Even-ok commited on
Commit
2cd71d1
·
verified ·
1 Parent(s): 0a6055d

Upload folder using huggingface_hub

Browse files
checkpoint-900/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/pretrained_models/UD-VLA_LIBERO_SPATIAL",
3
+ "action_config": {
4
+ "_attn_implementation": "flash_attention_2",
5
+ "action_dim": 7,
6
+ "attention_dropout": 0.0,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 4096,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2048,
11
+ "max_position_embeddings": 5120,
12
+ "num_attention_heads": 32,
13
+ "num_hidden_layers": 2,
14
+ "num_key_value_heads": 8,
15
+ "pad_token_id": 151643,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "use_cache": true,
22
+ "vision_loss_weight": 5.0
23
+ },
24
+ "action_dim": 7,
25
+ "action_experts": false,
26
+ "architectures": [
27
+ "Emu3MoE"
28
+ ],
29
+ "attention_dropout": 0.1,
30
+ "boa_token_id": 151844,
31
+ "boi_token_id": 151852,
32
+ "bos_token_id": 151849,
33
+ "bov_token_id": 151854,
34
+ "eof_token_id": 151847,
35
+ "eoi_token_id": 151853,
36
+ "eol_token_id": 151846,
37
+ "eos_token_id": 151850,
38
+ "eov_token_id": 184621,
39
+ "hidden_act": "silu",
40
+ "hidden_size": 4096,
41
+ "image_area": 262144,
42
+ "img_token_id": 151851,
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 14336,
45
+ "max_position_embeddings": 1650,
46
+ "model_type": "Emu3",
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 32,
49
+ "num_key_value_heads": 8,
50
+ "pad_token_id": 151643,
51
+ "pretraining_tp": 1,
52
+ "qkv_bias": false,
53
+ "rms_norm_eps": 1e-05,
54
+ "rope_scaling": null,
55
+ "rope_theta": 1000000.0,
56
+ "tie_word_embeddings": false,
57
+ "torch_dtype": "bfloat16",
58
+ "transformers_version": "4.44.0",
59
+ "use_bidirectional_attn_mask": false,
60
+ "use_blockwise_attn_mask": true,
61
+ "use_cache": true,
62
+ "vision_loss_weight": 0.5,
63
+ "vocab_size": 184622
64
+ }
checkpoint-900/emu3.tiktoken ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/emu3_vision_tokens.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-900/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151849,
4
+ "eos_token_id": 151850,
5
+ "pad_token_id": 151643,
6
+ "transformers_version": "4.44.0"
7
+ }
checkpoint-900/model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0df19542ae6b38b9f1b5f3bde4b56f76f140ca595ca696541b45097ebb69c008
3
+ size 4885136092
checkpoint-900/model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8f00b559954aecd3550acd3bca24696836589c47628365a3a9fc3240d2e1d4
3
+ size 4999819320
checkpoint-900/model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09d560482180eddc44d3339bbf2ed112a55928a260974d302cad5365b9d3e77
3
+ size 4915916184
checkpoint-900/model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0d64a13907cdf853b456d7b65c4f0c6ac1932c532b571b285e055c32e301ba
3
+ size 2183554760
checkpoint-900/model.safetensors.index.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16984392284
4
+ },
5
+ "weight_map": {
6
+ "_action_token_mask": "model-00001-of-00004.safetensors",
7
+ "_image_token_mask": "model-00001-of-00004.safetensors",
8
+ "lm_head.weight": "model-00004-of-00004.safetensors",
