Hugging Face's logo

sahil2801
/
ev_glaive-Math

Text Generation
Transformers
PyTorch
opt
Inference Endpoints
text-generation-inference
Model card Files Community
sahil2801 commited on
Commit
e2e4915
•
1 Parent(s): 774ac18

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. config.json +32 -0
  2. generation_config.json +7 -0
  3. optimizer.pt +3 -0
  4. pytorch_model-00001-of-00003.bin +3 -0
  5. pytorch_model-00002-of-00003.bin +3 -0
  6. pytorch_model-00003-of-00003.bin +3 -0
  7. pytorch_model.bin.index.json +524 -0
  8. rng_state_0.pth +3 -0
  9. rng_state_1.pth +3 -0
  10. rng_state_2.pth +3 -0
  11. rng_state_3.pth +3 -0
  12. rng_state_4.pth +3 -0
  13. rng_state_5.pth +3 -0
  14. rng_state_6.pth +3 -0
  15. rng_state_7.pth +3 -0
  16. scheduler.pt +3 -0
  17. special_tokens_map.json +6 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +6 -0
  20. trainer_state.json +1216 -0
  21. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 0,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 16384,
16
+ "hidden_size": 4096,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "learned_embeddings": true,
21
+ "max_position_embeddings": 2048,
22
+ "model_type": "opt",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 32,
25
+ "pad_token_id": 1,
26
+ "scale_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.28.0",
29
+ "use_cache": true,
30
+ "vocab_size": 50000,
31
+ "word_embed_proj_dim": 4096
32
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.28.0"
7
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af24341bedabd319d84e824e21bdcb64a93252eccaa86227a19a2ac1c7e99ab1
3
+ size 6657387954
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38ee5c0f7072461b706e03fba96ddd2914df45eea251078e037a0fa8a67ee5f1
3
+ size 9982139269
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733e438996d7d40e3cd9b18bd446f136aa51860ace0ccf5b49fbd889a904fed1
3
+ size 9934807401
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:443f76e0cef37ace030dbce4c191ffdf7eefe88bba5ccd82f5f0627fd4863c1e
3
+ size 7531890026
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,524 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 27448639488
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.decoder.embed_positions.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.decoder.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.decoder.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
10
+ "model.decoder.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.decoder.layers.0.fc1.bias": "pytorch_model-00001-of-00003.bin",
12
+ "model.decoder.layers.0.fc1.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.decoder.layers.0.fc2.bias": "pytorch_model-00001-of-00003.bin",
14
+ "model.decoder.layers.0.fc2.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.decoder.layers.0.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
16
+ "model.decoder.layers.0.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.decoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
18
+ "model.decoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.decoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
20
+ "model.decoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.decoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
22
+ "model.decoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.decoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
24
+ "model.decoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.decoder.layers.0.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
26
+ "model.decoder.layers.0.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.decoder.layers.1.fc1.bias": "pytorch_model-00001-of-00003.bin",
28
+ "model.decoder.layers.1.fc1.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.decoder.layers.1.fc2.bias": "pytorch_model-00001-of-00003.bin",
30
+ "model.decoder.layers.1.fc2.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.decoder.layers.1.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
32
+ "model.decoder.layers.1.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.decoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
34
+ "model.decoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.decoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
36
+ "model.decoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
37
+ "model.decoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
38
+ "model.decoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
39
+ "model.decoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
40
+ "model.decoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.decoder.layers.1.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
42
+ "model.decoder.layers.1.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.decoder.layers.10.fc1.bias": "pytorch_model-00001-of-00003.bin",
44
+ "model.decoder.layers.10.fc1.weight": "pytorch_model-00001-of-00003.bin",
45
+ "model.decoder.layers.10.fc2.bias": "pytorch_model-00001-of-00003.bin",
46
+ "model.decoder.layers.10.fc2.weight": "pytorch_model-00001-of-00003.bin",
47
+ "model.decoder.layers.10.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
48
+ "model.decoder.layers.10.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
49
+ "model.decoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
50
+ "model.decoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
51
+ "model.decoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
52
+ "model.decoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
53
+ "model.decoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
54
+ "model.decoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
55
+ "model.decoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
56
+ "model.decoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
57
+ "model.decoder.layers.10.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
58
+ "model.decoder.layers.10.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
59
+ "model.decoder.layers.11.fc1.bias": "pytorch_model-00002-of-00003.bin",
60
+ "model.decoder.layers.11.fc1.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.decoder.layers.11.fc2.bias": "pytorch_model-00002-of-00003.bin",
62
+ "model.decoder.layers.11.fc2.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.decoder.layers.11.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
64
+ "model.decoder.layers.11.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.decoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
66
+ "model.decoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
67
+ "model.decoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
68
+ "model.decoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
69
+ "model.decoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
70
+ "model.decoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
71
+ "model.decoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
72
+ "model.decoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
73
+ "model.decoder.layers.11.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
74
+ "model.decoder.layers.11.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
75
+ "model.decoder.layers.12.fc1.bias": "pytorch_model-00002-of-00003.bin",
76
+ "model.decoder.layers.12.fc1.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.decoder.layers.12.fc2.bias": "pytorch_model-00002-of-00003.bin",
78
+ "model.decoder.layers.12.fc2.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.decoder.layers.12.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
80
+ "model.decoder.layers.12.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.decoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
82
+ "model.decoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.decoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
84
+ "model.decoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.decoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
86
+ "model.decoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.decoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
88
+ "model.decoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.decoder.layers.12.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
90
+ "model.decoder.layers.12.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.decoder.layers.13.fc1.bias": "pytorch_model-00002-of-00003.bin",
92
+ "model.decoder.layers.13.fc1.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.decoder.layers.13.fc2.bias": "pytorch_model-00002-of-00003.bin",
94
