Hugging Face's logo

gigant
/
led_tib

Text2Text Generation
Transformers
PyTorch
led
Inference Endpoints
Model card Files Community
1
gigant commited on
Commit
45b30e7
·
1 Parent(s): d8bf49a

Upload 13 files

Browse files
Files changed (13) hide show
  1. config.json +59 -0
  2. generation_config.json +15 -0
  3. merges.txt +0 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +51 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +65 -0
  11. trainer_state.json +543 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "allenai/led-base-16384",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "LEDForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_window": [
10
+ 1024,
11
+ 1024,
12
+ 1024,
13
+ 1024,
14
+ 1024,
15
+ 1024
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 768,
21
+ "decoder_attention_heads": 12,
22
+ "decoder_ffn_dim": 3072,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 2,
26
+ "dropout": 0.1,
27
+ "early_stopping": true,
28
+ "encoder_attention_heads": 12,
29
+ "encoder_ffn_dim": 3072,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 2,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1",
36
+ "2": "LABEL_2"
37
+ },
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1,
43
+ "LABEL_2": 2
44
+ },
45
+ "length_penalty": 2.0,
46
+ "max_decoder_position_embeddings": 1024,
47
+ "max_encoder_position_embeddings": 16384,
48
+ "max_length": 512,
49
+ "min_length": 100,
50
+ "model_type": "led",
51
+ "no_repeat_ngram_size": 3,
52
+ "num_beams": 2,
53
+ "num_hidden_layers": 6,
54
+ "pad_token_id": 1,
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.26.1",
57
+ "use_cache": false,
58
+ "vocab_size": 50265
59
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "length_penalty": 2.0,
8
+ "max_length": 512,
9
+ "min_length": 100,
10
+ "no_repeat_ngram_size": 3,
11
+ "num_beams": 2,
12
+ "pad_token_id": 1,
13
+ "transformers_version": "4.26.1",
14
+ "use_cache": false
15
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31a62e04ca4e4a2ff4ba9af226d6a8bdd8a2408db11cbe1dcdf372411c7a8df6
3
+ size 1294929093
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a0b79fd896fb2c5b6969a83f4954909c9f1e0ea1712e76caacc4a146aae663
3
+ size 647680813
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5696b7f72d7c51b73808afbee177c7cb1981b9a504f58732b3a83cf315a56262
3
+ size 14639
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b25c9b37ea436ac9e0b11121e5435f484b3e45d61a0163627e92d5548b93023a
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 16384,
37
+ "name_or_path": "allenai/led-base-16384",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": "/home/gigant/.cache/huggingface/hub/models--allenai--led-base-16384/snapshots/38335783885b338d93791936c54bb4be46bebed9/special_tokens_map.json",
55
+ "tokenizer_class": "LEDTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