9
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
113
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
114
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
126
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
127
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
226
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
227
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
228
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
230
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
231
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
235
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
236
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
237
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
239
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
240
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
241
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
242
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
243
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
244
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
272
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
273
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
276
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
281
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
282
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
283
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
284
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
286
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.norm.weight": "model-00004-of-00004.safetensors"
299
+ }
300
+ }
checkpoint-900/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6248ae890d0895cd1d94c00124f0c6bbb4f978dab3f03e5e37c061861453f0d
3
+ size 15024
checkpoint-900/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c7c50bf897190f8ac79ce82d9bffa9e4bbdefba6653a6f2deeafbbdf94d593
3
+ size 15024
checkpoint-900/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb100100aaad7ade640e5f50fbe447c8b11347cd9b67fe0b2c71d9594084569a
3
+ size 15024
checkpoint-900/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57c355761923ae37a2869fb54922b652924533719f8ba7ff20aee3a6a054ef1c
3
+ size 15024
checkpoint-900/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|extra_203|>",
3
+ "eos_token": "<|extra_204|>",
4
+ "pad_token": "<|endoftext|>"
5
+ }
checkpoint-900/tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {},
3
+ "auto_map": {
4
+ "AutoTokenizer": [
5
+ "tokenization_emu3.Emu3Tokenizer",
6
+ null
7
+ ]
8
+ },
9
+ "bos_token": "<|extra_203|>",
10
+ "clean_up_tokenization_spaces": true,
11
+ "eos_token": "<|extra_204|>",
12
+ "model_max_length": 1650,
13
+ "pad_token": "<|endoftext|>",
14
+ "padding_side": "right",
15
+ "tokenizer_class": "Emu3Tokenizer",
16
+ "use_fast": false
17
+ }
checkpoint-900/trainer_state.json ADDED
@@ -0,0 +1,618 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 900.0,
5
+ "eval_steps": 500,
6
+ "global_step": 900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "action_loss_ratio": 87.17951202392578,
13
+ "action_mean_loss": 3.492661714553833,
14
