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 -368
- 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-base",
|
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": 768,
|
13 |
-
"id2label": {
|
14 |
-
"0": "entailment",
|
15 |
-
"1": "neutral",
|
16 |
-
"2": "contradiction"
|
17 |
-
},
|
18 |
-
"initializer_range": 0.02,
|
19 |
-
"intermediate_size": 3072,
|
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": 12,
|
29 |
-
"num_hidden_layers": 12,
|
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 sha256:8c7978bf8054801da6f4c756ac3ee82d92c0f486af86b40dc0bf28323cf03296
|
3 |
-
size 997349515
|
|
|
|
|
|
|
|
last-checkpoint/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:19f88d4ac00fa7feb29c8dd174036ce80b27f550f2e7dcaa40ee80769e3c83a2
|
3 |
-
size 498663405
|
|
|
|
|
|
|
|
last-checkpoint/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:fc559e8f3be7931753acd7e14135ef3c355c45429768068a18a2cdbd924ae84e
|
3 |
-
size 14503
|
|
|
|
|
|
|
|
last-checkpoint/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0ac5f79294afe5b58702f8cfd595843c97cf8ecf3eb18e0b1f699ed162ad0894
|
3 |
-
size 559
|
|
|
|
|
|
|
|
last-checkpoint/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:7ac05aa2ac2c93c43b69f88d2a334721a2027f6a3102b80f21e4e6745984e25d
|
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
@@ -1,368 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": 0.9120778013038088,
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/nlp-final-project/results/roberta-base-e-snli-classification-nli-base/checkpoint-8000",
|
4 |
-
"epoch": 1.0251630941286114,
|
5 |
-
"global_step": 8800,
|
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": 3.0900621118012425e-06,
|
13 |
-
"loss": 1.0317,
|
14 |
-
"step": 400
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.05,
|
18 |
-
"eval_accuracy": 0.7803292013818329,
|
19 |
-
"eval_f1": 0.7770741838405094,
|
20 |
-
"eval_loss": 0.5733650326728821,
|
21 |
-
"eval_runtime": 5.0438,
|
22 |
-
"eval_samples_per_second": 1951.29,
|
23 |
-
"eval_steps_per_second": 30.532,
|
24 |
-
"step": 400
|
25 |
-
},
|
26 |
-
{
|
27 |
-
"epoch": 0.09,
|
28 |
-
"learning_rate": 6.187888198757764e-06,
|
29 |
-
"loss": 0.544,
|
30 |
-
"step": 800
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 0.09,
|
34 |
-
"eval_accuracy": 0.855517171306645,
|
35 |
-
"eval_f1": 0.8547612368327439,
|
36 |
-
"eval_loss": 0.3994133174419403,
|
37 |
-
"eval_runtime": 4.3487,
|
38 |
-
"eval_samples_per_second": 2263.221,
|
39 |
-
"eval_steps_per_second": 35.413,
|
40 |
-
"step": 800
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"epoch": 0.14,
|
44 |
-
"learning_rate": 9.293478260869566e-06,
|
45 |
-
"loss": 0.4604,
|
46 |
-
"step": 1200
|
47 |
-
},
|
48 |
-
{
|
49 |
-
"epoch": 0.14,
|
50 |
-
"eval_accuracy": 0.8687258687258688,
|
51 |
-
"eval_f1": 0.8681066915368941,
|
52 |
-
"eval_loss": 0.3491659164428711,
|
53 |
-
"eval_runtime": 4.2453,
|
54 |
-
"eval_samples_per_second": 2318.326,
|
55 |
-
"eval_steps_per_second": 36.275,
|
56 |
-
"step": 1200
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 0.19,
|
60 |
-
"learning_rate": 9.87369195552649e-06,
|
61 |
-
"loss": 0.4235,
|
62 |
-
"step": 1600