trainer_state.json ADDED
@@ -0,0 +1,543 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 6.092730844793713,
5
+ "global_step": 7750,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.2,
12
+ "learning_rate": 8.333333333333334e-06,
13
+ "loss": 3.8654,
14
+ "step": 250
15
+ },
16
+ {
17
+ "epoch": 0.2,
18
+ "eval_loss": 3.5099494457244873,
19
+ "eval_rouge2_fmeasure": 0.0532,
20
+ "eval_rouge2_precision": 0.064,
21
+ "eval_rouge2_recall": 0.0596,
22
+ "eval_runtime": 2410.2832,
23
+ "eval_samples_per_second": 0.222,
24
+ "eval_steps_per_second": 0.111,
25
+ "step": 250
26
+ },
27
+ {
28
+ "epoch": 0.39,
29
+ "learning_rate": 1.6666666666666667e-05,
30
+ "loss": 3.5981,
31
+ "step": 500
32
+ },
33
+ {
34
+ "epoch": 0.39,
35
+ "eval_loss": 3.4266083240509033,
36
+ "eval_rouge2_fmeasure": 0.0569,
37
+ "eval_rouge2_precision": 0.0643,
38
+ "eval_rouge2_recall": 0.0679,
39
+ "eval_runtime": 4056.8313,
40
+ "eval_samples_per_second": 0.132,
41
+ "eval_steps_per_second": 0.066,
42
+ "step": 500
43
+ },
44
+ {
45
+ "epoch": 0.59,
46
+ "learning_rate": 2.5e-05,
47
+ "loss": 3.5025,
48
+ "step": 750
49
+ },
50
+ {
51
+ "epoch": 0.59,
52
+ "eval_loss": 3.350733995437622,
53
+ "eval_rouge2_fmeasure": 0.0601,
54
+ "eval_rouge2_precision": 0.074,
55
+ "eval_rouge2_recall": 0.0647,
56
+ "eval_runtime": 1930.5126,
57
+ "eval_samples_per_second": 0.278,
58
+ "eval_steps_per_second": 0.139,
59
+ "step": 750
60
+ },
61
+ {
62
+ "epoch": 0.79,
63
+ "learning_rate": 3.3333333333333335e-05,
64
+ "loss": 3.4387,
65
+ "step": 1000
66
+ },
67
+ {
68
+ "epoch": 0.79,
69
+ "eval_loss": 3.3093879222869873,
70
+ "eval_rouge2_fmeasure": 0.0619,
71
+ "eval_rouge2_precision": 0.0733,
72
+ "eval_rouge2_recall": 0.0727,
73
+ "eval_runtime": 2616.0446,
74
+ "eval_samples_per_second": 0.205,
75
+ "eval_steps_per_second": 0.102,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 0.98,
80
+ "learning_rate": 4.166666666666667e-05,
81
+ "loss": 3.3984,
82
+ "step": 1250
83
+ },
84
+ {
85
+ "epoch": 0.98,
86
+ "eval_loss": 3.2635767459869385,
87
+ "eval_rouge2_fmeasure": 0.0636,
88
+ "eval_rouge2_precision": 0.0744,
89
+ "eval_rouge2_recall": 0.0742,
90
+ "eval_runtime": 2524.005,
91
+ "eval_samples_per_second": 0.212,
92
+ "eval_steps_per_second": 0.106,
93
+ "step": 1250
94
+ },
95
+ {
96
+ "epoch": 1.18,
97
+ "learning_rate": 5e-05,
98
+ "loss": 3.2649,
99
+ "step": 1500
100
+ },
101
+ {
102
+ "epoch": 1.18,
103
+ "eval_loss": 3.234286069869995,
104
+ "eval_rouge2_fmeasure": 0.0637,
105
+ "eval_rouge2_precision": 0.0759,
106
+ "eval_rouge2_recall": 0.073,
107
+ "eval_runtime": 2247.7809,
108
+ "eval_samples_per_second": 0.238,
109
+ "eval_steps_per_second": 0.119,
110
+ "step": 1500
111
+ },
112
+ {
113
+ "epoch": 1.38,
114
+ "learning_rate": 4.9324324324324325e-05,
115
+ "loss": 3.216,
116
+ "step": 1750