+ "epoch": 20.0,
15
+ "grad_norm": 5.307751507507029,
16
+ "learning_rate": 4.9960534568565435e-06,
17
+ "loss": 3.2552,
18
+ "other_loss_ratio": 0.0,
19
+ "other_mean_loss": 0.0,
20
+ "step": 20,
21
+ "vision_loss_ratio": 12.820487022399902,
22
+ "vision_mean_loss": 1.1984593868255615
23
+ },
24
+ {
25
+ "action_loss_ratio": 83.3780517578125,
26
+ "action_mean_loss": 4.0559916496276855,
27
+ "epoch": 40.0,
28
+ "grad_norm": 5.329794852514364,
29
+ "learning_rate": 4.984229402628956e-06,
30
+ "loss": 3.238,
31
+ "other_loss_ratio": 0.0,
32
+ "other_mean_loss": 0.0,
33
+ "step": 40,
34
+ "vision_loss_ratio": 16.621944427490234,
35
+ "vision_mean_loss": 1.8867045640945435
36
+ },
37
+ {
38
+ "action_loss_ratio": 83.18673706054688,
39
+ "action_mean_loss": 3.7354936599731445,
40
+ "epoch": 60.0,
41
+ "grad_norm": 5.727186278904086,
42
+ "learning_rate": 4.964574501457378e-06,
43
+ "loss": 3.2458,
44
+ "other_loss_ratio": 0.0,
45
+ "other_mean_loss": 0.0,
46
+ "step": 60,
47
+ "vision_loss_ratio": 16.813268661499023,
48
+ "vision_mean_loss": 1.7616628408432007
49
+ },
50
+ {
51
+ "action_loss_ratio": 84.26898956298828,
52
+ "action_mean_loss": 3.7994015216827393,
53
+ "epoch": 80.0,
54
+ "grad_norm": 5.038061847614736,
55
+ "learning_rate": 4.937166322257262e-06,
56
+ "loss": 3.1948,
57
+ "other_loss_ratio": 0.0,
58
+ "other_mean_loss": 0.0,
59
+ "step": 80,
60
+ "vision_loss_ratio": 15.731012344360352,
61
+ "vision_mean_loss": 1.6549347639083862
62
+ },
63
+ {
64
+ "action_loss_ratio": 84.94904327392578,
65
+ "action_mean_loss": 3.220731496810913,
66
+ "epoch": 100.0,
67
+ "grad_norm": 5.209129883797487,
68
+ "learning_rate": 4.902113032590307e-06,
69
+ "loss": 3.1995,
70
+ "other_loss_ratio": 0.0,
71
+ "other_mean_loss": 0.0,
72
+ "step": 100,
73
+ "vision_loss_ratio": 15.050962448120117,
74
+ "vision_mean_loss": 1.3314875364303589
75
+ },
76
+ {
77
+ "action_loss_ratio": 85.51789855957031,
78
+ "action_mean_loss": 3.589684247970581,
79
+ "epoch": 120.0,
80
+ "grad_norm": 5.575843156470664,
81
+ "learning_rate": 4.859552971776504e-06,
82
+ "loss": 3.1992,
83
+ "other_loss_ratio": 0.0,
84
+ "other_mean_loss": 0.0,
85
+ "step": 120,
86
+ "vision_loss_ratio": 14.482098579406738,
87
+ "vision_mean_loss": 1.4184285402297974
88
+ },
89
+ {
90
+ "action_loss_ratio": 79.70157623291016,
91
+ "action_mean_loss": 3.8257267475128174,
92
+ "epoch": 140.0,
93
+ "grad_norm": 5.04269551398109,
94
+ "learning_rate": 4.80965410493204e-06,
95
+ "loss": 3.1926,
96
+ "other_loss_ratio": 0.0,
97
+ "other_mean_loss": 0.0,
98
+ "step": 140,
99
+ "vision_loss_ratio": 20.298423767089844,
100
+ "vision_mean_loss": 2.273453712463379
101
+ },
102
+ {
103
+ "action_loss_ratio": 85.07321166992188,
104
+ "action_mean_loss": 3.8016629219055176,
105
+ "epoch": 160.0,
106
+ "grad_norm": 5.141958781457068,
107
+ "learning_rate": 4.752613360087727e-06,
108
+ "loss": 3.1704,
109
+ "other_loss_ratio": 0.0,
110
+ "other_mean_loss": 0.0,
111
+ "step": 160,
112
+ "vision_loss_ratio": 14.926783561706543,
113
+ "vision_mean_loss": 1.5564090013504028
114
+ },
115
+ {
116
+ "action_loss_ratio": 85.39839172363281,
117
