Hugging Face's logo

Weke
/
gr00t-piper

Safetensors
gr00t_n1
Model card Files
xet
 Community
Weke commited on
Commit
7df92c7
·
verified ·
1 Parent(s): 7c05343

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +65 -0
  2. experiment_cfg/metadata.json +143 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +809 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. trainer_state.json +1433 -0
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--nvidia--GR00T-N1-2B/snapshots/fc879581ca32f4f6d6e02cf0cc80452f6b0c3873",
3
+ "action_dim": 32,
4
+ "action_head_cfg": {
5
+ "action_dim": 32,
6
+ "action_horizon": 16,
7
+ "add_pos_embed": true,
8
+ "diffusion_model_cfg": {
9
+ "attention_head_dim": 48,
10
+ "dropout": 0.2,
11
+ "final_dropout": true,
12
+ "interleave_self_attention": true,
13
+ "norm_type": "ada_norm",
14
+ "num_attention_heads": 32,
15
+ "num_layers": 16,
16
+ "output_dim": 1024,
17
+ "positional_embeddings": null
18
+ },
19
+ "freeze_decode_layer": false,
20
+ "hidden_size": 1024,
21
+ "input_embedding_dim": 1536,
22
+ "load_pretrained_det_decode_layer_path": null,
23
+ "max_action_dim": 32,
24
+ "max_state_dim": 64,
25
+ "model_dtype": "float32",
26
+ "noise_beta_alpha": 1.5,
27
+ "noise_beta_beta": 1.0,
28
+ "noise_s": 0.999,
29
+ "num_inference_timesteps": 16,
30
+ "num_timestep_buckets": 1000,
31
+ "tune_diffusion_model": true,
32
+ "tune_projector": true
33
+ },
34
+ "action_horizon": 16,
35
+ "architectures": [
36
+ "GR00T_N1"
37
+ ],
38
+ "attn_implementation": null,
39
+ "backbone_cfg": {
40
+ "allow_reshape_visual": true,
41
+ "load_pretrained_det_eagle_path": null,
42
+ "model_name": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
43
+ "processor_cfg": {
44
+ "max_input_tiles": 1,
45
+ "model_path": "$GR00T_BACKBONE_PATH/eagle2_hg_model",
46
+ "model_spec": {
47
+ "num_image_token": 64,
48
+ "template": "qwen2-chat"
49
+ }
50
+ },
51
+ "projector_dim": 2048,
52
+ "remove_llm": false,
53
+ "reproject_vision": false,
54
+ "scale_image_resolution": 1,
55
+ "select_layer": 12,
56
+ "tune_llm": false,
57
+ "tune_visual": true
58
+ },
59
+ "compute_dtype": "bfloat16",
60
+ "hidden_size": 1536,
61
+ "model_dtype": "float32",
62
+ "model_type": "gr00t_n1",
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.45.2"
65
+ }
experiment_cfg/metadata.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "new_embodiment": {
3
+ "statistics": {
4
+ "state": {
5
+ "joint_pos": {
6
+ "max": [
7
+ 24567.0,
8
+ 97813.0,
9
+ 646.0,
10
+ 99853.0,
11
+ 37833.0,
12
+ 3280.0
13
+ ],
14
+ "min": [
15
+ -35600.0,
16
+ -525.0,
17
+ -41604.0,
18
+ -16863.0,
19
+ -56137.0,
20
+ -106680.0
21
+ ],
22
+ "mean": [
23
+ -147.70492553710938,
24
+ 48371.5390625,
25
+ -13737.5634765625,
26
+ 3305.83837890625,
27
+ -971.80859375,
28
+ -8693.7783203125
29
+ ],
30
+ "std": [
31
+ 14448.701171875,
32
+ 36961.66015625,
33
+ 11591.15625,
34
+ 11364.8828125,
35
+ 22761.443359375,
36
+ 10902.580078125
37
+ ],
38
+ "q01": [
39
+ -31048.0,
40
+ -525.0,
41
+ -38662.0,
42
+ -8778.63,
43
+ -51088.66,
44
+ -68948.66
45
+ ],
46
+ "q99": [
47
+ 17969.0,
48
+ 97467.0,
49
+ 646.0,
50
+ 71405.79999999971,
51
+ 25736.0,
52
+ 687.0
53
+ ]
54
+ }
55
+ },
56
+ "action": {
57
+ "joint_action": {
58
+ "max": [
59
+ 24869.0,
60
+ 98524.0,
61
+ 0.0,
62
+ 100000.0,
63
+ 37944.0,
64
+ 3504.0
65
+ ],
66
+ "min": [
67
+ -36039.0,
68
+ 0.0,
69
+ -41956.0,
70
+ -17273.0,
71
+ -57695.0,
72
+ -107253.0
73
+ ],
74
+ "mean": [
75
+ -91.72042083740234,
76
+ 48285.359375,
77
+ -13895.6083984375,
78
+ 3007.5546875,
79
+ -1808.1285400390625,
80
+ -8513.0146484375
81
+ ],
82
+ "std": [
83
+ 14533.5576171875,
84
+ 36949.78515625,
85
+ 11593.962890625,
86
+ 11389.94921875,
87
+ 22612.578125,
88
+ 10947.2470703125
89
+ ],
90
+ "q01": [
91
+ -31584.0,
92
+ 0.0,
93
+ -39036.0,
94
+ -8706.0,
95
+ -51559.0,
96
+ -67608.56
97
+ ],
98
+ "q99": [
99
+ 18224.0,
100
+ 97612.51999999999,
101
+ 0.0,
102
+ 71451.87999999942,
103
+ 25045.0,
104
+ 608.0
105
+ ]
106
+ }
107
+ }
108
+ },
109
+ "modalities": {
110
+ "video": {
111
+ "ego_view": {
112
+ "resolution": [
113
+ 848,
114
+ 480
115
+ ],
116
+ "channels": 3,
117
+ "fps": 30.0
118
+ }
119
+ },
120
+ "state": {
121
+ "joint_pos": {
122
+ "absolute": true,
123
+ "rotation_type": null,
124
+ "shape": [
125
+ 6
126
+ ],
127
+ "continuous": true
128
+ }
129
+ },
130
+ "action": {
131
+ "joint_action": {
132
+ "absolute": true,
133
+ "rotation_type": null,
134
+ "shape": [
135
+ 6
136
+ ],
137
+ "continuous": true
138
+ }
139
+ }
140
+ },
141
+ "embodiment_tag": "new_embodiment"
142
+ }
143
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29fc8615c20c90bad0b8a50d05ebdfc7a9981f1e245a0dc019c6b651a029429a
3
+ size 4938446392
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43836dd6aa53cdcdf31d0a052ba85554a0de73a8243638a6fffe12442901ee92
3
+ size 3821736024
model.safetensors.index.json ADDED
@@ -0,0 +1,809 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8760067008
4
+ },
5
+ "weight_map": {
6
+ "action_head.action_decoder.layer1.W": "model-00002-of-00002.safetensors",
7
+ "action_head.action_decoder.layer1.b": "model-00002-of-00002.safetensors",
8
+ "action_head.action_decoder.layer2.W": "model-00002-of-00002.safetensors",
9
+ "action_head.action_decoder.layer2.b": "model-00002-of-00002.safetensors",
10
+ "action_head.action_encoder.W1.W": "model-00002-of-00002.safetensors",
11
+ "action_head.action_encoder.W1.b": "model-00002-of-00002.safetensors",
12
+ "action_head.action_encoder.W2.W": "model-00002-of-00002.safetensors",
13
+ "action_head.action_encoder.W2.b": "model-00002-of-00002.safetensors",
14
+ "action_head.action_encoder.W3.W": "model-00002-of-00002.safetensors",
15
+ "action_head.action_encoder.W3.b": "model-00002-of-00002.safetensors",
16
+ "action_head.model.proj_out_1.bias": "model-00002-of-00002.safetensors",
17
+ "action_head.model.proj_out_1.weight": "model-00002-of-00002.safetensors",
18
+ "action_head.model.proj_out_2.bias": "model-00002-of-00002.safetensors",
19
+ "action_head.model.proj_out_2.weight": "model-00002-of-00002.safetensors",
20
+ "action_head.model.timestep_encoder.timestep_embedder.linear_1.bias": "model-00002-of-00002.safetensors",
21
+ "action_head.model.timestep_encoder.timestep_embedder.linear_1.weight": "model-00002-of-00002.safetensors",
22
+ "action_head.model.timestep_encoder.timestep_embedder.linear_2.bias": "model-00002-of-00002.safetensors",
23
+ "action_head.model.timestep_encoder.timestep_embedder.linear_2.weight": "model-00002-of-00002.safetensors",
24
+ "action_head.model.transformer_blocks.0.attn1.to_k.bias": "model-00002-of-00002.safetensors",
25
+ "action_head.model.transformer_blocks.0.attn1.to_k.weight": "model-00002-of-00002.safetensors",
26
+ "action_head.model.transformer_blocks.0.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
27
+ "action_head.model.transformer_blocks.0.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
28
+ "action_head.model.transformer_blocks.0.attn1.to_q.bias": "model-00002-of-00002.safetensors",
29
+ "action_head.model.transformer_blocks.0.attn1.to_q.weight": "model-00002-of-00002.safetensors",
30
+ "action_head.model.transformer_blocks.0.attn1.to_v.bias": "model-00002-of-00002.safetensors",
31
+ "action_head.model.transformer_blocks.0.attn1.to_v.weight": "model-00002-of-00002.safetensors",
32
+ "action_head.model.transformer_blocks.0.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
33
+ "action_head.model.transformer_blocks.0.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
34
+ "action_head.model.transformer_blocks.0.ff.net.2.bias": "model-00002-of-00002.safetensors",
35
+ "action_head.model.transformer_blocks.0.ff.net.2.weight": "model-00002-of-00002.safetensors",
36
+ "action_head.model.transformer_blocks.0.norm1.linear.bias": "model-00002-of-00002.safetensors",
37
+ "action_head.model.transformer_blocks.0.norm1.linear.weight": "model-00002-of-00002.safetensors",
38
+ "action_head.model.transformer_blocks.1.attn1.to_k.bias": "model-00002-of-00002.safetensors",
39
+ "action_head.model.transformer_blocks.1.attn1.to_k.weight": "model-00002-of-00002.safetensors",
40
+ "action_head.model.transformer_blocks.1.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
41
+ "action_head.model.transformer_blocks.1.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
42
+ "action_head.model.transformer_blocks.1.attn1.to_q.bias": "model-00002-of-00002.safetensors",
43
+ "action_head.model.transformer_blocks.1.attn1.to_q.weight": "model-00002-of-00002.safetensors",
44
+ "action_head.model.transformer_blocks.1.attn1.to_v.bias": "model-00002-of-00002.safetensors",
45
+ "action_head.model.transformer_blocks.1.attn1.to_v.weight": "model-00002-of-00002.safetensors",
46
+ "action_head.model.transformer_blocks.1.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
47
+ "action_head.model.transformer_blocks.1.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
48
+ "action_head.model.transformer_blocks.1.ff.net.2.bias": "model-00002-of-00002.safetensors",
49
+ "action_head.model.transformer_blocks.1.ff.net.2.weight": "model-00002-of-00002.safetensors",
50
+ "action_head.model.transformer_blocks.1.norm1.linear.bias": "model-00002-of-00002.safetensors",
51
+ "action_head.model.transformer_blocks.1.norm1.linear.weight": "model-00002-of-00002.safetensors",
52
+ "action_head.model.transformer_blocks.10.attn1.to_k.bias": "model-00002-of-00002.safetensors",
53
+ "action_head.model.transformer_blocks.10.attn1.to_k.weight": "model-00002-of-00002.safetensors",
54
+ "action_head.model.transformer_blocks.10.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
55
+ "action_head.model.transformer_blocks.10.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
56
+ "action_head.model.transformer_blocks.10.attn1.to_q.bias": "model-00002-of-00002.safetensors",
57
+ "action_head.model.transformer_blocks.10.attn1.to_q.weight": "model-00002-of-00002.safetensors",
58
+ "action_head.model.transformer_blocks.10.attn1.to_v.bias": "model-00002-of-00002.safetensors",
59
+ "action_head.model.transformer_blocks.10.attn1.to_v.weight": "model-00002-of-00002.safetensors",
60
+ "action_head.model.transformer_blocks.10.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
61
+ "action_head.model.transformer_blocks.10.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
62
+ "action_head.model.transformer_blocks.10.ff.net.2.bias": "model-00002-of-00002.safetensors",
63
+ "action_head.model.transformer_blocks.10.ff.net.2.weight": "model-00002-of-00002.safetensors",
64
+ "action_head.model.transformer_blocks.10.norm1.linear.bias": "model-00002-of-00002.safetensors",
65
+ "action_head.model.transformer_blocks.10.norm1.linear.weight": "model-00002-of-00002.safetensors",
66
+ "action_head.model.transformer_blocks.11.attn1.to_k.bias": "model-00002-of-00002.safetensors",
67
+ "action_head.model.transformer_blocks.11.attn1.to_k.weight": "model-00002-of-00002.safetensors",
68
+ "action_head.model.transformer_blocks.11.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
69
+ "action_head.model.transformer_blocks.11.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
70
+ "action_head.model.transformer_blocks.11.attn1.to_q.bias": "model-00002-of-00002.safetensors",
71
+ "action_head.model.transformer_blocks.11.attn1.to_q.weight": "model-00002-of-00002.safetensors",
72
+ "action_head.model.transformer_blocks.11.attn1.to_v.bias": "model-00002-of-00002.safetensors",
73
+ "action_head.model.transformer_blocks.11.attn1.to_v.weight": "model-00002-of-00002.safetensors",
74
+ "action_head.model.transformer_blocks.11.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
75
+ "action_head.model.transformer_blocks.11.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
76
+ "action_head.model.transformer_blocks.11.ff.net.2.bias": "model-00002-of-00002.safetensors",
77
+ "action_head.model.transformer_blocks.11.ff.net.2.weight": "model-00002-of-00002.safetensors",
78
+ "action_head.model.transformer_blocks.11.norm1.linear.bias": "model-00002-of-00002.safetensors",
79
+ "action_head.model.transformer_blocks.11.norm1.linear.weight": "model-00002-of-00002.safetensors",
80
+ "action_head.model.transformer_blocks.12.attn1.to_k.bias": "model-00002-of-00002.safetensors",
81
+ "action_head.model.transformer_blocks.12.attn1.to_k.weight": "model-00002-of-00002.safetensors",
82
+ "action_head.model.transformer_blocks.12.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
83
+ "action_head.model.transformer_blocks.12.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
84
+ "action_head.model.transformer_blocks.12.attn1.to_q.bias": "model-00002-of-00002.safetensors",
85
+ "action_head.model.transformer_blocks.12.attn1.to_q.weight": "model-00002-of-00002.safetensors",
86
+ "action_head.model.transformer_blocks.12.attn1.to_v.bias": "model-00002-of-00002.safetensors",
87
+ "action_head.model.transformer_blocks.12.attn1.to_v.weight": "model-00002-of-00002.safetensors",
88
