Training in progress, epoch 1, checkpoint
Browse files
last-checkpoint/README.md
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1130520122
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6e30cd1973ffd581d9841a4142304c15933bd2e35a8c8da4f5748dff2786807
|
3 |
size 1130520122
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 565251810
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f56c48926de377ce9d4614f603c07171ebd1e50e5dd83e538cfc95f815b9f5c
|
3 |
size 565251810
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a35737710db5d432ce9a1d2a028fb95e0f070338de7e2dd89045bd562c011764
|
3 |
+
size 14180
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6909db50d7352964f2947bab64e77e4b2204326b328911ba1924aee34ca6ed39
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,639 +1,329 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"eval_steps":
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.1,
|
13 |
-
"grad_norm": 23.
|
14 |
-
"learning_rate":
|
15 |
-
"loss": 3.
|
16 |
-
"step":
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.1,
|
20 |
-
"eval_nli-pairs_loss":
|
21 |
-
"eval_nli-pairs_runtime":
|
22 |
-
"eval_nli-pairs_samples_per_second":
|
23 |
-
"eval_nli-pairs_steps_per_second":
|
24 |
-
"step":
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.1,
|
28 |
-
"eval_scitail-pairs-pos_loss":
|
29 |
-
"eval_scitail-pairs-pos_runtime":
|
30 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
31 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
32 |
-
"step":
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.1,
|
36 |
-
"eval_qnli-contrastive_loss":
|
37 |
-
"eval_qnli-contrastive_runtime": 15.
|
38 |
-
"eval_qnli-contrastive_samples_per_second":
|
39 |
-
"eval_qnli-contrastive_steps_per_second": 22.
|
40 |
-
"step":
|
41 |
},
|
42 |
{
|
43 |
"epoch": 0.2,
|
44 |
-
"grad_norm":
|
45 |
-
"learning_rate":
|
46 |
-
"loss": 1.
|
47 |
-
"step":
|
48 |
},
|
49 |
{
|
50 |
"epoch": 0.2,
|
51 |
-
"eval_nli-pairs_loss":
|
52 |
-
"eval_nli-pairs_runtime":
|
53 |
-
"eval_nli-pairs_samples_per_second":
|
54 |
-
"eval_nli-pairs_steps_per_second":
|
55 |
-
"step":
|
56 |
},
|
57 |
{
|
58 |
"epoch": 0.2,
|
59 |
-
"eval_scitail-pairs-pos_loss": 0.
|
60 |
-
"eval_scitail-pairs-pos_runtime":
|
61 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
62 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
63 |
-
"step":
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.2,
|
67 |
-
"eval_qnli-contrastive_loss":
|
68 |
-
"eval_qnli-contrastive_runtime": 15.
|
69 |
-
"eval_qnli-contrastive_samples_per_second":
|
70 |
-
"eval_qnli-contrastive_steps_per_second":
|
71 |
-
"step":
|
72 |
},
|
73 |
{
|
74 |
"epoch": 0.3,
|
75 |
-
"grad_norm":
|
76 |
-
"learning_rate":
|
77 |
-
"loss": 1.
|
78 |
-
"step":
|
79 |
},
|
80 |
{
|
81 |
"epoch": 0.3,
|
82 |
-
"eval_nli-pairs_loss": 0.
|
83 |
-
"eval_nli-pairs_runtime":
|
84 |
-
"eval_nli-pairs_samples_per_second":
|
85 |
-
"eval_nli-pairs_steps_per_second":
|
86 |
-
"step":
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.3,
|
90 |
-
"eval_scitail-pairs-pos_loss": 0.
|
91 |
-
"eval_scitail-pairs-pos_runtime":
|
92 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
93 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
94 |
-
"step":
|
95 |
},
|
96 |
{
|
97 |
"epoch": 0.3,
|
98 |
-
"eval_qnli-contrastive_loss": 1.
|
99 |
-
"eval_qnli-contrastive_runtime": 15.
|
100 |
-
"eval_qnli-contrastive_samples_per_second":
|
101 |
-
"eval_qnli-contrastive_steps_per_second":
|
102 |
-
"step":
|
103 |
},
|
104 |
{
|
105 |
"epoch": 0.4,
|
106 |
-
"grad_norm":
|
107 |
-
"learning_rate":
|
108 |
-
"loss":
|
109 |
-
"step":
|
110 |
},
|
111 |
{
|
112 |
"epoch": 0.4,
|
113 |
-
"eval_nli-pairs_loss": 0.
|
114 |
-
"eval_nli-pairs_runtime":
|
115 |
-
"eval_nli-pairs_samples_per_second":
|
116 |
-
"eval_nli-pairs_steps_per_second":
|
117 |
-
"step":
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.4,
|
121 |
-
"eval_scitail-pairs-pos_loss": 0.
|
122 |
-
"eval_scitail-pairs-pos_runtime":
|
123 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
124 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
125 |
-
"step":
|
126 |
},
|
127 |
{
|
128 |
"epoch": 0.4,
|
129 |
-
"eval_qnli-contrastive_loss": 0.
|
130 |
-
"eval_qnli-contrastive_runtime": 15.
