Ruben Mordechai Wolhandler
commited on
Commit
•
8062db2
1
Parent(s):
8d86530
upload_model
Browse files- all_results.json +6 -0
- checkpoint-23500/config.json +76 -0
- checkpoint-23500/merges.txt +0 -0
- checkpoint-23500/optimizer.pt +3 -0
- checkpoint-23500/pytorch_model.bin +3 -0
- checkpoint-23500/scheduler.pt +3 -0
- checkpoint-23500/special_tokens_map.json +1 -0
- checkpoint-23500/tokenizer_config.json +1 -0
- checkpoint-23500/trainer_state.json +298 -0
- checkpoint-23500/training_args.bin +3 -0
- checkpoint-23500/vocab.json +0 -0
- config.json +76 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +6 -0
- trainer_state.json +304 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_n_objs": -1,
|
4 |
+
"train_runtime": 4566.2664,
|
5 |
+
"train_samples_per_second": 5.178
|
6 |
+
}
|
checkpoint-23500/config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": 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_length": 128,
|
43 |
+
"max_position_embeddings": 1024,
|
44 |
+
"min_length": 12,
|
45 |
+
"model_type": "bart",
|
46 |
+
"no_repeat_ngram_size": 3,
|
47 |
+
"normalize_before": false,
|
48 |
+
"normalize_embedding": true,
|
49 |
+
"num_beams": 4,
|
50 |
+
"num_hidden_layers": 6,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"scale_embedding": false,
|
53 |
+
"static_position_embeddings": false,
|
54 |
+
"task_specific_params": {
|
55 |
+
"summarization": {
|
56 |
+
"length_penalty": 1.0,
|
57 |
+
"max_length": 128,
|
58 |
+
"min_length": 12,
|
59 |
+
"num_beams": 4
|
60 |
+
},
|
61 |
+
"summarization_cnn": {
|
62 |
+
"length_penalty": 2.0,
|
63 |
+
"max_length": 142,
|
64 |
+
"min_length": 56,
|
65 |
+
"num_beams": 4
|
66 |
+
},
|
67 |
+
"summarization_xsum": {
|
68 |
+
"length_penalty": 1.0,
|
69 |
+
"max_length": 62,
|
70 |
+
"min_length": 11,
|
71 |
+
"num_beams": 6
|
72 |
+
}
|
73 |
+
},
|
74 |
+
"use_cache": true,
|
75 |
+
"vocab_size": 50265
|
76 |
+
}
|
checkpoint-23500/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-23500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58d39a651154cd393f227c3336ed10db09a3d2178db58adf18a37b0e99eb901a
|
3 |
+
size 460101341
|
checkpoint-23500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3740e721cc5147dec92474bdc315cc3bc0ff63b954ee18e73bae54511f3798e0
|
3 |
+
size 557985683
|
checkpoint-23500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee19733281561cdec874e78983d9d6d23223dc7e8a803f37f872c496f84956cc
|
3 |
+
size 623
|
checkpoint-23500/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
checkpoint-23500/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "name_or_path": "facebook/bart-base"}
|
checkpoint-23500/trainer_state.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.9814767825425017,
|
5 |
+
"global_step": 23500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.06343567622430855,
|
12 |
+
"learning_rate": 4.8942738729594864e-05,
|
13 |
+
"loss": 2.408385009765625,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1268713524486171,
|
18 |
+
"learning_rate": 4.788547745918972e-05,
|
19 |
+
"loss": 2.0042470703125,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.19030702867292565,
|
24 |
+
"learning_rate": 4.682821618878457e-05,
|
25 |
+
"loss": 1.8769989013671875,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.2537427048972342,
|
30 |
+
"learning_rate": 4.5770954918379434e-05,
|
31 |
+
"loss": 1.820308837890625,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.31717838112154273,
|
36 |
+
"learning_rate": 4.4713693647974295e-05,
|
37 |
+
"loss": 1.7414315185546876,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.3806140573458513,
|
42 |
+
"learning_rate": 4.365643237756914e-05,
|
43 |
+
"loss": 1.6673572998046875,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.44404973357015987,
|
48 |
+
"learning_rate": 4.2599171107164004e-05,
|
49 |
+
"loss": 1.5917396240234376,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.5074854097944684,
|
54 |
+
"learning_rate": 4.1541909836758865e-05,
|
55 |
+