117
+ },
118
+ {
119
+ "epoch": 1.38,
120
+ "eval_loss": 3.2126200199127197,
121
+ "eval_rouge2_fmeasure": 0.0712,
122
+ "eval_rouge2_precision": 0.0831,
123
+ "eval_rouge2_recall": 0.0813,
124
+ "eval_runtime": 2828.2468,
125
+ "eval_samples_per_second": 0.19,
126
+ "eval_steps_per_second": 0.095,
127
+ "step": 1750
128
+ },
129
+ {
130
+ "epoch": 1.57,
131
+ "learning_rate": 4.8648648648648654e-05,
132
+ "loss": 3.1606,
133
+ "step": 2000
134
+ },
135
+ {
136
+ "epoch": 1.57,
137
+ "eval_loss": 3.177541732788086,
138
+ "eval_rouge2_fmeasure": 0.0742,
139
+ "eval_rouge2_precision": 0.0887,
140
+ "eval_rouge2_recall": 0.0829,
141
+ "eval_runtime": 2074.6945,
142
+ "eval_samples_per_second": 0.258,
143
+ "eval_steps_per_second": 0.129,
144
+ "step": 2000
145
+ },
146
+ {
147
+ "epoch": 1.77,
148
+ "learning_rate": 4.797297297297298e-05,
149
+ "loss": 3.1322,
150
+ "step": 2250
151
+ },
152
+ {
153
+ "epoch": 1.77,
154
+ "eval_loss": 3.1448476314544678,
155
+ "eval_rouge2_fmeasure": 0.0703,
156
+ "eval_rouge2_precision": 0.0827,
157
+ "eval_rouge2_recall": 0.0834,
158
+ "eval_runtime": 2157.0729,
159
+ "eval_samples_per_second": 0.248,
160
+ "eval_steps_per_second": 0.124,
161
+ "step": 2250
162
+ },
163
+ {
164
+ "epoch": 1.97,
165
+ "learning_rate": 4.72972972972973e-05,
166
+ "loss": 3.1309,
167
+ "step": 2500
168
+ },
169
+ {
170
+ "epoch": 1.97,
171
+ "eval_loss": 3.1447222232818604,
172
+ "eval_rouge2_fmeasure": 0.074,
173
+ "eval_rouge2_precision": 0.0865,
174
+ "eval_rouge2_recall": 0.087,
175
+ "eval_runtime": 2643.4072,
176
+ "eval_samples_per_second": 0.203,
177
+ "eval_steps_per_second": 0.101,
178
+ "step": 2500
179
+ },
180
+ {
181
+ "epoch": 2.16,
182
+ "learning_rate": 4.662162162162162e-05,
183
+ "loss": 2.8665,
184
+ "step": 2750
185
+ },
186
+ {
187
+ "epoch": 2.16,
188
+ "eval_loss": 3.1453962326049805,
189
+ "eval_rouge2_fmeasure": 0.0769,
190
+ "eval_rouge2_precision": 0.0899,
191
+ "eval_rouge2_recall": 0.0887,
192
+ "eval_runtime": 2159.3278,
193
+ "eval_samples_per_second": 0.248,
194
+ "eval_steps_per_second": 0.124,
195
+ "step": 2750
196
+ },
197
+ {
198
+ "epoch": 2.36,
199
+ "learning_rate": 4.594594594594595e-05,
200
+ "loss": 2.8471,
201
+ "step": 3000
202
+ },
203
+ {
204
+ "epoch": 2.36,
205
+ "eval_loss": 3.1419382095336914,
206
+ "eval_rouge2_fmeasure": 0.0749,
207
+ "eval_rouge2_precision": 0.0862,
208
+ "eval_rouge2_recall": 0.0931,
209
+ "eval_runtime": 2983.4363,
210
+ "eval_samples_per_second": 0.18,
211
+ "eval_steps_per_second": 0.09,
212
+ "step": 3000
213
+ },
214
+ {
215
+ "epoch": 2.55,
216
+ "learning_rate": 4.5270270270270274e-05,
217
+ "loss": 2.8132,
218
+ "step": 3250
219
+ },
220
+ {
221
+ "epoch": 2.55,
222
+ "eval_loss": 3.098118305206299,
223
+ "eval_rouge2_fmeasure": 0.0781,
224
+ "eval_rouge2_precision": 0.0911,
225