+ "model.decoder.layers.13.fc2.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.decoder.layers.13.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
96
+ "model.decoder.layers.13.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.decoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
98
+ "model.decoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.decoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
100
+ "model.decoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.decoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
102
+ "model.decoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.decoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
104
+ "model.decoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.decoder.layers.13.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
106
+ "model.decoder.layers.13.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.decoder.layers.14.fc1.bias": "pytorch_model-00002-of-00003.bin",
108
+ "model.decoder.layers.14.fc1.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.decoder.layers.14.fc2.bias": "pytorch_model-00002-of-00003.bin",
110
+ "model.decoder.layers.14.fc2.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.decoder.layers.14.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
112
+ "model.decoder.layers.14.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.decoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
114
+ "model.decoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.decoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
116
+ "model.decoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
117
+ "model.decoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
118
+ "model.decoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
119
+ "model.decoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
120
+ "model.decoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
121
+ "model.decoder.layers.14.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
122
+ "model.decoder.layers.14.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
123
+ "model.decoder.layers.15.fc1.bias": "pytorch_model-00002-of-00003.bin",
124
+ "model.decoder.layers.15.fc1.weight": "pytorch_model-00002-of-00003.bin",
125
+ "model.decoder.layers.15.fc2.bias": "pytorch_model-00002-of-00003.bin",
126
+ "model.decoder.layers.15.fc2.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.decoder.layers.15.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
128
+ "model.decoder.layers.15.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.decoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
130
+ "model.decoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.decoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
132
+ "model.decoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.decoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
134
+ "model.decoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.decoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
136
+ "model.decoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.decoder.layers.15.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
138
+ "model.decoder.layers.15.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.decoder.layers.16.fc1.bias": "pytorch_model-00002-of-00003.bin",
140
+ "model.decoder.layers.16.fc1.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.decoder.layers.16.fc2.bias": "pytorch_model-00002-of-00003.bin",
142
+ "model.decoder.layers.16.fc2.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.decoder.layers.16.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
144
+ "model.decoder.layers.16.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.decoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
146
+ "model.decoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.decoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
148
+ "model.decoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.decoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
150
+ "model.decoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.decoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
152
+ "model.decoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
153
+ "model.decoder.layers.16.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
154
+ "model.decoder.layers.16.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.decoder.layers.17.fc1.bias": "pytorch_model-00002-of-00003.bin",
156
+ "model.decoder.layers.17.fc1.weight": "pytorch_model-00002-of-00003.bin",
157
+ "model.decoder.layers.17.fc2.bias": "pytorch_model-00002-of-00003.bin",
158
+ "model.decoder.layers.17.fc2.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.decoder.layers.17.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
160
+ "model.decoder.layers.17.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.decoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
162
+ "model.decoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
163
+ "model.decoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
164
+ "model.decoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
165
+ "model.decoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
166
+ "model.decoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
167
+ "model.decoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
168
+ "model.decoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
169
+ "model.decoder.layers.17.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
170
+ "model.decoder.layers.17.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
171
+ "model.decoder.layers.18.fc1.bias": "pytorch_model-00002-of-00003.bin",
172
+ "model.decoder.layers.18.fc1.weight": "pytorch_model-00002-of-00003.bin",
173
+ "model.decoder.layers.18.fc2.bias": "pytorch_model-00002-of-00003.bin",
174
+ "model.decoder.layers.18.fc2.weight": "pytorch_model-00002-of-00003.bin",
175
+ "model.decoder.layers.18.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
176
+ "model.decoder.layers.18.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
177
+ "model.decoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
178
+ "model.decoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
179
+ "model.decoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
180
+ "model.decoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
181
+ "model.decoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
182
+ "model.decoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
183
+ "model.decoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
184
+ "model.decoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
185
+ "model.decoder.layers.18.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
186
+ "model.decoder.layers.18.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
187
+ "model.decoder.layers.19.fc1.bias": "pytorch_model-00002-of-00003.bin",
188
+ "model.decoder.layers.19.fc1.weight": "pytorch_model-00002-of-00003.bin",
189
+ "model.decoder.layers.19.fc2.bias": "pytorch_model-00002-of-00003.bin",
190
+ "model.decoder.layers.19.fc2.weight": "pytorch_model-00002-of-00003.bin",
191
+ "model.decoder.layers.19.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
192
+ "model.decoder.layers.19.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
193
+ "model.decoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
194
+ "model.decoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
195
+ "model.decoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
196
+ "model.decoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
197
+ "model.decoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
198
+ "model.decoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
199
+ "model.decoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
200
+ "model.decoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
201
+ "model.decoder.layers.19.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
202
+ "model.decoder.layers.19.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
203
+ "model.decoder.layers.2.fc1.bias": "pytorch_model-00001-of-00003.bin",
204
+ "model.decoder.layers.2.fc1.weight": "pytorch_model-00001-of-00003.bin",
205
+ "model.decoder.layers.2.fc2.bias": "pytorch_model-00001-of-00003.bin",
206
+ "model.decoder.layers.2.fc2.weight": "pytorch_model-00001-of-00003.bin",
207
+ "model.decoder.layers.2.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
208
+ "model.decoder.layers.2.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
209
+ "model.decoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
