Model save
Browse files- last-checkpoint/config.json +0 -38
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/optimizer.pt +0 -3
- last-checkpoint/pytorch_model.bin +0 -3
- last-checkpoint/rng_state.pth +0 -3
- last-checkpoint/scaler.pt +0 -3
- last-checkpoint/scheduler.pt +0 -3
- last-checkpoint/special_tokens_map.json +0 -15
- last-checkpoint/tokenizer.json +0 -0
- last-checkpoint/tokenizer_config.json +0 -15
- last-checkpoint/trainer_state.json +0 -288
- last-checkpoint/training_args.bin +0 -3
- last-checkpoint/vocab.json +0 -0
- pytorch_model.bin +1 -1
last-checkpoint/config.json
DELETED
@@ -1,38 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "roberta-large",
|
3 |
-
"architectures": [
|
4 |
-
"RobertaForSequenceClassification"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": null,
|
9 |
-
"eos_token_id": 2,
|
10 |
-
"hidden_act": "gelu",
|
11 |
-
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size": 1024,
|
13 |
-
"id2label": {
|
14 |
-
"0": "entailment",
|
15 |
-
"1": "neutral",
|
16 |
-
"2": "contradiction"
|
17 |
-
},
|
18 |
-
"initializer_range": 0.02,
|
19 |
-
"intermediate_size": 4096,
|
20 |
-
"label2id": {
|
21 |
-
"contradiction": 2,
|
22 |
-
"entailment": 0,
|
23 |
-
"neutral": 1
|
24 |
-
},
|
25 |
-
"layer_norm_eps": 1e-05,
|
26 |
-
"max_position_embeddings": 514,
|
27 |
-
"model_type": "roberta",
|
28 |
-
"num_attention_heads": 16,
|
29 |
-
"num_hidden_layers": 24,
|
30 |
-
"pad_token_id": 1,
|
31 |
-
"position_embedding_type": "absolute",
|
32 |
-
"problem_type": "single_label_classification",
|
33 |
-
"torch_dtype": "float32",
|
34 |
-
"transformers_version": "4.27.1",
|
35 |
-
"type_vocab_size": 1,
|
36 |
-
"use_cache": true,
|
37 |
-
"vocab_size": 50265
|
38 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:43b746406019bd322df48fd0f5832641bf2c23f192d1ba2c1bcf2cc6ec4661ff
|
3 |
-
size 2843228158
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:c70a2b61096d5fd16d601664f84ccd8cb72633596aa2bd5105a81863e667c6b3
|
3 |
-
size 1421588461
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b11b41a45679a6cc286e868bec1372008710d641cbd28a995ea530dff638bd50
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ad34206adf67443db75af07189b4384fe36c9a4922d3cd2b4375c9ae9591e609
|
3 |
-
size 559
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:ce44e4c1c23e749cd9382e42f9e5375956ba931527c483dc2fade7c594fb4a25
|
3 |
-
size 623
|
|
|
|
|
|
|
|
last-checkpoint/special_tokens_map.json
DELETED
@@ -1,15 +0,0 @@
|
|
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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/tokenizer_config.json
DELETED
@@ -1,15 +0,0 @@
|
|
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": 512,
|
9 |
-
"pad_token": "<pad>",
|
10 |
-
"sep_token": "</s>",
|
11 |
-
"special_tokens_map_file": null,
|
12 |
-
"tokenizer_class": "RobertaTokenizer",
|
13 |
-
"trim_offsets": true,
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/trainer_state.json
DELETED
@@ -1,288 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.9274853061519247,