+ "action_head.model.transformer_blocks.12.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
89
+ "action_head.model.transformer_blocks.12.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
90
+ "action_head.model.transformer_blocks.12.ff.net.2.bias": "model-00002-of-00002.safetensors",
91
+ "action_head.model.transformer_blocks.12.ff.net.2.weight": "model-00002-of-00002.safetensors",
92
+ "action_head.model.transformer_blocks.12.norm1.linear.bias": "model-00002-of-00002.safetensors",
93
+ "action_head.model.transformer_blocks.12.norm1.linear.weight": "model-00002-of-00002.safetensors",
94
+ "action_head.model.transformer_blocks.13.attn1.to_k.bias": "model-00002-of-00002.safetensors",
95
+ "action_head.model.transformer_blocks.13.attn1.to_k.weight": "model-00002-of-00002.safetensors",
96
+ "action_head.model.transformer_blocks.13.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
97
+ "action_head.model.transformer_blocks.13.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
98
+ "action_head.model.transformer_blocks.13.attn1.to_q.bias": "model-00002-of-00002.safetensors",
99
+ "action_head.model.transformer_blocks.13.attn1.to_q.weight": "model-00002-of-00002.safetensors",
100
+ "action_head.model.transformer_blocks.13.attn1.to_v.bias": "model-00002-of-00002.safetensors",
101
+ "action_head.model.transformer_blocks.13.attn1.to_v.weight": "model-00002-of-00002.safetensors",
102
+ "action_head.model.transformer_blocks.13.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
103
+ "action_head.model.transformer_blocks.13.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
104
+ "action_head.model.transformer_blocks.13.ff.net.2.bias": "model-00002-of-00002.safetensors",
105
+ "action_head.model.transformer_blocks.13.ff.net.2.weight": "model-00002-of-00002.safetensors",
106
+ "action_head.model.transformer_blocks.13.norm1.linear.bias": "model-00002-of-00002.safetensors",
107
+ "action_head.model.transformer_blocks.13.norm1.linear.weight": "model-00002-of-00002.safetensors",
108
+ "action_head.model.transformer_blocks.14.attn1.to_k.bias": "model-00002-of-00002.safetensors",
109
+ "action_head.model.transformer_blocks.14.attn1.to_k.weight": "model-00002-of-00002.safetensors",
110
+ "action_head.model.transformer_blocks.14.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
111
+ "action_head.model.transformer_blocks.14.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
112
+ "action_head.model.transformer_blocks.14.attn1.to_q.bias": "model-00002-of-00002.safetensors",
113
+ "action_head.model.transformer_blocks.14.attn1.to_q.weight": "model-00002-of-00002.safetensors",
114
+ "action_head.model.transformer_blocks.14.attn1.to_v.bias": "model-00002-of-00002.safetensors",
115
+ "action_head.model.transformer_blocks.14.attn1.to_v.weight": "model-00002-of-00002.safetensors",
116
+ "action_head.model.transformer_blocks.14.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
117
+ "action_head.model.transformer_blocks.14.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
118
+ "action_head.model.transformer_blocks.14.ff.net.2.bias": "model-00002-of-00002.safetensors",
119
+ "action_head.model.transformer_blocks.14.ff.net.2.weight": "model-00002-of-00002.safetensors",
120
+ "action_head.model.transformer_blocks.14.norm1.linear.bias": "model-00002-of-00002.safetensors",
121
+ "action_head.model.transformer_blocks.14.norm1.linear.weight": "model-00002-of-00002.safetensors",
122
+ "action_head.model.transformer_blocks.15.attn1.to_k.bias": "model-00002-of-00002.safetensors",
123
+ "action_head.model.transformer_blocks.15.attn1.to_k.weight": "model-00002-of-00002.safetensors",
124
+ "action_head.model.transformer_blocks.15.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
125
+ "action_head.model.transformer_blocks.15.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
126
+ "action_head.model.transformer_blocks.15.attn1.to_q.bias": "model-00002-of-00002.safetensors",
127
+ "action_head.model.transformer_blocks.15.attn1.to_q.weight": "model-00002-of-00002.safetensors",
128
+ "action_head.model.transformer_blocks.15.attn1.to_v.bias": "model-00002-of-00002.safetensors",
129
+ "action_head.model.transformer_blocks.15.attn1.to_v.weight": "model-00002-of-00002.safetensors",
130
+ "action_head.model.transformer_blocks.15.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
131
+ "action_head.model.transformer_blocks.15.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
132
+ "action_head.model.transformer_blocks.15.ff.net.2.bias": "model-00002-of-00002.safetensors",
133
+ "action_head.model.transformer_blocks.15.ff.net.2.weight": "model-00002-of-00002.safetensors",
134
+ "action_head.model.transformer_blocks.15.norm1.linear.bias": "model-00002-of-00002.safetensors",
135
+ "action_head.model.transformer_blocks.15.norm1.linear.weight": "model-00002-of-00002.safetensors",
136
+ "action_head.model.transformer_blocks.2.attn1.to_k.bias": "model-00002-of-00002.safetensors",
137
+ "action_head.model.transformer_blocks.2.attn1.to_k.weight": "model-00002-of-00002.safetensors",
138
+ "action_head.model.transformer_blocks.2.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
139
+ "action_head.model.transformer_blocks.2.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
140
+ "action_head.model.transformer_blocks.2.attn1.to_q.bias": "model-00002-of-00002.safetensors",
141
+ "action_head.model.transformer_blocks.2.attn1.to_q.weight": "model-00002-of-00002.safetensors",
142
+ "action_head.model.transformer_blocks.2.attn1.to_v.bias": "model-00002-of-00002.safetensors",
143
+ "action_head.model.transformer_blocks.2.attn1.to_v.weight": "model-00002-of-00002.safetensors",
144
+ "action_head.model.transformer_blocks.2.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
145
+ "action_head.model.transformer_blocks.2.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
146
+ "action_head.model.transformer_blocks.2.ff.net.2.bias": "model-00002-of-00002.safetensors",
147
+ "action_head.model.transformer_blocks.2.ff.net.2.weight": "model-00002-of-00002.safetensors",
148
+ "action_head.model.transformer_blocks.2.norm1.linear.bias": "model-00002-of-00002.safetensors",
149
+ "action_head.model.transformer_blocks.2.norm1.linear.weight": "model-00002-of-00002.safetensors",
150
+ "action_head.model.transformer_blocks.3.attn1.to_k.bias": "model-00002-of-00002.safetensors",
151
+ "action_head.model.transformer_blocks.3.attn1.to_k.weight": "model-00002-of-00002.safetensors",
152
+ "action_head.model.transformer_blocks.3.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
153
+ "action_head.model.transformer_blocks.3.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
154
+ "action_head.model.transformer_blocks.3.attn1.to_q.bias": "model-00002-of-00002.safetensors",
155
+ "action_head.model.transformer_blocks.3.attn1.to_q.weight": "model-00002-of-00002.safetensors",
156
+ "action_head.model.transformer_blocks.3.attn1.to_v.bias": "model-00002-of-00002.safetensors",
157
+ "action_head.model.transformer_blocks.3.attn1.to_v.weight": "model-00002-of-00002.safetensors",
158
+ "action_head.model.transformer_blocks.3.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
159
+ "action_head.model.transformer_blocks.3.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
160
+ "action_head.model.transformer_blocks.3.ff.net.2.bias": "model-00002-of-00002.safetensors",
161
+ "action_head.model.transformer_blocks.3.ff.net.2.weight": "model-00002-of-00002.safetensors",
162
+ "action_head.model.transformer_blocks.3.norm1.linear.bias": "model-00002-of-00002.safetensors",
163
+ "action_head.model.transformer_blocks.3.norm1.linear.weight": "model-00002-of-00002.safetensors",
164
+ "action_head.model.transformer_blocks.4.attn1.to_k.bias": "model-00002-of-00002.safetensors",
165
+ "action_head.model.transformer_blocks.4.attn1.to_k.weight": "model-00002-of-00002.safetensors",
166
+ "action_head.model.transformer_blocks.4.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
167
+ "action_head.model.transformer_blocks.4.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
168
+ "action_head.model.transformer_blocks.4.attn1.to_q.bias": "model-00002-of-00002.safetensors",
169
+ "action_head.model.transformer_blocks.4.attn1.to_q.weight": "model-00002-of-00002.safetensors",
170
+ "action_head.model.transformer_blocks.4.attn1.to_v.bias": "model-00002-of-00002.safetensors",
171
+ "action_head.model.transformer_blocks.4.attn1.to_v.weight": "model-00002-of-00002.safetensors",
172
+ "action_head.model.transformer_blocks.4.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
173
+ "action_head.model.transformer_blocks.4.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
174
+ "action_head.model.transformer_blocks.4.ff.net.2.bias": "model-00002-of-00002.safetensors",
175
+ "action_head.model.transformer_blocks.4.ff.net.2.weight": "model-00002-of-00002.safetensors",
176
+ "action_head.model.transformer_blocks.4.norm1.linear.bias": "model-00002-of-00002.safetensors",
177
+ "action_head.model.transformer_blocks.4.norm1.linear.weight": "model-00002-of-00002.safetensors",
178
+ "action_head.model.transformer_blocks.5.attn1.to_k.bias": "model-00002-of-00002.safetensors",
179
+ "action_head.model.transformer_blocks.5.attn1.to_k.weight": "model-00002-of-00002.safetensors",
180
+ "action_head.model.transformer_blocks.5.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
181
+ "action_head.model.transformer_blocks.5.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
182
+ "action_head.model.transformer_blocks.5.attn1.to_q.bias": "model-00002-of-00002.safetensors",
183
+ "action_head.model.transformer_blocks.5.attn1.to_q.weight": "model-00002-of-00002.safetensors",
184
+ "action_head.model.transformer_blocks.5.attn1.to_v.bias": "model-00002-of-00002.safetensors",
185
+ "action_head.model.transformer_blocks.5.attn1.to_v.weight": "model-00002-of-00002.safetensors",
186
+ "action_head.model.transformer_blocks.5.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
187
+ "action_head.model.transformer_blocks.5.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
188
+ "action_head.model.transformer_blocks.5.ff.net.2.bias": "model-00002-of-00002.safetensors",
189
+ "action_head.model.transformer_blocks.5.ff.net.2.weight": "model-00002-of-00002.safetensors",
190
+ "action_head.model.transformer_blocks.5.norm1.linear.bias": "model-00002-of-00002.safetensors",
191
+ "action_head.model.transformer_blocks.5.norm1.linear.weight": "model-00002-of-00002.safetensors",
192
+ "action_head.model.transformer_blocks.6.attn1.to_k.bias": "model-00002-of-00002.safetensors",
193
+ "action_head.model.transformer_blocks.6.attn1.to_k.weight": "model-00002-of-00002.safetensors",
194
+ "action_head.model.transformer_blocks.6.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
195
+ "action_head.model.transformer_blocks.6.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
196
+ "action_head.model.transformer_blocks.6.attn1.to_q.bias": "model-00002-of-00002.safetensors",
197
+ "action_head.model.transformer_blocks.6.attn1.to_q.weight": "model-00002-of-00002.safetensors",
198
+ "action_head.model.transformer_blocks.6.attn1.to_v.bias": "model-00002-of-00002.safetensors",
199
+ "action_head.model.transformer_blocks.6.attn1.to_v.weight": "model-00002-of-00002.safetensors",
200
+ "action_head.model.transformer_blocks.6.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
201
+ "action_head.model.transformer_blocks.6.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
202
+ "action_head.model.transformer_blocks.6.ff.net.2.bias": "model-00002-of-00002.safetensors",
203
+ "action_head.model.transformer_blocks.6.ff.net.2.weight": "model-00002-of-00002.safetensors",
204
+ "action_head.model.transformer_blocks.6.norm1.linear.bias": "model-00002-of-00002.safetensors",
205
+ "action_head.model.transformer_blocks.6.norm1.linear.weight": "model-00002-of-00002.safetensors",
206
+ "action_head.model.transformer_blocks.7.attn1.to_k.bias": "model-00002-of-00002.safetensors",
207
+ "action_head.model.transformer_blocks.7.attn1.to_k.weight": "model-00002-of-00002.safetensors",
208
+ "action_head.model.transformer_blocks.7.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
209
+ "action_head.model.transformer_blocks.7.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
210
+ "action_head.model.transformer_blocks.7.attn1.to_q.bias": "model-00002-of-00002.safetensors",
211
+ "action_head.model.transformer_blocks.7.attn1.to_q.weight": "model-00002-of-00002.safetensors",
212
+ "action_head.model.transformer_blocks.7.attn1.to_v.bias": "model-00002-of-00002.safetensors",
213
+ "action_head.model.transformer_blocks.7.attn1.to_v.weight": "model-00002-of-00002.safetensors",
214
+ "action_head.model.transformer_blocks.7.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
215
+ "action_head.model.transformer_blocks.7.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
216
+ "action_head.model.transformer_blocks.7.ff.net.2.bias": "model-00002-of-00002.safetensors",