+ "action_mean_loss": 3.8305673599243164,
118
+ "epoch": 180.0,
119
+ "grad_norm": 5.464021030744428,
120
+ "learning_rate": 4.68865585100403e-06,
121
+ "loss": 3.1443,
122
+ "other_loss_ratio": 0.0,
123
+ "other_mean_loss": 0.0,
124
+ "step": 180,
125
+ "vision_loss_ratio": 14.601609230041504,
126
+ "vision_mean_loss": 1.5282377004623413
127
+ },
128
+ {
129
+ "action_loss_ratio": 81.42992401123047,
130
+ "action_mean_loss": 3.9839138984680176,
131
+ "epoch": 200.0,
132
+ "grad_norm": 5.142266561639327,
133
+ "learning_rate": 4.618033988749896e-06,
134
+ "loss": 3.1672,
135
+ "other_loss_ratio": 0.0,
136
+ "other_mean_loss": 0.0,
137
+ "step": 200,
138
+ "vision_loss_ratio": 18.57008171081543,
139
+ "vision_mean_loss": 2.119905471801758
140
+ },
141
+ {
142
+ "action_loss_ratio": 83.61074829101562,
143
+ "action_mean_loss": 3.8878681659698486,
144
+ "epoch": 220.0,
145
+ "grad_norm": 5.62895279430695,
146
+ "learning_rate": 4.541026485551579e-06,
147
+ "loss": 3.1265,
148
+ "other_loss_ratio": 0.0,
149
+ "other_mean_loss": 0.0,
150
+ "step": 220,
151
+ "vision_loss_ratio": 16.389251708984375,
152
+ "vision_mean_loss": 1.7782193422317505
153
+ },
154
+ {
155
+ "action_loss_ratio": 82.32794952392578,
156
+ "action_mean_loss": 3.632842540740967,
157
+ "epoch": 240.0,
158
+ "grad_norm": 5.106068123833609,
159
+ "learning_rate": 4.457937254842823e-06,
160
+ "loss": 3.1506,
161
+ "other_loss_ratio": 0.0,
162
+ "other_mean_loss": 0.0,
163
+ "step": 240,
164
+ "vision_loss_ratio": 17.67205238342285,
165
+ "vision_mean_loss": 1.8195457458496094
166
+ },
167
+ {
168
+ "action_loss_ratio": 85.77775573730469,
169
+ "action_mean_loss": 3.854332447052002,
170
+ "epoch": 260.0,
171
+ "grad_norm": 5.556443997999331,
172
+ "learning_rate": 4.3690942118573774e-06,
173
+ "loss": 3.1438,
174
+ "other_loss_ratio": 0.0,
175
+ "other_mean_loss": 0.0,
176
+ "step": 260,
177
+ "vision_loss_ratio": 14.222243309020996,
178
+ "vision_mean_loss": 1.4911431074142456
179
+ },
180
+ {
181
+ "action_loss_ratio": 82.28608703613281,
182
+ "action_mean_loss": 3.8654937744140625,
183
+ "epoch": 280.0,
184
+ "grad_norm": 5.100007087336655,
185
+ "learning_rate": 4.274847979497379e-06,
186
+ "loss": 3.1318,
187
+ "other_loss_ratio": 0.0,
188
+ "other_mean_loss": 0.0,
189
+ "step": 280,
190
+ "vision_loss_ratio": 17.71392059326172,
191
+ "vision_mean_loss": 1.9416460990905762
192
+ },
193
+ {
194
+ "action_loss_ratio": 84.23397064208984,
195
+ "action_mean_loss": 3.169405937194824,
196
+ "epoch": 300.0,
197
+ "grad_norm": 5.5925595530442065,
198
+ "learning_rate": 4.175570504584947e-06,
199
+ "loss": 3.1357,
200
+ "other_loss_ratio": 0.0,
201
+ "other_mean_loss": 0.0,
202
+ "step": 300,
203
+ "vision_loss_ratio": 15.766029357910156,
204
+ "vision_mean_loss": 1.3841707706451416
205
+ },
206
+ {
207
+ "action_loss_ratio": 86.55780792236328,
208
+ "action_mean_loss": 3.491978168487549,
209
+ "epoch": 320.0,
210
+ "grad_norm": 5.601886698005213,
211
+ "learning_rate": 4.071653589957993e-06,
212
+ "loss": 3.0852,
213
+ "other_loss_ratio": 0.0,
214
+ "other_mean_loss": 0.0,
215
+ "step": 320,
216
+ "vision_loss_ratio": 13.442193984985352,
217