"loss": 1.4989898681640625,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.570921086018777,
|
60 |
+
"learning_rate": 4.048464856635372e-05,
|
61 |
+
"loss": 1.4598778076171874,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.6343567622430855,
|
66 |
+
"learning_rate": 3.9427387295948574e-05,
|
67 |
+
"loss": 1.3672525634765624,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.697792438467394,
|
72 |
+
"learning_rate": 3.8370126025543435e-05,
|
73 |
+
"loss": 1.3376380615234376,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.7612281146917026,
|
78 |
+
"learning_rate": 3.73128647551383e-05,
|
79 |
+
"loss": 1.280780029296875,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.8246637909160112,
|
84 |
+
"learning_rate": 3.6255603484733144e-05,
|
85 |
+
"loss": 1.2319114990234374,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.8880994671403197,
|
90 |
+
"learning_rate": 3.5198342214328006e-05,
|
91 |
+
"loss": 1.1800660400390626,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.9515351433646283,
|
96 |
+
"learning_rate": 3.414108094392287e-05,
|
97 |
+
"loss": 1.12030810546875,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.0149708195889369,
|
102 |
+
"learning_rate": 3.308381967351772e-05,
|
103 |
+
"loss": 1.09913232421875,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.0784064958132453,
|
108 |
+
"learning_rate": 3.2026558403112576e-05,
|
109 |
+
"loss": 1.0072744750976563,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.141842172037554,
|
114 |
+
"learning_rate": 3.096929713270744e-05,
|
115 |
+
"loss": 1.0016256713867187,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.2052778482618625,
|
120 |
+
"learning_rate": 2.9912035862302295e-05,
|
121 |
+
"loss": 0.9350516357421875,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.268713524486171,
|
126 |
+
"learning_rate": 2.885477459189715e-05,
|
127 |
+
"loss": 0.9032111206054687,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.3321492007104796,
|
132 |
+
"learning_rate": 2.7797513321492007e-05,
|
133 |
+
"loss": 0.8644053344726562,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.395584876934788,
|
138 |
+
"learning_rate": 2.674025205108687e-05,
|
139 |
+
"loss": 0.8429204711914062,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.4590205531590967,
|
144 |
+
"learning_rate": 2.5682990780681726e-05,
|
145 |
+
"loss": 0.8093466186523437,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.5224562293834052,
|
150 |
+
"learning_rate": 2.462572951027658e-05,
|
151 |
+
"loss": 0.7872549438476563,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.5858919056077139,
|
156 |
+
"learning_rate": 2.356846823987144e-05,
|
157 |
+
"loss": 0.7391060180664063,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.6493275818320223,
|
162 |
+
"learning_rate": 2.2511206969466293e-05,
|
163 |
+
"loss": 0.72500390625,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.7127632580563308,
|
168 |
+
"learning_rate": 2.1453945699061154e-05,
|
169 |
+
"loss": 0.704537841796875,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.7761989342806395,
|
174 |
+
"learning_rate": 2.039668442865601e-05,
|
175 |
+
"loss": 0.675576171875,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.8396346105049481,
|
180 |
+
"learning_rate": 1.933942315825087e-05,
|
181 |
+
"loss": 0.65029541015625,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.9030702867292564,
|
186 |
+
"learning_rate": 1.8282161887845725e-05,
|
187 |
+
"loss": 0.6266005859375,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.966505962953565,
|
192 |
+
"learning_rate": 1.7224900617440583e-05,
|
193 |
+
"loss": 0.6266526489257812,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.0299416391778737,
|
198 |
+
"learning_rate": 1.616763934703544e-05,
|
199 |
+
"loss": 0.60100439453125,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.093377315402182,
|
204 |
+
"learning_rate": 1.5110378076630297e-05,
|
205 |
+
"loss": 0.5694144287109375,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.1568129916264906,
|
210 |
+