217
+ "action_head.model.transformer_blocks.7.ff.net.2.weight": "model-00002-of-00002.safetensors",
218
+ "action_head.model.transformer_blocks.7.norm1.linear.bias": "model-00002-of-00002.safetensors",
219
+ "action_head.model.transformer_blocks.7.norm1.linear.weight": "model-00002-of-00002.safetensors",
220
+ "action_head.model.transformer_blocks.8.attn1.to_k.bias": "model-00002-of-00002.safetensors",
221
+ "action_head.model.transformer_blocks.8.attn1.to_k.weight": "model-00002-of-00002.safetensors",
222
+ "action_head.model.transformer_blocks.8.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
223
+ "action_head.model.transformer_blocks.8.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
224
+ "action_head.model.transformer_blocks.8.attn1.to_q.bias": "model-00002-of-00002.safetensors",
225
+ "action_head.model.transformer_blocks.8.attn1.to_q.weight": "model-00002-of-00002.safetensors",
226
+ "action_head.model.transformer_blocks.8.attn1.to_v.bias": "model-00002-of-00002.safetensors",
227
+ "action_head.model.transformer_blocks.8.attn1.to_v.weight": "model-00002-of-00002.safetensors",
228
+ "action_head.model.transformer_blocks.8.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
229
+ "action_head.model.transformer_blocks.8.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
230
+ "action_head.model.transformer_blocks.8.ff.net.2.bias": "model-00002-of-00002.safetensors",
231
+ "action_head.model.transformer_blocks.8.ff.net.2.weight": "model-00002-of-00002.safetensors",
232
+ "action_head.model.transformer_blocks.8.norm1.linear.bias": "model-00002-of-00002.safetensors",
233
+ "action_head.model.transformer_blocks.8.norm1.linear.weight": "model-00002-of-00002.safetensors",
234
+ "action_head.model.transformer_blocks.9.attn1.to_k.bias": "model-00002-of-00002.safetensors",
235
+ "action_head.model.transformer_blocks.9.attn1.to_k.weight": "model-00002-of-00002.safetensors",
236
+ "action_head.model.transformer_blocks.9.attn1.to_out.0.bias": "model-00002-of-00002.safetensors",
237
+ "action_head.model.transformer_blocks.9.attn1.to_out.0.weight": "model-00002-of-00002.safetensors",
238
+ "action_head.model.transformer_blocks.9.attn1.to_q.bias": "model-00002-of-00002.safetensors",
239
+ "action_head.model.transformer_blocks.9.attn1.to_q.weight": "model-00002-of-00002.safetensors",
240
+ "action_head.model.transformer_blocks.9.attn1.to_v.bias": "model-00002-of-00002.safetensors",
241
+ "action_head.model.transformer_blocks.9.attn1.to_v.weight": "model-00002-of-00002.safetensors",
242
+ "action_head.model.transformer_blocks.9.ff.net.0.proj.bias": "model-00002-of-00002.safetensors",
243
+ "action_head.model.transformer_blocks.9.ff.net.0.proj.weight": "model-00002-of-00002.safetensors",
244
+ "action_head.model.transformer_blocks.9.ff.net.2.bias": "model-00002-of-00002.safetensors",
245
+ "action_head.model.transformer_blocks.9.ff.net.2.weight": "model-00002-of-00002.safetensors",
246
+ "action_head.model.transformer_blocks.9.norm1.linear.bias": "model-00002-of-00002.safetensors",
247
+ "action_head.model.transformer_blocks.9.norm1.linear.weight": "model-00002-of-00002.safetensors",
248
+ "action_head.position_embedding.weight": "model-00002-of-00002.safetensors",
249
+ "action_head.state_encoder.layer1.W": "model-00002-of-00002.safetensors",
250
+ "action_head.state_encoder.layer1.b": "model-00002-of-00002.safetensors",
251
+ "action_head.state_encoder.layer2.W": "model-00002-of-00002.safetensors",
252
+ "action_head.state_encoder.layer2.b": "model-00002-of-00002.safetensors",
253
+ "backbone.linear.bias": "model-00002-of-00002.safetensors",
254
+ "backbone.linear.weight": "model-00002-of-00002.safetensors",
255
+ "backbone.model.language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
256
+ "backbone.model.language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
257
+ "backbone.model.language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
258
+ "backbone.model.language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
259
+ "backbone.model.language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
260
+ "backbone.model.language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "backbone.model.language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
262
+ "backbone.model.language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
263
+ "backbone.model.language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
264
+ "backbone.model.language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
265
+ "backbone.model.language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "backbone.model.language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
267
+ "backbone.model.language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
268
+ "backbone.model.language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
269
+ "backbone.model.language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "backbone.model.language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
271
+ "backbone.model.language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
272
+ "backbone.model.language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
273
+ "backbone.model.language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
274
+ "backbone.model.language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
275
+ "backbone.model.language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
276
+ "backbone.model.language_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
277
+ "backbone.model.language_model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
278
+ "backbone.model.language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
279
+ "backbone.model.language_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
280
+ "backbone.model.language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
281
+ "backbone.model.language_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
282
+ "backbone.model.language_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
283
+ "backbone.model.language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "backbone.model.language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "backbone.model.language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "backbone.model.language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "backbone.model.language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "backbone.model.language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
289
+ "backbone.model.language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
290
+ "backbone.model.language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
291
+ "backbone.model.language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
292
+ "backbone.model.language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
293
+ "backbone.model.language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
294
+ "backbone.model.language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
295
+ "backbone.model.language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
296
+ "backbone.model.language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
297
+ "backbone.model.language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
298
+ "backbone.model.language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
299
+ "backbone.model.language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
300
+ "backbone.model.language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
301
+ "backbone.model.language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
302
+ "backbone.model.language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
303
+ "backbone.model.language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
304
+ "backbone.model.language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
305
+ "backbone.model.language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
306
+ "backbone.model.language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
307
+ "backbone.model.language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
308
+ "backbone.model.language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
309
+ "backbone.model.language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
310
+ "backbone.model.language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
311
+ "backbone.model.language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
312
+ "backbone.model.language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
313
+ "backbone.model.language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
314
+ "backbone.model.language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
315
+ "backbone.model.language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
316
+ "backbone.model.language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
317
+ "backbone.model.language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "backbone.model.language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
319
+ "backbone.model.language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
320
+ "backbone.model.language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
321
+ "backbone.model.language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
322
+ "backbone.model.language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
323
+ "backbone.model.language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
324
+ "backbone.model.language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
325
+ "backbone.model.language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
326
+ "backbone.model.language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
327
+ "backbone.model.language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
328
+ "backbone.model.language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
329
+ "backbone.model.language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
330
+ "backbone.model.language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
331
+ "backbone.model.language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
332
+ "backbone.model.language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
333
+ "backbone.model.language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
334
+ "backbone.model.language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
335
+ "backbone.model.language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
336
+ "backbone.model.language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
337
+ "backbone.model.language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
338
+ "backbone.model.language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
339
+ "backbone.model.language_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
340
+ "backbone.model.language_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
341
+ "backbone.model.language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
342
+ "backbone.model.language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
343
+ "backbone.model.language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
344
+ "backbone.model.language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
345
+ "backbone.model.language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
346
+ "backbone.model.language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
347
+ "backbone.model.language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
348
+ "backbone.model.language_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
349
+ "backbone.model.language_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
350
+ "backbone.model.language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
351
+ "backbone.model.language_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
352
+ "backbone.model.language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
353
+ "backbone.model.language_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
354
+ "backbone.model.language_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
355
+ "backbone.model.language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
356
+ "backbone.model.language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
357
+ "backbone.model.language_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
358
+ "backbone.model.language_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
359
+ "backbone.model.language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
360
+ "backbone.model.language_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
361
+ "backbone.model.language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
362
+ "backbone.model.language_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
363
+ "backbone.model.language_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
364
+ "backbone.model.language_model.model.norm.weight": "model-00002-of-00002.safetensors",
365
+ "backbone.model.mlp1.0.bias": "model-00002-of-00002.safetensors",
