Hugging Face's logo

grizzlypath26
/
script2sumFinal

Transformers
PyTorch
led
text2text-generation
Model card Files
xet
Community
1
grizzlypath26 commited on
Commit
5de6049
·
1 Parent(s): 86dac49

Initial Upload

Browse files
Files changed (13) hide show
  1. config.json +59 -0
  2. generation_config.json +14 -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 +64 -0
  11. trainer_state.json +556 -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": 1024,
49
+ "min_length": 768,
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": "4.28.1",
57
+ "use_cache": false,
58
+ "vocab_size": 50265
59
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "decoder_start_token_id": 2,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "length_penalty": 2.0,
7
+ "max_length": 1024,
8
+ "min_length": 768,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 2,
11
+ "pad_token_id": 1,
12
+ "transformers_version": "4.28.1",
13
+ "use_cache": false
14
+ }
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 sha256:2861555cd33f099bd630dd240aef62adcb3837709b09f430a14a47a103c11742
3
+ size 2059269
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0dd2f16af31a6d3b7ebcb51138b4ae066b33eb468dcdb64ccc7ea2356e5f84f
3
+ size 647680813
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a00ad45db8a44733e5a9d2b70fe7847a88cc61dadecc1473c7b9b85e83cd156
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6360cfe0ab89c3d36f172699450dd087cf2996c7b6d59f8845acf290058d4cf
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 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 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
+ "tokenizer_class": "LEDTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
trainer_state.json ADDED
@@ -0,0 +1,556 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 17.770034843205575,
5
+ "global_step": 5100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.89,
12
+ "learning_rate": 2.4902343750000002e-05,
13
+ "loss": 3.791,
14
+ "step": 255
15
+ },
16
+ {
17
+ "epoch": 0.89,
18
+ "eval_average_rogue": 0.2125,
19
+ "eval_loss": 3.328416347503662,
20
+ "eval_rouge1_fmeasure": 0.3288,
21
+ "eval_rouge1_precision": 0.3115,
22
+ "eval_rouge1_recall": 0.3637,
23
+ "eval_rouge2_fmeasure": 0.06,
24
+ "eval_rouge2_precision": 0.0569,
25
+ "eval_rouge2_recall": 0.0664,
26
+ "eval_rougeL_fmeasure": 0.145,
27
+ "eval_rougeL_precision": 0.1366,
28
+ "eval_rougeL_recall": 0.1631,
29
+ "eval_rougeLsum_fmeasure": 0.3161,
30
+ "eval_rougeLsum_precision": 0.2997,
31
+ "eval_rougeLsum_recall": 0.3496,
32
+ "eval_runtime": 3350.2964,
33
+ "eval_samples_per_second": 0.038,
34
+ "eval_steps_per_second": 0.038,
35
+ "step": 255