+ "eval_rouge2_recall": 0.0941,
226
+ "eval_runtime": 2574.3859,
227
+ "eval_samples_per_second": 0.208,
228
+ "eval_steps_per_second": 0.104,
229
+ "step": 3250
230
+ },
231
+ {
232
+ "epoch": 2.75,
233
+ "learning_rate": 4.4594594594594596e-05,
234
+ "loss": 2.8546,
235
+ "step": 3500
236
+ },
237
+ {
238
+ "epoch": 2.75,
239
+ "eval_loss": 3.0922365188598633,
240
+ "eval_rouge2_fmeasure": 0.0793,
241
+ "eval_rouge2_precision": 0.0936,
242
+ "eval_rouge2_recall": 0.0953,
243
+ "eval_runtime": 2377.8762,
244
+ "eval_samples_per_second": 0.225,
245
+ "eval_steps_per_second": 0.113,
246
+ "step": 3500
247
+ },
248
+ {
249
+ "epoch": 2.95,
250
+ "learning_rate": 4.391891891891892e-05,
251
+ "loss": 2.8386,
252
+ "step": 3750
253
+ },
254
+ {
255
+ "epoch": 2.95,
256
+ "eval_loss": 3.0805723667144775,
257
+ "eval_rouge2_fmeasure": 0.0798,
258
+ "eval_rouge2_precision": 0.0944,
259
+ "eval_rouge2_recall": 0.0969,
260
+ "eval_runtime": 1993.7746,
261
+ "eval_samples_per_second": 0.269,
262
+ "eval_steps_per_second": 0.134,
263
+ "step": 3750
264
+ },
265
+ {
266
+ "epoch": 3.14,
267
+ "learning_rate": 4.324324324324325e-05,
268
+ "loss": 2.6516,
269
+ "step": 4000
270
+ },
271
+ {
272
+ "epoch": 3.14,
273
+ "eval_loss": 3.106261730194092,
274
+ "eval_rouge2_fmeasure": 0.086,
275
+ "eval_rouge2_precision": 0.0994,
276
+ "eval_rouge2_recall": 0.103,
277
+ "eval_runtime": 2088.8612,
278
+ "eval_samples_per_second": 0.257,
279
+ "eval_steps_per_second": 0.128,
280
+ "step": 4000
281
+ },
282
+ {
283
+ "epoch": 3.34,
284
+ "learning_rate": 4.256756756756757e-05,
285
+ "loss": 2.5352,
286
+ "step": 4250
287
+ },
288
+ {
289
+ "epoch": 3.34,
290
+ "eval_loss": 3.117241621017456,
291
+ "eval_rouge2_fmeasure": 0.0804,
292
+ "eval_rouge2_precision": 0.0932,
293
+ "eval_rouge2_recall": 0.0948,
294
+ "eval_runtime": 2087.6258,
295
+ "eval_samples_per_second": 0.257,
296
+ "eval_steps_per_second": 0.128,
297
+ "step": 4250
298
+ },
299
+ {
300
+ "epoch": 3.54,
301
+ "learning_rate": 4.189189189189189e-05,
302
+ "loss": 2.6103,
303
+ "step": 4500
304
+ },
305
+ {
306
+ "epoch": 3.54,
307
+ "eval_loss": 3.1120684146881104,
308
+ "eval_rouge2_fmeasure": 0.0861,
309
+ "eval_rouge2_precision": 0.0987,
310
+ "eval_rouge2_recall": 0.1034,
311
+ "eval_runtime": 2169.5251,
312
+ "eval_samples_per_second": 0.247,
313
+ "eval_steps_per_second": 0.124,
314
+ "step": 4500
315
+ },
316
+ {
317
+ "epoch": 3.73,
318
+ "learning_rate": 4.1216216216216216e-05,
319
+ "loss": 2.6073,
320
+ "step": 4750
321
+ },
322
+ {
323
+ "epoch": 3.73,
324
+ "eval_loss": 3.084920883178711,
325
+ "eval_rouge2_fmeasure": 0.0853,
326
+ "eval_rouge2_precision": 0.0968,
327
+ "eval_rouge2_recall": 0.1034,
328
+ "eval_runtime": 2389.3484,
329
+ "eval_samples_per_second": 0.224,
330
+ "eval_steps_per_second": 0.112,
331
+ "step": 4750
332
+ },
333
+ {
334