366
+ "backbone.model.mlp1.0.weight": "model-00002-of-00002.safetensors",
367
+ "backbone.model.mlp1.1.bias": "model-00002-of-00002.safetensors",
368
+ "backbone.model.mlp1.1.weight": "model-00002-of-00002.safetensors",
369
+ "backbone.model.mlp1.3.bias": "model-00002-of-00002.safetensors",
370
+ "backbone.model.mlp1.3.weight": "model-00002-of-00002.safetensors",
371
+ "backbone.model.vision_model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
372
+ "backbone.model.vision_model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
373
+ "backbone.model.vision_model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
374
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
375
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
376
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
377
+ "backbone.model.vision_model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
378
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
379
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
380
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
381
+ "backbone.model.vision_model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
382
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
383
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
384
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
385
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
386
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
387
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
388
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
389
+ "backbone.model.vision_model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
390
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
391
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
392
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
393
+ "backbone.model.vision_model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
394
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
395
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
396
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
397
+ "backbone.model.vision_model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
398
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
399
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
401
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
402
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
403
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
404
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
405
+ "backbone.model.vision_model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
406
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
407
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
408
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
409
+ "backbone.model.vision_model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
410
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
411
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
412
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
413
+ "backbone.model.vision_model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
414
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
415
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
416
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
417
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
418
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
419
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
420
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
421
+ "backbone.model.vision_model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
422
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
423
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
424
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
425
+ "backbone.model.vision_model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
426
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
427
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
428
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
429
+ "backbone.model.vision_model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
430
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
431
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
432
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
433
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
434
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
435
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
436
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
437
+ "backbone.model.vision_model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
438
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
439
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
440
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
441
+ "backbone.model.vision_model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
442
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
443
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
444
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
445
+ "backbone.model.vision_model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
446
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
447
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
448
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
449
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
450
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
451
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
452
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
453
+ "backbone.model.vision_model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
454
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
455
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
456
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
457
+ "backbone.model.vision_model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
458
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
459
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
460
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
461
+ "backbone.model.vision_model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
462
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
463
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
464
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
465
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
466
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
467
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
468
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
469
+ "backbone.model.vision_model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
470
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
471
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
472
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
473
+ "backbone.model.vision_model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
474
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
475
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
476
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
477
+ "backbone.model.vision_model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
478
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
479
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
480
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
481
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
482
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
483
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
484
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
485
+ "backbone.model.vision_model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
486
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
487
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
488
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
489
+ "backbone.model.vision_model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
490
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
491
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
492
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
493
+ "backbone.model.vision_model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
494
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
495
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
496
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
497
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
498
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
499
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
500
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
501
+ "backbone.model.vision_model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
502
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
503
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
504
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
505
+ "backbone.model.vision_model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
506
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
507
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
508
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
509
+ "backbone.model.vision_model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
510
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
511
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
512
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
513
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
514
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
515
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
516
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
517
+ "backbone.model.vision_model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
518
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
519
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
520
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
521
+ "backbone.model.vision_model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
522
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
523
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
524
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
525
+ "backbone.model.vision_model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
526
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
527
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
528
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
529
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
530
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
531
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
532
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
533
+ "backbone.model.vision_model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
534
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
535
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
536
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
537
+ "backbone.model.vision_model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
538
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
539
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
540
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
541
+ "backbone.model.vision_model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
542
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
543
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
544
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
545
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
546
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
547
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
548
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
549
+ "backbone.model.vision_model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
550
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
551
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
552
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
553
+ "backbone.model.vision_model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
554
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
555
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
556
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
557
+ "backbone.model.vision_model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
558
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
559
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
560
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
561
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
562
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
563
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
564
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
565
+ "backbone.model.vision_model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
566
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
567
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
568
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