|
131 |
-
"eval_qnli-contrastive_samples_per_second":
|
132 |
-
"eval_qnli-contrastive_steps_per_second":
|
133 |
-
"step":
|
134 |
},
|
135 |
{
|
136 |
"epoch": 0.5,
|
137 |
-
"grad_norm":
|
138 |
-
"learning_rate":
|
139 |
-
"loss":
|
140 |
-
"step":
|
141 |
},
|
142 |
{
|
143 |
"epoch": 0.5,
|
144 |
-
"eval_nli-pairs_loss": 0.
|
145 |
-
"eval_nli-pairs_runtime":
|
146 |
-
"eval_nli-pairs_samples_per_second":
|
147 |
-
"eval_nli-pairs_steps_per_second":
|
148 |
-
"step":
|
149 |
},
|
150 |
{
|
151 |
"epoch": 0.5,
|
152 |
-
"eval_scitail-pairs-pos_loss": 0.
|
153 |
-
"eval_scitail-pairs-pos_runtime":
|
154 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
155 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
156 |
-
"step":
|
157 |
},
|
158 |
{
|
159 |
"epoch": 0.5,
|
160 |
-
"eval_qnli-contrastive_loss": 0.
|
161 |
-
"eval_qnli-contrastive_runtime": 15.
|
162 |
-
"eval_qnli-contrastive_samples_per_second": 347.
|
163 |
-
"eval_qnli-contrastive_steps_per_second": 21.
|
164 |
-
"step":
|
165 |
},
|
166 |
{
|
167 |
"epoch": 0.6,
|
168 |
-
"grad_norm":
|
169 |
-
"learning_rate":
|
170 |
-
"loss": 0.
|
171 |
-
"step":
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.6,
|
175 |
-
"eval_nli-pairs_loss": 0.
|
176 |
-
"eval_nli-pairs_runtime":
|
177 |
-
"eval_nli-pairs_samples_per_second":
|
178 |
-
"eval_nli-pairs_steps_per_second":
|
179 |
-
"step":
|
180 |
},
|
181 |
{
|
182 |
"epoch": 0.6,
|
183 |
-
"eval_scitail-pairs-pos_loss": 0.
|
184 |
-
"eval_scitail-pairs-pos_runtime":
|
185 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
186 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
187 |
-
"step":
|
188 |
},
|
189 |
{
|
190 |
"epoch": 0.6,
|
191 |
-
"eval_qnli-contrastive_loss": 0.
|
192 |
-
"eval_qnli-contrastive_runtime": 15.
|
193 |
-
"eval_qnli-contrastive_samples_per_second":
|
194 |
-
"eval_qnli-contrastive_steps_per_second":
|
195 |
-
"step":
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.7,
|
199 |
-
"grad_norm":
|
200 |
-
"learning_rate":
|
201 |
-
"loss":
|
202 |
-
"step":
|
203 |
},
|
204 |
{
|
205 |
"epoch": 0.7,
|
206 |
-
"eval_nli-pairs_loss": 0.
|
207 |
-
"eval_nli-pairs_runtime":
|
208 |
-
"eval_nli-pairs_samples_per_second":
|
209 |
-
"eval_nli-pairs_steps_per_second":
|
210 |
-
"step":
|
211 |
},
|
212 |
{
|
213 |
"epoch": 0.7,
|
214 |
-
"eval_scitail-pairs-pos_loss": 0.
|
215 |
-
"eval_scitail-pairs-pos_runtime":
|
216 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
217 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
218 |
-
"step":
|
219 |
},
|
220 |
{
|
221 |
"epoch": 0.7,
|
222 |
-
"eval_qnli-contrastive_loss": 0.
|
223 |
-
"eval_qnli-contrastive_runtime": 15.
|
224 |
-
"eval_qnli-contrastive_samples_per_second": 351.
|
225 |
-
"eval_qnli-contrastive_steps_per_second": 22.
|
226 |
-
"step":
|
227 |
},
|
228 |
{
|
229 |
"epoch": 0.8,
|
230 |
-
"grad_norm":
|
231 |
-
"learning_rate":
|
232 |
-
"loss": 0.
|
233 |
-
"step":
|
234 |
},
|
235 |
{
|
236 |
"epoch": 0.8,
|
237 |
-
"eval_nli-pairs_loss": 0.
|
238 |
-
"eval_nli-pairs_runtime":
|
239 |
-
"eval_nli-pairs_samples_per_second":
|
240 |
-
"eval_nli-pairs_steps_per_second":
|
241 |
-
"step":
|
242 |
},
|
243 |
{
|
244 |
"epoch": 0.8,
|
245 |
-
"eval_scitail-pairs-pos_loss": 0.
|
246 |
-
"eval_scitail-pairs-pos_runtime":
|
247 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
248 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
249 |
-
"step":
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.8,
|
253 |
-
"eval_qnli-contrastive_loss": 0.
|
254 |
-
"eval_qnli-contrastive_runtime": 15.
|
255 |
-
"eval_qnli-contrastive_samples_per_second":
|
256 |
-
"eval_qnli-contrastive_steps_per_second": 21.