210
+ "model.decoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
211
+ "model.decoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
212
+ "model.decoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
213
+ "model.decoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
214
+ "model.decoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
215
+ "model.decoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
216
+ "model.decoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.decoder.layers.2.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
218
+ "model.decoder.layers.2.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.decoder.layers.20.fc1.bias": "pytorch_model-00002-of-00003.bin",
220
+ "model.decoder.layers.20.fc1.weight": "pytorch_model-00002-of-00003.bin",
221
+ "model.decoder.layers.20.fc2.bias": "pytorch_model-00002-of-00003.bin",
222
+ "model.decoder.layers.20.fc2.weight": "pytorch_model-00002-of-00003.bin",
223
+ "model.decoder.layers.20.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
224
+ "model.decoder.layers.20.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
225
+ "model.decoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
226
+ "model.decoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
227
+ "model.decoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
228
+ "model.decoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
229
+ "model.decoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
230
+ "model.decoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
231
+ "model.decoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
232
+ "model.decoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
233
+ "model.decoder.layers.20.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
234
+ "model.decoder.layers.20.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
235
+ "model.decoder.layers.21.fc1.bias": "pytorch_model-00002-of-00003.bin",
236
+ "model.decoder.layers.21.fc1.weight": "pytorch_model-00002-of-00003.bin",
237
+ "model.decoder.layers.21.fc2.bias": "pytorch_model-00002-of-00003.bin",
238
+ "model.decoder.layers.21.fc2.weight": "pytorch_model-00002-of-00003.bin",
239
+ "model.decoder.layers.21.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
240
+ "model.decoder.layers.21.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
241
+ "model.decoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
242
+ "model.decoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
243
+ "model.decoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
244
+ "model.decoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
245
+ "model.decoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
246
+ "model.decoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
247
+ "model.decoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
248
+ "model.decoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
249
+ "model.decoder.layers.21.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
250
+ "model.decoder.layers.21.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
251
+ "model.decoder.layers.22.fc1.bias": "pytorch_model-00002-of-00003.bin",
252
+ "model.decoder.layers.22.fc1.weight": "pytorch_model-00002-of-00003.bin",
253
+ "model.decoder.layers.22.fc2.bias": "pytorch_model-00002-of-00003.bin",
254
+ "model.decoder.layers.22.fc2.weight": "pytorch_model-00002-of-00003.bin",
255
+ "model.decoder.layers.22.final_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
256
+ "model.decoder.layers.22.final_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
257
+ "model.decoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
258
+ "model.decoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
259
+ "model.decoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
260
+ "model.decoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
261
+ "model.decoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
262
+ "model.decoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
263
+ "model.decoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
264
+ "model.decoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
265
+ "model.decoder.layers.22.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
266
+ "model.decoder.layers.22.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
267
+ "model.decoder.layers.23.fc1.bias": "pytorch_model-00002-of-00003.bin",
268
+ "model.decoder.layers.23.fc1.weight": "pytorch_model-00002-of-00003.bin",
269
+ "model.decoder.layers.23.fc2.bias": "pytorch_model-00003-of-00003.bin",
270
+ "model.decoder.layers.23.fc2.weight": "pytorch_model-00003-of-00003.bin",
271
+ "model.decoder.layers.23.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
272
+ "model.decoder.layers.23.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
273
+ "model.decoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00003.bin",
274
+ "model.decoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
275
+ "model.decoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00003.bin",
276
+ "model.decoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
277
+ "model.decoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00003.bin",
278
+ "model.decoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
279
+ "model.decoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00003.bin",
280
+ "model.decoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
281
+ "model.decoder.layers.23.self_attn_layer_norm.bias": "pytorch_model-00002-of-00003.bin",
282
+ "model.decoder.layers.23.self_attn_layer_norm.weight": "pytorch_model-00002-of-00003.bin",
283
+ "model.decoder.layers.24.fc1.bias": "pytorch_model-00003-of-00003.bin",
284
+ "model.decoder.layers.24.fc1.weight": "pytorch_model-00003-of-00003.bin",
285
+ "model.decoder.layers.24.fc2.bias": "pytorch_model-00003-of-00003.bin",
286
+ "model.decoder.layers.24.fc2.weight": "pytorch_model-00003-of-00003.bin",
287
+ "model.decoder.layers.24.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
288
+ "model.decoder.layers.24.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
289
+ "model.decoder.layers.24.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
290
+ "model.decoder.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
291
+ "model.decoder.layers.24.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
292
+ "model.decoder.layers.24.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
293
+ "model.decoder.layers.24.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
294
+ "model.decoder.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
295
+ "model.decoder.layers.24.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
296
+ "model.decoder.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
297
+ "model.decoder.layers.24.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
298
+ "model.decoder.layers.24.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
299
+ "model.decoder.layers.25.fc1.bias": "pytorch_model-00003-of-00003.bin",
300
+ "model.decoder.layers.25.fc1.weight": "pytorch_model-00003-of-00003.bin",
301
+ "model.decoder.layers.25.fc2.bias": "pytorch_model-00003-of-00003.bin",
302
+ "model.decoder.layers.25.fc2.weight": "pytorch_model-00003-of-00003.bin",
303
+ "model.decoder.layers.25.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
304
+ "model.decoder.layers.25.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
305
+ "model.decoder.layers.25.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
306
+ "model.decoder.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
307
+ "model.decoder.layers.25.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
308
+ "model.decoder.layers.25.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
309
+ "model.decoder.layers.25.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
310
+ "model.decoder.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
311
+ "model.decoder.layers.25.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
312
+ "model.decoder.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
313
+ "model.decoder.layers.25.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
314
+ "model.decoder.layers.25.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
315
+ "model.decoder.layers.26.fc1.bias": "pytorch_model-00003-of-00003.bin",
316
+ "model.decoder.layers.26.fc1.weight": "pytorch_model-00003-of-00003.bin",
317
+ "model.decoder.layers.26.fc2.bias": "pytorch_model-00003-of-00003.bin",
318
+ "model.decoder.layers.26.fc2.weight": "pytorch_model-00003-of-00003.bin",