569
+ "backbone.model.vision_model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
570
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
571
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
572
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
573
+ "backbone.model.vision_model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
574
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
575
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
576
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
577
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
578
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
579
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
580
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
581
+ "backbone.model.vision_model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
582
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
583
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
584
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
585
+ "backbone.model.vision_model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
586
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
587
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
588
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
589
+ "backbone.model.vision_model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
590
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
591
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
592
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
593
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
594
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
595
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
596
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
597
+ "backbone.model.vision_model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
598
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00002.safetensors",
599
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00002.safetensors",
600
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00002.safetensors",
601
+ "backbone.model.vision_model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00002.safetensors",
602
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
603
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
604
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
605
+ "backbone.model.vision_model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
606
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
607
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
608
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
609
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
610
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
611
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
612
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
613
+ "backbone.model.vision_model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
614
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00002.safetensors",
615
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00002.safetensors",
616
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00002.safetensors",
617
+ "backbone.model.vision_model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00002.safetensors",
618
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
619
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
620
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
621
+ "backbone.model.vision_model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
622
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
623
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
624
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
625
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
626
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
627
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
628
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
629
+ "backbone.model.vision_model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
630
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00002.safetensors",
631
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00002.safetensors",
632
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00002.safetensors",
633
+ "backbone.model.vision_model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00002.safetensors",
634
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
635
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
636
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
637
+ "backbone.model.vision_model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
638
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
639
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
640
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
641
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
642
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
643
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
644
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
645
+ "backbone.model.vision_model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
646
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00002.safetensors",
647
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00002.safetensors",
648
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00002.safetensors",
649
+ "backbone.model.vision_model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00002.safetensors",
650
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
651
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
652
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
653
+ "backbone.model.vision_model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
654
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
655
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
656
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
657
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
658
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
659
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
660
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
661
+ "backbone.model.vision_model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
662
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00002.safetensors",
663
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00002.safetensors",
664
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00002.safetensors",
665
+ "backbone.model.vision_model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00002.safetensors",
666
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
667
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
668
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
669
+ "backbone.model.vision_model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
670
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
671
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
672
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
673
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
674
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
675
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
676
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
677
+ "backbone.model.vision_model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
678
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00002.safetensors",
679
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00002.safetensors",
680
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00002.safetensors",
681
+ "backbone.model.vision_model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00002.safetensors",
682
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
683
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
684
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
685
+ "backbone.model.vision_model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
686
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
687
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
688
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
689
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
690
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
691
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
692
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
693
+ "backbone.model.vision_model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
694
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
695
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
696
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
697
+ "backbone.model.vision_model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
698
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
699
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
700
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
701
+ "backbone.model.vision_model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
702
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
703
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
704
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
705
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
706
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
707
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
708
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
709
+ "backbone.model.vision_model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
710
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
711
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
712
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
713
+ "backbone.model.vision_model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
714
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
715
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
716
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
717
+ "backbone.model.vision_model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
718
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
719
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
720
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
721
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
722
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
723
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
724
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
725
+ "backbone.model.vision_model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
726
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
727
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
728
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
729
+ "backbone.model.vision_model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
730
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
731
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
732
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
733
+ "backbone.model.vision_model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
734
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
735
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
736
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
737
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
738
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
739
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
740
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
741
+ "backbone.model.vision_model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
742
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
743
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
744
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
745
+ "backbone.model.vision_model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
746
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
747
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
748
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
749
+ "backbone.model.vision_model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
750
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
751
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
752
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
753
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
754
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
755
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
756
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
757
+ "backbone.model.vision_model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
758
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
759
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
760
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
761
+ "backbone.model.vision_model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
762
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
763
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
764
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
765