|
257 |
-
"step":
|
258 |
},
|
259 |
{
|
260 |
"epoch": 0.9,
|
261 |
-
"grad_norm":
|
262 |
-
"learning_rate":
|
263 |
-
"loss": 0.
|
264 |
-
"step":
|
265 |
},
|
266 |
{
|
267 |
"epoch": 0.9,
|
268 |
-
"eval_nli-pairs_loss": 0.
|
269 |
-
"eval_nli-pairs_runtime":
|
270 |
-
"eval_nli-pairs_samples_per_second":
|
271 |
-
"eval_nli-pairs_steps_per_second":
|
272 |
-
"step":
|
273 |
},
|
274 |
{
|
275 |
"epoch": 0.9,
|
276 |
-
"eval_scitail-pairs-pos_loss": 0.
|
277 |
-
"eval_scitail-pairs-pos_runtime":
|
278 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
279 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
280 |
-
"step":
|
281 |
},
|
282 |
{
|
283 |
"epoch": 0.9,
|
284 |
-
"eval_qnli-contrastive_loss": 0.
|
285 |
-
"eval_qnli-contrastive_runtime": 15.
|
286 |
-
"eval_qnli-contrastive_samples_per_second":
|
287 |
-
"eval_qnli-contrastive_steps_per_second": 21.
|
288 |
-
"step":
|
289 |
},
|
290 |
{
|
291 |
"epoch": 1.0,
|
292 |
-
"grad_norm":
|
293 |
-
"learning_rate":
|
294 |
-
"loss": 0.
|
295 |
-
"step":
|
296 |
},
|
297 |
{
|
298 |
"epoch": 1.0,
|
299 |
-
"eval_nli-pairs_loss": 0.
|
300 |
-
"eval_nli-pairs_runtime":
|
301 |
-
"eval_nli-pairs_samples_per_second":
|
302 |
-
"eval_nli-pairs_steps_per_second":
|
303 |
-
"step":
|
304 |
},
|
305 |
{
|
306 |
"epoch": 1.0,
|
307 |
-
"eval_scitail-pairs-pos_loss": 0.
|
308 |
-
"eval_scitail-pairs-pos_runtime":
|
309 |
-
"eval_scitail-pairs-pos_samples_per_second":
|
310 |
-
"eval_scitail-pairs-pos_steps_per_second":
|
311 |
-
"step":
|
312 |
},
|
313 |
{
|
314 |
"epoch": 1.0,
|
315 |
-
"eval_qnli-contrastive_loss": 0.
|
316 |
-
"eval_qnli-contrastive_runtime": 15.
|
317 |
-
"eval_qnli-contrastive_samples_per_second":
|
318 |
-
"eval_qnli-contrastive_steps_per_second":
|
319 |
-
"step":
|
320 |
-
},
|
321 |
-
{
|
322 |
-
"epoch": 1.1,
|
323 |
-
"grad_norm": 17.123151779174805,
|
324 |
-
"learning_rate": 1.5161494182199708e-05,
|
325 |
-
"loss": 0.726,
|
326 |
-
"step": 5181
|
327 |
-
},
|
328 |
-
{
|
329 |
-
"epoch": 1.1,
|
330 |
-
"eval_nli-pairs_loss": 0.37437891960144043,
|
331 |
-
"eval_nli-pairs_runtime": 14.6826,
|
332 |
-
"eval_nli-pairs_samples_per_second": 463.677,
|
333 |
-
"eval_nli-pairs_steps_per_second": 29.014,
|
334 |
-
"step": 5181
|
335 |
-
},
|
336 |
-
{
|
337 |
-
"epoch": 1.1,
|
338 |
-
"eval_scitail-pairs-pos_loss": 0.34239521622657776,
|
339 |
-
"eval_scitail-pairs-pos_runtime": 3.4343,
|
340 |
-
"eval_scitail-pairs-pos_samples_per_second": 379.703,
|
341 |
-
"eval_scitail-pairs-pos_steps_per_second": 23.877,
|
342 |
-
"step": 5181
|
343 |
-
},
|
344 |
-
{
|
345 |
-
"epoch": 1.1,
|
346 |
-
"eval_qnli-contrastive_loss": 0.04533466696739197,
|
347 |
-
"eval_qnli-contrastive_runtime": 15.5919,
|
348 |
-
"eval_qnli-contrastive_samples_per_second": 350.374,
|
349 |
-
"eval_qnli-contrastive_steps_per_second": 21.934,
|
350 |
-
"step": 5181
|
351 |
-
},
|
352 |
-
{
|
353 |
-
"epoch": 1.2,
|
354 |
-
"grad_norm": 4.296922206878662,
|
355 |
-
"learning_rate": 1.3030457061862642e-05,
|
356 |
-
"loss": 0.8151,
|
357 |
-
"step": 5652
|
358 |
-
},
|
359 |
-
{
|
360 |
-
"epoch": 1.2,
|
361 |
-
"eval_nli-pairs_loss": 0.3501867353916168,
|
362 |
-
"eval_nli-pairs_runtime": 14.648,
|
363 |
-
"eval_nli-pairs_samples_per_second": 464.772,
|
364 |
-
"eval_nli-pairs_steps_per_second": 29.082,
|
365 |
-
"step": 5652
|
366 |
-
},
|
367 |
-
{
|
368 |
-
"epoch": 1.2,
|
369 |
-
"eval_scitail-pairs-pos_loss": 0.26023754477500916,
|
370 |
-