+ "vision_mean_loss": 1.2653543949127197
218
+ },
219
+ {
220
+ "action_loss_ratio": 77.99794006347656,
221
+ "action_mean_loss": 4.085394859313965,
222
+ "epoch": 340.0,
223
+ "grad_norm": 5.37518846128701,
224
+ "learning_rate": 3.963507348203431e-06,
225
+ "loss": 3.1043,
226
+ "other_loss_ratio": 0.0,
227
+ "other_mean_loss": 0.0,
228
+ "step": 340,
229
+ "vision_loss_ratio": 22.002059936523438,
230
+ "vision_mean_loss": 2.6890013217926025
231
+ },
232
+ {
233
+ "action_loss_ratio": 83.92550659179688,
234
+ "action_mean_loss": 3.7593491077423096,
235
+ "epoch": 360.0,
236
+ "grad_norm": 5.281719131865867,
237
+ "learning_rate": 3.851558583130146e-06,
238
+ "loss": 3.0747,
239
+ "other_loss_ratio": 0.0,
240
+ "other_mean_loss": 0.0,
241
+ "step": 360,
242
+ "vision_loss_ratio": 16.074495315551758,
243
+ "vision_mean_loss": 1.6800910234451294
244
+ },
245
+ {
246
+ "action_loss_ratio": 81.40982818603516,
247
+ "action_mean_loss": 3.74065899848938,
248
+ "epoch": 380.0,
249
+ "grad_norm": 5.395672287497414,
250
+ "learning_rate": 3.736249105369357e-06,
251
+ "loss": 3.0631,
252
+ "other_loss_ratio": 0.0,
253
+ "other_mean_loss": 0.0,
254
+ "step": 380,
255
+ "vision_loss_ratio": 18.59016990661621,
256
+ "vision_mean_loss": 1.9931106567382812
257
+ },
258
+ {
259
+ "action_loss_ratio": 84.95108795166016,
260
+ "action_mean_loss": 3.402333974838257,
261
+ "epoch": 400.0,
262
+ "grad_norm": 5.4610084322477315,
263
+ "learning_rate": 3.618033988749895e-06,
264
+ "loss": 3.1097,
265
+ "other_loss_ratio": 0.0,
266
+ "other_mean_loss": 0.0,
267
+ "step": 400,
268
+ "vision_loss_ratio": 15.048912048339844,
269
+ "vision_mean_loss": 1.4063384532928467
270
+ },
271
+ {
272
+ "action_loss_ratio": 83.2823486328125,
273
+ "action_mean_loss": 3.869166135787964,
274
+ "epoch": 420.0,
275
+ "grad_norm": 5.429774974127678,
276
+ "learning_rate": 3.4973797743297104e-06,
277
+ "loss": 3.0648,
278
+ "other_loss_ratio": 0.0,
279
+ "other_mean_loss": 0.0,
280
+ "step": 420,
281
+ "vision_loss_ratio": 16.717655181884766,
282
+ "vision_mean_loss": 1.8122434616088867
283
+ },
284
+ {
285
+ "action_loss_ratio": 82.7828369140625,
286
+ "action_mean_loss": 3.777729034423828,
287
+ "epoch": 440.0,
288
+ "grad_norm": 5.271263884192678,
289
+ "learning_rate": 3.3747626291714498e-06,
290
+ "loss": 3.0153,
291
+ "other_loss_ratio": 0.0,
292
+ "other_mean_loss": 0.0,
293
+ "step": 440,
294
+ "vision_loss_ratio": 17.2171630859375,
295
+ "vision_mean_loss": 1.8332799673080444
296
+ },
297
+ {
298
+ "action_loss_ratio": 79.5228271484375,
299
+ "action_mean_loss": 3.5700252056121826,
300
+ "epoch": 460.0,
301
+ "grad_norm": 5.471461574880301,
302
+ "learning_rate": 3.2506664671286085e-06,
303
+ "loss": 3.061,
304
+ "other_loss_ratio": 0.0,
305
+ "other_mean_loss": 0.0,
306
+ "step": 460,
307
+ "vision_loss_ratio": 20.477170944213867,
308
+ "vision_mean_loss": 2.1449947357177734
309
+ },
310
+ {
311
+ "action_loss_ratio": 82.9408187866211,
312
+ "action_mean_loss": 3.6688039302825928,
313
+ "epoch": 480.0,
314
+ "grad_norm": 5.695292963543473,
315
+ "learning_rate": 3.125581039058627e-06,
316
+ "loss": 3.0251,
317