36
+ },
37
+ {
38
+ "epoch": 1.78,
39
+ "learning_rate": 4.9804687500000004e-05,
40
+ "loss": 3.3793,
41
+ "step": 510
42
+ },
43
+ {
44
+ "epoch": 1.78,
45
+ "eval_average_rogue": 0.2109,
46
+ "eval_loss": 3.268017292022705,
47
+ "eval_rouge1_fmeasure": 0.3285,
48
+ "eval_rouge1_precision": 0.3068,
49
+ "eval_rouge1_recall": 0.3699,
50
+ "eval_rouge2_fmeasure": 0.0571,
51
+ "eval_rouge2_precision": 0.053,
52
+ "eval_rouge2_recall": 0.065,
53
+ "eval_rougeL_fmeasure": 0.1417,
54
+ "eval_rougeL_precision": 0.1315,
55
+ "eval_rougeL_recall": 0.1631,
56
+ "eval_rougeLsum_fmeasure": 0.3163,
57
+ "eval_rougeLsum_precision": 0.2954,
58
+ "eval_rougeLsum_recall": 0.356,
59
+ "eval_runtime": 3338.0119,
60
+ "eval_samples_per_second": 0.038,
61
+ "eval_steps_per_second": 0.038,
62
+ "step": 510
63
+ },
64
+ {
65
+ "epoch": 2.67,
66
+ "learning_rate": 4.758033664881408e-05,
67
+ "loss": 3.1826,
68
+ "step": 765
69
+ },
70
+ {
71
+ "epoch": 2.67,
72
+ "eval_average_rogue": 0.214,
73
+ "eval_loss": 3.245297431945801,
74
+ "eval_rouge1_fmeasure": 0.3293,
75
+ "eval_rouge1_precision": 0.3099,
76
+ "eval_rouge1_recall": 0.3668,
77
+ "eval_rouge2_fmeasure": 0.0644,
78
+ "eval_rouge2_precision": 0.0605,
79
+ "eval_rouge2_recall": 0.0717,
80
+ "eval_rougeL_fmeasure": 0.145,
81
+ "eval_rougeL_precision": 0.1356,
82
+ "eval_rougeL_recall": 0.1647,
83
+ "eval_rougeLsum_fmeasure": 0.3173,
84
+ "eval_rougeLsum_precision": 0.2986,
85
+ "eval_rougeLsum_recall": 0.3531,
86
+ "eval_runtime": 3330.8537,
87
+ "eval_samples_per_second": 0.038,
88
+ "eval_steps_per_second": 0.038,
89
+ "step": 765
90
+ },
91
+ {
92
+ "epoch": 3.55,
93
+ "learning_rate": 4.5141545524101e-05,
94
+ "loss": 3.0133,
95
+ "step": 1020
96
+ },
97
+ {
98
+ "epoch": 3.55,
99
+ "eval_average_rogue": 0.1948,
100
+ "eval_loss": 3.2580819129943848,
101
+ "eval_rouge1_fmeasure": 0.2983,
102
+ "eval_rouge1_precision": 0.2893,
103
+ "eval_rouge1_recall": 0.3239,
104
+ "eval_rouge2_fmeasure": 0.0545,
105
+ "eval_rouge2_precision": 0.0527,
106
+ "eval_rouge2_recall": 0.0591,
107
+ "eval_rougeL_fmeasure": 0.1397,
108
+ "eval_rougeL_precision": 0.1356,
109
+ "eval_rougeL_recall": 0.1534,
110
+ "eval_rougeLsum_fmeasure": 0.2865,
111
+ "eval_rougeLsum_precision": 0.2776,
112
+ "eval_rougeLsum_recall": 0.3105,
113
+ "eval_runtime": 3289.5263,
114
+ "eval_samples_per_second": 0.039,
115
+ "eval_steps_per_second": 0.039,
116
+ "step": 1020
117
+ },
118
+ {
119
+ "epoch": 4.44,
120
+ "learning_rate": 4.2702754399387915e-05,
121
+ "loss": 2.8569,
122
+ "step": 1275
123
+ },
124
+ {
125
+ "epoch": 4.44,
126
+ "eval_average_rogue": 0.2256,
127
+ "eval_loss": 3.2716007232666016,
128
+ "eval_rouge1_fmeasure": 0.3491,