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.19,
|
66 |
-
"eval_accuracy": 0.8776671408250356,
|
67 |
-
"eval_f1": 0.8764133428741641,
|
68 |
-
"eval_loss": 0.3322618901729584,
|
69 |
-
"eval_runtime": 4.4615,
|
70 |
-
"eval_samples_per_second": 2205.99,
|
71 |
-
"eval_steps_per_second": 34.518,
|
72 |
-
"step": 1600
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 0.23,
|
76 |
-
"learning_rate": 9.710186396337476e-06,
|
77 |
-
"loss": 0.3934,
|
78 |
-
"step": 2000
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"epoch": 0.23,
|
82 |
-
"eval_accuracy": 0.884068278805121,
|
83 |
-
"eval_f1": 0.8831390301360367,
|
84 |
-
"eval_loss": 0.32249000668525696,
|
85 |
-
"eval_runtime": 4.2395,
|
86 |
-
"eval_samples_per_second": 2321.481,
|
87 |
-
"eval_steps_per_second": 36.325,
|
88 |
-
"step": 2000
|
89 |
-
},
|
90 |
-
{
|
91 |
-
"epoch": 0.28,
|
92 |
-
"learning_rate": 9.546680837148464e-06,
|
93 |
-
"loss": 0.3863,
|
94 |
-
"step": 2400
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"epoch": 0.28,
|
98 |
-
"eval_accuracy": 0.8872180451127819,
|
99 |
-
"eval_f1": 0.887543528243619,
|
100 |
-
"eval_loss": 0.3085917532444,
|
101 |
-
"eval_runtime": 4.3491,
|
102 |
-
"eval_samples_per_second": 2263.01,
|
103 |
-
"eval_steps_per_second": 35.41,
|
104 |
-
"step": 2400
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 0.33,
|
108 |
-
"learning_rate": 9.38317527795945e-06,
|
109 |
-
"loss": 0.3767,
|
110 |
-
"step": 2800
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 0.33,
|
114 |
-
"eval_accuracy": 0.8897581792318634,
|
115 |
-
"eval_f1": 0.8891603343028002,
|
116 |
-
"eval_loss": 0.29720813035964966,
|
117 |
-
"eval_runtime": 4.3717,
|
118 |
-
"eval_samples_per_second": 2251.299,
|
119 |
-
"eval_steps_per_second": 35.227,
|
120 |
-
"step": 2800
|
121 |
-
},
|
122 |
-
{
|
123 |
-
"epoch": 0.37,
|
124 |
-
"learning_rate": 9.219669718770439e-06,
|
125 |
-
"loss": 0.3726,
|
126 |
-
"step": 3200
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"epoch": 0.37,
|
130 |
-
"eval_accuracy": 0.8936191830928673,
|
131 |
-
"eval_f1": 0.8931996056385407,
|
132 |
-
"eval_loss": 0.29100456833839417,
|
133 |
-
"eval_runtime": 4.4246,
|
134 |
-
"eval_samples_per_second": 2224.393,
|
135 |
-
"eval_steps_per_second": 34.806,
|
136 |
-
"step": 3200
|
137 |
-
},
|
138 |
-
{
|
139 |
-
"epoch": 0.42,
|
140 |
-
"learning_rate": 9.056164159581427e-06,
|
141 |
-
"loss": 0.3624,
|
142 |
-
"step": 3600
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 0.42,
|
146 |
-
"eval_accuracy": 0.8937207884576306,
|
147 |
-
"eval_f1": 0.8933970762962105,
|
148 |
-
"eval_loss": 0.2934032082557678,
|
149 |
-
"eval_runtime": 4.3374,
|
150 |
-
"eval_samples_per_second": 2269.111,
|
151 |
-
"eval_steps_per_second": 35.505,
|
152 |
-
"step": 3600
|
153 |
-
},
|
154 |
-
{
|
155 |
-
"epoch": 0.47,
|
156 |
-
"learning_rate": 8.892658600392414e-06,
|
157 |
-
"loss": 0.361,
|
158 |
-
"step": 4000
|
159 |
-
},
|
160 |
-
{
|
161 |
-
"epoch": 0.47,
|
162 |
-
"eval_accuracy": 0.8989026620605568,
|
163 |
-
"eval_f1": 0.898874821280442,
|
164 |
-
"eval_loss": 0.28308674693107605,
|
165 |
-
"eval_runtime": 4.2135,
|
166 |
-
"eval_samples_per_second": 2335.846,
|
167 |
-
"eval_steps_per_second": 36.55,
