Fitsum Gaim commited on
Commit
9240c88
1 Parent(s): 3693ed9
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ checkpoint-*/
2
+ runs/
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.5347459301325058,
4
+ "train_runtime": 6415.5456,
5
+ "train_samples": 130319,
6
+ "train_samples_per_second": 40.626,
7
+ "train_steps_per_second": 3.386
8
+ }
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 6,
19
+ "num_heads": 8,
20
+ "num_layers": 6,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "task_specific_params": {
25
+ "summarization": {
26
+ "early_stopping": true,
27
+ "length_penalty": 2.0,
28
+ "max_length": 200,
29
+ "min_length": 30,
30
+ "no_repeat_ngram_size": 3,
31
+ "num_beams": 4,
32
+ "prefix": "summarize: "
33
+ },
34
+ "translation_en_to_de": {
35
+ "early_stopping": true,
36
+ "max_length": 300,
37
+ "num_beams": 4,
38
+ "prefix": "translate English to German: "
39
+ },
40
+ "translation_en_to_fr": {
41
+ "early_stopping": true,
42
+ "max_length": 300,
43
+ "num_beams": 4,
44
+ "prefix": "translate English to French: "
45
+ },
46
+ "translation_en_to_ro": {
47
+ "early_stopping": true,
48
+ "max_length": 300,
49
+ "num_beams": 4,
50
+ "prefix": "translate English to Romanian: "
51
+ }
52
+ },
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.16.0",
55
+ "use_cache": true,
56
+ "vocab_size": 32100
57
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa8dfad8c3a8697d9aea43078b486376a88806e02cfc61b36ad95a4e9e039a9
3
+ size 242028283
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>"]}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.5347459301325058,
4
+ "train_runtime": 6415.5456,
5
+ "train_samples": 130319,
6
+ "train_samples_per_second": 40.626,
7
+ "train_steps_per_second": 3.386
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,283 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 21720,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.05,
12
+ "learning_rate": 2.930939226519337e-05,
13
+ "loss": 0.6989,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.09,
18
+ "learning_rate": 2.861878453038674e-05,
19
+ "loss": 0.6341,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.14,
24
+ "learning_rate": 2.7928176795580113e-05,
25
+ "loss": 0.5836,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.18,
30
+ "learning_rate": 2.7237569060773482e-05,
31
+ "loss": 0.5758,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.23,
36
+ "learning_rate": 2.6546961325966852e-05,
37
+ "loss": 0.5956,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.28,
42
+ "learning_rate": 2.585635359116022e-05,
43
+ "loss": 0.584,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.32,
48
+ "learning_rate": 2.516574585635359e-05,
49
+ "loss": 0.5533,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.37,
54
+ "learning_rate": 2.4475138121546964e-05,
55
+ "loss": 0.5688,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.41,
60
+ "learning_rate": 2.3784530386740334e-05,
61
+ "loss": 0.5749,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.46,
66
+ "learning_rate": 2.3093922651933703e-05,
67
+ "loss": 0.5635,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.51,
72
+ "learning_rate": 2.2403314917127073e-05,
73
+ "loss": 0.554,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.55,
78
+ "learning_rate": 2.1712707182320442e-05,
79
+ "loss": 0.5563,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.6,
84
+ "learning_rate": 2.1022099447513815e-05,
85
+ "loss": 0.5607,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.64,
90
+ "learning_rate": 2.0331491712707185e-05,
91
+ "loss": 0.5657,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.69,
96
+ "learning_rate": 1.9640883977900554e-05,
97
+ "loss": 0.5345,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.74,
102
+ "learning_rate": 1.8950276243093924e-05,
103
+ "loss": 0.5502,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.78,
108
+ "learning_rate": 1.825966850828729e-05,
109
+ "loss": 0.5417,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.83,
114
+ "learning_rate": 1.7569060773480663e-05,
115
+ "loss": 0.5506,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.87,
120
+ "learning_rate": 1.6878453038674033e-05,
121
+ "loss": 0.5352,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.92,
126
+ "learning_rate": 1.6187845303867402e-05,
127
+ "loss": 0.5388,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.97,
132
+ "learning_rate": 1.5497237569060772e-05,
133
+ "loss": 0.5312,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.01,
138
+ "learning_rate": 1.4806629834254145e-05,
139
+ "loss": 0.5222,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.06,
144
+ "learning_rate": 1.4116022099447514e-05,
145
+ "loss": 0.4981,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.1,
150
+ "learning_rate": 1.3425414364640886e-05,
151
+ "loss": 0.5235,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.15,
156
+ "learning_rate": 1.2734806629834255e-05,
157
+ "loss": 0.5144,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.2,
162
+ "learning_rate": 1.2044198895027623e-05,
163
+ "loss": 0.5037,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.24,
168
+ "learning_rate": 1.1353591160220994e-05,
169
+ "loss": 0.4856,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.29,
174
+ "learning_rate": 1.0662983425414364e-05,
175
+ "loss": 0.5175,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.34,
180
+ "learning_rate": 9.972375690607735e-06,
181
+ "loss": 0.5023,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.38,
186
+ "learning_rate": 9.281767955801105e-06,
187
+ "loss": 0.4884,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.43,
192
+ "learning_rate": 8.591160220994474e-06,
193
+ "loss": 0.5,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.47,
198
+ "learning_rate": 7.900552486187846e-06,
199
+ "loss": 0.5106,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.52,
204
+ "learning_rate": 7.209944751381215e-06,
205
+ "loss": 0.52,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.57,
210
+ "learning_rate": 6.519337016574586e-06,
211
+ "loss": 0.4942,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.61,
216
+ "learning_rate": 5.828729281767956e-06,
217
+ "loss": 0.4999,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.66,
222
+ "learning_rate": 5.1381215469613265e-06,
223
+ "loss": 0.4934,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.7,
228
+ "learning_rate": 4.447513812154697e-06,
229
+ "loss": 0.5301,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.75,
234
+ "learning_rate": 3.756906077348067e-06,
235
+ "loss": 0.4763,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.8,
240
+ "learning_rate": 3.0662983425414365e-06,
241
+ "loss": 0.4909,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.84,
246
+ "learning_rate": 2.375690607734807e-06,
247
+ "loss": 0.506,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.89,
252
+ "learning_rate": 1.6850828729281769e-06,
253
+ "loss": 0.5036,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.93,
258
+ "learning_rate": 9.944751381215469e-07,
259
+ "loss": 0.4891,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.98,
264
+ "learning_rate": 3.0386740331491715e-07,
265
+ "loss": 0.4841,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 2.0,
270
+ "step": 21720,
271
+ "total_flos": 2.645641233904435e+16,
272
+ "train_loss": 0.5347459301325058,
273
+ "train_runtime": 6415.5456,
274
+ "train_samples_per_second": 40.626,
275
+ "train_steps_per_second": 3.386
276
+ }
277
+ ],
278
+ "max_steps": 21720,
279
+ "num_train_epochs": 2,
280
+ "total_flos": 2.645641233904435e+16,
281
+ "trial_name": null,
282
+ "trial_params": null
283
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63fac16264b1351d56e31b661c4ac323fa9b6e7dbb8cf772a8638e26af30be78
3
+ size 3119