319
+ "model.decoder.layers.26.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
320
+ "model.decoder.layers.26.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
321
+ "model.decoder.layers.26.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
322
+ "model.decoder.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
323
+ "model.decoder.layers.26.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
324
+ "model.decoder.layers.26.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
325
+ "model.decoder.layers.26.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
326
+ "model.decoder.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
327
+ "model.decoder.layers.26.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
328
+ "model.decoder.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
329
+ "model.decoder.layers.26.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
330
+ "model.decoder.layers.26.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
331
+ "model.decoder.layers.27.fc1.bias": "pytorch_model-00003-of-00003.bin",
332
+ "model.decoder.layers.27.fc1.weight": "pytorch_model-00003-of-00003.bin",
333
+ "model.decoder.layers.27.fc2.bias": "pytorch_model-00003-of-00003.bin",
334
+ "model.decoder.layers.27.fc2.weight": "pytorch_model-00003-of-00003.bin",
335
+ "model.decoder.layers.27.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
336
+ "model.decoder.layers.27.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
337
+ "model.decoder.layers.27.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
338
+ "model.decoder.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
339
+ "model.decoder.layers.27.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
340
+ "model.decoder.layers.27.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
341
+ "model.decoder.layers.27.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
342
+ "model.decoder.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
343
+ "model.decoder.layers.27.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
344
+ "model.decoder.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
345
+ "model.decoder.layers.27.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
346
+ "model.decoder.layers.27.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
347
+ "model.decoder.layers.28.fc1.bias": "pytorch_model-00003-of-00003.bin",
348
+ "model.decoder.layers.28.fc1.weight": "pytorch_model-00003-of-00003.bin",
349
+ "model.decoder.layers.28.fc2.bias": "pytorch_model-00003-of-00003.bin",
350
+ "model.decoder.layers.28.fc2.weight": "pytorch_model-00003-of-00003.bin",
351
+ "model.decoder.layers.28.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
352
+ "model.decoder.layers.28.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
353
+ "model.decoder.layers.28.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
354
+ "model.decoder.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
355
+ "model.decoder.layers.28.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
356
+ "model.decoder.layers.28.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
357
+ "model.decoder.layers.28.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
358
+ "model.decoder.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
359
+ "model.decoder.layers.28.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
360
+ "model.decoder.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
361
+ "model.decoder.layers.28.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
362
+ "model.decoder.layers.28.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
363
+ "model.decoder.layers.29.fc1.bias": "pytorch_model-00003-of-00003.bin",
364
+ "model.decoder.layers.29.fc1.weight": "pytorch_model-00003-of-00003.bin",
365
+ "model.decoder.layers.29.fc2.bias": "pytorch_model-00003-of-00003.bin",
366
+ "model.decoder.layers.29.fc2.weight": "pytorch_model-00003-of-00003.bin",
367
+ "model.decoder.layers.29.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
368
+ "model.decoder.layers.29.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
369
+ "model.decoder.layers.29.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
370
+ "model.decoder.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
371
+ "model.decoder.layers.29.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
372
+ "model.decoder.layers.29.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
373
+ "model.decoder.layers.29.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
374
+ "model.decoder.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
375
+ "model.decoder.layers.29.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
376
+ "model.decoder.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
377
+ "model.decoder.layers.29.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
378
+ "model.decoder.layers.29.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
379
+ "model.decoder.layers.3.fc1.bias": "pytorch_model-00001-of-00003.bin",
380
+ "model.decoder.layers.3.fc1.weight": "pytorch_model-00001-of-00003.bin",
381
+ "model.decoder.layers.3.fc2.bias": "pytorch_model-00001-of-00003.bin",
382
+ "model.decoder.layers.3.fc2.weight": "pytorch_model-00001-of-00003.bin",
383
+ "model.decoder.layers.3.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
384
+ "model.decoder.layers.3.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
385
+ "model.decoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
386
+ "model.decoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
387
+ "model.decoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
388
+ "model.decoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
389
+ "model.decoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
390
+ "model.decoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
391
+ "model.decoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
392
+ "model.decoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
393
+ "model.decoder.layers.3.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
394
+ "model.decoder.layers.3.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
395
+ "model.decoder.layers.30.fc1.bias": "pytorch_model-00003-of-00003.bin",
396
+ "model.decoder.layers.30.fc1.weight": "pytorch_model-00003-of-00003.bin",
397
+ "model.decoder.layers.30.fc2.bias": "pytorch_model-00003-of-00003.bin",
398
+ "model.decoder.layers.30.fc2.weight": "pytorch_model-00003-of-00003.bin",
399
+ "model.decoder.layers.30.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
400
+ "model.decoder.layers.30.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
401
+ "model.decoder.layers.30.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
402
+ "model.decoder.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
403
+ "model.decoder.layers.30.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
404
+ "model.decoder.layers.30.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
405
+ "model.decoder.layers.30.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
406
+ "model.decoder.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
407
+ "model.decoder.layers.30.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
408
+ "model.decoder.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
409
+ "model.decoder.layers.30.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
410
+ "model.decoder.layers.30.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
411
+ "model.decoder.layers.31.fc1.bias": "pytorch_model-00003-of-00003.bin",
412
+ "model.decoder.layers.31.fc1.weight": "pytorch_model-00003-of-00003.bin",
413
+ "model.decoder.layers.31.fc2.bias": "pytorch_model-00003-of-00003.bin",
414
+ "model.decoder.layers.31.fc2.weight": "pytorch_model-00003-of-00003.bin",
415
+ "model.decoder.layers.31.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
416
+ "model.decoder.layers.31.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
417
+ "model.decoder.layers.31.self_attn.k_proj.bias": "pytorch_model-00003-of-00003.bin",
418
+ "model.decoder.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
419
+ "model.decoder.layers.31.self_attn.out_proj.bias": "pytorch_model-00003-of-00003.bin",
420
+ "model.decoder.layers.31.self_attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
421
+ "model.decoder.layers.31.self_attn.q_proj.bias": "pytorch_model-00003-of-00003.bin",
422
+ "model.decoder.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
423
+ "model.decoder.layers.31.self_attn.v_proj.bias": "pytorch_model-00003-of-00003.bin",
424