+ "other_loss_ratio": 0.0,
318
+ "other_mean_loss": 0.0,
319
+ "step": 480,
320
+ "vision_loss_ratio": 17.05918312072754,
321
+ "vision_mean_loss": 1.76072359085083
322
+ },
323
+ {
324
+ "action_loss_ratio": 81.28376007080078,
325
+ "action_mean_loss": 3.9420902729034424,
326
+ "epoch": 500.0,
327
+ "grad_norm": 5.220026896187614,
328
+ "learning_rate": 3e-06,
329
+ "loss": 3.0215,
330
+ "other_loss_ratio": 0.0,
331
+ "other_mean_loss": 0.0,
332
+ "step": 500,
333
+ "vision_loss_ratio": 18.716243743896484,
334
+ "vision_mean_loss": 2.11796236038208
335
+ },
336
+ {
337
+ "action_loss_ratio": 81.72908782958984,
338
+ "action_mean_loss": 2.9122588634490967,
339
+ "epoch": 520.0,
340
+ "grad_norm": 5.800737863445548,
341
+ "learning_rate": 2.8744189609413735e-06,
342
+ "loss": 3.0261,
343
+ "other_loss_ratio": 0.0,
344
+ "other_mean_loss": 0.0,
345
+ "step": 520,
346
+ "vision_loss_ratio": 18.270906448364258,
347
+ "vision_mean_loss": 1.5191131830215454
348
+ },
349
+ {
350
+ "action_loss_ratio": 80.6470718383789,
351
+ "action_mean_loss": 3.383985757827759,
352
+ "epoch": 540.0,
353
+ "grad_norm": 5.240964782331805,
354
+ "learning_rate": 2.7493335328713917e-06,
355
+ "loss": 3.0154,
356
+ "other_loss_ratio": 0.0,
357
+ "other_mean_loss": 0.0,
358
+ "step": 540,
359
+ "vision_loss_ratio": 19.352924346923828,
360
+ "vision_mean_loss": 1.8947995901107788
361
+ },
362
+ {
363
+ "action_loss_ratio": 80.24288177490234,
364
+ "action_mean_loss": 3.4896368980407715,
365
+ "epoch": 560.0,
366
+ "grad_norm": 5.477930522439451,
367
+ "learning_rate": 2.6252373708285504e-06,
368
+ "loss": 3.0291,
369
+ "other_loss_ratio": 0.0,
370
+ "other_mean_loss": 0.0,
371
+ "step": 560,
372
+ "vision_loss_ratio": 19.757116317749023,
373
+ "vision_mean_loss": 2.0048134326934814
374
+ },
375
+ {
376
+ "action_loss_ratio": 82.88014221191406,
377
+ "action_mean_loss": 3.5021066665649414,
378
+ "epoch": 580.0,
379
+ "grad_norm": 5.831902081417629,
380
+ "learning_rate": 2.502620225670291e-06,
381
+ "loss": 3.0304,
382
+ "other_loss_ratio": 0.0,
383
+ "other_mean_loss": 0.0,
384
+ "step": 580,
385
+ "vision_loss_ratio": 17.11986541748047,
386
+ "vision_mean_loss": 1.6879361867904663
387
+ },
388
+ {
389
+ "action_loss_ratio": 85.08258819580078,
390
+ "action_mean_loss": 3.8970515727996826,
391
+ "epoch": 600.0,
392
+ "grad_norm": 5.780216977543107,
393
+ "learning_rate": 2.3819660112501054e-06,
394
+ "loss": 3.0008,
395
+ "other_loss_ratio": 0.0,
396
+ "other_mean_loss": 0.0,
397
+ "step": 600,
398
+ "vision_loss_ratio": 14.917412757873535,
399
+ "vision_mean_loss": 1.594284176826477
400
+ },
401
+ {
402
+ "action_loss_ratio": 85.86053466796875,
403
+ "action_mean_loss": 3.1556904315948486,
404
+ "epoch": 620.0,
405
+ "grad_norm": 5.55626629122766,
406
+ "learning_rate": 2.263750894630644e-06,
407
+ "loss": 2.9965,
408
+ "other_loss_ratio": 0.0,
409
+ "other_mean_loss": 0.0,
410
+ "step": 620,
411
+ "vision_loss_ratio": 14.139459609985352,
412
+ "vision_mean_loss": 1.2125798463821411
413
+ },
414
+ {
415
+ "action_loss_ratio": 85.43881225585938,
416
+ "action_mean_loss": 3.7446155548095703,
417
+ "epoch": 640.0,
418