"eval_scitail-pairs-pos_runtime": 3.3385,
|
371 |
-
"eval_scitail-pairs-pos_samples_per_second": 390.589,
|
372 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.562,
|
373 |
-
"step": 5652
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 1.2,
|
377 |
-
"eval_qnli-contrastive_loss": 0.18350932002067566,
|
378 |
-
"eval_qnli-contrastive_runtime": 15.5173,
|
379 |
-
"eval_qnli-contrastive_samples_per_second": 352.059,
|
380 |
-
"eval_qnli-contrastive_steps_per_second": 22.04,
|
381 |
-
"step": 5652
|
382 |
-
},
|
383 |
-
{
|
384 |
-
"epoch": 1.3,
|
385 |
-
"grad_norm": 5.370415210723877,
|
386 |
-
"learning_rate": 1.0733590017323587e-05,
|
387 |
-
"loss": 0.7127,
|
388 |
-
"step": 6123
|
389 |
-
},
|
390 |
-
{
|
391 |
-
"epoch": 1.3,
|
392 |
-
"eval_nli-pairs_loss": 0.33619123697280884,
|
393 |
-
"eval_nli-pairs_runtime": 14.5016,
|
394 |
-
"eval_nli-pairs_samples_per_second": 469.464,
|
395 |
-
"eval_nli-pairs_steps_per_second": 29.376,
|
396 |
-
"step": 6123
|
397 |
-
},
|
398 |
-
{
|
399 |
-
"epoch": 1.3,
|
400 |
-
"eval_scitail-pairs-pos_loss": 0.24599790573120117,
|
401 |
-
"eval_scitail-pairs-pos_runtime": 3.3041,
|
402 |
-
"eval_scitail-pairs-pos_samples_per_second": 394.666,
|
403 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.818,
|
404 |
-
"step": 6123
|
405 |
-
},
|
406 |
-
{
|
407 |
-
"epoch": 1.3,
|
408 |
-
"eval_qnli-contrastive_loss": 0.10889358073472977,
|
409 |
-
"eval_qnli-contrastive_runtime": 15.451,
|
410 |
-
"eval_qnli-contrastive_samples_per_second": 353.569,
|
411 |
-
"eval_qnli-contrastive_steps_per_second": 22.134,
|
412 |
-
"step": 6123
|
413 |
-
},
|
414 |
-
{
|
415 |
-
"epoch": 1.4,
|
416 |
-
"grad_norm": 105.34712219238281,
|
417 |
-
"learning_rate": 8.401493879376199e-06,
|
418 |
-
"loss": 0.8408,
|
419 |
-
"step": 6594
|
420 |
-
},
|
421 |
-
{
|
422 |
-
"epoch": 1.4,
|
423 |
-
"eval_nli-pairs_loss": 0.3184218406677246,
|
424 |
-
"eval_nli-pairs_runtime": 14.4863,
|
425 |
-
"eval_nli-pairs_samples_per_second": 469.961,
|
426 |
-
"eval_nli-pairs_steps_per_second": 29.407,
|
427 |
-
"step": 6594
|
428 |
-
},
|
429 |
-
{
|
430 |
-
"epoch": 1.4,
|
431 |
-
"eval_scitail-pairs-pos_loss": 0.27837762236595154,
|
432 |
-
"eval_scitail-pairs-pos_runtime": 3.3858,
|
433 |
-
"eval_scitail-pairs-pos_samples_per_second": 385.134,
|
434 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.219,
|
435 |
-
"step": 6594
|
436 |
-
},
|
437 |
-
{
|
438 |
-
"epoch": 1.4,
|
439 |
-
"eval_qnli-contrastive_loss": 0.07013922929763794,
|
440 |
-
"eval_qnli-contrastive_runtime": 15.4468,
|
441 |
-
"eval_qnli-contrastive_samples_per_second": 353.666,
|
442 |
-
"eval_qnli-contrastive_steps_per_second": 22.141,
|
443 |
-
"step": 6594
|
444 |
-
},
|
445 |
-
{
|
446 |
-
"epoch": 1.5,
|
447 |
-
"grad_norm": 1.1197956800460815,
|
448 |
-
"learning_rate": 6.15190528470631e-06,
|
449 |
-
"loss": 0.7845,
|
450 |
-
"step": 7065
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 1.5,
|
454 |
-
"eval_nli-pairs_loss": 0.3191192150115967,
|
455 |
-
"eval_nli-pairs_runtime": 14.505,
|
456 |
-
"eval_nli-pairs_samples_per_second": 469.355,
|
457 |
-
"eval_nli-pairs_steps_per_second": 29.369,
|
458 |
-
"step": 7065
|
459 |
-
},
|
460 |
-
{
|
461 |
-
"epoch": 1.5,
|
462 |
-
"eval_scitail-pairs-pos_loss": 0.2821648120880127,
|
463 |
-
"eval_scitail-pairs-pos_runtime": 3.3778,
|
464 |
-
"eval_scitail-pairs-pos_samples_per_second": 386.049,
|
465 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.276,