+ "backbone.model.vision_model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
766
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
767
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
768
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
769
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
770
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
771
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
772
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
773
+ "backbone.model.vision_model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
774
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
775
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
776
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
777
+ "backbone.model.vision_model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
778
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
779
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
780
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
781
+ "backbone.model.vision_model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
782
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
783
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
784
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
785
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
786
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
787
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
788
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
789
+ "backbone.model.vision_model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
790
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
791
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
792
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
793
+ "backbone.model.vision_model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
794
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
795
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
796
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
797
+ "backbone.model.vision_model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
798
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
799
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
800
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
801
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
802
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
803
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
804
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
805
+ "backbone.model.vision_model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
806
+ "backbone.model.vision_model.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
807
+ "backbone.model.vision_model.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors"
808
+ }
809
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa2863d539ebf7975893c619cf0dbd2f33d463bdfaa01e1cacb05f45b93fd9d
3
+ size 10272357262
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcab623f074973cbd6845b734d0a38f150e3ccbc19326f2215df46ba28349281
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a1e3232c9dd0558d3b582345b4a537ca2d63d9ae2df7d7189cbdc92c4e384f
3
+ size 1064
trainer_state.json ADDED
@@ -0,0 +1,1433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.545454545454545,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022727272727272728,
13
+ "grad_norm": 864166.375,
14
+ "learning_rate": 1e-05,
15
+ "loss": 935851212.8,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.045454545454545456,
20
+ "grad_norm": 851375.4375,
21
+ "learning_rate": 2e-05,
22
+ "loss": 779824793.6,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06818181818181818,
27
+ "grad_norm": 663149.625,
28
+ "learning_rate": 3e-05,
29
+ "loss": 931242291.2,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.09090909090909091,
34
+ "grad_norm": 578363.8125,
35
+ "learning_rate": 4e-05,
36
+ "loss": 833480396.8,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11363636363636363,
41
+ "grad_norm": 736728.9375,
42
+ "learning_rate": 5e-05,
43
+ "loss": 923433779.2,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.13636363636363635,
48
+ "grad_norm": 582158.875,
49
+ "learning_rate": 6e-05,
50
+ "loss": 779678822.4,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.1590909090909091,
55
+ "grad_norm": 3016550.25,
56
+ "learning_rate": 7e-05,
57
+ "loss": 880521625.6,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.18181818181818182,
62
+ "grad_norm": 16130207.0,
63
+ "learning_rate": 8e-05,
64
+ "loss": 796326297.6,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20454545454545456,
69
+ "grad_norm": 72006536.0,
70
+ "learning_rate": 9e-05,
71
+ "loss": 827050598.4,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.22727272727272727,
76
+ "grad_norm": 115259504.0,
77
+ "learning_rate": 0.0001,
78
+ "loss": 779086131.2,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.25,
83
+ "grad_norm": 35422613504.0,
84
+ "learning_rate": 9.999316524962345e-05,
85
+ "loss": 679432448.0,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2727272727272727,
90
+ "grad_norm": 11170627584.0,
91
+ "learning_rate": 9.997266286704631e-05,
92
+ "loss": 543212544.0,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29545454545454547,
97
+ "grad_norm": 460055968.0,
98
+ "learning_rate": 9.993849845741524e-05,
99
+ "loss": 488552294.4,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.3181818181818182,
104
+ "grad_norm": 643671040.0,
105
+ "learning_rate": 9.989068136093873e-05,
106
+ "loss": 381352115.2,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.3409090909090909,
111
+ "grad_norm": 514593984.0,
112
+ "learning_rate": 9.98292246503335e-05,
113
+ "loss": 344548966.4,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.36363636363636365,
118
+ "grad_norm": 2670534912.0,
119
+ "learning_rate": 9.975414512725057e-05,
120
+ "loss": 256186470.4,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38636363636363635,
125
+ "grad_norm": 367520064.0,
126
+ "learning_rate": 9.966546331768191e-05,
127
+ "loss": 252642892.8,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.4090909090909091,
132
+ "grad_norm": 6415584768.0,
133
+ "learning_rate": 9.956320346634876e-05,
134
+ "loss": 214356454.4,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4318181818181818,
139
+ "grad_norm": 342542784.0,
140
+ "learning_rate": 9.944739353007344e-05,
141
+ "loss": 184521523.2,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.45454545454545453,
146
+ "grad_norm": 670325952.0,
147
+ "learning_rate": 9.931806517013612e-05,
148
+ "loss": 203785408.0,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4772727272727273,
153
+ "grad_norm": 408250880.0,
154
+ "learning_rate": 9.917525374361912e-05,
155
+ "loss": 165584844.8,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.5,
160
+ "grad_norm": 237331648.0,
161
+ "learning_rate": 9.901899829374047e-05,
162
+ "loss": 161461657.6,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5227272727272727,
167
+ "grad_norm": 261846496.0,
168
+ "learning_rate": 9.884934153917997e-05,
169
+ "loss": 232488601.6,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5454545454545454,
174
+ "grad_norm": 258512032.0,
175
+ "learning_rate": 9.86663298624003e-05,
176
+ "loss": 213760076.8,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5681818181818182,
181
+ "grad_norm": 176516288.0,
182
+ "learning_rate": 9.847001329696653e-05,
183
+ "loss": 190539545.6,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5909090909090909,
188
+ "grad_norm": 208952080.0,
189
+ "learning_rate": 9.826044551386744e-05,
190
+ "loss": 160166745.6,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6136363636363636,
195
+ "grad_norm": 444205504.0,
196
+ "learning_rate": 9.803768380684242e-05,
197
+ "loss": 142089868.8,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6363636363636364,
202
+ "grad_norm": 456830976.0,
203
+ "learning_rate": 9.780178907671789e-05,
204
+ "loss": 164681638.4,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6590909090909091,
209
+ "grad_norm": 240448720.0,
210
+ "learning_rate": 9.755282581475769e-05,
211
+ "loss": 126908902.4,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6818181818181818,
216
+ "grad_norm": 289517440.0,
217
+ "learning_rate": 9.729086208503174e-05,
218
+ "loss": 144903500.8,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.7045454545454546,
223
+ "grad_norm": 155611392.0,
224
+ "learning_rate": 9.701596950580806e-05,
225
+ "loss": 109276416.0,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7272727272727273,
230
+ "grad_norm": 145763984.0,
231
+ "learning_rate": 9.672822322997305e-05,
232
+ "loss": 82450060.8,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.75,
237
+ "grad_norm": 183422624.0,
238
+ "learning_rate": 9.642770192448536e-05,
239
+ "loss": 94446822.4,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7727272727272727,
244
+ "grad_norm": 165524336.0,
245
+ "learning_rate": 9.611448774886924e-05,
246
+ "loss": 88033280.0,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7954545454545454,
251
+ "grad_norm": 370229248.0,
252
+ "learning_rate": 9.578866633275288e-05,
253
+ "loss": 151451392.0,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8181818181818182,
258
+ "grad_norm": 182722992.0,
259
+ "learning_rate": 9.545032675245813e-05,
260
+ "loss": 81520544.0,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8409090909090909,
265
+ "grad_norm": 110293848.0,
266
+ "learning_rate": 9.509956150664796e-05,
267
+ "loss": 74347558.4,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8636363636363636,
272
+ "grad_norm": 210000608.0,
273
+ "learning_rate": 9.473646649103818e-05,
274
+ "loss": 98096115.2,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8863636363636364,
279
+ "grad_norm": 252706992.0,
280
+ "learning_rate": 9.43611409721806e-05,
281
+ "loss": 45600521.6,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.9090909090909091,
286
+ "grad_norm": 286857856.0,
287
+ "learning_rate": 9.397368756032445e-05,
288
+ "loss": 47684240.0,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9318181818181818,
293
+ "grad_norm": 145927072.0,
294
+ "learning_rate": 9.357421218136386e-05,
295
+ "loss": 55028972.8,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9545454545454546,
300
+ "grad_norm": 246543744.0,
301
+ "learning_rate": 9.316282404787871e-05,
302
+ "loss": 62455718.4,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9772727272727273,
307
+ "grad_norm": 148089840.0,
308
+ "learning_rate": 9.273963562927695e-05,
309
+ "loss": 80031763.2,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 1.0,
314
+ "grad_norm": 258538496.0,
315
+ "learning_rate": 9.230476262104677e-05,
316
+ "loss": 63331763.2,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 1.0227272727272727,
321
+ "grad_norm": 246891264.0,
322
+ "learning_rate": 9.185832391312644e-05,
323
+ "loss": 79613408.0,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 1.0454545454545454,
328
+ "grad_norm": 99700408.0,
329
+ "learning_rate": 9.140044155740101e-05,
330
+ "loss": 60524844.8,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 1.0681818181818181,
335
+ "grad_norm": 269340576.0,
336
+ "learning_rate": 9.093124073433463e-05,
337
+ "loss": 53263574.4,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.0909090909090908,
342
+ "grad_norm": 152498880.0,
343
+ "learning_rate": 9.045084971874738e-05,
344
+ "loss": 37747696.0,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.1136363636363635,
349
+ "grad_norm": 405291296.0,
350
+ "learning_rate": 8.995939984474624e-05,
351
+ "loss": 83147424.0,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.1363636363636362,
356
+ "grad_norm": 153301696.0,
357
+ "learning_rate": 8.945702546981969e-05,
358
+ "loss": 46162393.6,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.1590909090909092,
363
+ "grad_norm": 386725408.0,
364
+ "learning_rate": 8.894386393810563e-05,
365
+ "loss": 57197043.2,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 1.1818181818181819,
370
+ "grad_norm": 112014240.0,
371
+ "learning_rate": 8.842005554284296e-05,
372
+ "loss": 44577619.2,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 1.2045454545454546,
377
+ "grad_norm": 198261360.0,
378
+ "learning_rate": 8.788574348801675e-05,
379
+ "loss": 49147491.2,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 1.2272727272727273,
384
+ "grad_norm": 127353744.0,
385
+ "learning_rate": 8.73410738492077e-05,
386
+ "loss": 30261772.8,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 1.25,
391
+ "grad_norm": 182823824.0,
392
+ "learning_rate": 8.678619553365659e-05,
393
+ "loss": 48019424.0,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 1.2727272727272727,
398
+ "grad_norm": 286290624.0,
399
+ "learning_rate": 8.622126023955446e-05,
400
+ "loss": 60011494.4,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 1.2954545454545454,
405
+ "grad_norm": 78245984.0,
406
