Muhammad Khalifa commited on
Commit
651204f
·
1 Parent(s): 044add8

first commit

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<<": 32100,
3
+ ">>": 32101,
4
+ "[CLS]": 32102,
5
+ "[SEP]": 32103
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c05c608e6d775d52d199df87b3af9f3843d3ae63eef01b4702743461dc2ddbd
3
+ size 3136877397
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904813fbf202223b7cceca21e24eaa502c04cddcea968511464afb8f6dd77f94
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1133e7b4054ddcb09e90361eba3fa18d4fd20b990f3cd2eb978a86e5b23871ba
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "cls_token": "[CLS]",
105
+ "eos_token": "</s>",
106
+ "pad_token": "<pad>",
107
+ "sep_token": "[SEP]",
108
+ "unk_token": "<unk>"
109
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "clean_up_tokenization_spaces": true,
105
+ "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
108
+ "pad_token": "<pad>",
109
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
trainer_state.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.47151947021484375,
3
+ "best_model_checkpoint": "ckpts/discrim/contrastive_models/gen.t5.large/flan_t5_large_svamp-clean_100K_max_align_5/checkpoint-2000",
4
+ "epoch": 0.5918035212309514,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 2.958579881656805e-06,
13
+ "loss": 1.0002,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.03,
18
+ "learning_rate": 5.91715976331361e-06,
19
+ "loss": 1.0001,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 8.875739644970414e-06,
25
+ "loss": 0.9989,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.06,
30
+ "learning_rate": 1.183431952662722e-05,
31
+ "loss": 0.9972,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.07,
36
+ "learning_rate": 1.4792899408284025e-05,
37
+ "loss": 0.995,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.09,
42
+ "learning_rate": 1.7751479289940828e-05,
43
+ "loss": 0.9897,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "learning_rate": 2.071005917159763e-05,
49
+ "loss": 0.9809,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.12,
54
+ "learning_rate": 2.366863905325444e-05,
55
+ "loss": 0.8868,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.13,
60
+ "learning_rate": 2.6627218934911244e-05,
61
+ "loss": 0.7408,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.15,
66
+ "learning_rate": 2.958579881656805e-05,
67
+ "loss": 0.674,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.16,
72
+ "learning_rate": 3.254437869822485e-05,
73
+ "loss": 0.6155,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.18,
78
+ "learning_rate": 3.5502958579881656e-05,
79
+ "loss": 0.5576,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 0.19,
84
+ "learning_rate": 3.846153846153846e-05,
85
+ "loss": 0.5003,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 0.21,
90
+ "learning_rate": 4.142011834319526e-05,
91
+ "loss": 0.4514,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 0.22,
96
+ "learning_rate": 4.4378698224852076e-05,
97
+ "loss": 0.4074,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 0.24,
102
+ "learning_rate": 4.733727810650888e-05,
103
+ "loss": 0.3495,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 0.25,
108
+ "learning_rate": 5.029585798816568e-05,
109
+ "loss": 0.3617,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 0.27,
114
+ "learning_rate": 5.325443786982249e-05,
115
+ "loss": 0.3384,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 0.28,