129
+ "eval_rouge1_precision": 0.3326,
130
+ "eval_rouge1_recall": 0.3835,
131
+ "eval_rouge2_fmeasure": 0.0671,
132
+ "eval_rouge2_precision": 0.0641,
133
+ "eval_rouge2_recall": 0.0732,
134
+ "eval_rougeL_fmeasure": 0.1516,
135
+ "eval_rougeL_precision": 0.1436,
136
+ "eval_rougeL_recall": 0.1701,
137
+ "eval_rougeLsum_fmeasure": 0.3346,
138
+ "eval_rougeLsum_precision": 0.3189,
139
+ "eval_rougeLsum_recall": 0.368,
140
+ "eval_runtime": 3297.3203,
141
+ "eval_samples_per_second": 0.039,
142
+ "eval_steps_per_second": 0.039,
143
+ "step": 1275
144
+ },
145
+ {
146
+ "epoch": 5.33,
147
+ "learning_rate": 4.026396327467483e-05,
148
+ "loss": 2.7008,
149
+ "step": 1530
150
+ },
151
+ {
152
+ "epoch": 5.33,
153
+ "eval_average_rogue": 0.2285,
154
+ "eval_loss": 3.313244104385376,
155
+ "eval_rouge1_fmeasure": 0.3531,
156
+ "eval_rouge1_precision": 0.3326,
157
+ "eval_rouge1_recall": 0.3925,
158
+ "eval_rouge2_fmeasure": 0.0693,
159
+ "eval_rouge2_precision": 0.0653,
160
+ "eval_rouge2_recall": 0.0772,
161
+ "eval_rougeL_fmeasure": 0.1521,
162
+ "eval_rougeL_precision": 0.1427,
163
+ "eval_rougeL_recall": 0.1725,
164
+ "eval_rougeLsum_fmeasure": 0.3396,
165
+ "eval_rougeLsum_precision": 0.3202,
166
+ "eval_rougeLsum_recall": 0.3776,
167
+ "eval_runtime": 3297.2909,
168
+ "eval_samples_per_second": 0.039,
169
+ "eval_steps_per_second": 0.039,
170
+ "step": 1530
171
+ },
172
+ {
173
+ "epoch": 6.22,
174
+ "learning_rate": 3.7825172149961744e-05,
175
+ "loss": 2.5657,
176
+ "step": 1785
177
+ },
178
+ {
179
+ "epoch": 6.22,
180
+ "eval_average_rogue": 0.2241,
181
+ "eval_loss": 3.349586009979248,
182
+ "eval_rouge1_fmeasure": 0.3473,
183
+ "eval_rouge1_precision": 0.3291,
184
+ "eval_rouge1_recall": 0.385,
185
+ "eval_rouge2_fmeasure": 0.0658,
186
+ "eval_rouge2_precision": 0.0622,
187
+ "eval_rouge2_recall": 0.0731,
188
+ "eval_rougeL_fmeasure": 0.1504,
189
+ "eval_rougeL_precision": 0.1416,
190
+ "eval_rougeL_recall": 0.17,
191
+ "eval_rougeLsum_fmeasure": 0.3326,
192
+ "eval_rougeLsum_precision": 0.3154,
193
+ "eval_rougeLsum_recall": 0.3683,
194
+ "eval_runtime": 3292.4741,
195
+ "eval_samples_per_second": 0.039,
196
+ "eval_steps_per_second": 0.039,
197
+ "step": 1785
198
+ },
199
+ {
200
+ "epoch": 7.11,
201
+ "learning_rate": 3.538638102524866e-05,
202
+ "loss": 2.4327,
203
+ "step": 2040
204
+ },
205
+ {
206
+ "epoch": 7.11,
207
+ "eval_average_rogue": 0.2298,
208
+ "eval_loss": 3.437542200088501,
209
+ "eval_rouge1_fmeasure": 0.3551,
210
+ "eval_rouge1_precision": 0.3347,
211
+ "eval_rouge1_recall": 0.3946,
212
+ "eval_rouge2_fmeasure": 0.0703,
213
+ "eval_rouge2_precision": 0.0664,
214
+ "eval_rouge2_recall": 0.0778,