|
168 |
-
"step": 4000
|
169 |
-
},
|
170 |
-
{
|
171 |
-
"epoch": 0.51,
|
172 |
-
"learning_rate": 8.729153041203402e-06,
|
173 |
-
"loss": 0.3553,
|
174 |
-
"step": 4400
|
175 |
-
},
|
176 |
-
{
|
177 |
-
"epoch": 0.51,
|
178 |
-
"eval_accuracy": 0.8993090835196098,
|
179 |
-
"eval_f1": 0.898521939461863,
|
180 |
-
"eval_loss": 0.29054638743400574,
|
181 |
-
"eval_runtime": 4.2186,
|
182 |
-
"eval_samples_per_second": 2332.993,
|
183 |
-
"eval_steps_per_second": 36.505,
|
184 |
-
"step": 4400
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 0.56,
|
188 |
-
"learning_rate": 8.565647482014388e-06,
|
189 |
-
"loss": 0.3451,
|
190 |
-
"step": 4800
|
191 |
-
},
|
192 |
-
{
|
193 |
-
"epoch": 0.56,
|
194 |
-
"eval_accuracy": 0.9023572444625076,
|
195 |
-
"eval_f1": 0.901894187198396,
|
196 |
-
"eval_loss": 0.27245137095451355,
|
197 |
-
"eval_runtime": 4.2088,
|
198 |
-
"eval_samples_per_second": 2338.443,
|
199 |
-
"eval_steps_per_second": 36.59,
|
200 |
-
"step": 4800
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 0.61,
|
204 |
-
"learning_rate": 8.402141922825377e-06,
|
205 |
-
"loss": 0.3475,
|
206 |
-
"step": 5200
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 0.61,
|
210 |
-
"eval_accuracy": 0.9051005893111156,
|
211 |
-
"eval_f1": 0.9046245607228055,
|
212 |
-
"eval_loss": 0.2711792588233948,
|
213 |
-
"eval_runtime": 4.2086,
|
214 |
-
"eval_samples_per_second": 2338.56,
|
215 |
-
"eval_steps_per_second": 36.592,
|
216 |
-
"step": 5200
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"epoch": 0.65,
|
220 |
-
"learning_rate": 8.238636363636365e-06,
|
221 |
-
"loss": 0.3398,
|
222 |
-
"step": 5600
|
223 |
-
},
|
224 |
-
{
|
225 |
-
"epoch": 0.65,
|
226 |
-
"eval_accuracy": 0.9027636659215607,
|
227 |
-
"eval_f1": 0.9024225307003263,
|
228 |
-
"eval_loss": 0.2787366211414337,
|
229 |
-
"eval_runtime": 4.3854,
|
230 |
-
"eval_samples_per_second": 2244.277,
|
231 |
-
"eval_steps_per_second": 35.117,
|
232 |
-
"step": 5600
|
233 |
-
},
|
234 |
-
{
|
235 |
-
"epoch": 0.7,
|
236 |
-
"learning_rate": 8.075130804447351e-06,
|
237 |
-
"loss": 0.3322,
|
238 |
-
"step": 6000
|
239 |
-
},
|
240 |
-
{
|
241 |
-
"epoch": 0.7,
|
242 |
-
"eval_accuracy": 0.9045925624872994,
|
243 |
-
"eval_f1": 0.9043146299021979,
|
244 |
-
"eval_loss": 0.2696707248687744,
|
245 |
-
"eval_runtime": 4.2347,
|
246 |
-
"eval_samples_per_second": 2324.111,
|
247 |
-
"eval_steps_per_second": 36.366,
|
248 |
-
"step": 6000
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 0.75,
|
252 |
-
"learning_rate": 7.912034009156312e-06,
|
253 |
-
"loss": 0.3288,
|
254 |
-
"step": 6400
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.75,
|
258 |
-
"eval_accuracy": 0.9013411908148751,
|
259 |
-
"eval_f1": 0.90060674757625,
|
260 |
-
"eval_loss": 0.2721998691558838,
|
261 |
-
"eval_runtime": 4.1964,
|
262 |
-
"eval_samples_per_second": 2345.34,
|
263 |
-
"eval_steps_per_second": 36.698,
|
264 |
-
"step": 6400
|
265 |
-
},
|
266 |
-
{
|
267 |
-
"epoch": 0.79,
|
268 |
-
"learning_rate": 7.7485284499673e-06,
|
269 |
-
"loss": 0.324,
|
270 |
-
"step": 6800
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"epoch": 0.79,
|
274 |
-
"eval_accuracy": 0.9066246697825645,
|