+ "model.decoder.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
425
+ "model.decoder.layers.31.self_attn_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
426
+ "model.decoder.layers.31.self_attn_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
427
+ "model.decoder.layers.4.fc1.bias": "pytorch_model-00001-of-00003.bin",
428
+ "model.decoder.layers.4.fc1.weight": "pytorch_model-00001-of-00003.bin",
429
+ "model.decoder.layers.4.fc2.bias": "pytorch_model-00001-of-00003.bin",
430
+ "model.decoder.layers.4.fc2.weight": "pytorch_model-00001-of-00003.bin",
431
+ "model.decoder.layers.4.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
432
+ "model.decoder.layers.4.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
433
+ "model.decoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
434
+ "model.decoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
435
+ "model.decoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
436
+ "model.decoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
437
+ "model.decoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
438
+ "model.decoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
439
+ "model.decoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
440
+ "model.decoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
441
+ "model.decoder.layers.4.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
442
+ "model.decoder.layers.4.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
443
+ "model.decoder.layers.5.fc1.bias": "pytorch_model-00001-of-00003.bin",
444
+ "model.decoder.layers.5.fc1.weight": "pytorch_model-00001-of-00003.bin",
445
+ "model.decoder.layers.5.fc2.bias": "pytorch_model-00001-of-00003.bin",
446
+ "model.decoder.layers.5.fc2.weight": "pytorch_model-00001-of-00003.bin",
447
+ "model.decoder.layers.5.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
448
+ "model.decoder.layers.5.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
449
+ "model.decoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
450
+ "model.decoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
451
+ "model.decoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
452
+ "model.decoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
453
+ "model.decoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
454
+ "model.decoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
455
+ "model.decoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
456
+ "model.decoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
457
+ "model.decoder.layers.5.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
458
+ "model.decoder.layers.5.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
459
+ "model.decoder.layers.6.fc1.bias": "pytorch_model-00001-of-00003.bin",
460
+ "model.decoder.layers.6.fc1.weight": "pytorch_model-00001-of-00003.bin",
461
+ "model.decoder.layers.6.fc2.bias": "pytorch_model-00001-of-00003.bin",
462
+ "model.decoder.layers.6.fc2.weight": "pytorch_model-00001-of-00003.bin",
463
+ "model.decoder.layers.6.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
464
+ "model.decoder.layers.6.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
465
+ "model.decoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
466
+ "model.decoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
467
+ "model.decoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
468
+ "model.decoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
469
+ "model.decoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
470
+ "model.decoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
471
+ "model.decoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
472
+ "model.decoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
473
+ "model.decoder.layers.6.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
474
+ "model.decoder.layers.6.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
475
+ "model.decoder.layers.7.fc1.bias": "pytorch_model-00001-of-00003.bin",
476
+ "model.decoder.layers.7.fc1.weight": "pytorch_model-00001-of-00003.bin",
477
+ "model.decoder.layers.7.fc2.bias": "pytorch_model-00001-of-00003.bin",
478
+ "model.decoder.layers.7.fc2.weight": "pytorch_model-00001-of-00003.bin",
479
+ "model.decoder.layers.7.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
480
+ "model.decoder.layers.7.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
481
+ "model.decoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
482
+ "model.decoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
483
+ "model.decoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
484
+ "model.decoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
485
+ "model.decoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
486
+ "model.decoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
487
+ "model.decoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
488
+ "model.decoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
489
+ "model.decoder.layers.7.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
490
+ "model.decoder.layers.7.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
491
+ "model.decoder.layers.8.fc1.bias": "pytorch_model-00001-of-00003.bin",
492
+ "model.decoder.layers.8.fc1.weight": "pytorch_model-00001-of-00003.bin",
493
+ "model.decoder.layers.8.fc2.bias": "pytorch_model-00001-of-00003.bin",
494
+ "model.decoder.layers.8.fc2.weight": "pytorch_model-00001-of-00003.bin",
495
+ "model.decoder.layers.8.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
496
+ "model.decoder.layers.8.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
497
+ "model.decoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
498
+ "model.decoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
499
+ "model.decoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
500
+ "model.decoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
501
+ "model.decoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
502
+ "model.decoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
503
+ "model.decoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
504
+ "model.decoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
505
+ "model.decoder.layers.8.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
506
+ "model.decoder.layers.8.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
507
+ "model.decoder.layers.9.fc1.bias": "pytorch_model-00001-of-00003.bin",
508
+ "model.decoder.layers.9.fc1.weight": "pytorch_model-00001-of-00003.bin",
509
+ "model.decoder.layers.9.fc2.bias": "pytorch_model-00001-of-00003.bin",
510
+ "model.decoder.layers.9.fc2.weight": "pytorch_model-00001-of-00003.bin",
511
+ "model.decoder.layers.9.final_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
512
+ "model.decoder.layers.9.final_layer_norm.weight": "pytorch_model-00001-of-00003.bin",
513
+ "model.decoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00001-of-00003.bin",
514
+ "model.decoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
515
+ "model.decoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00001-of-00003.bin",
516
+ "model.decoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
517
+ "model.decoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00001-of-00003.bin",
518
+ "model.decoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
519
+ "model.decoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00001-of-00003.bin",
520
+ "model.decoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
521
+ "model.decoder.layers.9.self_attn_layer_norm.bias": "pytorch_model-00001-of-00003.bin",
522
+ "model.decoder.layers.9.self_attn_layer_norm.weight": "pytorch_model-00001-of-00003.bin"
523
+ }
524
+ }
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c925b9e2e75d9bc3b18dc0008f7190c145ee1fd3b8de9e48caf046620ab2876
3
+ size 14647
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04812e4ea0e42df2b95d26dada1999dfd4e523f8473f65ebeace56aac3a2f47b
3
+ size 14647
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d74523c8bb01a14b834846223a5c7f9072070db559ca2dbc808dcc445778ce2
3
+ size 14647
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6990512580fbdee8bb4ff2df495914884d0f86b2f8fdea1b4ff3f6667c976cf
3
+ size 14647
rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdec7152917cb8e0efe0c32778ce884f7a19af1ae5052fa9281292df8fd1ab3b
3
+ size 14647
rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d01f01762ab9a011b7d38593996b34ee97f2074dcba30681c5b20790dccd7b7f
3
+ size 14647
rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2841ce97b6e8d3195f0e3de46775cddfdfaa19d088b1df3ef6e773e6789d6b9