215
+ "eval_rougeL_fmeasure": 0.1527,
216
+ "eval_rougeL_precision": 0.1433,
217
+ "eval_rougeL_recall": 0.1732,
218
+ "eval_rougeLsum_fmeasure": 0.341,
219
+ "eval_rougeLsum_precision": 0.3218,
220
+ "eval_rougeLsum_recall": 0.3788,
221
+ "eval_runtime": 3284.3798,
222
+ "eval_samples_per_second": 0.039,
223
+ "eval_steps_per_second": 0.039,
224
+ "step": 2040
225
+ },
226
+ {
227
+ "epoch": 8.0,
228
+ "learning_rate": 3.294758990053558e-05,
229
+ "loss": 2.3352,
230
+ "step": 2295
231
+ },
232
+ {
233
+ "epoch": 8.0,
234
+ "eval_average_rogue": 0.2284,
235
+ "eval_loss": 3.4355413913726807,
236
+ "eval_rouge1_fmeasure": 0.3551,
237
+ "eval_rouge1_precision": 0.3334,
238
+ "eval_rouge1_recall": 0.397,
239
+ "eval_rouge2_fmeasure": 0.0682,
240
+ "eval_rouge2_precision": 0.064,
241
+ "eval_rouge2_recall": 0.0762,
242
+ "eval_rougeL_fmeasure": 0.1507,
243
+ "eval_rougeL_precision": 0.1406,
244
+ "eval_rougeL_recall": 0.1721,
245
+ "eval_rougeLsum_fmeasure": 0.3396,
246
+ "eval_rougeLsum_precision": 0.3189,
247
+ "eval_rougeLsum_recall": 0.3797,
248
+ "eval_runtime": 3319.5759,
249
+ "eval_samples_per_second": 0.039,
250
+ "eval_steps_per_second": 0.039,
251
+ "step": 2295
252
+ },
253
+ {
254
+ "epoch": 8.89,
255
+ "learning_rate": 3.0508798775822494e-05,
256
+ "loss": 2.2068,
257
+ "step": 2550
258
+ },
259
+ {
260
+ "epoch": 8.89,
261
+ "eval_average_rogue": 0.2319,
262
+ "eval_loss": 3.517580032348633,
263
+ "eval_rouge1_fmeasure": 0.3593,
264
+ "eval_rouge1_precision": 0.3378,
265
+ "eval_rouge1_recall": 0.4005,
266
+ "eval_rouge2_fmeasure": 0.0711,
267
+ "eval_rouge2_precision": 0.0669,
268
+ "eval_rouge2_recall": 0.0793,
269
+ "eval_rougeL_fmeasure": 0.153,
270
+ "eval_rougeL_precision": 0.1431,
271
+ "eval_rougeL_recall": 0.1738,
272
+ "eval_rougeLsum_fmeasure": 0.3441,
273
+ "eval_rougeLsum_precision": 0.3239,
274
+ "eval_rougeLsum_recall": 0.383,
275
+ "eval_runtime": 3268.2597,
276
+ "eval_samples_per_second": 0.039,
277
+ "eval_steps_per_second": 0.039,
278
+ "step": 2550
279
+ },
280
+ {
281
+ "epoch": 9.77,
282
+ "learning_rate": 2.8070007651109415e-05,
283
+ "loss": 2.1177,
284
+ "step": 2805
285
+ },
286
+ {
287
+ "epoch": 9.77,
288
+ "eval_average_rogue": 0.2322,
289
+ "eval_loss": 3.5942444801330566,
290
+ "eval_rouge1_fmeasure": 0.3615,
291
+ "eval_rouge1_precision": 0.3407,
292
+ "eval_rouge1_recall": 0.402,
293
+ "eval_rouge2_fmeasure": 0.0691,
294
+ "eval_rouge2_precision": 0.0652,
295
+ "eval_rouge2_recall": 0.0771,
296
+ "eval_rougeL_fmeasure": 0.1516,
297
+ "eval_rougeL_precision": 0.1422,
298
+ "eval_rougeL_recall": 0.1722,
299
+ "eval_rougeLsum_fmeasure": 0.3465,
300
+ "eval_rougeLsum_precision": 0.3267,
