elmadany commited on
Commit
6bdf31b
1 Parent(s): 00b99e0

commit from elmadany

Browse files
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/elmadany/T5/OSACT2022/T5_output/new_multinode_Torjoman_Clean_1M_data_with_Sim_MSA_1M_base_5e-5_256_256/checkpoint-74024",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "transformers_version": "4.5.1",
24
+ "use_cache": true,
25
+ "vocab_size": 110080
26
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a1657ba9ecaa5d45c89e09598d122c4a3f49dcc47e8e269bbfd2987645bb235
3
+ size 2262342065
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15aa8bcc2c1513f70c47bd4ef4d7555a28df0a19183c3dfdeec372d8a68bd0dd
3
+ size 1131179919
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7bbfaf7a9f97ea7016a14b6b828cb40fc7d1c13c3ad605cdfb860fbc490f5bf
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c7ae4407451bf02b459edec774d0539a06615005dd34d5c85c5c06765ff1606
3
+ size 2435308
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "/home/elmadany/T5/ArT5_models/MSA_1M_base"}
trainer_state.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 22.0,
5
+ "global_step": 215380,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 4.9500000000000004e-05,
13
+ "loss": 5.4101,
14
+ "step": 3896
15
+ },
16
+ {
17
+ "epoch": 2.0,
18
+ "learning_rate": 4.9e-05,
19
+ "loss": 3.7774,
20
+ "step": 7792
21
+ },
22
+ {
23
+ "epoch": 3.0,
24
+ "learning_rate": 4.85e-05,
25
+ "loss": 3.4166,
26
+ "step": 11688
27
+ },
28
+ {
29
+ "epoch": 4.0,
30
+ "learning_rate": 4.8e-05,
31
+ "loss": 3.2281,
32
+ "step": 15584
33
+ },
34
+ {
35
+ "epoch": 5.0,
36
+ "learning_rate": 4.75e-05,
37
+ "loss": 3.105,
38
+ "step": 19480
39
+ },
40
+ {
41
+ "epoch": 6.0,
42
+ "learning_rate": 4.7e-05,
43
+ "loss": 3.0041,
44
+ "step": 23376
45
+ },
46
+ {
47
+ "epoch": 7.0,
48
+ "learning_rate": 4.6500000000000005e-05,
49
+ "loss": 2.9418,
50
+ "step": 27272
51
+ },
52
+ {
53
+ "epoch": 8.0,
54
+ "learning_rate": 4.600000000000001e-05,
55
+ "loss": 2.8758,
56
+ "step": 31168
57
+ },
58
+ {
59
+ "epoch": 9.0,
60
+ "learning_rate": 4.55e-05,
61
+ "loss": 2.8427,
62
+ "step": 35064
63
+ },
64
+ {
65
+ "epoch": 10.0,
66
+ "learning_rate": 4.5e-05,
67
+ "loss": 2.791,
68
+ "step": 38960
69
+ },
70
+ {
71
+ "epoch": 11.0,
72
+ "learning_rate": 4.4500000000000004e-05,
73
+ "loss": 2.7628,
74
+ "step": 42856
75
+ },
76
+ {
77
+ "epoch": 12.0,
78
+ "learning_rate": 4.4000000000000006e-05,
79
+ "loss": 2.7277,
80
+ "step": 46752
81
+ },
82
+ {
83
+ "epoch": 13.0,
84
+ "learning_rate": 4.35e-05,
85
+ "loss": 2.7199,
86
+ "step": 50648
87
+ },
88
+ {
89
+ "epoch": 14.0,
90
+ "learning_rate": 4.3e-05,
91
+ "loss": 2.6665,
92
+ "step": 54544
93
+ },
94
+ {
95
+ "epoch": 15.0,
96
+ "learning_rate": 4.25e-05,
97
+ "loss": 2.6518,
98
+ "step": 58440
99
+ },
100
+ {
101
+ "epoch": 16.0,
102
+ "learning_rate": 4.2e-05,
103
+ "loss": 2.6451,
104
+ "step": 62336
105
+ },
106
+ {
107
+ "epoch": 17.0,
108
+ "learning_rate": 4.15e-05,
109
+ "loss": 2.6108,
110
+ "step": 66232
111
+ },
112
+ {
113
+ "epoch": 18.0,
114
+ "learning_rate": 4.1e-05,
115
+ "loss": 2.5972,
116
+ "step": 70128
117
+ },
118
+ {
119
+ "epoch": 19.0,
120
+ "learning_rate": 4.05e-05,
121
+ "loss": 2.5859,
122
+ "step": 74024
123
+ },
124
+ {
125
+ "epoch": 8.0,
126
+ "learning_rate": 4.600000000000001e-05,
127
+ "loss": 2.9427,
128
+ "step": 78320
129
+ },
130
+ {
131
+ "epoch": 9.0,
132
+ "learning_rate": 4.55e-05,
133
+ "loss": 2.9183,
134
+ "step": 88110
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 4.5e-05,
139
+ "loss": 2.8809,
140
+ "step": 97900
141
+ },
142
+ {
143
+ "epoch": 11.0,
144
+ "learning_rate": 4.4500000000000004e-05,
145
+ "loss": 2.8521,
146
+ "step": 107690
147
+ },
148
+ {
149
+ "epoch": 12.0,
150
+ "learning_rate": 4.4000000000000006e-05,
151
+ "loss": 2.8272,
152
+ "step": 117480
153
+ },
154
+ {
155
+ "epoch": 13.0,
156
+ "learning_rate": 4.35e-05,
157
+ "loss": 2.8104,
158
+ "step": 127270
159
+ },
160
+ {
161
+ "epoch": 14.0,
162
+ "learning_rate": 4.3e-05,
163
+ "loss": 2.7856,
164
+ "step": 137060
165
+ },
166
+ {
167
+ "epoch": 15.0,
168
+ "learning_rate": 4.25e-05,
169
+ "loss": 2.7625,
170
+ "step": 146850
171
+ },
172
+ {
173
+ "epoch": 16.0,
174
+ "learning_rate": 4.2e-05,
175
+ "loss": 2.7459,
176
+ "step": 156640
177
+ },
178
+ {
179
+ "epoch": 17.0,
180
+ "learning_rate": 4.15e-05,
181
+ "loss": 2.734,
182
+ "step": 166430
183
+ },
184
+ {
185
+ "epoch": 18.0,
186
+ "learning_rate": 4.1e-05,
187
+ "loss": 2.7209,
188
+ "step": 176220
189
+ },
190
+ {
191
+ "epoch": 19.0,
192
+ "learning_rate": 4.05e-05,
193
+ "loss": 2.7129,
194
+ "step": 186010
195
+ },
196
+ {
197
+ "epoch": 20.0,
198
+ "learning_rate": 4e-05,
199
+ "loss": 2.6932,
200
+ "step": 195800
201
+ },
202
+ {
203
+ "epoch": 21.0,
204
+ "learning_rate": 3.9500000000000005e-05,
205
+ "loss": 2.6885,
206
+ "step": 205590
207
+ },
208
+ {
209
+ "epoch": 22.0,
210
+ "learning_rate": 3.9000000000000006e-05,
211
+ "loss": 2.679,
212
+ "step": 215380
213
+ }
214
+ ],
215
+ "max_steps": 979000,
216
+ "num_train_epochs": 100,
217
+ "total_flos": 5.872346596487864e+23,
218
+ "trial_name": null,
219
+ "trial_params": null
220
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5039979155a9e5f4d85b972984098e3104effeaf65483290ef839085078fc422
3
+ size 2607