"learning_rate": 1.4053116806225156e-05,
|
211 |
+
"loss": 0.5693157958984375,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.2202486678507993,
|
216 |
+
"learning_rate": 1.2995855535820012e-05,
|
217 |
+
"loss": 0.5522522583007813,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.283684344075108,
|
222 |
+
"learning_rate": 1.193859426541487e-05,
|
223 |
+
"loss": 0.5293363647460938,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.3471200202994162,
|
228 |
+
"learning_rate": 1.0881332995009726e-05,
|
229 |
+
"loss": 0.52986669921875,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.410555696523725,
|
234 |
+
"learning_rate": 9.824071724604584e-06,
|
235 |
+
"loss": 0.5213316040039062,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.4739913727480336,
|
240 |
+
"learning_rate": 8.766810454199442e-06,
|
241 |
+
"loss": 0.5159844970703125,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.537427048972342,
|
246 |
+
"learning_rate": 7.7095491837943e-06,
|
247 |
+
"loss": 0.508293701171875,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.6008627251966505,
|
252 |
+
"learning_rate": 6.652287913389158e-06,
|
253 |
+
"loss": 0.4958880615234375,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.664298401420959,
|
258 |
+
"learning_rate": 5.595026642984015e-06,
|
259 |
+
"loss": 0.48646127319335936,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.727734077645268,
|
264 |
+
"learning_rate": 4.537765372578872e-06,
|
265 |
+
"loss": 0.4905679626464844,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.791169753869576,
|
270 |
+
"learning_rate": 3.4805041021737297e-06,
|
271 |
+
"loss": 0.4853497314453125,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.854605430093885,
|
276 |
+
"learning_rate": 2.4232428317685867e-06,
|
277 |
+
"loss": 0.48792453002929687,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.9180411063181935,
|
282 |
+
"learning_rate": 1.3659815613634441e-06,
|
283 |
+
"loss": 0.48739105224609375,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.9814767825425017,
|
288 |
+
"learning_rate": 3.087202909583016e-07,
|
289 |
+
"loss": 0.4768514404296875,
|
290 |
+
"step": 23500
|
291 |
+
}
|
292 |
+
],
|
293 |
+
"max_steps": 23646,
|
294 |
+
"num_train_epochs": 3,
|
295 |
+
"total_flos": 63070308736114176,
|
296 |
+
"trial_name": null,
|
297 |
+
"trial_params": null
|
298 |
+
}
|
checkpoint-23500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c61e6cf034ebad9c80de8ce3f02ec0f1110230bbe433eee1fc85193b4e1fb7
|
3 |
+
size 2095
|
checkpoint-23500/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": 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_length": 128,
|
43 |
+
"max_position_embeddings": 1024,
|
44 |
+
"min_length": 12,
|
45 |
+
"model_type": "bart",
|
46 |
+
"no_repeat_ngram_size": 3,
|
47 |
+
"normalize_before": false,
|
48 |
+
"normalize_embedding": true,
|
49 |
+
"num_beams": 4,
|
50 |
+
"num_hidden_layers": 6,
|
51 |
+
"pad_token_id": 1,
|
52 |
+
"scale_embedding": false,
|
53 |
+
"static_position_embeddings": false,
|
54 |
+
"task_specific_params": {
|
55 |
+
"summarization": {
|
56 |
+
"length_penalty": 1.0,
|
57 |
+
"max_length": 128,
|
58 |
+
"min_length": 12,
|
59 |
+
"num_beams": 4
|
60 |
+
},
|
61 |
+
"summarization_cnn": {
|
62 |
+
"length_penalty": 2.0,
|
63 |
+
"max_length": 142,
|
64 |
+
"min_length": 56,
|
65 |
+
"num_beams": 4
|
66 |
+
},
|
67 |
+
"summarization_xsum": {
|
68 |
+
"length_penalty": 1.0,
|
69 |
+
"max_length": 62,
|
70 |
+
"min_length": 11,
|
71 |
+
"num_beams": 6
|
72 |
+
}
|
73 |
+
},
|
74 |
+
"use_cache": true,
|
75 |
+
"vocab_size": 50265
|
76 |
+
}
|
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 sha256:436bb098ce0a24c7c88e3cd9ec569b4ec6c1755d33692919fe1ed07d0ee2bfed
|
3 |
+
size 557985683
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "name_or_path": "facebook/bart-base"}
|
train_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_n_objs": -1,
|
4 |
+
"train_runtime": 4566.2664,
|
5 |
+
"train_samples_per_second": 5.178
|