120
+ "learning_rate": 5.6213017751479294e-05,
121
+ "loss": 0.2962,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 0.3,
126
+ "learning_rate": 5.91715976331361e-05,
127
+ "loss": 0.2602,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 0.3,
132
+ "eval_loss": 0.6183895468711853,
133
+ "eval_runtime": 115.5435,
134
+ "eval_samples_per_second": 156.513,
135
+ "eval_steps_per_second": 19.568,
136
+ "step": 1000
137
+ },
138
+ {
139
+ "epoch": 0.31,
140
+ "learning_rate": 5.9999239256099436e-05,
141
+ "loss": 0.2554,
142
+ "step": 1050
143
+ },
144
+ {
145
+ "epoch": 0.33,
146
+ "learning_rate": 5.9995658680583245e-05,
147
+ "loss": 0.2386,
148
+ "step": 1100
149
+ },
150
+ {
151
+ "epoch": 0.34,
152
+ "learning_rate": 5.9989143572558144e-05,
153
+ "loss": 0.213,
154
+ "step": 1150
155
+ },
156
+ {
157
+ "epoch": 0.36,
158
+ "learning_rate": 5.997969456940961e-05,
159
+ "loss": 0.2021,
160
+ "step": 1200
161
+ },
162
+ {
163
+ "epoch": 0.37,
164
+ "learning_rate": 5.9967312595551613e-05,
165
+ "loss": 0.1926,
166
+ "step": 1250
167
+ },
168
+ {
169
+ "epoch": 0.38,
170
+ "learning_rate": 5.9951998862336304e-05,
171
+ "loss": 0.1712,
172
+ "step": 1300
173
+ },
174
+ {
175
+ "epoch": 0.4,
176
+ "learning_rate": 5.9933754867935396e-05,
177
+ "loss": 0.1654,
178
+ "step": 1350
179
+ },
180
+ {
181
+ "epoch": 0.41,
182
+ "learning_rate": 5.991258239719367e-05,
183
+ "loss": 0.1424,
184
+ "step": 1400
185
+ },
186
+ {
187
+ "epoch": 0.43,
188
+ "learning_rate": 5.9888483521454334e-05,
189
+ "loss": 0.1452,
190
+ "step": 1450
191
+ },
192
+ {
193
+ "epoch": 0.44,
194
+ "learning_rate": 5.986146059835637e-05,
195
+ "loss": 0.1485,
196
+ "step": 1500
197
+ },
198
+ {
199
+ "epoch": 0.46,
200
+ "learning_rate": 5.983151627160388e-05,
201
+ "loss": 0.1182,
202
+ "step": 1550
203
+ },
204
+ {
205
+ "epoch": 0.47,
206
+ "learning_rate": 5.9798653470707503e-05,
207
+ "loss": 0.1215,
208
+ "step": 1600
209
+ },
210
+ {
211
+ "epoch": 0.49,
212
+ "learning_rate": 5.976287541069771e-05,
213
+ "loss": 0.1183,
214
+ "step": 1650
215
+ },
216
+ {
217
+ "epoch": 0.5,
218
+ "learning_rate": 5.972418559181037e-05,
219
+ "loss": 0.0983,
220
+ "step": 1700
221
+ },
222
+ {
223
+ "epoch": 0.52,
224
+ "learning_rate": 5.968258779914428e-05,
225
+ "loss": 0.1155,
226
+ "step": 1750
227
+ },
228
+ {
229
+ "epoch": 0.53,
230
+ "learning_rate": 5.9638086102290845e-05,
231
+ "loss": 0.0874,
232
+ "step": 1800
233
+ },
234
+ {
235
+ "epoch": 0.55,
236
+ "learning_rate": 5.9590684854935956e-05,
237
+ "loss": 0.0993,
238
+ "step": 1850
239
+ },
240
+ {
241
+ "epoch": 0.56,
242
+ "learning_rate": 5.9540388694434064e-05,
243
+ "loss": 0.088,
244
+ "step": 1900
245
+ },
246
+ {
247
+ "epoch": 0.58,
248
+ "learning_rate": 5.948720254135451e-05,
249
+ "loss": 0.0849,
250
+ "step": 1950
251
+ },
252
+ {
253
+ "epoch": 0.59,
254
+ "learning_rate": 5.943113159900009e-05,
255
+ "loss": 0.0864,
256
+ "step": 2000
257
+ },
258
+ {
259
+ "epoch": 0.59,
260
+ "eval_loss": 0.47151947021484375,
261
+ "eval_runtime": 115.9067,
262
+ "eval_samples_per_second": 156.022,
263
+ "eval_steps_per_second": 19.507,
264
+ "step": 2000
265
+ }
266
+ ],
267
+ "max_steps": 16895,
268
+ "num_train_epochs": 5,
269
+ "total_flos": 0.0,
270
+ "trial_name": null,
271
+ "trial_params": null
272
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f951071485bdcc0766cffcc8f58a4a447d206ce924d2f36cec1ce13f4083b7
3
+ size 3835