1.2394191775433106e-05,
+      "loss": 0.017,
+      "step": 2890
+    },
+    {
+      "epoch": 4.957264957264957,
+      "grad_norm": 0.12773366272449493,
+      "learning_rate": 1.2296549753472696e-05,
+      "loss": 0.0176,
+      "step": 2900
+    },
+    {
+      "epoch": 4.9743589743589745,
+      "grad_norm": 0.15548300743103027,
+      "learning_rate": 1.2199025989184032e-05,
+      "loss": 0.0141,
+      "step": 2910
+    },
+    {
+      "epoch": 4.9914529914529915,
+      "grad_norm": 0.12168218195438385,
+      "learning_rate": 1.21016247485725e-05,
+      "loss": 0.0179,
+      "step": 2920
+    },
+    {
+      "epoch": 5.0085470085470085,
+      "grad_norm": 0.12161333858966827,
+      "learning_rate": 1.2004350292283897e-05,
+      "loss": 0.0171,
+      "step": 2930
+    },
+    {
+      "epoch": 5.0256410256410255,
+      "grad_norm": 0.2516013979911804,
+      "learning_rate": 1.1907206875418068e-05,
+      "loss": 0.0165,
+      "step": 2940
+    },
+    {
+      "epoch": 5.042735042735043,
+      "grad_norm": 0.16508907079696655,
+      "learning_rate": 1.1810198747342769e-05,
+      "loss": 0.0186,
+      "step": 2950
+    },
+    {
+      "epoch": 5.05982905982906,
+      "grad_norm": 0.09363128989934921,
+      "learning_rate": 1.1713330151507786e-05,
+      "loss": 0.0145,
+      "step": 2960
+    },
+    {
+      "epoch": 5.076923076923077,
+      "grad_norm": 0.1175096333026886,
+      "learning_rate": 1.161660532525931e-05,
+      "loss": 0.016,
+      "step": 2970
+    },
+    {
+      "epoch": 5.094017094017094,
+      "grad_norm": 0.18064428865909576,
+      "learning_rate": 1.1520028499654584e-05,
+      "loss": 0.0147,
+      "step": 2980
+    },
+    {
+      "epoch": 5.111111111111111,
+      "grad_norm": 0.12403568625450134,
+      "learning_rate": 1.1423603899276833e-05,
+      "loss": 0.0144,
+      "step": 2990
+    },
+    {
+      "epoch": 5.128205128205128,
+      "grad_norm": 0.2672509551048279,
+      "learning_rate": 1.1327335742050442e-05,
+      "loss": 0.016,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 5001,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d7d8c2b55704776186a9207b3175b6c657758e2
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9945eca28b94cc6398098b3d2092b0e9731d322853d46197bf3dc7a37a961
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1d93236e4cee0aefeb72f31db126775dbbdfed27
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ed3ffe024dd151c65eb826083fb58083fbf503901ac040459c44795fb46581
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a813454ca4a280691bc14cf0081f796f9a32d972
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e782ba28ffec111c690d45ea5de37d10ecd8f620fb09fe4c2cd13af5b48280cf
+size 1611553483
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7ab2651de11d93cbb7e9297d7dc82bdac5fe7b0a
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0361e2999e6ebf69b5475734034a7149e063bab21bdd95d90fc2dfbb338e183b
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cddb85352b4d053450624108786800cbad81d6cb
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19ead5779e3f8f2f666b7793de3a03d118f57f1b16a97eeb87bd732d18b445
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d7d8c2b55704776186a9207b3175b6c657758e2
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9945eca28b94cc6398098b3d2092b0e9731d322853d46197bf3dc7a37a961
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ad23f822179be016205e24642dd0a21e2f46bd10
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1dec183be61a7220ef7fbc977014048a32937727e79c4f53fe87e51f55c501
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..50a07874a062b718e61a6fced19da2cd90cfd79b
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fab13009f758f13dd77c3e421b19cf2d786fe6cd5f53b4bb933b0fd2b590646
+size 1611553483
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4292a0bb221a1ccecc95e7643a714422ce410fdc
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95aba6d3c422dbe8f91558805ce751e5b729ef084ba799ab6c9b4c54fe1909b6
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de4e41c4a6949df056e028b10a18e7f8cd7b7580
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed0/default/train_5shot_seed0_processingline_5k/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d8e6d8e53e6b837084d0cc18fdd63ca9e40bd44a65d38eb52695647a8e84e8
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d7d8c2b55704776186a9207b3175b6c657758e2
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9945eca28b94cc6398098b3d2092b0e9731d322853d46197bf3dc7a37a961