+ "learning_rate": 8.564642241456986e-05,
407
+ "loss": 47857244.8,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 1.3181818181818181,
412
+ "grad_norm": 408751168.0,
413
+ "learning_rate": 8.506183921362443e-05,
414
+ "loss": 70248691.2,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 1.3409090909090908,
419
+ "grad_norm": 113171200.0,
420
+ "learning_rate": 8.44676704559283e-05,
421
+ "loss": 53175008.0,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 1.3636363636363638,
426
+ "grad_norm": 201525456.0,
427
+ "learning_rate": 8.386407858128706e-05,
428
+ "loss": 33759475.2,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 1.3863636363636362,
433
+ "grad_norm": 697200320.0,
434
+ "learning_rate": 8.32512286056924e-05,
435
+ "loss": 32540745.6,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 1.4090909090909092,
440
+ "grad_norm": 336322880.0,
441
+ "learning_rate": 8.262928807620843e-05,
442
+ "loss": 48147216.0,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 1.4318181818181819,
447
+ "grad_norm": 132475312.0,
448
+ "learning_rate": 8.199842702516583e-05,
449
+ "loss": 37222713.6,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 1.4545454545454546,
454
+ "grad_norm": 401426752.0,
455
+ "learning_rate": 8.135881792367686e-05,
456
+ "loss": 31534899.2,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 1.4772727272727273,
461
+ "grad_norm": 208541024.0,
462
+ "learning_rate": 8.07106356344834e-05,
463
+ "loss": 25690548.8,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 1.5,
468
+ "grad_norm": 116395000.0,
469
+ "learning_rate": 8.005405736415126e-05,
470
+ "loss": 35130710.4,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 1.5227272727272727,
475
+ "grad_norm": 221156224.0,
476
+ "learning_rate": 7.938926261462366e-05,
477
+ "loss": 52561321.6,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 1.5454545454545454,
482
+ "grad_norm": 139324544.0,
483
+ "learning_rate": 7.871643313414718e-05,
484
+ "loss": 46616777.6,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 1.5681818181818183,
489
+ "grad_norm": 126530176.0,
490
+ "learning_rate": 7.803575286758364e-05,
491
+ "loss": 32868204.8,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 1.5909090909090908,
496
+ "grad_norm": 112456576.0,
497
+ "learning_rate": 7.734740790612136e-05,
498
+ "loss": 42719804.8,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 1.6136363636363638,
503
+ "grad_norm": 178001280.0,
504
+ "learning_rate": 7.66515864363997e-05,
505
+ "loss": 56040908.8,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 1.6363636363636362,
510
+ "grad_norm": 408028640.0,
511
+ "learning_rate": 7.594847868906076e-05,
512
+ "loss": 27305916.8,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 1.6590909090909092,
517
+ "grad_norm": 146312144.0,
518
+ "learning_rate": 7.52382768867422e-05,
519
+ "loss": 34246518.4,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 1.6818181818181817,
524
+ "grad_norm": 121166176.0,
525
+ "learning_rate": 7.452117519152542e-05,
526
+ "loss": 34342003.2,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 1.7045454545454546,
531
+ "grad_norm": 1605302144.0,
532
+ "learning_rate": 7.379736965185368e-05,
533
+ "loss": 18556844.8,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.7272727272727273,
538
+ "grad_norm": 145793296.0,
539
+ "learning_rate": 7.30670581489344e-05,
540
+ "loss": 30094729.6,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 1.75,
545
+ "grad_norm": 238633424.0,
546
+ "learning_rate": 7.233044034264034e-05,
547
+ "loss": 28264518.4,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 1.7727272727272727,
552
+ "grad_norm": 146943280.0,
553
+ "learning_rate": 7.158771761692464e-05,
554
+ "loss": 21468862.4,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 1.7954545454545454,
559
+ "grad_norm": 155326464.0,
560
+ "learning_rate": 7.083909302476453e-05,
561
+ "loss": 24784724.8,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 1.8181818181818183,
566
+ "grad_norm": 194690608.0,
567
+ "learning_rate": 7.008477123264848e-05,
568
+ "loss": 20140659.2,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.8409090909090908,
573
+ "grad_norm": 269470976.0,
574
+ "learning_rate": 6.932495846462261e-05,
575
+ "loss": 32951574.4,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.8636363636363638,
580
+ "grad_norm": 170968176.0,
581
+ "learning_rate": 6.855986244591104e-05,
582
+ "loss": 24495520.0,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.8863636363636362,
587
+ "grad_norm": 137592768.0,
588
+ "learning_rate": 6.778969234612584e-05,
589
+ "loss": 21688649.6,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.9090909090909092,
594
+ "grad_norm": 77953224.0,
595
+ "learning_rate": 6.701465872208216e-05,
596
+ "loss": 31676636.8,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.9318181818181817,
601
+ "grad_norm": 455976896.0,
602
+ "learning_rate": 6.623497346023418e-05,
603
+ "loss": 47546489.6,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.9545454545454546,
608
+ "grad_norm": 461556352.0,
609
+ "learning_rate": 6.545084971874738e-05,
610
+ "loss": 26543750.4,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.9772727272727273,
615
+ "grad_norm": 342992832.0,
616
+ "learning_rate": 6.466250186922325e-05,
617
+ "loss": 23164931.2,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 2.0,
622
+ "grad_norm": 176021600.0,
623
+ "learning_rate": 6.387014543809223e-05,
624
+ "loss": 24812347.2,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 2.022727272727273,
629
+ "grad_norm": 168301712.0,
630
+ "learning_rate": 6.307399704769099e-05,
631
+ "loss": 29569001.6,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 2.0454545454545454,
636
+ "grad_norm": 170714448.0,
637
+ "learning_rate": 6.227427435703997e-05,
638
+ "loss": 24018566.4,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 2.0681818181818183,
643
+ "grad_norm": 260947392.0,
644
+ "learning_rate": 6.147119600233758e-05,
645
+ "loss": 26362905.6,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 2.090909090909091,
650
+ "grad_norm": 82909696.0,
651
+ "learning_rate": 6.066498153718735e-05,
652
+ "loss": 20936886.4,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 2.1136363636363638,
657
+ "grad_norm": 152754880.0,
658
+ "learning_rate": 5.985585137257401e-05,
659
+ "loss": 22602596.8,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 2.1363636363636362,
664
+ "grad_norm": 71488880.0,
665
+ "learning_rate": 5.90440267166055e-05,
666
+ "loss": 36498016.0,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 2.159090909090909,
671
+ "grad_norm": 104700112.0,
672
+ "learning_rate": 5.8229729514036705e-05,
673
+ "loss": 30277987.2,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 2.1818181818181817,
678
+ "grad_norm": 184239504.0,
679
+ "learning_rate": 5.74131823855921e-05,
680
+ "loss": 24437344.0,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 2.2045454545454546,
685
+ "grad_norm": 322096480.0,
686
+ "learning_rate": 5.6594608567103456e-05,
687
+ "loss": 28966016.0,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 2.227272727272727,
692
+ "grad_norm": 107924136.0,
693
+ "learning_rate": 5.577423184847932e-05,
694
+ "loss": 23697406.4,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 2.25,
699
+ "grad_norm": 287611424.0,
700
+ "learning_rate": 5.495227651252315e-05,
701
+ "loss": 35587129.6,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 2.2727272727272725,
706
+ "grad_norm": 142485760.0,
707
+ "learning_rate": 5.4128967273616625e-05,
708
+ "loss": 22553091.2,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 2.2954545454545454,
713
+ "grad_norm": 125698872.0,
714
+ "learning_rate": 5.330452921628497e-05,
715
+ "loss": 21591241.6,
716
+ "step": 1010
717
+ },
718
+ {
719
+ "epoch": 2.3181818181818183,
720
+ "grad_norm": 121039208.0,
721
+ "learning_rate": 5.247918773366112e-05,
722
+ "loss": 29732899.2,
723
+ "step": 1020
724
+ },
725
+ {
726
+ "epoch": 2.340909090909091,
727
+ "grad_norm": 192014624.0,
728
+ "learning_rate": 5.165316846586541e-05,
729
+ "loss": 19519462.4,
730
+ "step": 1030
731
+ },
732
+ {
733
+ "epoch": 2.3636363636363638,
734
+ "grad_norm": 219596560.0,
735
+ "learning_rate": 5.0826697238317935e-05,
736
+ "loss": 25972294.4,
737
+ "step": 1040
738
+ },
739
+ {
740
+ "epoch": 2.3863636363636362,
741
+ "grad_norm": 453196864.0,
742
+ "learning_rate": 5e-05,
743
+ "loss": 20440235.2,
744
+ "step": 1050
745
+ },
746
+ {
747
+ "epoch": 2.409090909090909,
748
+ "grad_norm": 271006016.0,
749
+ "learning_rate": 4.917330276168208e-05,
750
+ "loss": 19903924.8,
751
+ "step": 1060
752
+ },
753
+ {
754
+ "epoch": 2.4318181818181817,
755
+ "grad_norm": 322238688.0,
756
+ "learning_rate": 4.834683153413459e-05,
757
+ "loss": 30931248.0,
758
+ "step": 1070
759
+ },
760
+ {
761
+ "epoch": 2.4545454545454546,
762
+ "grad_norm": 115611168.0,
763
+ "learning_rate": 4.7520812266338885e-05,
764
+ "loss": 20302214.4,
765
+ "step": 1080
766
+ },
767
+ {
768
+ "epoch": 2.4772727272727275,
769
+ "grad_norm": 887404288.0,
770
+ "learning_rate": 4.669547078371504e-05,
771
+ "loss": 19957492.8,
772
+ "step": 1090
773
+ },
774
+ {
775
+ "epoch": 2.5,
776
+ "grad_norm": 10758360064.0,
777
+ "learning_rate": 4.5871032726383386e-05,
778
+ "loss": 22953964.8,
779
+ "step": 1100
780
+ },
781
+ {
782
+ "epoch": 2.5227272727272725,
783
+ "grad_norm": 427750944.0,
784
+ "learning_rate": 4.504772348747687e-05,
785
+ "loss": 18938011.2,
786
+ "step": 1110
787
+ },
788
+ {
789
+ "epoch": 2.5454545454545454,
790
+ "grad_norm": 149082768.0,
791
+ "learning_rate": 4.4225768151520694e-05,
792
+ "loss": 26505913.6,
793
+ "step": 1120
794
+ },
795
+ {
796
+ "epoch": 2.5681818181818183,
797
+ "grad_norm": 316686912.0,
798
+ "learning_rate": 4.3405391432896555e-05,
799
+ "loss": 20391016.0,
800
+ "step": 1130
801
+ },
802
+ {
803
+ "epoch": 2.590909090909091,
804
+ "grad_norm": 100088072.0,
805
+ "learning_rate": 4.2586817614407895e-05,
806
+ "loss": 26414075.2,
807
+ "step": 1140
808
+ },
809
+ {
810
+ "epoch": 2.6136363636363638,
811
+ "grad_norm": 92582088.0,
812
+ "learning_rate": 4.17702704859633e-05,
813
+ "loss": 15236398.4,
814
+ "step": 1150
815
+ },
816
+ {
817
+ "epoch": 2.6363636363636362,
818
+ "grad_norm": 473522784.0,
819
+ "learning_rate": 4.095597328339452e-05,
820
+ "loss": 24309235.2,
821
+ "step": 1160
822
+ },
823
+ {
824
+ "epoch": 2.659090909090909,
825
+ "grad_norm": 109819416.0,
826
+ "learning_rate": 4.0144148627425993e-05,
827
+ "loss": 22481440.0,
828
+ "step": 1170
829
+ },
830
+ {
831
+ "epoch": 2.6818181818181817,
832
+ "grad_norm": 131413952.0,
833
+ "learning_rate": 3.933501846281267e-05,
834
+ "loss": 15105643.2,
835
+ "step": 1180
836
+ },
837
+ {
838
+ "epoch": 2.7045454545454546,
839
+ "grad_norm": 196484560.0,
840
+ "learning_rate": 3.852880399766243e-05,
841
+ "loss": 22866424.0,
842
+ "step": 1190
843
+ },
844
+ {
845
+ "epoch": 2.7272727272727275,
846
+ "grad_norm": 298367968.0,
847
+ "learning_rate": 3.772572564296005e-05,
848
+ "loss": 20215891.2,
849
+ "step": 1200
850
+ },
851
+ {
852
+ "epoch": 2.75,
853
+ "grad_norm": 94960424.0,
854
+ "learning_rate": 3.6926002952309016e-05,
855
+ "loss": 18007924.8,
856
+ "step": 1210
857
+ },
858
+ {
859
+ "epoch": 2.7727272727272725,
860
+ "grad_norm": 85202336.0,
861
+ "learning_rate": 3.612985456190778e-05,
862
+ "loss": 20693896.0,
863
+ "step": 1220
864
+ },
865
+ {
866
+ "epoch": 2.7954545454545454,
867
+ "grad_norm": 7084129280.0,
868
+ "learning_rate": 3.533749813077677e-05,
869
+ "loss": 16236560.0,
870
+ "step": 1230
871
+ },
872
+ {
873
+ "epoch": 2.8181818181818183,
874
+ "grad_norm": 85127592.0,
875
+ "learning_rate": 3.4549150281252636e-05,
876
+ "loss": 23334752.0,
877
+ "step": 1240
878
+ },
879
+ {
880
+ "epoch": 2.840909090909091,
881
+ "grad_norm": 142297552.0,
882
+ "learning_rate": 3.3765026539765834e-05,
883
+ "loss": 18909488.0,
884
+ "step": 1250
885
+ },
886
+ {
887
+ "epoch": 2.8636363636363638,
888
+ "grad_norm": 284615232.0,
889
+ "learning_rate": 3.298534127791785e-05,
890
+ "loss": 19228300.8,
891
+ "step": 1260
892
+ },
893
+ {
894
+ "epoch": 2.8863636363636362,
895
+ "grad_norm": 102847704.0,
896
+ "learning_rate": 3.221030765387417e-05,
897
+ "loss": 26358712.0,
898
+ "step": 1270
899
+ },
900
+ {
901
+ "epoch": 2.909090909090909,
902
+ "grad_norm": 288731616.0,
903
+ "learning_rate": 3.144013755408895e-05,
904
+ "loss": 21636097.6,
905
+ "step": 1280
906
+ },
907
+ {
908
+ "epoch": 2.9318181818181817,
909
+ "grad_norm": 106496784.0,
910
+ "learning_rate": 3.0675041535377405e-05,
911
+ "loss": 20164374.4,
912
+ "step": 1290
913
+ },
914
+ {
915
+ "epoch": 2.9545454545454546,
916
+ "grad_norm": 223327328.0,
917
+ "learning_rate": 2.991522876735154e-05,
918
+ "loss": 21382241.6,
919
+ "step": 1300
920
+ },
921
+ {
922
+ "epoch": 2.9772727272727275,
923
+ "grad_norm": 73936632.0,
924
+ "learning_rate": 2.916090697523549e-05,
925
+ "loss": 16625654.4,
926