6 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,304 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 23646,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.06343567622430855,
|
12 |
+
"learning_rate": 4.8942738729594864e-05,
|
13 |
+
"loss": 2.408385009765625,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1268713524486171,
|
18 |
+
"learning_rate": 4.788547745918972e-05,
|
19 |
+
"loss": 2.0042470703125,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.19030702867292565,
|
24 |
+
"learning_rate": 4.682821618878457e-05,
|
25 |
+
"loss": 1.8769989013671875,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.2537427048972342,
|
30 |
+
"learning_rate": 4.5770954918379434e-05,
|
31 |
+
"loss": 1.820308837890625,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.31717838112154273,
|
36 |
+
"learning_rate": 4.4713693647974295e-05,
|
37 |
+
"loss": 1.7414315185546876,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.3806140573458513,
|
42 |
+
"learning_rate": 4.365643237756914e-05,
|
43 |
+
"loss": 1.6673572998046875,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.44404973357015987,
|
48 |
+
"learning_rate": 4.2599171107164004e-05,
|
49 |
+
"loss": 1.5917396240234376,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.5074854097944684,
|
54 |
+
"learning_rate": 4.1541909836758865e-05,
|
55 |
+
"loss": 1.4989898681640625,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.570921086018777,
|
60 |
+
"learning_rate": 4.048464856635372e-05,
|
61 |
+
"loss": 1.4598778076171874,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.6343567622430855,
|
66 |
+
"learning_rate": 3.9427387295948574e-05,
|
67 |
+
"loss": 1.3672525634765624,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.697792438467394,
|
72 |
+
"learning_rate": 3.8370126025543435e-05,
|
73 |
+
"loss": 1.3376380615234376,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.7612281146917026,
|
78 |
+
"learning_rate": 3.73128647551383e-05,
|
79 |
+
"loss": 1.280780029296875,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.8246637909160112,
|
84 |
+
"learning_rate": 3.6255603484733144e-05,
|
85 |
+
"loss": 1.2319114990234374,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.8880994671403197,
|
90 |
+
"learning_rate": 3.5198342214328006e-05,
|
91 |
+
"loss": 1.1800660400390626,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.9515351433646283,
|
96 |
+
"learning_rate": 3.414108094392287e-05,
|
97 |
+
"loss": 1.12030810546875,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.0149708195889369,
|
102 |
+
"learning_rate": 3.308381967351772e-05,
|
103 |
+
"loss": 1.09913232421875,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.0784064958132453,
|
108 |
+
"learning_rate": 3.2026558403112576e-05,
|
109 |
+
"loss": 1.0072744750976563,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.141842172037554,
|
114 |
+
"learning_rate": 3.096929713270744e-05,
|
115 |
+
"loss": 1.0016256713867187,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.2052778482618625,
|
120 |
+
"learning_rate": 2.9912035862302295e-05,
|
121 |
+
"loss": 0.9350516357421875,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.268713524486171,
|
126 |
+
"learning_rate": 2.885477459189715e-05,
|
127 |
+
"loss": 0.9032111206054687,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.3321492007104796,
|
132 |
+
"learning_rate": 2.7797513321492007e-05,
|
133 |
+
"loss": 0.8644053344726562,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.395584876934788,
|
138 |
+
"learning_rate": 2.674025205108687e-05,
|
139 |
+
"loss": 0.8429204711914062,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.4590205531590967,
|
144 |
+
"learning_rate": 2.5682990780681726e-05,
|
145 |
+
"loss": 0.8093466186523437,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.5224562293834052,
|
150 |
+
"learning_rate": 2.462572951027658e-05,
|
151 |
+
"loss": 0.7872549438476563,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.5858919056077139,
|
156 |
+
"learning_rate": 2.356846823987144e-05,
|
157 |
+