301
+ "eval_rougeLsum_recall": 0.3853,
302
+ "eval_runtime": 3329.9183,
303
+ "eval_samples_per_second": 0.038,
304
+ "eval_steps_per_second": 0.038,
305
+ "step": 2805
306
+ },
307
+ {
308
+ "epoch": 10.66,
309
+ "learning_rate": 2.563121652639633e-05,
310
+ "loss": 2.0452,
311
+ "step": 3060
312
+ },
313
+ {
314
+ "epoch": 10.66,
315
+ "eval_average_rogue": 0.2329,
316
+ "eval_loss": 3.618927001953125,
317
+ "eval_rouge1_fmeasure": 0.3627,
318
+ "eval_rouge1_precision": 0.3451,
319
+ "eval_rouge1_recall": 0.3992,
320
+ "eval_rouge2_fmeasure": 0.0688,
321
+ "eval_rouge2_precision": 0.0655,
322
+ "eval_rouge2_recall": 0.0756,
323
+ "eval_rougeL_fmeasure": 0.152,
324
+ "eval_rougeL_precision": 0.1437,
325
+ "eval_rougeL_recall": 0.1712,
326
+ "eval_rougeLsum_fmeasure": 0.3482,
327
+ "eval_rougeLsum_precision": 0.3317,
328
+ "eval_rougeLsum_recall": 0.383,
329
+ "eval_runtime": 3288.5395,
330
+ "eval_samples_per_second": 0.039,
331
+ "eval_steps_per_second": 0.039,
332
+ "step": 3060
333
+ },
334
+ {
335
+ "epoch": 11.55,
336
+ "learning_rate": 2.3192425401683247e-05,
337
+ "loss": 1.9276,
338
+ "step": 3315
339
+ },
340
+ {
341
+ "epoch": 11.55,
342
+ "eval_average_rogue": 0.235,
343
+ "eval_loss": 3.685786247253418,
344
+ "eval_rouge1_fmeasure": 0.3662,
345
+ "eval_rouge1_precision": 0.3468,
346
+ "eval_rouge1_recall": 0.4051,
347
+ "eval_rouge2_fmeasure": 0.0706,
348
+ "eval_rouge2_precision": 0.0668,
349
+ "eval_rouge2_recall": 0.0788,
350
+ "eval_rougeL_fmeasure": 0.1525,
351
+ "eval_rougeL_precision": 0.1437,
352
+ "eval_rougeL_recall": 0.1723,
353
+ "eval_rougeLsum_fmeasure": 0.3508,
354
+ "eval_rougeLsum_precision": 0.3328,
355
+ "eval_rougeLsum_recall": 0.3883,
356
+ "eval_runtime": 3283.2817,
357
+ "eval_samples_per_second": 0.039,
358
+ "eval_steps_per_second": 0.039,
359
+ "step": 3315
360
+ },
361
+ {
362
+ "epoch": 12.44,
363
+ "learning_rate": 2.0753634276970162e-05,
364
+ "loss": 1.9006,
365
+ "step": 3570
366
+ },
367
+ {
368
+ "epoch": 12.44,
369
+ "eval_average_rogue": 0.2331,
370
+ "eval_loss": 3.7175817489624023,
371
+ "eval_rouge1_fmeasure": 0.3627,
372
+ "eval_rouge1_precision": 0.3429,
373
+ "eval_rouge1_recall": 0.4025,
374
+ "eval_rouge2_fmeasure": 0.0698,
375
+ "eval_rouge2_precision": 0.0659,
376
+ "eval_rouge2_recall": 0.0783,
377
+ "eval_rougeL_fmeasure": 0.152,
378
+ "eval_rougeL_precision": 0.1429,
379
+ "eval_rougeL_recall": 0.1722,
380
+ "eval_rougeLsum_fmeasure": 0.3477,
381
+ "eval_rougeLsum_precision": 0.329,
382
+ "eval_rougeLsum_recall": 0.386,
383
+ "eval_runtime": 3384.322,
384
+ "eval_samples_per_second": 0.038,
385
+ "eval_steps_per_second": 0.038,
386
+ "step": 3570
387
+ },
388
