init commit;
Browse files- config.json +75 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +276 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "LABEL_0",
|
32 |
+
"1": "LABEL_1",
|
33 |
+
"2": "LABEL_2"
|
34 |
+
},
|
35 |
+
"init_std": 0.02,
|
36 |
+
"is_encoder_decoder": true,
|
37 |
+
"label2id": {
|
38 |
+
"LABEL_0": 0,
|
39 |
+
"LABEL_1": 1,
|
40 |
+
"LABEL_2": 2
|
41 |
+
},
|
42 |
+
"max_position_embeddings": 1024,
|
43 |
+
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
+
"normalize_before": false,
|
46 |
+
"normalize_embedding": true,
|
47 |
+
"num_beams": 4,
|
48 |
+
"num_hidden_layers": 6,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"scale_embedding": false,
|
51 |
+
"task_specific_params": {
|
52 |
+
"summarization": {
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 128,
|
55 |
+
"min_length": 12,
|
56 |
+
"num_beams": 4
|
57 |
+
},
|
58 |
+
"summarization_cnn": {
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_xsum": {
|
65 |
+
"length_penalty": 1.0,
|
66 |
+
"max_length": 62,
|
67 |
+
"min_length": 11,
|
68 |
+
"num_beams": 6
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.21.2",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 50265
|
75 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:613b9b6fe431c1f82e2bec492a78a465767c65aef7fc444a9006a2bec083d2e3
|
3 |
+
size 557969145
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"errors": "replace",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"model_max_length": 1024,
|
9 |
+
"name_or_path": "facebook/bart-base",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"tokenizer_class": "BartTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 24.761,
|
3 |
+
"best_model_checkpoint": "./output\\checkpoint-1052",
|
4 |
+
"epoch": 20.0,
|
5 |
+
"global_step": 10520,
|
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": 9.5e-06,
|
13 |
+
"loss": 3.0166,
|
14 |
+
"step": 526
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_gen_len": 15.76,
|
19 |
+
"eval_rouge2": 6.32,
|
20 |
+
"eval_rougeL": 21.606,
|
21 |
+
"step": 526
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 2.0,
|
25 |
+
"learning_rate": 9e-06,
|
26 |
+
"loss": 2.7368,
|
27 |
+
"step": 1052
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.0,
|
31 |
+
"eval_gen_len": 22.06,
|
32 |
+
"eval_rouge2": 8.84,
|
33 |
+
"eval_rougeL": 24.761,
|
34 |
+
"step": 1052
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"learning_rate": 8.5e-06,
|
39 |
+
"loss": 2.5849,
|
40 |
+
"step": 1578
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"eval_gen_len": 19.17,
|
45 |
+
"eval_rouge2": 7.97,
|
46 |
+
"eval_rougeL": 23.301,
|
47 |
+
"step": 1578
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 4.0,
|
51 |
+
"learning_rate": 8.000000000000001e-06,
|
52 |
+
"loss": 2.4639,
|
53 |
+
"step": 2104
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 4.0,
|
57 |
+
"eval_gen_len": 16.53,
|
58 |
+
"eval_rouge2": 6.92,
|
59 |
+
"eval_rougeL": 22.252,
|
60 |
+
"step": 2104
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 5.0,
|
64 |
+
"learning_rate": 7.500000000000001e-06,
|
65 |
+
"loss": 2.3647,
|
66 |
+
"step": 2630
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_gen_len": 15.61,
|
71 |
+
"eval_rouge2": 6.25,
|
72 |
+
"eval_rougeL": 21.732,
|
73 |
+
"step": 2630
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 6.0,
|
77 |
+
"learning_rate": 7e-06,
|
78 |
+
"loss": 2.2886,
|
79 |
+
"step": 3156
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 6.0,
|
83 |
+
"eval_gen_len": 16.78,
|
84 |
+
"eval_rouge2": 7.3,
|
85 |
+
"eval_rougeL": 23.088,
|
86 |
+
"step": 3156
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 7.0,
|
90 |
+
"learning_rate": 6.5000000000000004e-06,
|
91 |
+
"loss": 2.202,
|
92 |
+
"step": 3682
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"eval_gen_len": 18.84,
|
97 |
+
"eval_rouge2": 6.67,
|
98 |
+
"eval_rougeL": 22.378,
|
99 |
+
"step": 3682
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 8.0,
|
103 |
+
"learning_rate": 6e-06,
|
104 |
+
"loss": 2.1348,
|
105 |
+
"step": 4208
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 8.0,
|
109 |
+
"eval_gen_len": 14.52,
|
110 |
+
"eval_rouge2": 6.22,
|
111 |
+