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-large-e-snli-classification-nli-base/checkpoint-6000",
|
4 |
-
"epoch": 0.7921714818266542,
|
5 |
-
"global_step": 6800,
|
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": 3.082298136645963e-06,
|
13 |
-
"loss": 0.9995,
|
14 |
-
"step": 400
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.05,
|
18 |
-
"eval_accuracy": 0.8464742938427149,
|
19 |
-
"eval_f1": 0.8436602565292818,
|
20 |
-
"eval_loss": 0.42355620861053467,
|
21 |
-
"eval_runtime": 9.7799,
|
22 |
-
"eval_samples_per_second": 1006.353,
|
23 |
-
"eval_steps_per_second": 15.747,
|
24 |
-
"step": 400
|
25 |
-
},
|
26 |
-
{
|
27 |
-
"epoch": 0.09,
|
28 |
-
"learning_rate": 6.187888198757764e-06,
|
29 |
-
"loss": 0.4089,
|
30 |
-
"step": 800
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 0.09,
|
34 |
-
"eval_accuracy": 0.8933143669985776,
|
35 |
-
"eval_f1": 0.8925604380368285,
|
36 |
-
"eval_loss": 0.2960757315158844,
|
37 |
-
"eval_runtime": 9.9483,
|
38 |
-
"eval_samples_per_second": 989.314,
|
39 |
-
"eval_steps_per_second": 15.48,
|
40 |
-
"step": 800
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"epoch": 0.14,
|
44 |
-
"learning_rate": 9.285714285714288e-06,
|
45 |
-
"loss": 0.3681,
|
46 |
-
"step": 1200
|
47 |
-
},
|
48 |
-
{
|
49 |
-
"epoch": 0.14,
|
50 |
-
"eval_accuracy": 0.8923999187157082,
|
51 |
-
"eval_f1": 0.8914399447140089,
|
52 |
-
"eval_loss": 0.2979675531387329,
|
53 |
-
"eval_runtime": 11.3415,
|
54 |
-
"eval_samples_per_second": 867.789,
|
55 |
-
"eval_steps_per_second": 13.578,
|
56 |
-
"step": 1200
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.19,
|
60 |
-
"learning_rate": 9.874100719424462e-06,
|
61 |
-
"loss": 0.3467,
|
62 |
-
"step": 1600
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.19,
|
66 |
-
"eval_accuracy": 0.89900426742532,
|
67 |
-
"eval_f1": 0.8976972154704725,
|
68 |
-
"eval_loss": 0.28719303011894226,
|
69 |
-
"eval_runtime": 9.8854,
|
70 |
-
"eval_samples_per_second": 995.605,
|
71 |
-
"eval_steps_per_second": 15.578,
|
72 |
-
"step": 1600
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 0.23,
|
76 |
-
"learning_rate": 9.71100392413342e-06,
|
77 |
-
"loss": 0.324,
|
78 |
-
"step": 2000
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"epoch": 0.23,
|
82 |
-
"eval_accuracy": 0.9109937004673847,
|
83 |
-
"eval_f1": 0.9105643338042256,
|
84 |
-
"eval_loss": 0.2506079077720642,
|
85 |
-
"eval_runtime": 9.9303,
|
86 |
-
"eval_samples_per_second": 991.111,
|
87 |
-
"eval_steps_per_second": 15.508,
|
88 |
-
"step": 2000
|
89 |
-
},
|
90 |
-
{
|
91 |
-
"epoch": 0.28,
|
92 |
-
"learning_rate": 9.547498364944409e-06,
|
93 |
-
"loss": 0.3222,
|
94 |
-
"step": 2400
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"epoch": 0.28,
|
98 |
-
"eval_accuracy": 0.9128225970331233,
|
99 |
-
"eval_f1": 0.9131812993042298,
|
100 |
-
"eval_loss": 0.2551884353160858,
|
101 |
-
"eval_runtime": 9.9844,
|
102 |
-
"eval_samples_per_second": 985.737,
|
103 |