3
+ size 14647
rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f55ccf8c530a38d9c0a5314f1e174d26d9f1b12bb6bc1f506a68e8d087e577e
3
+ size 14647
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e54873a0444b4bd355288b00b561ddf9f12cd28b3393a7ed91dc4a5fc4f28d09
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 2048,
4
+ "padding_side": "right",
5
+ "tokenizer_class": "PreTrainedTokenizerFast"
6
+ }
trainer_state.json ADDED
@@ -0,0 +1,1216 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9433962264150944,
5
+ "global_step": 200,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 1.0000000000000002e-06,
13
+ "loss": 0.5589,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2.0000000000000003e-06,
19
+ "loss": 0.595,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 3e-06,
25
+ "loss": 0.5789,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.000000000000001e-06,
31
+ "loss": 0.4756,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 5e-06,
37
+ "loss": 0.459,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 6e-06,
43
+ "loss": 0.4651,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 7e-06,
49
+ "loss": 0.4627,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 8.000000000000001e-06,
55
+ "loss": 0.4229,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.04,
60
+ "learning_rate": 9e-06,
61
+ "loss": 0.4236,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 1e-05,
67
+ "loss": 0.4091,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.05,
72
+ "learning_rate": 1.1000000000000001e-05,
73
+ "loss": 0.4054,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 1.2e-05,
79
+ "loss": 0.4086,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.06,
84
+ "learning_rate": 1.3000000000000001e-05,
85
+ "loss": 0.4248,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "learning_rate": 1.4e-05,
91
+ "loss": 0.4115,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.07,
96
+ "learning_rate": 1.5000000000000002e-05,
97
+ "loss": 0.3929,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.08,
102
+ "learning_rate": 1.6000000000000003e-05,
103
+ "loss": 0.3826,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.08,
108
+ "learning_rate": 1.7e-05,
109
+ "loss": 0.3515,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.08,
114
+ "learning_rate": 1.8e-05,
115
+ "loss": 0.3855,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.09,
120
+ "learning_rate": 1.9e-05,
121
+ "loss": 0.3749,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.09,
126
+ "learning_rate": 2e-05,
127
+ "loss": 0.3924,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.1,
132
+ "learning_rate": 1.9999869950890106e-05,
133
+ "loss": 0.3435,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.1,
138
+ "learning_rate": 1.9999479806942976e-05,
139
+ "loss": 0.3812,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.11,
144
+ "learning_rate": 1.9998829578306187e-05,
145
+ "loss": 0.3787,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.11,
150
+ "learning_rate": 1.9997919281892066e-05,
151
+ "loss": 0.3587,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.12,
156
+ "learning_rate": 1.9996748941377265e-05,
157
+ "loss": 0.4033,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.12,
162
+ "learning_rate": 1.9995318587202132e-05,
163
+ "loss": 0.352,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.13,
168
+ "learning_rate": 1.999362825656992e-05,
169
+ "loss": 0.349,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.13,
174
+ "learning_rate": 1.9991677993445832e-05,
175
+ "loss": 0.3826,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.14,
180
+ "learning_rate": 1.998946784855586e-05,
181
+ "loss": 0.3636,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.14,
186
+ "learning_rate": 1.9986997879385488e-05,
187
+ "loss": 0.3419,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.15,
192
+ "learning_rate": 1.998426815017817e-05,
193
+ "loss": 0.4001,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.15,
198
+ "learning_rate": 1.998127873193367e-05,
199
+ "loss": 0.3487,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.16,
204
+ "learning_rate": 1.9978029702406236e-05,
205
+ "loss": 0.3757,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.16,
210
+ "learning_rate": 1.9974521146102535e-05,
211
+ "loss": 0.3584,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.17,
216
+ "learning_rate": 1.9970753154279506e-05,
217
+ "loss": 0.3504,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.17,
222
+ "learning_rate": 1.9966725824941933e-05,
223
+ "loss": 0.3571,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.17,
228
+ "learning_rate": 1.996243926283994e-05,
229
+ "loss": 0.359,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.18,
234
+ "learning_rate": 1.9957893579466252e-05,
235
+ "loss": 0.3369,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.18,
240
+ "learning_rate": 1.9953088893053268e-05,
241
+ "loss": 0.3519,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.19,
246
+ "learning_rate": 1.994802532857004e-05,
247
+ "loss": 0.3577,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.19,
252
+ "learning_rate": 1.9942703017718977e-05,
253
+ "loss": 0.3461,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.2,
258
+ "learning_rate": 1.9937122098932428e-05,
259
+ "loss": 0.3426,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.2,
264
+ "learning_rate": 1.9931282717369104e-05,
265
+ "loss": 0.374,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.21,
270
+ "learning_rate": 1.992518502491028e-05,
271
+ "loss": 0.3566,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.21,
276
+ "learning_rate": 1.991882918015585e-05,
277
+ "loss": 0.3701,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.22,
282
+ "learning_rate": 1.99122153484202e-05,
283
+ "loss": 0.342,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.22,
288
+ "learning_rate": 1.9905343701727926e-05,
289
+ "loss": 0.3396,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.23,
294
+ "learning_rate": 1.989821441880933e-05,
295
+ "loss": 0.3572,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.23,
300
+ "learning_rate": 1.989082768509579e-05,
301
+ "loss": 0.3535,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.24,
306
+ "learning_rate": 1.9883183692714935e-05,
307
+ "loss": 0.3543,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.24,
312
+ "learning_rate": 1.9875282640485647e-05,
313
+ "loss": 0.3513,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.25,
318
+ "learning_rate": 1.986712473391289e-05,
319
+ "loss": 0.3565,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.25,
324
+ "learning_rate": 1.985871018518236e-05,
325
+ "loss": 0.335,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.25,
330
+ "learning_rate": 1.9850039213154972e-05,
331
+ "loss": 0.328,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.26,
336
+ "learning_rate": 1.984111204336116e-05,
337
+ "loss": 0.3126,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.26,
342
+ "learning_rate": 1.9831928907995032e-05,
343
+ "loss": 0.3719,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.27,
348
+ "learning_rate": 1.9822490045908293e-05,
349
+ "loss": 0.3852,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.27,
354
+ "learning_rate": 1.9812795702604073e-05,
355
+ "loss": 0.351,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.28,
360
+ "learning_rate": 1.9802846130230508e-05,
361
+ "loss": 0.3666,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.28,
366
+ "learning_rate": 1.9792641587574212e-05,
367
+ "loss": 0.3609,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.29,
372
+ "learning_rate": 1.978218234005352e-05,
373
+ "loss": 0.3126,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.29,
378
+ "learning_rate": 1.9771468659711595e-05,
379
+ "loss": 0.3305,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.3,
384
+ "learning_rate": 1.9760500825209362e-05,
385
+ "loss": 0.3426,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.3,
390
+ "learning_rate": 1.9749279121818235e-05,
391
+ "loss": 0.3118,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.31,
396
+ "learning_rate": 1.9737803841412732e-05,
397
+ "loss": 0.3213,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.31,
402
+ "learning_rate": 1.9726075282462847e-05,
403
+ "loss": 0.3293,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.32,
408
+ "learning_rate": 1.9714093750026308e-05,
409
+ "loss": 0.3571,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.32,