|
466 |
-
"step": 7065
|
467 |
-
},
|
468 |
-
{
|
469 |
-
"epoch": 1.5,
|
470 |
-
"eval_qnli-contrastive_loss": 0.03179321065545082,
|
471 |
-
"eval_qnli-contrastive_runtime": 15.41,
|
472 |
-
"eval_qnli-contrastive_samples_per_second": 354.509,
|
473 |
-
"eval_qnli-contrastive_steps_per_second": 22.193,
|
474 |
-
"step": 7065
|
475 |
-
},
|
476 |
-
{
|
477 |
-
"epoch": 1.6,
|
478 |
-
"grad_norm": 3.4374799728393555,
|
479 |
-
"learning_rate": 4.1128886407133994e-06,
|
480 |
-
"loss": 0.5766,
|
481 |
-
"step": 7536
|
482 |
-
},
|
483 |
-
{
|
484 |
-
"epoch": 1.6,
|
485 |
-
"eval_nli-pairs_loss": 0.30556315183639526,
|
486 |
-
"eval_nli-pairs_runtime": 14.4825,
|
487 |
-
"eval_nli-pairs_samples_per_second": 470.083,
|
488 |
-
"eval_nli-pairs_steps_per_second": 29.415,
|
489 |
-
"step": 7536
|
490 |
-
},
|
491 |
-
{
|
492 |
-
"epoch": 1.6,
|
493 |
-
"eval_scitail-pairs-pos_loss": 0.277355819940567,
|
494 |
-
"eval_scitail-pairs-pos_runtime": 3.3048,
|
495 |
-
"eval_scitail-pairs-pos_samples_per_second": 394.581,
|
496 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.813,
|
497 |
-
"step": 7536
|
498 |
-
},
|
499 |
-
{
|
500 |
-
"epoch": 1.6,
|
501 |
-
"eval_qnli-contrastive_loss": 0.056649066507816315,
|
502 |
-
"eval_qnli-contrastive_runtime": 15.5222,
|
503 |
-
"eval_qnli-contrastive_samples_per_second": 351.949,
|
504 |
-
"eval_qnli-contrastive_steps_per_second": 22.033,
|
505 |
-
"step": 7536
|
506 |
-
},
|
507 |
-
{
|
508 |
-
"epoch": 1.7,
|
509 |
-
"grad_norm": 5.434581279754639,
|
510 |
-
"learning_rate": 2.3960211678026622e-06,
|
511 |
-
"loss": 0.7304,
|
512 |
-
"step": 8007
|
513 |
-
},
|
514 |
-
{
|
515 |
-
"epoch": 1.7,
|
516 |
-
"eval_nli-pairs_loss": 0.29907679557800293,
|
517 |
-
"eval_nli-pairs_runtime": 14.5118,
|
518 |
-
"eval_nli-pairs_samples_per_second": 469.136,
|
519 |
-
"eval_nli-pairs_steps_per_second": 29.355,
|
520 |
-
"step": 8007
|
521 |
-
},
|
522 |
-
{
|
523 |
-
"epoch": 1.7,
|
524 |
-
"eval_scitail-pairs-pos_loss": 0.2736453711986542,
|
525 |
-
"eval_scitail-pairs-pos_runtime": 3.2966,
|
526 |
-
"eval_scitail-pairs-pos_samples_per_second": 395.561,
|
527 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.874,
|
528 |
-
"step": 8007
|
529 |
-
},
|
530 |
-
{
|
531 |
-
"epoch": 1.7,
|
532 |
-
"eval_qnli-contrastive_loss": 0.0541638545691967,
|
533 |
-
"eval_qnli-contrastive_runtime": 15.4865,
|
534 |
-
"eval_qnli-contrastive_samples_per_second": 352.758,
|
535 |
-
"eval_qnli-contrastive_steps_per_second": 22.084,
|
536 |
-
"step": 8007
|
537 |
-
},
|
538 |
-
{
|
539 |
-
"epoch": 1.8,
|
540 |
-
"grad_norm": 17.071992874145508,
|
541 |
-
"learning_rate": 1.0952517314705368e-06,
|
542 |
-
"loss": 0.6639,
|
543 |
-
"step": 8478
|
544 |
-
},
|
545 |
-
{
|
546 |
-
"epoch": 1.8,
|
547 |
-
"eval_nli-pairs_loss": 0.29488247632980347,
|
548 |
-
"eval_nli-pairs_runtime": 14.521,
|
549 |
-
"eval_nli-pairs_samples_per_second": 468.837,
|
550 |
-
"eval_nli-pairs_steps_per_second": 29.337,
|
551 |
-
"step": 8478
|
552 |
-
},
|
553 |
-
{
|
554 |
-
"epoch": 1.8,
|
555 |
-
"eval_scitail-pairs-pos_loss": 0.26940035820007324,
|
556 |
-
"eval_scitail-pairs-pos_runtime": 3.3511,
|
557 |
-
"eval_scitail-pairs-pos_samples_per_second": 389.126,
|
558 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.47,
|
559 |
-
"step": 8478
|
560 |
-
},
|
561 |
-
{
|
562 |
-
"epoch": 1.8,
|
563 |
-
"eval_qnli-contrastive_loss": 0.05149933323264122,
|
564 |
-
"eval_qnli-contrastive_runtime": 15.4893,