-
"eval_steps_per_second": 15.424,
|
104 |
-
"step": 2400
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.33,
|
108 |
-
"learning_rate": 9.383992805755397e-06,
|
109 |
-
"loss": 0.3138,
|
110 |
-
"step": 2800
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.33,
|
114 |
-
"eval_accuracy": 0.9183092867303394,
|
115 |
-
"eval_f1": 0.9182731413386942,
|
116 |
-
"eval_loss": 0.23789888620376587,
|
117 |
-
"eval_runtime": 10.0071,
|
118 |
-
"eval_samples_per_second": 983.498,
|
119 |
-
"eval_steps_per_second": 15.389,
|
120 |
-
"step": 2800
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"epoch": 0.37,
|
124 |
-
"learning_rate": 9.220487246566384e-06,
|
125 |
-
"loss": 0.3107,
|
126 |
-
"step": 3200
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"epoch": 0.37,
|
130 |
-
"eval_accuracy": 0.9155659418817313,
|
131 |
-
"eval_f1": 0.9151783750171821,
|
132 |
-
"eval_loss": 0.23962362110614777,
|
133 |
-
"eval_runtime": 9.9366,
|
134 |
-
"eval_samples_per_second": 990.484,
|
135 |
-
"eval_steps_per_second": 15.498,
|
136 |
-
"step": 3200
|
137 |
-
},
|
138 |
-
{
|
139 |
-
"epoch": 0.42,
|
140 |
-
"learning_rate": 9.056981687377372e-06,
|
141 |
-
"loss": 0.304,
|
142 |
-
"step": 3600
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 0.42,
|
146 |
-
"eval_accuracy": 0.9176996545417598,
|
147 |
-
"eval_f1": 0.9174168238144101,
|
148 |
-
"eval_loss": 0.23535017669200897,
|
149 |
-
"eval_runtime": 9.936,
|
150 |
-
"eval_samples_per_second": 990.544,
|
151 |
-
"eval_steps_per_second": 15.499,
|
152 |
-
"step": 3600
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 0.47,
|
156 |
-
"learning_rate": 8.893476128188358e-06,
|
157 |
-
"loss": 0.3027,
|
158 |
-
"step": 4000
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 0.47,
|
162 |
-
"eval_accuracy": 0.9191221296484454,
|
163 |
-
"eval_f1": 0.9190571565466592,
|
164 |
-
"eval_loss": 0.23602379858493805,
|
165 |
-
"eval_runtime": 10.6438,
|
166 |
-
"eval_samples_per_second": 924.674,
|
167 |
-
"eval_steps_per_second": 14.469,
|
168 |
-
"step": 4000
|
169 |
-
},
|
170 |
-
{
|
171 |
-
"epoch": 0.51,
|
172 |
-
"learning_rate": 8.729970568999347e-06,
|
173 |
-
"loss": 0.2968,
|
174 |
-
"step": 4400
|
175 |
-
},
|
176 |
-
{
|
177 |
-
"epoch": 0.51,
|
178 |
-
"eval_accuracy": 0.9187157081893924,
|
179 |
-
"eval_f1": 0.9182261319193824,
|
180 |
-
"eval_loss": 0.23287305235862732,
|
181 |
-
"eval_runtime": 9.9312,
|
182 |
-
"eval_samples_per_second": 991.014,
|
183 |
-
"eval_steps_per_second": 15.507,
|
184 |
-
"step": 4400
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 0.56,
|
188 |
-
"learning_rate": 8.566465009810335e-06,
|
189 |
-
"loss": 0.2888,
|
190 |
-
"step": 4800
|
191 |
-
},
|
192 |
-
{
|
193 |
-
"epoch": 0.56,
|
194 |
-
"eval_accuracy": 0.9196301564722618,
|
195 |
-
"eval_f1": 0.9189361658403055,
|
196 |
-
"eval_loss": 0.24621723592281342,
|
197 |
-
"eval_runtime": 9.9085,
|
198 |
-
"eval_samples_per_second": 993.291,
|
199 |
-
"eval_steps_per_second": 15.542,
|
200 |
-
"step": 4800