414
+ "learning_rate": 1.9701859555740647e-05,
415
+ "loss": 0.3239,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.33,
420
+ "learning_rate": 1.9689373017815076e-05,
421
+ "loss": 0.3312,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.33,
426
+ "learning_rate": 1.9676634461022222e-05,
427
+ "loss": 0.3802,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.33,
432
+ "learning_rate": 1.9663644216689683e-05,
433
+ "loss": 0.327,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.34,
438
+ "learning_rate": 1.96504026226914e-05,
439
+ "loss": 0.3728,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.34,
444
+ "learning_rate": 1.9636910023438878e-05,
445
+ "loss": 0.3283,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.35,
450
+ "learning_rate": 1.9623166769872216e-05,
451
+ "loss": 0.3309,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.35,
456
+ "learning_rate": 1.9609173219450998e-05,
457
+ "loss": 0.3307,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.36,
462
+ "learning_rate": 1.9594929736144978e-05,
463
+ "loss": 0.3376,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.36,
468
+ "learning_rate": 1.9580436690424617e-05,
469
+ "loss": 0.3178,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.37,
474
+ "learning_rate": 1.9565694459251457e-05,
475
+ "loss": 0.3214,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.37,
480
+ "learning_rate": 1.955070342606831e-05,
481
+ "loss": 0.3754,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.38,
486
+ "learning_rate": 1.9535463980789277e-05,
487
+ "loss": 0.3474,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.38,
492
+ "learning_rate": 1.9519976519789615e-05,
493
+ "loss": 0.3201,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.39,
498
+ "learning_rate": 1.9504241445895434e-05,
499
+ "loss": 0.3326,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.39,
504
+ "learning_rate": 1.9488259168373198e-05,
505
+ "loss": 0.3196,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.4,
510
+ "learning_rate": 1.9472030102919102e-05,
511
+ "loss": 0.3076,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.4,
516
+ "learning_rate": 1.9455554671648248e-05,
517
+ "loss": 0.3871,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.41,
522
+ "learning_rate": 1.9438833303083677e-05,
523
+ "loss": 0.3449,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.41,
528
+ "learning_rate": 1.9421866432145203e-05,
529
+ "loss": 0.3474,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.42,
534
+ "learning_rate": 1.9404654500138117e-05,
535
+ "loss": 0.3478,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.42,
540
+ "learning_rate": 1.938719795474171e-05,
541
+ "loss": 0.3307,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.42,
546
+ "learning_rate": 1.936949724999762e-05,
547
+ "loss": 0.3277,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.43,
552
+ "learning_rate": 1.9351552846298026e-05,
553
+ "loss": 0.3278,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.43,
558
+ "learning_rate": 1.9333365210373668e-05,
559
+ "loss": 0.3204,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.44,
564
+ "learning_rate": 1.9314934815281728e-05,
565
+ "loss": 0.3328,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.44,
570
+ "learning_rate": 1.9296262140393498e-05,
571
+ "loss": 0.3183,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.45,
576
+ "learning_rate": 1.9277347671381924e-05,
577
+ "loss": 0.3662,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.45,
582
+ "learning_rate": 1.925819190020898e-05,
583
+ "loss": 0.3034,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.46,
588
+ "learning_rate": 1.9238795325112867e-05,
589
+ "loss": 0.304,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.46,
594
+ "learning_rate": 1.921915845059505e-05,
595
+ "loss": 0.2996,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.47,
600
+ "learning_rate": 1.9199281787407136e-05,
601
+ "loss": 0.3254,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.47,
606
+ "learning_rate": 1.9179165852537596e-05,
607
+ "loss": 0.3244,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.48,
612
+ "learning_rate": 1.9158811169198315e-05,
613
+ "loss": 0.3305,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.48,
618
+ "learning_rate": 1.913821826681099e-05,
619
+ "loss": 0.3426,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.49,
624
+ "learning_rate": 1.9117387680993333e-05,
625
+ "loss": 0.3289,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.49,
630
+ "learning_rate": 1.9096319953545186e-05,
631
+ "loss": 0.3276,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.5,
636
+ "learning_rate": 1.9075015632434382e-05,
637
+ "loss": 0.3383,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.5,
642
+ "learning_rate": 1.9053475271782523e-05,
643
+ "loss": 0.3166,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.5,
648
+ "learning_rate": 1.9031699431850553e-05,
649
+ "loss": 0.3272,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.51,
654
+ "learning_rate": 1.900968867902419e-05,
655
+ "loss": 0.3438,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.51,
660
+ "learning_rate": 1.898744358579921e-05,
661
+ "loss": 0.329,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.52,
666
+ "learning_rate": 1.896496473076651e-05,
667
+ "loss": 0.3292,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.52,
672
+ "learning_rate": 1.8942252698597113e-05,
673
+ "loss": 0.3305,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.53,
678
+ "learning_rate": 1.891930808002694e-05,
679
+ "loss": 0.3257,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.53,
684
+ "learning_rate": 1.889613147184143e-05,
685
+ "loss": 0.3225,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.54,
690
+ "learning_rate": 1.8872723476860033e-05,
691
+ "loss": 0.3302,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.54,
696
+ "learning_rate": 1.8849084703920536e-05,
697
+ "loss": 0.3468,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.55,
702
+ "learning_rate": 1.8825215767863215e-05,
703
+ "loss": 0.3448,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.55,
708
+ "learning_rate": 1.8801117289514847e-05,
709
+ "loss": 0.3381,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.56,
714
+ "learning_rate": 1.8776789895672557e-05,
715
+ "loss": 0.3191,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.56,
720
+ "learning_rate": 1.8752234219087538e-05,
721
+ "loss": 0.2992,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.57,
726
+ "learning_rate": 1.8727450898448562e-05,
727
+ "loss": 0.3463,
728
+ "step": 120
729
+ },
730
+ {
731
+ "epoch": 0.57,
732
+ "learning_rate": 1.8702440578365387e-05,
733
+ "loss": 0.3306,
734
+ "step": 121
735
+ },
736
+ {
737
+ "epoch": 0.58,
738
+ "learning_rate": 1.867720390935199e-05,
739
+ "loss": 0.3113,
740
+ "step": 122
741
+ },
742
+ {
743
+ "epoch": 0.58,
744
+ "learning_rate": 1.8651741547809633e-05,
745
+ "loss": 0.3349,
746
+ "step": 123
747
+ },
748
+ {
749
+ "epoch": 0.58,
750
+ "learning_rate": 1.8626054156009807e-05,
751
+ "loss": 0.3386,
752
+ "step": 124
753
+ },
754
+ {
755
+ "epoch": 0.59,
756
+ "learning_rate": 1.8600142402077006e-05,
757
+ "loss": 0.3454,
758
+ "step": 125
759
+ },
760
+ {
761
+ "epoch": 0.59,
762
+ "learning_rate": 1.8574006959971335e-05,
763
+ "loss": 0.2986,
764
+ "step": 126
765
+ },
766
+ {
767
+ "epoch": 0.6,
768
+ "learning_rate": 1.8547648509470985e-05,
769
+ "loss": 0.2873,
770
+ "step": 127
771
+ },
772
+ {
773
+ "epoch": 0.6,
774
+ "learning_rate": 1.8521067736154567e-05,
775
+ "loss": 0.3618,
776
+ "step": 128
777
+ },
778
+ {
779
+ "epoch": 0.61,
780
+ "learning_rate": 1.849426533138326e-05,
781
+ "loss": 0.3221,
782
+ "step": 129
783
+ },
784
+ {
785
+ "epoch": 0.61,
786
+ "learning_rate": 1.8467241992282842e-05,
787
+ "loss": 0.3083,
788
+ "step": 130
789
+ },
790
+ {
791
+ "epoch": 0.62,
792
+ "learning_rate": 1.8439998421725555e-05,
793
+ "loss": 0.3481,
794
+ "step": 131
795
+ },
796
+ {
797
+ "epoch": 0.62,
798
+ "learning_rate": 1.8412535328311813e-05,
799
+ "loss": 0.3263,
800
+ "step": 132
801
+ },
802
+ {
803
+ "epoch": 0.63,
804
+ "learning_rate": 1.8384853426351793e-05,
805
+ "loss": 0.3102,
806
+ "step": 133
807
+ },
808
+ {
809
+ "epoch": 0.63,
810
+ "learning_rate": 1.835695343584683e-05,
811
+ "loss": 0.3209,
812
+ "step": 134
813
+ },
814
+ {
815
+ "epoch": 0.64,
816
+ "learning_rate": 1.8328836082470717e-05,
817
+ "loss": 0.3233,
818
+ "step": 135
819
+ },
820
+ {
821
+ "epoch": 0.64,
822