"loss": 0.7391060180664063,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.6493275818320223,
|
162 |
+
"learning_rate": 2.2511206969466293e-05,
|
163 |
+
"loss": 0.72500390625,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.7127632580563308,
|
168 |
+
"learning_rate": 2.1453945699061154e-05,
|
169 |
+
"loss": 0.704537841796875,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.7761989342806395,
|
174 |
+
"learning_rate": 2.039668442865601e-05,
|
175 |
+
"loss": 0.675576171875,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.8396346105049481,
|
180 |
+
"learning_rate": 1.933942315825087e-05,
|
181 |
+
"loss": 0.65029541015625,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.9030702867292564,
|
186 |
+
"learning_rate": 1.8282161887845725e-05,
|
187 |
+
"loss": 0.6266005859375,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.966505962953565,
|
192 |
+
"learning_rate": 1.7224900617440583e-05,
|
193 |
+
"loss": 0.6266526489257812,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.0299416391778737,
|
198 |
+
"learning_rate": 1.616763934703544e-05,
|
199 |
+
"loss": 0.60100439453125,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.093377315402182,
|
204 |
+
"learning_rate": 1.5110378076630297e-05,
|
205 |
+
"loss": 0.5694144287109375,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.1568129916264906,
|
210 |
+
"learning_rate": 1.4053116806225156e-05,
|
211 |
+
"loss": 0.5693157958984375,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.2202486678507993,
|
216 |
+
"learning_rate": 1.2995855535820012e-05,
|
217 |
+
"loss": 0.5522522583007813,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.283684344075108,
|
222 |
+
"learning_rate": 1.193859426541487e-05,
|
223 |
+
"loss": 0.5293363647460938,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.3471200202994162,
|
228 |
+
"learning_rate": 1.0881332995009726e-05,
|
229 |
+
"loss": 0.52986669921875,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.410555696523725,
|
234 |
+
"learning_rate": 9.824071724604584e-06,
|
235 |
+
"loss": 0.5213316040039062,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.4739913727480336,
|
240 |
+
"learning_rate": 8.766810454199442e-06,
|
241 |
+
"loss": 0.5159844970703125,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.537427048972342,
|
246 |
+
"learning_rate": 7.7095491837943e-06,
|
247 |
+
"loss": 0.508293701171875,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.6008627251966505,
|
252 |
+
"learning_rate": 6.652287913389158e-06,
|
253 |
+
"loss": 0.4958880615234375,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.664298401420959,
|
258 |
+
"learning_rate": 5.595026642984015e-06,
|
259 |
+
"loss": 0.48646127319335936,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.727734077645268,
|
264 |
+
"learning_rate": 4.537765372578872e-06,
|
265 |
+
"loss": 0.4905679626464844,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.791169753869576,
|
270 |
+
"learning_rate": 3.4805041021737297e-06,
|
271 |
+
"loss": 0.4853497314453125,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.854605430093885,
|
276 |
+
"learning_rate": 2.4232428317685867e-06,
|
277 |
+
"loss": 0.48792453002929687,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.9180411063181935,
|
282 |
+
"learning_rate": 1.3659815613634441e-06,
|
283 |
+
"loss": 0.48739105224609375,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.9814767825425017,
|
288 |
+
"learning_rate": 3.087202909583016e-07,
|
289 |
+
"loss": 0.4768514404296875,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.0,
|
294 |
+
"step": 23646,
|
295 |
+
"train_runtime": 4566.2664,
|
296 |
+
"train_samples_per_second": 5.178
|
297 |
+
}
|
298 |
+
],
|
299 |
+
"max_steps": 23646,
|
300 |
+
"num_train_epochs": 3,
|
301 |
+
"total_flos": 63460156661015040,
|
302 |
+
"trial_name": null,
|
303 |
+
"trial_params": null
|
304 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c61e6cf034ebad9c80de8ce3f02ec0f1110230bbe433eee1fc85193b4e1fb7
|
3 |
+
size 2095
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|