|
565 |
-
"eval_qnli-contrastive_samples_per_second": 352.694,
|
566 |
-
"eval_qnli-contrastive_steps_per_second": 22.08,
|
567 |
-
"step": 8478
|
568 |
-
},
|
569 |
-
{
|
570 |
-
"epoch": 1.9,
|
571 |
-
"grad_norm": 4.333444118499756,
|
572 |
-
"learning_rate": 2.817598576525049e-07,
|
573 |
-
"loss": 0.6153,
|
574 |
-
"step": 8949
|
575 |
-
},
|
576 |
-
{
|
577 |
-
"epoch": 1.9,
|
578 |
-
"eval_nli-pairs_loss": 0.29380860924720764,
|
579 |
-
"eval_nli-pairs_runtime": 14.6947,
|
580 |
-
"eval_nli-pairs_samples_per_second": 463.296,
|
581 |
-
"eval_nli-pairs_steps_per_second": 28.99,
|
582 |
-
"step": 8949
|
583 |
-
},
|
584 |
-
{
|
585 |
-
"epoch": 1.9,
|
586 |
-
"eval_scitail-pairs-pos_loss": 0.27175840735435486,
|
587 |
-
"eval_scitail-pairs-pos_runtime": 3.3734,
|
588 |
-
"eval_scitail-pairs-pos_samples_per_second": 386.557,
|
589 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.308,
|
590 |
-
"step": 8949
|
591 |
-
},
|
592 |
-
{
|
593 |
-
"epoch": 1.9,
|
594 |
-
"eval_qnli-contrastive_loss": 0.05886112153530121,
|
595 |
-
"eval_qnli-contrastive_runtime": 15.7063,
|
596 |
-
"eval_qnli-contrastive_samples_per_second": 347.823,
|
597 |
-
"eval_qnli-contrastive_steps_per_second": 21.775,
|
598 |
-
"step": 8949
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"epoch": 2.0,
|
602 |
-
"grad_norm": 17.020780563354492,
|
603 |
-
"learning_rate": 7.929627552805131e-11,
|
604 |
-
"loss": 0.6665,
|
605 |
-
"step": 9420
|
606 |
-
},
|
607 |
-
{
|
608 |
-
"epoch": 2.0,
|
609 |
-
"eval_nli-pairs_loss": 0.2937406301498413,
|
610 |
-
"eval_nli-pairs_runtime": 14.6591,
|
611 |
-
"eval_nli-pairs_samples_per_second": 464.421,
|
612 |
-
"eval_nli-pairs_steps_per_second": 29.06,
|
613 |
-
"step": 9420
|
614 |
-
},
|
615 |
-
{
|
616 |
-
"epoch": 2.0,
|
617 |
-
"eval_scitail-pairs-pos_loss": 0.27235355973243713,
|
618 |
-
"eval_scitail-pairs-pos_runtime": 3.3473,
|
619 |
-
"eval_scitail-pairs-pos_samples_per_second": 389.563,
|
620 |
-
"eval_scitail-pairs-pos_steps_per_second": 24.497,
|
621 |
-
"step": 9420
|
622 |
-
},
|
623 |
-
{
|
624 |
-
"epoch": 2.0,
|
625 |
-
"eval_qnli-contrastive_loss": 0.05692654103040695,
|
626 |
-
"eval_qnli-contrastive_runtime": 15.5164,
|
627 |
-
"eval_qnli-contrastive_samples_per_second": 352.078,
|
628 |
-
"eval_qnli-contrastive_steps_per_second": 22.041,
|
629 |
-
"step": 9420
|
630 |
}
|
631 |
],
|
632 |
-
"logging_steps":
|
633 |
-
"max_steps":
|
634 |
"num_input_tokens_seen": 0,
|
635 |
"num_train_epochs": 2,
|
636 |
-
"save_steps":
|
637 |
"stateful_callbacks": {
|
638 |
"TrainerControl": {
|
639 |
"args": {
|
@@ -641,13 +331,13 @@
|
|
641 |
"should_evaluate": false,
|
642 |
"should_log": false,
|
643 |
"should_save": true,
|
644 |
-
"should_training_stop":
|
645 |
},
|
646 |
"attributes": {}
|
647 |
}
|
648 |
},
|
649 |
"total_flos": 0.0,
|
650 |
-
"train_batch_size":
|
651 |
"trial_name": null,
|
652 |
"trial_params": null
|
653 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 1757,
|
6 |
+
"global_step": 17570,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.1,
|
13 |
+
"grad_norm": 23.659637451171875,
|
14 |
+
"learning_rate": 9.97723392145703e-07,
|
15 |
+
"loss": 3.8346,
|
16 |
+
"step": 1757
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.1,
|
20 |
+
"eval_nli-pairs_loss": 2.8535287380218506,
|
21 |
+
"eval_nli-pairs_runtime": 23.1384,
|
22 |
+
"eval_nli-pairs_samples_per_second": 294.229,
|
23 |
+
"eval_nli-pairs_steps_per_second": 18.411,