"eval_rougeL": 22.215,
|
112 |
+
"step": 4208
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 9.0,
|
116 |
+
"learning_rate": 5.500000000000001e-06,
|
117 |
+
"loss": 2.0736,
|
118 |
+
"step": 4734
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 9.0,
|
122 |
+
"eval_gen_len": 17.94,
|
123 |
+
"eval_rouge2": 6.56,
|
124 |
+
"eval_rougeL": 22.336,
|
125 |
+
"step": 4734
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 10.0,
|
129 |
+
"learning_rate": 5e-06,
|
130 |
+
"loss": 2.0202,
|
131 |
+
"step": 5260
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 10.0,
|
135 |
+
"eval_gen_len": 16.91,
|
136 |
+
"eval_rouge2": 6.38,
|
137 |
+
"eval_rougeL": 21.603,
|
138 |
+
"step": 5260
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 11.0,
|
142 |
+
"learning_rate": 4.5e-06,
|
143 |
+
"loss": 1.9656,
|
144 |
+
"step": 5786
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 11.0,
|
148 |
+
"eval_gen_len": 17.7,
|
149 |
+
"eval_rouge2": 6.6,
|
150 |
+
"eval_rougeL": 22.292,
|
151 |
+
"step": 5786
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 12.0,
|
155 |
+
"learning_rate": 4.000000000000001e-06,
|
156 |
+
"loss": 1.9173,
|
157 |
+
"step": 6312
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 12.0,
|
161 |
+
"eval_gen_len": 17.21,
|
162 |
+
"eval_rouge2": 6.32,
|
163 |
+
"eval_rougeL": 21.212,
|
164 |
+
"step": 6312
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 13.0,
|
168 |
+
"learning_rate": 3.5e-06,
|
169 |
+
"loss": 1.8784,
|
170 |
+
"step": 6838
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 13.0,
|
174 |
+
"eval_gen_len": 18.93,
|
175 |
+
"eval_rouge2": 6.95,
|
176 |
+
"eval_rougeL": 22.939,
|
177 |
+
"step": 6838
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 14.0,
|
181 |
+
"learning_rate": 3e-06,
|
182 |
+
"loss": 1.8346,
|
183 |
+
"step": 7364
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 14.0,
|
187 |
+
"eval_gen_len": 19.19,
|
188 |
+
"eval_rouge2": 6.42,
|
189 |
+
"eval_rougeL": 21.364,
|
190 |
+
"step": 7364
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 15.0,
|
194 |
+
"learning_rate": 2.5e-06,
|
195 |
+
"loss": 1.8006,
|
196 |
+
"step": 7890
|
197 |
+
},
|
198 |
+
{
|
199 |
+
"epoch": 15.0,
|
200 |
+
"eval_gen_len": 18.08,
|
201 |
+
"eval_rouge2": 5.86,
|
202 |
+
"eval_rougeL": 21.227,
|
203 |
+
"step": 7890
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 16.0,
|
207 |
+
"learning_rate": 2.0000000000000003e-06,
|
208 |
+
"loss": 1.7784,
|
209 |
+
"step": 8416
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 16.0,
|
213 |
+
"eval_gen_len": 17.06,
|
214 |
+
"eval_rouge2": 6.49,
|
215 |
+
"eval_rougeL": 21.942,
|
216 |
+
"step": 8416
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 17.0,
|
220 |
+
"learning_rate": 1.5e-06,
|
221 |
+
"loss": 1.7526,
|
222 |
+
"step": 8942
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 17.0,
|
226 |
+
"eval_gen_len": 18.66,
|
227 |
+
"eval_rouge2": 7.02,
|
228 |
+
"eval_rougeL": 22.17,
|
229 |
+
"step": 8942
|
230 |
+
},
|
231 |
+
{
|
232 |
+
"epoch": 18.0,
|
233 |
+
"learning_rate": 1.0000000000000002e-06,
|
234 |
+
"loss": 1.7409,
|
235 |
+
"step": 9468
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 18.0,
|
239 |
+
"eval_gen_len": 17.86,
|
240 |
+
"eval_rouge2": 6.65,
|
241 |
+
"eval_rougeL": 21.959,
|
242 |
+
"step": 9468
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 19.0,
|
246 |
+
"learning_rate": 5.000000000000001e-07,
|
247 |
+
"loss": 1.7238,
|
248 |
+
"step": 9994
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 19.0,
|
252 |
+
"eval_gen_len": 17.61,
|
253 |
+
"eval_rouge2": 6.23,
|
254 |
+
"eval_rougeL": 21.571,
|
255 |
+
"step": 9994
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 20.0,
|
259 |
+
"learning_rate": 0.0,
|
260 |
+
"loss": 1.7105,
|
261 |
+
"step": 10520
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 20.0,
|
265 |
+
"eval_gen_len": 17.14,
|
266 |
+
"eval_rouge2": 6.42,
|
267 |
+
"eval_rougeL": 21.664,
|
268 |
+
"step": 10520
|
269 |
+
}
|
270 |
+
],
|
271 |
+
"max_steps": 10520,
|
272 |
+
"num_train_epochs": 20,
|
273 |
+
"total_flos": 9621641311027200.0,
|
274 |
+
"trial_name": null,
|
275 |
+
"trial_params": null
|
276 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|