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 0.61,
|
204 |
-
"learning_rate": 8.402959450621321e-06,
|
205 |
-
"loss": 0.2898,
|
206 |
-
"step": 5200
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 0.61,
|
210 |
-
"eval_accuracy": 0.9211542369437107,
|
211 |
-
"eval_f1": 0.9206360860900841,
|
212 |
-
"eval_loss": 0.23345668613910675,
|
213 |
-
"eval_runtime": 10.0954,
|
214 |
-
"eval_samples_per_second": 974.901,
|
215 |
-
"eval_steps_per_second": 15.254,
|
216 |
-
"step": 5200
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"epoch": 0.65,
|
220 |
-
"learning_rate": 8.23945389143231e-06,
|
221 |
-
"loss": 0.288,
|
222 |
-
"step": 5600
|
223 |
-
},
|
224 |
-
{
|
225 |
-
"epoch": 0.65,
|
226 |
-
"eval_accuracy": 0.9222718959561065,
|
227 |
-
"eval_f1": 0.9220252130752401,
|
228 |
-
"eval_loss": 0.23495520651340485,
|
229 |
-
"eval_runtime": 9.9904,
|
230 |
-
"eval_samples_per_second": 985.146,
|
231 |
-
"eval_steps_per_second": 15.415,
|
232 |
-
"step": 5600
|
233 |
-
},
|
234 |
-
{
|
235 |
-
"epoch": 0.7,
|
236 |
-
"learning_rate": 8.07635709614127e-06,
|
237 |
-
"loss": 0.2746,
|
238 |
-
"step": 6000
|
239 |
-
},
|
240 |
-
{
|
241 |
-
"epoch": 0.7,
|
242 |
-
"eval_accuracy": 0.9277585856533225,
|
243 |
-
"eval_f1": 0.9274853061519247,
|
244 |
-
"eval_loss": 0.22077496349811554,
|
245 |
-
"eval_runtime": 9.9415,
|
246 |
-
"eval_samples_per_second": 989.988,
|
247 |
-
"eval_steps_per_second": 15.491,
|
248 |
-
"step": 6000
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 0.75,
|
252 |
-
"learning_rate": 7.912851536952257e-06,
|
253 |
-
"loss": 0.2756,
|
254 |
-
"step": 6400
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.75,
|
258 |
-
"eval_accuracy": 0.9215606584027637,
|
259 |
-
"eval_f1": 0.9208559714907353,
|
260 |
-
"eval_loss": 0.23040013015270233,
|
261 |
-
"eval_runtime": 9.916,
|
262 |
-
"eval_samples_per_second": 992.538,
|
263 |
-
"eval_steps_per_second": 15.53,
|
264 |
-
"step": 6400
|
265 |
-
},
|
266 |
-
{
|
267 |
-
"epoch": 0.79,
|
268 |
-
"learning_rate": 7.749345977763243e-06,
|
269 |
-
"loss": 0.272,
|
270 |
-
"step": 6800
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"epoch": 0.79,
|
274 |
-
"eval_accuracy": 0.9237959764275554,
|
275 |
-
"eval_f1": 0.9236808650336354,
|
276 |
-
"eval_loss": 0.2243068963289261,
|
277 |
-
"eval_runtime": 11.5455,
|
278 |
-
"eval_samples_per_second": 852.451,
|
279 |
-
"eval_steps_per_second": 13.338,
|
280 |
-
"step": 6800
|
281 |
-
}
|
282 |
-
],
|
283 |
-
"max_steps": 25752,
|
284 |
-
"num_train_epochs": 3,
|
285 |
-
"total_flos": 4.208639555132851e+16,
|
286 |
-
"trial_name": null,
|
287 |
-
"trial_params": null
|
288 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:3c226ff8a79fc8c43647efdd29cbdbc642d1c7fa8c770b0a81535e6a61aee411
|
3 |
-
size 3695
|
|
|
|
|
|
|
|
last-checkpoint/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1421588461
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d27bd0c8fce811ee26a2630d332b495ceabc992b88ed7e0afd7cdda82dc97b4
|
3 |
size 1421588461
|