|
24 |
+
"step": 1757
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.1,
|
28 |
+
"eval_scitail-pairs-pos_loss": 2.323117256164551,
|
29 |
+
"eval_scitail-pairs-pos_runtime": 5.1803,
|
30 |
+
"eval_scitail-pairs-pos_samples_per_second": 251.722,
|
31 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.829,
|
32 |
+
"step": 1757
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.1,
|
36 |
+
"eval_qnli-contrastive_loss": 3.09728741645813,
|
37 |
+
"eval_qnli-contrastive_runtime": 15.5151,
|
38 |
+
"eval_qnli-contrastive_samples_per_second": 352.109,
|
39 |
+
"eval_qnli-contrastive_steps_per_second": 22.043,
|
40 |
+
"step": 1757
|
41 |
},
|
42 |
{
|
43 |
"epoch": 0.2,
|
44 |
+
"grad_norm": 13.776155471801758,
|
45 |
+
"learning_rate": 1.9965850882185546e-06,
|
46 |
+
"loss": 1.8532,
|
47 |
+
"step": 3514
|
48 |
},
|
49 |
{
|
50 |
"epoch": 0.2,
|
51 |
+
"eval_nli-pairs_loss": 1.3508331775665283,
|
52 |
+
"eval_nli-pairs_runtime": 22.8642,
|
53 |
+
"eval_nli-pairs_samples_per_second": 297.758,
|
54 |
+
"eval_nli-pairs_steps_per_second": 18.632,
|
55 |
+
"step": 3514
|
56 |
},
|
57 |
{
|
58 |
"epoch": 0.2,
|
59 |
+
"eval_scitail-pairs-pos_loss": 0.9754649996757507,
|
60 |
+
"eval_scitail-pairs-pos_runtime": 5.1924,
|
61 |
+
"eval_scitail-pairs-pos_samples_per_second": 251.136,
|
62 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.792,
|
63 |
+
"step": 3514
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.2,
|
67 |
+
"eval_qnli-contrastive_loss": 2.0602548122406006,
|
68 |
+
"eval_qnli-contrastive_runtime": 15.6036,
|
69 |
+
"eval_qnli-contrastive_samples_per_second": 350.111,
|
70 |
+
"eval_qnli-contrastive_steps_per_second": 21.918,
|
71 |
+
"step": 3514
|
72 |
},
|
73 |
{
|
74 |
"epoch": 0.3,
|
75 |
+
"grad_norm": 0.6704504489898682,
|
76 |
+
"learning_rate": 2.99601593625498e-06,
|
77 |
+
"loss": 1.2185,
|
78 |
+
"step": 5271
|
79 |
},
|
80 |
{
|
81 |
"epoch": 0.3,
|
82 |
+
"eval_nli-pairs_loss": 0.9380640983581543,
|
83 |
+
"eval_nli-pairs_runtime": 23.1102,
|
84 |
+
"eval_nli-pairs_samples_per_second": 294.589,
|
85 |
+
"eval_nli-pairs_steps_per_second": 18.433,
|
86 |
+
"step": 5271
|
87 |
},
|
88 |
{
|
89 |
"epoch": 0.3,
|
90 |
+
"eval_scitail-pairs-pos_loss": 0.7407301664352417,
|
91 |
+
"eval_scitail-pairs-pos_runtime": 5.2512,
|
92 |
+
"eval_scitail-pairs-pos_samples_per_second": 248.322,
|
93 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.615,
|
94 |
+
"step": 5271
|
95 |
},
|
96 |
{
|
97 |
"epoch": 0.3,
|
98 |
+
"eval_qnli-contrastive_loss": 1.2534083127975464,
|
99 |
+
"eval_qnli-contrastive_runtime": 15.6475,
|
100 |
+
"eval_qnli-contrastive_samples_per_second": 349.129,
|
101 |
+
"eval_qnli-contrastive_steps_per_second": 21.857,
|
102 |
+
"step": 5271
|
103 |
},
|
104 |
{
|
105 |
"epoch": 0.4,
|
106 |
+
"grad_norm": 26.072860717773438,
|
107 |
+
"learning_rate": 3.99601593625498e-06,
|
108 |
+
"loss": 0.9584,
|
109 |
+
"step": 7028
|
110 |
},
|
111 |
{
|
112 |
"epoch": 0.4,
|
113 |
+
"eval_nli-pairs_loss": 0.749484658241272,
|
114 |
+
"eval_nli-pairs_runtime": 23.0514,
|
115 |
+
"eval_nli-pairs_samples_per_second": 295.34,
|
116 |
+
"eval_nli-pairs_steps_per_second": 18.48,
|
117 |
+
"step": 7028
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.4,
|
121 |
+
"eval_scitail-pairs-pos_loss": 0.661561131477356,
|
122 |
+
"eval_scitail-pairs-pos_runtime": 5.2207,
|
123 |
+
"eval_scitail-pairs-pos_samples_per_second": 249.774,
|