+ "epoch": 3.93,
335
+ "learning_rate": 4.0540540540540545e-05,
336
+ "loss": 2.604,
337
+ "step": 5000
338
+ },
339
+ {
340
+ "epoch": 3.93,
341
+ "eval_loss": 3.0795133113861084,
342
+ "eval_rouge2_fmeasure": 0.0854,
343
+ "eval_rouge2_precision": 0.0963,
344
+ "eval_rouge2_recall": 0.1032,
345
+ "eval_runtime": 2327.6047,
346
+ "eval_samples_per_second": 0.23,
347
+ "eval_steps_per_second": 0.115,
348
+ "step": 5000
349
+ },
350
+ {
351
+ "epoch": 4.13,
352
+ "learning_rate": 3.986486486486487e-05,
353
+ "loss": 2.4631,
354
+ "step": 5250
355
+ },
356
+ {
357
+ "epoch": 4.13,
358
+ "eval_loss": 3.125535488128662,
359
+ "eval_rouge2_fmeasure": 0.0915,
360
+ "eval_rouge2_precision": 0.1039,
361
+ "eval_rouge2_recall": 0.1101,
362
+ "eval_runtime": 2351.1015,
363
+ "eval_samples_per_second": 0.228,
364
+ "eval_steps_per_second": 0.114,
365
+ "step": 5250
366
+ },
367
+ {
368
+ "epoch": 4.32,
369
+ "learning_rate": 3.918918918918919e-05,
370
+ "loss": 2.3876,
371
+ "step": 5500
372
+ },
373
+ {
374
+ "epoch": 4.32,
375
+ "eval_loss": 3.120990753173828,
376
+ "eval_rouge2_fmeasure": 0.0896,
377
+ "eval_rouge2_precision": 0.1025,
378
+ "eval_rouge2_recall": 0.1072,
379
+ "eval_runtime": 2104.3322,
380
+ "eval_samples_per_second": 0.255,
381
+ "eval_steps_per_second": 0.127,
382
+ "step": 5500
383
+ },
384
+ {
385
+ "epoch": 4.52,
386
+ "learning_rate": 3.851351351351351e-05,
387
+ "loss": 2.3936,
388
+ "step": 5750
389
+ },
390
+ {
391
+ "epoch": 4.52,
392
+ "eval_loss": 3.1416056156158447,
393
+ "eval_rouge2_fmeasure": 0.0831,
394
+ "eval_rouge2_precision": 0.0963,
395
+ "eval_rouge2_recall": 0.0962,
396
+ "eval_runtime": 2023.379,
397
+ "eval_samples_per_second": 0.265,
398
+ "eval_steps_per_second": 0.132,
399
+ "step": 5750
400
+ },
401
+ {
402
+ "epoch": 4.72,
403
+ "learning_rate": 3.783783783783784e-05,
404
+ "loss": 2.3542,
405
+ "step": 6000
406
+ },
407
+ {
408
+ "epoch": 4.72,
409
+ "eval_loss": 3.116647958755493,
410
+ "eval_rouge2_fmeasure": 0.0879,
411
+ "eval_rouge2_precision": 0.102,
412
+ "eval_rouge2_recall": 0.1027,
413
+ "eval_runtime": 1963.9449,
414
+ "eval_samples_per_second": 0.273,
415
+ "eval_steps_per_second": 0.136,
416
+ "step": 6000
417
+ },
418
+ {
419
+ "epoch": 4.91,
420
+ "learning_rate": 3.7162162162162165e-05,
421
+ "loss": 2.3892,
422
+ "step": 6250
423
+ },
424
+ {
425
+ "epoch": 4.91,
426
+ "eval_loss": 3.1029891967773438,
427
+ "eval_rouge2_fmeasure": 0.0912,
428
+ "eval_rouge2_precision": 0.1035,
429
+ "eval_rouge2_recall": 0.1092,
430
+ "eval_runtime": 2287.4367,
431
+ "eval_samples_per_second": 0.234,
432
+ "eval_steps_per_second": 0.117,
433
+ "step": 6250
434
+ },
435
+ {
436
+ "epoch": 5.11,
437
+ "learning_rate": 3.648648648648649e-05,
438
+ "loss": 2.279,
439
+ "step": 6500
440
+ },
441
+ {
442
+ "epoch": 5.11,
443
+ "eval_loss": 3.1869595050811768,