+ {
389
+ "epoch": 13.33,
390
+ "learning_rate": 1.8314843152257076e-05,
391
+ "loss": 1.8247,
392
+ "step": 3825
393
+ },
394
+ {
395
+ "epoch": 13.33,
396
+ "eval_average_rogue": 0.2358,
397
+ "eval_loss": 3.7242326736450195,
398
+ "eval_rouge1_fmeasure": 0.3679,
399
+ "eval_rouge1_precision": 0.3481,
400
+ "eval_rouge1_recall": 0.4077,
401
+ "eval_rouge2_fmeasure": 0.0698,
402
+ "eval_rouge2_precision": 0.066,
403
+ "eval_rouge2_recall": 0.0773,
404
+ "eval_rougeL_fmeasure": 0.1537,
405
+ "eval_rougeL_precision": 0.1444,
406
+ "eval_rougeL_recall": 0.1741,
407
+ "eval_rougeLsum_fmeasure": 0.3517,
408
+ "eval_rougeLsum_precision": 0.3323,
409
+ "eval_rougeLsum_recall": 0.3894,
410
+ "eval_runtime": 3438.3144,
411
+ "eval_samples_per_second": 0.037,
412
+ "eval_steps_per_second": 0.037,
413
+ "step": 3825
414
+ },
415
+ {
416
+ "epoch": 14.22,
417
+ "learning_rate": 1.5876052027543994e-05,
418
+ "loss": 1.7352,
419
+ "step": 4080
420
+ },
421
+ {
422
+ "epoch": 14.22,
423
+ "eval_average_rogue": 0.2336,
424
+ "eval_loss": 3.790210723876953,
425
+ "eval_rouge1_fmeasure": 0.3648,
426
+ "eval_rouge1_precision": 0.3457,
427
+ "eval_rouge1_recall": 0.4025,
428
+ "eval_rouge2_fmeasure": 0.0702,
429
+ "eval_rouge2_precision": 0.0667,
430
+ "eval_rouge2_recall": 0.0776,
431
+ "eval_rougeL_fmeasure": 0.1508,
432
+ "eval_rougeL_precision": 0.1422,
433
+ "eval_rougeL_recall": 0.1702,
434
+ "eval_rougeLsum_fmeasure": 0.3486,
435
+ "eval_rougeLsum_precision": 0.3307,
436
+ "eval_rougeLsum_recall": 0.3849,
437
+ "eval_runtime": 3429.0398,
438
+ "eval_samples_per_second": 0.037,
439
+ "eval_steps_per_second": 0.037,
440
+ "step": 4080
441
+ },
442
+ {
443
+ "epoch": 15.1,
444
+ "learning_rate": 1.3437260902830912e-05,
445
+ "loss": 1.7091,
446
+ "step": 4335
447
+ },
448
+ {
449
+ "epoch": 15.1,
450
+ "eval_average_rogue": 0.2351,
451
+ "eval_loss": 3.8391542434692383,
452
+ "eval_rouge1_fmeasure": 0.3664,
453
+ "eval_rouge1_precision": 0.346,
454
+ "eval_rouge1_recall": 0.4069,
455
+ "eval_rouge2_fmeasure": 0.0706,
456
+ "eval_rouge2_precision": 0.0666,
457
+ "eval_rouge2_recall": 0.0786,
458
+ "eval_rougeL_fmeasure": 0.1527,
459
+ "eval_rougeL_precision": 0.1435,
460
+ "eval_rougeL_recall": 0.1728,
461
+ "eval_rougeLsum_fmeasure": 0.3509,
462
+ "eval_rougeLsum_precision": 0.331,
463
+ "eval_rougeLsum_recall": 0.3892,
464
+ "eval_runtime": 3445.0892,
465
+ "eval_samples_per_second": 0.037,
466
+ "eval_steps_per_second": 0.037,
467
+ "step": 4335
468
+ },
469
+ {
470
+ "epoch": 15.99,
471
+ "learning_rate": 1.0998469778117827e-05,
472
+ "loss": 1.654,
473
+ "step": 4590
474
+ },
475
+ {
476
+ "epoch": 15.99,
477
+ "eval_average_rogue": 0.2347,