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c5700f81b65ec64f598218188c112ab8f0c0a796
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea0feb4370ead7ff6a1292f2b5b76b75b9bbf47d41217d0bb9153083155c519c
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6f51d722f034ef9a3efa3b0f5c43211f0df9a741
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe8dc32b58c9a7cca09ab98dc8a9496590c91fb253bd427730f5c777947767a5
+size 1611553483
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c3bc0114e506cb9b7bd95e8569a03664b50c56c1
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf069f5fedea3ab3661db622f74100ee36e8720ca863c22f605ab72516e926a
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cddb85352b4d053450624108786800cbad81d6cb
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19ead5779e3f8f2f666b7793de3a03d118f57f1b16a97eeb87bd732d18b445
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d7d8c2b55704776186a9207b3175b6c657758e2
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9945eca28b94cc6398098b3d2092b0e9731d322853d46197bf3dc7a37a961
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..17e6e20eea1ca5f20d127c1aabba433dcf0c4530
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35690d0a7b35fc9bf9994933b5ddd35c3b2ec1277fc08c55c2d5997d4ca60647
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..82229aff5095243e41ef5096beafb9df7b538a01
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cccb383db7888edafa0c3dec43a9ac0c2ced854bafd5c06fbbf2a250221906ff
+size 1611553483
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..476a1ba3489c2854c977d6e591eb72947d1b738e
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b563ac52d5d556cd1b95161c1c1ceefc4a5995cfd3578a5353e4cfe503037016
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de4e41c4a6949df056e028b10a18e7f8cd7b7580
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed1/default/train_5shot_seed1_processingline_5k/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d8e6d8e53e6b837084d0cc18fdd63ca9e40bd44a65d38eb52695647a8e84e8
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d7d8c2b55704776186a9207b3175b6c657758e2
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9945eca28b94cc6398098b3d2092b0e9731d322853d46197bf3dc7a37a961
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1a255ec2934169841d7b491c663fe09b1a5d8431
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f64d79fc19cd064e69f42794d11aad798e22e1d595155d41cf4a3c6f532b183
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b9323e9937811c092d56ba36059494de234c2bcc
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e1dab197b74ba01df13da1df784cd2e1749fa73174e996755137c05b3a2b03
+size 1611553483
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a0f789070535eecbdb1f27ae8fb8dd3481e11162
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751cde7cc46354adab4f2955eed24efe2246f8098963c9a16d0191890b358db6
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cddb85352b4d053450624108786800cbad81d6cb
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e19ead5779e3f8f2f666b7793de3a03d118f57f1b16a97eeb87bd732d18b445
+size 1465
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4d7d8c2b55704776186a9207b3175b6c657758e2
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc9945eca28b94cc6398098b3d2092b0e9731d322853d46197bf3dc7a37a961
+size 4999367032
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3b1ebf8749966ed46a543d00865f059dd35bc7af
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6914ee9b43e3b405e401a7da867162165936d13b585abe7e5ccde2e020e577f0
+size 2586705312
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/optimizer.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c66adba49194e213fbd78dca3c6ad1e24530a016
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba9070ee51f235c622f059766b1362feb11f41cb1892540abd39a69f923256f
+size 1611553483
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/rng_state.pth b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b31a765d3f88382c24966eca6ea9ef1e468749bd
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a77424afdeb2eef2c3455112a627a61db42a05fbbe5a95409ea0d24fd5986784
+size 14645
diff --git a/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/scheduler.pt b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..de4e41c4a6949df056e028b10a18e7f8cd7b7580
--- /dev/null
+++ b/FewShot/39tasks/5shot/FromBaseline26_Processingline_5k/seed2/default/train_5shot_seed2_processingline_5k/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d8e6d8e53e6b837084d0cc18fdd63ca9e40bd44a65d38eb52695647a8e84e8
+size 1465