444
+ "eval_rouge2_fmeasure": 0.0899,
445
+ "eval_rouge2_precision": 0.1002,
446
+ "eval_rouge2_recall": 0.1082,
447
+ "eval_runtime": 2536.3289,
448
+ "eval_samples_per_second": 0.211,
449
+ "eval_steps_per_second": 0.106,
450
+ "step": 6500
451
+ },
452
+ {
453
+ "epoch": 5.31,
454
+ "learning_rate": 3.581081081081081e-05,
455
+ "loss": 2.2169,
456
+ "step": 6750
457
+ },
458
+ {
459
+ "epoch": 5.31,
460
+ "eval_loss": 3.185154676437378,
461
+ "eval_rouge2_fmeasure": 0.0886,
462
+ "eval_rouge2_precision": 0.1011,
463
+ "eval_rouge2_recall": 0.1063,
464
+ "eval_runtime": 2343.7075,
465
+ "eval_samples_per_second": 0.229,
466
+ "eval_steps_per_second": 0.114,
467
+ "step": 6750
468
+ },
469
+ {
470
+ "epoch": 5.5,
471
+ "learning_rate": 3.513513513513514e-05,
472
+ "loss": 2.2019,
473
+ "step": 7000
474
+ },
475
+ {
476
+ "epoch": 5.5,
477
+ "eval_loss": 3.1997668743133545,
478
+ "eval_rouge2_fmeasure": 0.0869,
479
+ "eval_rouge2_precision": 0.0999,
480
+ "eval_rouge2_recall": 0.1012,
481
+ "eval_runtime": 2257.8311,
482
+ "eval_samples_per_second": 0.237,
483
+ "eval_steps_per_second": 0.119,
484
+ "step": 7000
485
+ },
486
+ {
487
+ "epoch": 5.7,
488
+ "learning_rate": 3.445945945945946e-05,
489
+ "loss": 2.2185,
490
+ "step": 7250
491
+ },
492
+ {
493
+ "epoch": 5.7,
494
+ "eval_loss": 3.176213026046753,
495
+ "eval_rouge2_fmeasure": 0.0913,
496
+ "eval_rouge2_precision": 0.1043,
497
+ "eval_rouge2_recall": 0.1099,
498
+ "eval_runtime": 2227.5514,
499
+ "eval_samples_per_second": 0.241,
500
+ "eval_steps_per_second": 0.12,
501
+ "step": 7250
502
+ },
503
+ {
504
+ "epoch": 5.9,
505
+ "learning_rate": 3.3783783783783784e-05,
506
+ "loss": 2.2231,
507
+ "step": 7500
508
+ },
509
+ {
510
+ "epoch": 5.9,
511
+ "eval_loss": 3.178241491317749,
512
+ "eval_rouge2_fmeasure": 0.0939,
513
+ "eval_rouge2_precision": 0.105,
514
+ "eval_rouge2_recall": 0.114,
515
+ "eval_runtime": 2442.3591,
516
+ "eval_samples_per_second": 0.219,
517
+ "eval_steps_per_second": 0.11,
518
+ "step": 7500
519
+ },
520
+ {
521
+ "epoch": 6.09,
522
+ "learning_rate": 3.310810810810811e-05,
523
+ "loss": 2.1192,
524
+ "step": 7750
525
+ },
526
+ {
527
+ "epoch": 6.09,
528
+ "eval_loss": 3.2204413414001465,
529
+ "eval_rouge2_fmeasure": 0.0935,
530
+ "eval_rouge2_precision": 0.1045,
531
+ "eval_rouge2_recall": 0.1107,
532
+ "eval_runtime": 2356.1215,
533
+ "eval_samples_per_second": 0.227,
534
+ "eval_steps_per_second": 0.114,
535
+ "step": 7750
536
+ }
537
+ ],
538
+ "max_steps": 20000,
539
+ "num_train_epochs": 16,
540
+ "total_flos": 6.698452137824748e+17,
541
+ "trial_name": null,
542
+ "trial_params": null
543
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d467093dc7042795f8768d5f019836e4c3f343b1cc5151745664f307f36bcd
3
+ size 3707
vocab.json ADDED
The diff for this file is too large to render. See raw diff