+ "learning_rate": 1.8300502097550807e-05,
823
+ "loss": 0.3186,
824
+ "step": 136
825
+ },
826
+ {
827
+ "epoch": 0.65,
828
+ "learning_rate": 1.8271952218049004e-05,
829
+ "loss": 0.353,
830
+ "step": 137
831
+ },
832
+ {
833
+ "epoch": 0.65,
834
+ "learning_rate": 1.8243187186542594e-05,
835
+ "loss": 0.3058,
836
+ "step": 138
837
+ },
838
+ {
839
+ "epoch": 0.66,
840
+ "learning_rate": 1.8214207751204917e-05,
841
+ "loss": 0.3083,
842
+ "step": 139
843
+ },
844
+ {
845
+ "epoch": 0.66,
846
+ "learning_rate": 1.8185014665785936e-05,
847
+ "loss": 0.2891,
848
+ "step": 140
849
+ },
850
+ {
851
+ "epoch": 0.67,
852
+ "learning_rate": 1.8155608689592604e-05,
853
+ "loss": 0.3288,
854
+ "step": 141
855
+ },
856
+ {
857
+ "epoch": 0.67,
858
+ "learning_rate": 1.8125990587469125e-05,
859
+ "loss": 0.2958,
860
+ "step": 142
861
+ },
862
+ {
863
+ "epoch": 0.67,
864
+ "learning_rate": 1.809616112977706e-05,
865
+ "loss": 0.3177,
866
+ "step": 143
867
+ },
868
+ {
869
+ "epoch": 0.68,
870
+ "learning_rate": 1.8066121092375303e-05,
871
+ "loss": 0.3451,
872
+ "step": 144
873
+ },
874
+ {
875
+ "epoch": 0.68,
876
+ "learning_rate": 1.8035871256599868e-05,
877
+ "loss": 0.2998,
878
+ "step": 145
879
+ },
880
+ {
881
+ "epoch": 0.69,
882
+ "learning_rate": 1.8005412409243604e-05,
883
+ "loss": 0.3137,
884
+ "step": 146
885
+ },
886
+ {
887
+ "epoch": 0.69,
888
+ "learning_rate": 1.797474534253571e-05,
889
+ "loss": 0.2978,
890
+ "step": 147
891
+ },
892
+ {
893
+ "epoch": 0.7,
894
+ "learning_rate": 1.7943870854121126e-05,
895
+ "loss": 0.3337,
896
+ "step": 148
897
+ },
898
+ {
899
+ "epoch": 0.7,
900
+ "learning_rate": 1.7912789747039805e-05,
901
+ "loss": 0.3047,
902
+ "step": 149
903
+ },
904
+ {
905
+ "epoch": 0.71,
906
+ "learning_rate": 1.7881502829705808e-05,
907
+ "loss": 0.3132,
908
+ "step": 150
909
+ },
910
+ {
911
+ "epoch": 0.71,
912
+ "learning_rate": 1.785001091588628e-05,
913
+ "loss": 0.3065,
914
+ "step": 151
915
+ },
916
+ {
917
+ "epoch": 0.72,
918
+ "learning_rate": 1.78183148246803e-05,
919
+ "loss": 0.3199,
920
+ "step": 152
921
+ },
922
+ {
923
+ "epoch": 0.72,
924
+ "learning_rate": 1.778641538049755e-05,
925
+ "loss": 0.2953,
926
+ "step": 153
927
+ },
928
+ {
929
+ "epoch": 0.73,
930
+ "learning_rate": 1.7754313413036907e-05,
931
+ "loss": 0.3494,
932
+ "step": 154
933
+ },
934
+ {
935
+ "epoch": 0.73,
936
+ "learning_rate": 1.7722009757264818e-05,
937
+ "loss": 0.3144,
938
+ "step": 155
939
+ },
940
+ {
941
+ "epoch": 0.74,
942
+ "learning_rate": 1.768950525339362e-05,
943
+ "loss": 0.3111,
944
+ "step": 156
945
+ },
946
+ {
947
+ "epoch": 0.74,
948
+ "learning_rate": 1.765680074685968e-05,
949
+ "loss": 0.3105,
950
+ "step": 157
951
+ },
952
+ {
953
+ "epoch": 0.75,
954
+ "learning_rate": 1.7623897088301387e-05,
955
+ "loss": 0.2959,
956
+ "step": 158
957
+ },
958
+ {
959
+ "epoch": 0.75,
960
+ "learning_rate": 1.7590795133537035e-05,
961
+ "loss": 0.3398,
962
+ "step": 159
963
+ },
964
+ {
965
+ "epoch": 0.75,
966
+ "learning_rate": 1.7557495743542586e-05,
967
+ "loss": 0.3265,
968
+ "step": 160
969
+ },
970
+ {
971
+ "epoch": 0.76,
972
+ "learning_rate": 1.7523999784429238e-05,
973
+ "loss": 0.303,
974
+ "step": 161
975
+ },
976
+ {
977
+ "epoch": 0.76,
978
+ "learning_rate": 1.7490308127420928e-05,
979
+ "loss": 0.2883,
980
+ "step": 162
981
+ },
982
+ {
983
+ "epoch": 0.77,
984
+ "learning_rate": 1.7456421648831658e-05,
985
+ "loss": 0.3115,
986
+ "step": 163
987
+ },
988
+ {
989
+ "epoch": 0.77,
990
+ "learning_rate": 1.74223412300427e-05,
991
+ "loss": 0.2881,
992
+ "step": 164
993
+ },
994
+ {
995
+ "epoch": 0.78,
996
+ "learning_rate": 1.7388067757479684e-05,
997
+ "loss": 0.2838,
998
+ "step": 165
999
+ },
1000
+ {
1001
+ "epoch": 0.78,
1002
+ "learning_rate": 1.7353602122589528e-05,
1003
+ "loss": 0.3163,
1004
+ "step": 166
1005
+ },
1006
+ {
1007
+ "epoch": 0.79,
1008
+ "learning_rate": 1.7318945221817255e-05,
1009
+ "loss": 0.3044,
1010
+ "step": 167
1011
+ },
1012
+ {
1013
+ "epoch": 0.79,
1014
+ "learning_rate": 1.7284097956582694e-05,
1015
+ "loss": 0.3064,
1016
+ "step": 168
1017
+ },
1018
+ {
1019
+ "epoch": 0.8,
1020
+ "learning_rate": 1.7249061233257004e-05,
1021
+ "loss": 0.2758,
1022
+ "step": 169
1023
+ },
1024
+ {
1025
+ "epoch": 0.8,
1026
+ "learning_rate": 1.721383596313912e-05,
1027
+ "loss": 0.3367,
1028
+ "step": 170
1029
+ },
1030
+ {
1031
+ "epoch": 0.81,
1032
+ "learning_rate": 1.7178423062432052e-05,
1033
+ "loss": 0.3172,
1034
+ "step": 171
1035
+ },
1036
+ {
1037
+ "epoch": 0.81,
1038
+ "learning_rate": 1.7142823452219036e-05,
1039
+ "loss": 0.3042,
1040
+ "step": 172
1041
+ },
1042
+ {
1043
+ "epoch": 0.82,
1044
+ "learning_rate": 1.7107038058439606e-05,
1045
+ "loss": 0.3262,
1046
+ "step": 173
1047
+ },
1048
+ {
1049
+ "epoch": 0.82,
1050
+ "learning_rate": 1.7071067811865477e-05,
1051
+ "loss": 0.3223,
1052
+ "step": 174
1053
+ },
1054
+ {
1055
+ "epoch": 0.83,
1056
+ "learning_rate": 1.7034913648076357e-05,
1057
+ "loss": 0.314,
1058
+ "step": 175
1059
+ },
1060
+ {
1061
+ "epoch": 0.83,
1062
+ "learning_rate": 1.699857650743562e-05,
1063
+ "loss": 0.3072,
1064
+ "step": 176
1065
+ },
1066
+ {
1067
+ "epoch": 0.83,
1068
+ "learning_rate": 1.6962057335065814e-05,
1069
+ "loss": 0.29,
1070
+ "step": 177
1071
+ },
1072
+ {
1073
+ "epoch": 0.84,
1074
+ "learning_rate": 1.692535708082412e-05,
1075
+ "loss": 0.286,
1076
+ "step": 178
1077
+ },
1078
+ {
1079
+ "epoch": 0.84,
1080
+ "learning_rate": 1.6888476699277608e-05,
1081
+ "loss": 0.3031,
1082
+ "step": 179
1083
+ },
1084
+ {
1085
+ "epoch": 0.85,
1086
+ "learning_rate": 1.6851417149678442e-05,
1087
+ "loss": 0.3431,
1088
+ "step": 180
1089
+ },
1090
+ {
1091
+ "epoch": 0.85,
1092
+ "learning_rate": 1.6814179395938915e-05,
1093
+ "loss": 0.2891,
1094
+ "step": 181
1095
+ },
1096
+ {
1097
+ "epoch": 0.86,
1098
+ "learning_rate": 1.6776764406606362e-05,
1099
+ "loss": 0.2751,
1100
+ "step": 182
1101
+ },
1102
+ {
1103
+ "epoch": 0.86,
1104
+ "learning_rate": 1.6739173154838e-05,
1105
+ "loss": 0.3016,
1106
+ "step": 183
1107
+ },
1108
+ {
1109
+ "epoch": 0.87,
1110
+ "learning_rate": 1.67014066183756e-05,
1111
+ "loss": 0.2722,
1112
+ "step": 184
1113
+ },
1114
+ {
1115
+ "epoch": 0.87,
1116
+ "learning_rate": 1.6663465779520042e-05,
1117
+ "loss": 0.3048,
1118
+ "step": 185
1119
+ },
1120
+ {
1121
+ "epoch": 0.88,
1122
+ "learning_rate": 1.6625351625105796e-05,
1123
+ "loss": 0.2792,
1124
+ "step": 186
1125
+ },
1126
+ {
1127
+ "epoch": 0.88,
1128
+ "learning_rate": 1.6587065146475232e-05,
1129
+ "loss": 0.3221,
1130
+ "step": 187
1131
+ },
1132
+ {
1133
+ "epoch": 0.89,
1134
+ "learning_rate": 1.6548607339452853e-05,
1135
+ "loss": 0.3173,
1136
+ "step": 188
1137
+ },
1138
+ {
1139
+ "epoch": 0.89,
1140
+ "learning_rate": 1.650997920431936e-05,
1141
+ "loss": 0.337,
1142
+ "step": 189
1143
+ },
1144
+ {
1145
+ "epoch": 0.9,
1146
+ "learning_rate": 1.6471181745785673e-05,
1147
+ "loss": 0.3171,
1148
+ "step": 190
1149
+ },
1150
+ {
1151
+ "epoch": 0.9,
1152
+ "learning_rate": 1.643221597296679e-05,
1153
+ "loss": 0.291,
1154
+ "step": 191
1155
+ },
1156
+ {
1157
+ "epoch": 0.91,
1158
+ "learning_rate": 1.6393082899355516e-05,
1159
+ "loss": 0.3013,
1160
+ "step": 192
1161
+ },
1162
+ {
1163
+ "epoch": 0.91,
1164
+ "learning_rate": 1.6353783542796137e-05,
1165
+ "loss": 0.276,
1166
+ "step": 193
1167
+ },
1168
+ {
1169
+ "epoch": 0.92,
1170
+ "learning_rate": 1.631431892545791e-05,
1171
+ "loss": 0.3074,
1172
+ "step": 194
1173
+ },
1174
+ {
1175
+ "epoch": 0.92,
1176
+ "learning_rate": 1.627469007380852e-05,
1177
+ "loss": 0.3104,
1178
+ "step": 195
1179
+ },
1180
+ {
1181
+ "epoch": 0.92,
1182
+ "learning_rate": 1.6234898018587336e-05,
1183
+ "loss": 0.3518,
1184
+ "step": 196
1185
+ },
1186
+ {
1187
+ "epoch": 0.93,
1188
+ "learning_rate": 1.619494379477863e-05,
1189
+ "loss": 0.3075,
1190
+ "step": 197
1191
+ },
1192
+ {
1193
+ "epoch": 0.93,
1194
+ "learning_rate": 1.6154828441584655e-05,
1195
+ "loss": 0.2868,
1196
+ "step": 198
1197
+ },
1198
+ {
1199
+ "epoch": 0.94,
1200
+ "learning_rate": 1.6114553002398602e-05,
1201
+ "loss": 0.3187,
1202
+ "step": 199
1203
+ },
1204
+ {
1205
+ "epoch": 0.94,
1206
+ "learning_rate": 1.607411852477748e-05,
1207
+ "loss": 0.2594,
1208
+ "step": 200
1209
+ }
1210
+ ],
1211
+ "max_steps": 636,
1212
+ "num_train_epochs": 3,
1213
+ "total_flos": 5.211759089759027e+16,
1214
+ "trial_name": null,
1215
+ "trial_params": null
1216
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31c0d08e287d577e15b95a3cc3b0f0d2c9af92cef22db013e7e2f9abf763d3ad
3
+ size 3771