478
+ "eval_loss": 3.8251237869262695,
479
+ "eval_rouge1_fmeasure": 0.3674,
480
+ "eval_rouge1_precision": 0.3475,
481
+ "eval_rouge1_recall": 0.4065,
482
+ "eval_rouge2_fmeasure": 0.0692,
483
+ "eval_rouge2_precision": 0.0655,
484
+ "eval_rouge2_recall": 0.0767,
485
+ "eval_rougeL_fmeasure": 0.1515,
486
+ "eval_rougeL_precision": 0.1425,
487
+ "eval_rougeL_recall": 0.1713,
488
+ "eval_rougeLsum_fmeasure": 0.3508,
489
+ "eval_rougeLsum_precision": 0.3318,
490
+ "eval_rougeLsum_recall": 0.3883,
491
+ "eval_runtime": 3431.7145,
492
+ "eval_samples_per_second": 0.037,
493
+ "eval_steps_per_second": 0.037,
494
+ "step": 4590
495
+ },
496
+ {
497
+ "epoch": 16.88,
498
+ "learning_rate": 8.559678653404744e-06,
499
+ "loss": 1.6034,
500
+ "step": 4845
501
+ },
502
+ {
503
+ "epoch": 16.88,
504
+ "eval_average_rogue": 0.2342,
505
+ "eval_loss": 3.8599014282226562,
506
+ "eval_rouge1_fmeasure": 0.3653,
507
+ "eval_rouge1_precision": 0.3449,
508
+ "eval_rouge1_recall": 0.4056,
509
+ "eval_rouge2_fmeasure": 0.0694,
510
+ "eval_rouge2_precision": 0.0655,
511
+ "eval_rouge2_recall": 0.0771,
512
+ "eval_rougeL_fmeasure": 0.1531,
513
+ "eval_rougeL_precision": 0.1438,
514
+ "eval_rougeL_recall": 0.1738,
515
+ "eval_rougeLsum_fmeasure": 0.3491,
516
+ "eval_rougeLsum_precision": 0.3295,
517
+ "eval_rougeLsum_recall": 0.3877,
518
+ "eval_runtime": 3434.4477,
519
+ "eval_samples_per_second": 0.037,
520
+ "eval_steps_per_second": 0.037,
521
+ "step": 4845
522
+ },
523
+ {
524
+ "epoch": 17.77,
525
+ "learning_rate": 6.120887528691661e-06,
526
+ "loss": 1.5801,
527
+ "step": 5100
528
+ },
529
+ {
530
+ "epoch": 17.77,
531
+ "eval_average_rogue": 0.2336,
532
+ "eval_loss": 3.8798491954803467,
533
+ "eval_rouge1_fmeasure": 0.3647,
534
+ "eval_rouge1_precision": 0.3432,
535
+ "eval_rouge1_recall": 0.4057,
536
+ "eval_rouge2_fmeasure": 0.0682,
537
+ "eval_rouge2_precision": 0.0643,
538
+ "eval_rouge2_recall": 0.0758,
539
+ "eval_rougeL_fmeasure": 0.1523,
540
+ "eval_rougeL_precision": 0.1426,
541
+ "eval_rougeL_recall": 0.1732,
542
+ "eval_rougeLsum_fmeasure": 0.3491,
543
+ "eval_rougeLsum_precision": 0.329,
544
+ "eval_rougeLsum_recall": 0.3882,
545
+ "eval_runtime": 3446.3776,
546
+ "eval_samples_per_second": 0.037,
547
+ "eval_steps_per_second": 0.037,
548
+ "step": 5100
549
+ }
550
+ ],
551
+ "max_steps": 5740,
552
+ "num_train_epochs": 20,
553
+ "total_flos": 1.37710446575616e+16,
554
+ "trial_name": null,
555
+ "trial_params": null
556
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da331962651fe066768b40191d99062aa03d57633cbc90004f9b61a756637fd2
3
+ size 3643
vocab.json ADDED
The diff for this file is too large to render. See raw diff