275 |
-
"eval_f1": 0.9065691454907331,
|
276 |
-
"eval_loss": 0.26766958832740784,
|
277 |
-
"eval_runtime": 4.5081,
|
278 |
-
"eval_samples_per_second": 2183.165,
|
279 |
-
"eval_steps_per_second": 34.16,
|
280 |
-
"step": 6800
|
281 |
-
},
|
282 |
-
{
|
283 |
-
"epoch": 0.84,
|
284 |
-
"learning_rate": 7.585022890778288e-06,
|
285 |
-
"loss": 0.3335,
|
286 |
-
"step": 7200
|
287 |
-
},
|
288 |
-
{
|
289 |
-
"epoch": 0.84,
|
290 |
-
"eval_accuracy": 0.9077423287949604,
|
291 |
-
"eval_f1": 0.907479569921263,
|
292 |
-
"eval_loss": 0.2629023790359497,
|
293 |
-
"eval_runtime": 4.168,
|
294 |
-
"eval_samples_per_second": 2361.347,
|
295 |
-
"eval_steps_per_second": 36.949,
|
296 |
-
"step": 7200
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.89,
|
300 |
-
"learning_rate": 7.421517331589274e-06,
|
301 |
-
"loss": 0.3309,
|
302 |
-
"step": 7600
|
303 |
-
},
|
304 |
-
{
|
305 |
-
"epoch": 0.89,
|
306 |
-
"eval_accuracy": 0.9061166429587483,
|
307 |
-
"eval_f1": 0.9058061283874342,
|
308 |
-
"eval_loss": 0.2577354609966278,
|
309 |
-
"eval_runtime": 4.4559,
|
310 |
-
"eval_samples_per_second": 2208.773,
|
311 |
-
"eval_steps_per_second": 34.561,
|
312 |
-
"step": 7600
|
313 |
-
},
|
314 |
-
{
|
315 |
-
"epoch": 0.93,
|
316 |
-
"learning_rate": 7.258011772400262e-06,
|
317 |
-
"loss": 0.3236,
|
318 |
-
"step": 8000
|
319 |
-
},
|
320 |
-
{
|
321 |
-
"epoch": 0.93,
|
322 |
-
"eval_accuracy": 0.9121113594797805,
|
323 |
-
"eval_f1": 0.9120778013038088,
|
324 |
-
"eval_loss": 0.25613412261009216,
|
325 |
-
"eval_runtime": 4.1922,
|
326 |
-
"eval_samples_per_second": 2347.706,
|
327 |
-
"eval_steps_per_second": 36.735,
|
328 |
-
"step": 8000
|
329 |
-
},
|
330 |
-
{
|
331 |
-
"epoch": 0.98,
|
332 |
-
"learning_rate": 7.09450621321125e-06,
|
333 |
-
"loss": 0.3183,
|
334 |
-
"step": 8400
|
335 |
-
},
|
336 |
-
{
|
337 |
-
"epoch": 0.98,
|
338 |
-
"eval_accuracy": 0.908758382442593,
|
339 |
-
"eval_f1": 0.9083914158392551,
|
340 |
-
"eval_loss": 0.2555808424949646,
|
341 |
-
"eval_runtime": 4.2479,
|
342 |
-
"eval_samples_per_second": 2316.917,
|
343 |
-
"eval_steps_per_second": 36.253,
|
344 |
-
"step": 8400
|
345 |
-
},
|
346 |
-
{
|
347 |
-
"epoch": 1.03,
|
348 |
-
"learning_rate": 6.931000654022237e-06,
|
349 |
-
"loss": 0.3022,
|
350 |
-
"step": 8800
|
351 |
-
},
|
352 |
-
{
|
353 |
-
"epoch": 1.03,
|
354 |
-
"eval_accuracy": 0.906421459053038,
|
355 |
-
"eval_f1": 0.9056135727779063,
|
356 |
-
"eval_loss": 0.2667880356311798,
|
357 |
-
"eval_runtime": 4.4383,
|
358 |
-
"eval_samples_per_second": 2217.519,
|
359 |
-
"eval_steps_per_second": 34.698,
|
360 |
-
"step": 8800
|
361 |
-
}
|
362 |
-
],
|
363 |
-
"max_steps": 25752,
|
364 |
-
"num_train_epochs": 3,
|
365 |
-
"total_flos": 1.536997071500478e+16,
|
366 |
-
"trial_name": null,
|
367 |
-
"trial_params": null
|
368 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
last-checkpoint/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:66cc9af448b4d5ffdf0aedbd94ba171b260816026a211b6bf3012033c4b680bb
|
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 498663405
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85cf3d22c5ddf332ef20a787904d9f9e91c003a948fe68bae406c94abaa9515d
|
3 |
size 498663405
|