+ "grad_norm": 6.317650377110351,
419
+ "learning_rate": 2.148441416869855e-06,
420
+ "loss": 3.0011,
421
+ "other_loss_ratio": 0.0,
422
+ "other_mean_loss": 0.0,
423
+ "step": 640,
424
+ "vision_loss_ratio": 14.561187744140625,
425
+ "vision_mean_loss": 1.4891060590744019
426
+ },
427
+ {
428
+ "action_loss_ratio": 83.94339752197266,
429
+ "action_mean_loss": 3.4414384365081787,
430
+ "epoch": 660.0,
431
+ "grad_norm": 5.505728558689247,
432
+ "learning_rate": 2.0364926517965693e-06,
433
+ "loss": 2.996,
434
+ "other_loss_ratio": 0.0,
435
+ "other_mean_loss": 0.0,
436
+ "step": 660,
437
+ "vision_loss_ratio": 16.056602478027344,
438
+ "vision_mean_loss": 1.5359740257263184
439
+ },
440
+ {
441
+ "action_loss_ratio": 79.97301483154297,
442
+ "action_mean_loss": 3.8252508640289307,
443
+ "epoch": 680.0,
444
+ "grad_norm": 5.626976655315619,
445
+ "learning_rate": 1.9283464100420063e-06,
446
+ "loss": 2.9926,
447
+ "other_loss_ratio": 0.0,
448
+ "other_mean_loss": 0.0,
449
+ "step": 680,
450
+ "vision_loss_ratio": 20.02699089050293,
451
+ "vision_mean_loss": 2.235161542892456
452
+ },
453
+ {
454
+ "action_loss_ratio": 87.16512298583984,
455
+ "action_mean_loss": 3.9701735973358154,
456
+ "epoch": 700.0,
457
+ "grad_norm": 5.766951661915987,
458
+ "learning_rate": 1.824429495415054e-06,
459
+ "loss": 2.9734,
460
+ "other_loss_ratio": 0.0,
461
+ "other_mean_loss": 0.0,
462
+ "step": 700,
463
+ "vision_loss_ratio": 12.834882736206055,
464
+ "vision_mean_loss": 1.3640660047531128
465
+ },
466
+ {
467
+ "action_loss_ratio": 83.4061050415039,
468
+ "action_mean_loss": 4.073487281799316,
469
+ "epoch": 720.0,
470
+ "grad_norm": 5.882683149191454,
471
+ "learning_rate": 1.7251520205026207e-06,
472
+ "loss": 2.9788,
473
+ "other_loss_ratio": 0.0,
474
+ "other_mean_loss": 0.0,
475
+ "step": 720,
476
+ "vision_loss_ratio": 16.59389877319336,
477
+ "vision_mean_loss": 1.8910096883773804
478
+ },
479
+ {
480
+ "action_loss_ratio": 80.62750244140625,
481
+ "action_mean_loss": 3.489854574203491,
482
+ "epoch": 740.0,
483
+ "grad_norm": 5.370245064840182,
484
+ "learning_rate": 1.6309057881426227e-06,
485
+ "loss": 2.9815,
486
+ "other_loss_ratio": 0.0,
487
+ "other_mean_loss": 0.0,
488
+ "step": 740,
489
+ "vision_loss_ratio": 19.372501373291016,
490
+ "vision_mean_loss": 1.9565305709838867
491
+ },
492
+ {
493
+ "action_loss_ratio": 85.37750244140625,
494
+ "action_mean_loss": 3.623373508453369,
495
+ "epoch": 760.0,
496
+ "grad_norm": 5.63407127907182,
497
+ "learning_rate": 1.5420627451571774e-06,
498
+ "loss": 2.944,
499
+ "other_loss_ratio": 0.0,
500
+ "other_mean_loss": 0.0,
501
+ "step": 760,
502
+ "vision_loss_ratio": 14.622495651245117,
503
+ "vision_mean_loss": 1.4479979276657104
504
+ },
505
+ {
506
+ "action_loss_ratio": 84.4804916381836,
507
+ "action_mean_loss": 3.724759578704834,
508
+ "epoch": 780.0,
509
+ "grad_norm": 5.972460705476916,
510
+ "learning_rate": 1.4589735144484218e-06,
511
+ "loss": 2.9518,
512
+ "other_loss_ratio": 0.0,
513
+ "other_mean_loss": 0.0,
514
+ "step": 780,
515
+ "vision_loss_ratio": 15.519501686096191,
516
+ "vision_mean_loss": 1.5966007709503174
517
+ },
518
+ {
519