+ "step": 1310
927
+ },
928
+ {
929
+ "epoch": 3.0,
930
+ "grad_norm": 195426608.0,
931
+ "learning_rate": 2.8412282383075363e-05,
932
+ "loss": 21499422.4,
933
+ "step": 1320
934
+ },
935
+ {
936
+ "epoch": 3.022727272727273,
937
+ "grad_norm": 239848320.0,
938
+ "learning_rate": 2.766955965735968e-05,
939
+ "loss": 19992364.8,
940
+ "step": 1330
941
+ },
942
+ {
943
+ "epoch": 3.0454545454545454,
944
+ "grad_norm": 132064736.0,
945
+ "learning_rate": 2.693294185106562e-05,
946
+ "loss": 17378974.4,
947
+ "step": 1340
948
+ },
949
+ {
950
+ "epoch": 3.0681818181818183,
951
+ "grad_norm": 158127008.0,
952
+ "learning_rate": 2.6202630348146324e-05,
953
+ "loss": 14476110.4,
954
+ "step": 1350
955
+ },
956
+ {
957
+ "epoch": 3.090909090909091,
958
+ "grad_norm": 193214896.0,
959
+ "learning_rate": 2.547882480847461e-05,
960
+ "loss": 19444292.8,
961
+ "step": 1360
962
+ },
963
+ {
964
+ "epoch": 3.1136363636363638,
965
+ "grad_norm": 135614960.0,
966
+ "learning_rate": 2.476172311325783e-05,
967
+ "loss": 17136611.2,
968
+ "step": 1370
969
+ },
970
+ {
971
+ "epoch": 3.1363636363636362,
972
+ "grad_norm": 146726304.0,
973
+ "learning_rate": 2.405152131093926e-05,
974
+ "loss": 17945476.8,
975
+ "step": 1380
976
+ },
977
+ {
978
+ "epoch": 3.159090909090909,
979
+ "grad_norm": 86271432.0,
980
+ "learning_rate": 2.3348413563600325e-05,
981
+ "loss": 22355953.6,
982
+ "step": 1390
983
+ },
984
+ {
985
+ "epoch": 3.1818181818181817,
986
+ "grad_norm": 286385248.0,
987
+ "learning_rate": 2.2652592093878666e-05,
988
+ "loss": 17187601.6,
989
+ "step": 1400
990
+ },
991
+ {
992
+ "epoch": 3.2045454545454546,
993
+ "grad_norm": 1212550912.0,
994
+ "learning_rate": 2.196424713241637e-05,
995
+ "loss": 20235840.0,
996
+ "step": 1410
997
+ },
998
+ {
999
+ "epoch": 3.227272727272727,
1000
+ "grad_norm": 73712976.0,
1001
+ "learning_rate": 2.128356686585282e-05,
1002
+ "loss": 30961001.6,
1003
+ "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 3.25,
1007
+ "grad_norm": 182859040.0,
1008
+ "learning_rate": 2.061073738537635e-05,
1009
+ "loss": 32744835.2,
1010
+ "step": 1430
1011
+ },
1012
+ {
1013
+ "epoch": 3.2727272727272725,
1014
+ "grad_norm": 64465348.0,
1015
+ "learning_rate": 1.9945942635848748e-05,
1016
+ "loss": 18790020.8,
1017
+ "step": 1440
1018
+ },
1019
+ {
1020
+ "epoch": 3.2954545454545454,
1021
+ "grad_norm": 79966296.0,
1022
+ "learning_rate": 1.928936436551661e-05,
1023
+ "loss": 21262963.2,
1024
+ "step": 1450
1025
+ },
1026
+ {
1027
+ "epoch": 3.3181818181818183,
1028
+ "grad_norm": 178412640.0,
1029
+ "learning_rate": 1.8641182076323148e-05,
1030
+ "loss": 20795022.4,
1031
+ "step": 1460
1032
+ },
1033
+ {
1034
+ "epoch": 3.340909090909091,
1035
+ "grad_norm": 117127040.0,
1036
+ "learning_rate": 1.800157297483417e-05,
1037
+ "loss": 18522465.6,
1038
+ "step": 1470
1039
+ },
1040
+ {
1041
+ "epoch": 3.3636363636363638,
1042
+ "grad_norm": 225748960.0,
1043
+ "learning_rate": 1.7370711923791567e-05,
1044
+ "loss": 16351683.2,
1045
+ "step": 1480
1046
+ },
1047
+ {
1048
+ "epoch": 3.3863636363636362,
1049
+ "grad_norm": 333275584.0,
1050
+ "learning_rate": 1.6748771394307585e-05,
1051
+ "loss": 15890913.6,
1052
+ "step": 1490
1053
+ },
1054
+ {
1055
+ "epoch": 3.409090909090909,
1056
+ "grad_norm": 94839864.0,
1057
+ "learning_rate": 1.6135921418712956e-05,
1058
+ "loss": 19005873.6,
1059
+ "step": 1500
1060
+ },
1061
+ {
1062
+ "epoch": 3.4318181818181817,
1063
+ "grad_norm": 123844928.0,
1064
+ "learning_rate": 1.553232954407171e-05,
1065
+ "loss": 15768131.2,
1066
+ "step": 1510
1067
+ },
1068
+ {
1069
+ "epoch": 3.4545454545454546,
1070
+ "grad_norm": 376811424.0,
1071
+ "learning_rate": 1.4938160786375572e-05,
1072
+ "loss": 20412670.4,
1073
+ "step": 1520
1074
+ },
1075
+ {
1076
+ "epoch": 3.4772727272727275,
1077
+ "grad_norm": 71331304.0,
1078
+ "learning_rate": 1.435357758543015e-05,
1079
+ "loss": 15396275.2,
1080
+ "step": 1530
1081
+ },
1082
+ {
1083
+ "epoch": 3.5,
1084
+ "grad_norm": 90793376.0,
1085
+ "learning_rate": 1.3778739760445552e-05,
1086
+ "loss": 17609350.4,
1087
+ "step": 1540
1088
+ },
1089
+ {
1090
+ "epoch": 3.5227272727272725,
1091
+ "grad_norm": 175962528.0,
1092
+ "learning_rate": 1.3213804466343421e-05,
1093
+ "loss": 16694264.0,
1094
+ "step": 1550
1095
+ },
1096
+ {
1097
+ "epoch": 3.5454545454545454,
1098
+ "grad_norm": 130335672.0,
1099
+ "learning_rate": 1.2658926150792322e-05,
1100
+ "loss": 15245347.2,
1101
+ "step": 1560
1102
+ },
1103
+ {
1104
+ "epoch": 3.5681818181818183,
1105
+ "grad_norm": 225995312.0,
1106
+ "learning_rate": 1.2114256511983274e-05,
1107
+ "loss": 14799392.0,
1108
+ "step": 1570
1109
+ },
1110
+ {
1111
+ "epoch": 3.590909090909091,
1112
+ "grad_norm": 91921688.0,
1113
+ "learning_rate": 1.157994445715706e-05,
1114
+ "loss": 23821099.2,
1115
+ "step": 1580
1116
+ },
1117
+ {
1118
+ "epoch": 3.6136363636363638,
1119
+ "grad_norm": 108905944.0,
1120
+ "learning_rate": 1.1056136061894384e-05,
1121
+ "loss": 20226878.4,
1122
+ "step": 1590
1123
+ },
1124
+ {
1125
+ "epoch": 3.6363636363636362,
1126
+ "grad_norm": 192163008.0,
1127
+ "learning_rate": 1.0542974530180327e-05,
1128
+ "loss": 15503652.8,
1129
+ "step": 1600
1130
+ },
1131
+ {
1132
+ "epoch": 3.659090909090909,
1133
+ "grad_norm": 82313128.0,
1134
+ "learning_rate": 1.0040600155253765e-05,
1135
+ "loss": 16259214.4,
1136
+ "step": 1610
1137
+ },
1138
+ {
1139
+ "epoch": 3.6818181818181817,
1140
+ "grad_norm": 127500728.0,
1141
+ "learning_rate": 9.549150281252633e-06,
1142
+ "loss": 13356518.4,
1143
+ "step": 1620
1144
+ },
1145
+ {
1146
+ "epoch": 3.7045454545454546,
1147
+ "grad_norm": 195588592.0,
1148
+ "learning_rate": 9.068759265665384e-06,
1149
+ "loss": 13309605.6,
1150
+ "step": 1630
1151
+ },
1152
+ {
1153
+ "epoch": 3.7272727272727275,
1154
+ "grad_norm": 124094728.0,
1155
+ "learning_rate": 8.599558442598998e-06,
1156
+ "loss": 17332201.6,
1157
+ "step": 1640
1158
+ },
1159
+ {
1160
+ "epoch": 3.75,
1161
+ "grad_norm": 194997536.0,
1162
+ "learning_rate": 8.141676086873572e-06,
1163
+ "loss": 27798745.6,
1164
+ "step": 1650
1165
+ },
1166
+ {
1167
+ "epoch": 3.7727272727272725,
1168
+ "grad_norm": 408983104.0,
1169
+ "learning_rate": 7.695237378953223e-06,
1170
+ "loss": 18060028.8,
1171
+ "step": 1660
1172
+ },
1173
+ {
1174
+ "epoch": 3.7954545454545454,
1175
+ "grad_norm": 64105764.0,
1176
+ "learning_rate": 7.260364370723044e-06,
1177
+ "loss": 14837972.8,
1178
+ "step": 1670
1179
+ },
1180
+ {
1181
+ "epoch": 3.8181818181818183,
1182
+ "grad_norm": 172431360.0,
1183
+ "learning_rate": 6.837175952121306e-06,
1184
+ "loss": 16195776.0,
1185
+ "step": 1680
1186
+ },
1187
+ {
1188
+ "epoch": 3.840909090909091,
1189
+ "grad_norm": 82362008.0,
1190
+ "learning_rate": 6.425787818636131e-06,
1191
+ "loss": 14680713.6,
1192
+ "step": 1690
1193
+ },
1194
+ {
1195
+ "epoch": 3.8636363636363638,
1196
+ "grad_norm": 146533344.0,
1197
+ "learning_rate": 6.026312439675552e-06,
1198
+ "loss": 16691865.6,
1199
+ "step": 1700
1200
+ },
1201
+ {
1202
+ "epoch": 3.8863636363636362,
1203
+ "grad_norm": 109454416.0,
1204
+ "learning_rate": 5.6388590278194096e-06,
1205
+ "loss": 17369052.8,
1206
+ "step": 1710
1207
+ },
1208
+ {
1209
+ "epoch": 3.909090909090909,
1210
+ "grad_norm": 294526976.0,
1211
+ "learning_rate": 5.263533508961827e-06,
1212
+ "loss": 9919254.4,
1213
+ "step": 1720
1214
+ },
1215
+ {
1216
+ "epoch": 3.9318181818181817,
1217
+ "grad_norm": 205665296.0,
1218
+ "learning_rate": 4.900438493352055e-06,
1219
+ "loss": 19957376.0,
1220
+ "step": 1730
1221
+ },
1222
+ {
1223
+ "epoch": 3.9545454545454546,
1224
+ "grad_norm": 117976384.0,
1225
+ "learning_rate": 4.549673247541875e-06,
1226
+ "loss": 14926936.0,
1227
+ "step": 1740
1228
+ },
1229
+ {
1230
+ "epoch": 3.9772727272727275,
1231
+ "grad_norm": 139144784.0,
1232
+ "learning_rate": 4.2113336672471245e-06,
1233
+ "loss": 15108585.6,
1234
+ "step": 1750
1235
+ },
1236
+ {
1237
+ "epoch": 4.0,
1238
+ "grad_norm": 204030640.0,
1239
+ "learning_rate": 3.885512251130763e-06,
1240
+ "loss": 16684348.8,
1241
+ "step": 1760
1242
+ },
1243
+ {
1244
+ "epoch": 4.0227272727272725,
1245
+ "grad_norm": 231758032.0,
1246
+ "learning_rate": 3.5722980755146517e-06,
1247
+ "loss": 14250145.6,
1248
+ "step": 1770
1249
+ },
1250
+ {
1251
+ "epoch": 4.045454545454546,
1252
+ "grad_norm": 114193512.0,
1253
+ "learning_rate": 3.271776770026963e-06,
1254
+ "loss": 14976139.2,
1255
+ "step": 1780
1256
+ },
1257
+ {
1258
+ "epoch": 4.068181818181818,
1259
+ "grad_norm": 45119975424.0,
1260
+ "learning_rate": 2.9840304941919415e-06,
1261
+ "loss": 13117681.6,
1262
+ "step": 1790
1263
+ },
1264
+ {
1265
+ "epoch": 4.090909090909091,
1266
+ "grad_norm": 87482056.0,
1267
+ "learning_rate": 2.7091379149682685e-06,
1268
+ "loss": 16316115.2,
1269
+ "step": 1800
1270
+ },
1271
+ {
1272
+ "epoch": 4.113636363636363,
1273
+ "grad_norm": 217095472.0,
1274
+ "learning_rate": 2.4471741852423237e-06,
1275
+ "loss": 12584548.8,
1276
+ "step": 1810
1277
+ },
1278
+ {
1279
+ "epoch": 4.136363636363637,
1280
+ "grad_norm": 279856288.0,
1281
+ "learning_rate": 2.1982109232821178e-06,
1282
+ "loss": 17845868.8,
1283
+ "step": 1820
1284
+ },
1285
+ {
1286
+ "epoch": 4.159090909090909,
1287
+ "grad_norm": 105613376.0,
1288
+ "learning_rate": 1.962316193157593e-06,
1289
+ "loss": 14880216.0,
1290
+ "step": 1830
1291
+ },
1292
+ {
1293
+ "epoch": 4.181818181818182,
1294
+ "grad_norm": 108838528.0,
1295
+ "learning_rate": 1.7395544861325718e-06,
1296
+ "loss": 14690222.4,
1297
+ "step": 1840
1298
+ },
1299
+ {
1300
+ "epoch": 4.204545454545454,
1301
+ "grad_norm": 98467304.0,
1302
+ "learning_rate": 1.5299867030334814e-06,
1303
+ "loss": 18249204.8,
1304
+ "step": 1850
1305
+ },
1306
+ {
1307
+ "epoch": 4.2272727272727275,
1308
+ "grad_norm": 145458192.0,
1309
+ "learning_rate": 1.333670137599713e-06,
1310
+ "loss": 11624424.8,
1311
+ "step": 1860
1312
+ },
1313
+ {
1314
+ "epoch": 4.25,
1315
+ "grad_norm": 75976648.0,
1316
+ "learning_rate": 1.1506584608200367e-06,
1317
+ "loss": 16304561.6,
1318
+ "step": 1870
1319
+ },
1320
+ {
1321
+ "epoch": 4.2727272727272725,
1322
+ "grad_norm": 152758896.0,
1323
+ "learning_rate": 9.810017062595322e-07,
1324
+ "loss": 18160070.4,
1325
+ "step": 1880
1326
+ },
1327
+ {
1328
+ "epoch": 4.295454545454546,
1329
+ "grad_norm": 210220208.0,
1330
+ "learning_rate": 8.247462563808817e-07,
1331
+ "loss": 23436678.4,
1332
+ "step": 1890
1333
+ },
1334
+ {
1335
+ "epoch": 4.318181818181818,
1336
+ "grad_norm": 199508576.0,
1337
+ "learning_rate": 6.819348298638839e-07,
1338
+ "loss": 14236168.0,
1339
+ "step": 1900
1340
+ },
1341
+ {
1342
+ "epoch": 4.340909090909091,
1343
+ "grad_norm": 63556520.0,
1344
+ "learning_rate": 5.526064699265753e-07,
1345
+ "loss": 20044918.4,
1346
+ "step": 1910
1347
+ },
1348
+ {
1349
+ "epoch": 4.363636363636363,
1350
+ "grad_norm": 59328524.0,
1351
+ "learning_rate": 4.367965336512403e-07,
1352
+ "loss": 13414170.4,
1353
+ "step": 1920
1354
+ },
1355
+ {
1356
+ "epoch": 4.386363636363637,
1357
+ "grad_norm": 360369888.0,
1358
+ "learning_rate": 3.3453668231809286e-07,
1359
+ "loss": 13388755.2,
1360
+ "step": 1930
1361
+ },
1362
+ {
1363
+ "epoch": 4.409090909090909,
1364
+ "grad_norm": 1001972800.0,
1365
+ "learning_rate": 2.458548727494292e-07,
1366
+ "loss": 18148713.6,
1367
+ "step": 1940
1368
+ },
1369
+ {
1370
+ "epoch": 4.431818181818182,
1371
+ "grad_norm": 104688328.0,
1372
+ "learning_rate": 1.7077534966650766e-07,
1373
+ "loss": 15079361.6,
1374
+ "step": 1950
1375
+ },
1376
+ {
1377
+ "epoch": 4.454545454545454,
1378
+ "grad_norm": 37318868.0,
1379
+ "learning_rate": 1.0931863906127327e-07,
1380
+ "loss": 12394652.0,
1381
+ "step": 1960
1382
+ },
1383
+ {
1384
+ "epoch": 4.4772727272727275,
1385
+ "grad_norm": 146546864.0,
1386
+ "learning_rate": 6.150154258476315e-08,
1387
+ "loss": 20620992.0,
1388
+ "step": 1970
1389
+ },
1390
+ {
1391
+ "epoch": 4.5,
1392
+ "grad_norm": 157523056.0,
1393
+ "learning_rate": 2.7337132953697554e-08,
1394
+ "loss": 13256707.2,
1395
+ "step": 1980
1396
+ },
1397
+ {
1398
+ "epoch": 4.5227272727272725,
1399
+ "grad_norm": 142617888.0,
1400
+ "learning_rate": 6.834750376549792e-09,
1401
+ "loss": 19604684.8,
1402
+ "step": 1990
1403
+ },
1404
+ {
1405
+ "epoch": 4.545454545454545,
1406
+ "grad_norm": 65029756.0,
1407
+ "learning_rate": 0.0,
1408
+ "loss": 12012332.0,
1409
+ "step": 2000
1410
+ }
1411
+ ],
1412
+ "logging_steps": 10,
1413
+ "max_steps": 2000,
1414
+ "num_input_tokens_seen": 0,
1415
+ "num_train_epochs": 5,
1416
+ "save_steps": 500,
1417
+ "stateful_callbacks": {
1418
+ "TrainerControl": {
1419
+ "args": {
1420
+ "should_epoch_stop": false,
1421
+ "should_evaluate": false,
1422
+ "should_log": false,
1423
+ "should_save": true,
1424
+ "should_training_stop": true
1425
+ },
1426
+ "attributes": {}
1427
+ }
1428
+ },
1429
+ "total_flos": 3.763682350698701e+16,
1430
+ "train_batch_size": 16,
1431
+ "trial_name": null,
1432
+ "trial_params": null
1433
+ }