+ "action_loss_ratio": 83.96039581298828,
520
+ "action_mean_loss": 3.903813362121582,
521
+ "epoch": 800.0,
522
+ "grad_norm": 6.050149089521998,
523
+ "learning_rate": 1.3819660112501054e-06,
524
+ "loss": 2.9369,
525
+ "other_loss_ratio": 0.0,
526
+ "other_mean_loss": 0.0,
527
+ "step": 800,
528
+ "vision_loss_ratio": 16.03960418701172,
529
+ "vision_mean_loss": 1.7401432991027832
530
+ },
531
+ {
532
+ "action_loss_ratio": 79.16110229492188,
533
+ "action_mean_loss": 3.541447401046753,
534
+ "epoch": 820.0,
535
+ "grad_norm": 5.992867445886701,
536
+ "learning_rate": 1.3113441489959702e-06,
537
+ "loss": 2.9465,
538
+ "other_loss_ratio": 0.0,
539
+ "other_mean_loss": 0.0,
540
+ "step": 820,
541
+ "vision_loss_ratio": 20.838899612426758,
542
+ "vision_mean_loss": 2.175306797027588
543
+ },
544
+ {
545
+ "action_loss_ratio": 85.74028015136719,
546
+ "action_mean_loss": 3.4975011348724365,
547
+ "epoch": 840.0,
548
+ "grad_norm": 6.1157389576772285,
549
+ "learning_rate": 1.2473866399122734e-06,
550
+ "loss": 2.9488,
551
+ "other_loss_ratio": 0.0,
552
+ "other_mean_loss": 0.0,
553
+ "step": 840,
554
+ "vision_loss_ratio": 14.259719848632812,
555
+ "vision_mean_loss": 1.3572527170181274
556
+ },
557
+ {
558
+ "action_loss_ratio": 85.2520523071289,
559
+ "action_mean_loss": 3.7458434104919434,
560
+ "epoch": 860.0,
561
+ "grad_norm": 5.6609345860321945,
562
+ "learning_rate": 1.1903458950679615e-06,
563
+ "loss": 2.9334,
564
+ "other_loss_ratio": 0.0,
565
+ "other_mean_loss": 0.0,
566
+ "step": 860,
567
+ "vision_loss_ratio": 14.747945785522461,
568
+ "vision_mean_loss": 1.5120044946670532
569
+ },
570
+ {
571
+ "action_loss_ratio": 80.90141296386719,
572
+ "action_mean_loss": 4.060303688049316,
573
+ "epoch": 880.0,
574
+ "grad_norm": 6.4572859985251005,
575
+ "learning_rate": 1.1404470282234973e-06,
576
+ "loss": 2.943,
577
+ "other_loss_ratio": 0.0,
578
+ "other_mean_loss": 0.0,
579
+ "step": 880,
580
+ "vision_loss_ratio": 19.098587036132812,
581
+ "vision_mean_loss": 2.2365593910217285
582
+ },
583
+ {
584
+ "action_loss_ratio": 85.3382339477539,
585
+ "action_mean_loss": 3.4962029457092285,
586
+ "epoch": 900.0,
587
+ "grad_norm": 5.537703431468463,
588
+ "learning_rate": 1.097886967409693e-06,
589
+ "loss": 2.9616,
590
+ "other_loss_ratio": 0.0,
591
+ "other_mean_loss": 0.0,
592
+ "step": 900,
593
+ "vision_loss_ratio": 14.661762237548828,
594
+ "vision_mean_loss": 1.4015735387802124
595
+ }
596
+ ],
597
+ "logging_steps": 20,
598
+ "max_steps": 1000,
599
+ "num_input_tokens_seen": 0,
600
+ "num_train_epochs": 1000,
601
+ "save_steps": 100,
602
+ "stateful_callbacks": {
603
+ "TrainerControl": {
604
+ "args": {
605
+ "should_epoch_stop": false,
606
+ "should_evaluate": false,
607
+ "should_log": false,
608
+ "should_save": true,
609
+ "should_training_stop": false
610
+ },
611
+ "attributes": {}
612
+ }
613
+ },
614
+ "total_flos": 151778525184000.0,
615
+ "train_batch_size": 4,
616
+ "trial_name": null,
617
+ "trial_params": null
618
+ }
checkpoint-900/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c35b02cea5ee781ae722881715b4724081307b623086c3101f1abe9ea677502d
3
+ size 7352