124 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.707,
|
125 |
+
"step": 7028
|
126 |
},
|
127 |
{
|
128 |
"epoch": 0.4,
|
129 |
+
"eval_qnli-contrastive_loss": 0.5139556527137756,
|
130 |
+
"eval_qnli-contrastive_runtime": 15.681,
|
131 |
+
"eval_qnli-contrastive_samples_per_second": 348.384,
|
132 |
+
"eval_qnli-contrastive_steps_per_second": 21.81,
|
133 |
+
"step": 7028
|
134 |
},
|
135 |
{
|
136 |
"epoch": 0.5,
|
137 |
+
"grad_norm": 24.09697914123535,
|
138 |
+
"learning_rate": 4.995446784291406e-06,
|
139 |
+
"loss": 0.8157,
|
140 |
+
"step": 8785
|
141 |
},
|
142 |
{
|
143 |
"epoch": 0.5,
|
144 |
+
"eval_nli-pairs_loss": 0.6549726724624634,
|
145 |
+
"eval_nli-pairs_runtime": 23.2274,
|
146 |
+
"eval_nli-pairs_samples_per_second": 293.102,
|
147 |
+
"eval_nli-pairs_steps_per_second": 18.34,
|
148 |
+
"step": 8785
|
149 |
},
|
150 |
{
|
151 |
"epoch": 0.5,
|
152 |
+
"eval_scitail-pairs-pos_loss": 0.6056841611862183,
|
153 |
+
"eval_scitail-pairs-pos_runtime": 5.2473,
|
154 |
+
"eval_scitail-pairs-pos_samples_per_second": 248.508,
|
155 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.627,
|
156 |
+
"step": 8785
|
157 |
},
|
158 |
{
|
159 |
"epoch": 0.5,
|
160 |
+
"eval_qnli-contrastive_loss": 0.3295331299304962,
|
161 |
+
"eval_qnli-contrastive_runtime": 15.7204,
|
162 |
+
"eval_qnli-contrastive_samples_per_second": 347.511,
|
163 |
+
"eval_qnli-contrastive_steps_per_second": 21.755,
|
164 |
+
"step": 8785
|
165 |
},
|
166 |
{
|
167 |
"epoch": 0.6,
|
168 |
+
"grad_norm": 9.664803504943848,
|
169 |
+
"learning_rate": 5.994877632327832e-06,
|
170 |
+
"loss": 0.6698,
|
171 |
+
"step": 10542
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.6,
|
175 |
+
"eval_nli-pairs_loss": 0.5809468626976013,
|
176 |
+
"eval_nli-pairs_runtime": 22.9525,
|
177 |
+
"eval_nli-pairs_samples_per_second": 296.612,
|
178 |
+
"eval_nli-pairs_steps_per_second": 18.56,
|
179 |
+
"step": 10542
|
180 |
},
|
181 |
{
|
182 |
"epoch": 0.6,
|
183 |
+
"eval_scitail-pairs-pos_loss": 0.5820835828781128,
|
184 |
+
"eval_scitail-pairs-pos_runtime": 5.1829,
|
185 |
+
"eval_scitail-pairs-pos_samples_per_second": 251.599,
|
186 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.821,
|
187 |
+
"step": 10542
|
188 |
},
|
189 |
{
|
190 |
"epoch": 0.6,
|
191 |
+
"eval_qnli-contrastive_loss": 0.24226614832878113,
|
192 |
+
"eval_qnli-contrastive_runtime": 15.6321,
|
193 |
+
"eval_qnli-contrastive_samples_per_second": 349.473,
|
194 |
+
"eval_qnli-contrastive_steps_per_second": 21.878,
|
195 |
+
"step": 10542
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.7,
|
199 |
+
"grad_norm": 66.77753448486328,
|
200 |
+
"learning_rate": 6.994877632327832e-06,
|
201 |
+
"loss": 0.6497,
|
202 |
+
"step": 12299
|
203 |
},
|
204 |
{
|
205 |
"epoch": 0.7,
|
206 |
+
"eval_nli-pairs_loss": 0.5178281664848328,
|
207 |
+
"eval_nli-pairs_runtime": 23.0673,
|
208 |
+
"eval_nli-pairs_samples_per_second": 295.136,
|
209 |
+
"eval_nli-pairs_steps_per_second": 18.468,
|
210 |
+
"step": 12299
|
211 |
},
|
212 |
{
|
213 |
"epoch": 0.7,
|
214 |
+
"eval_scitail-pairs-pos_loss": 0.504002571105957,
|
215 |
+
"eval_scitail-pairs-pos_runtime": 5.1845,
|
216 |
+
"eval_scitail-pairs-pos_samples_per_second": 251.52,
|
217 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.816,
|
218 |
+
"step": 12299
|
219 |
},
|
220 |
{
|
221 |
"epoch": 0.7,
|
222 |
+
"eval_qnli-contrastive_loss": 0.24089547991752625,
|
223 |
+
"eval_qnli-contrastive_runtime": 15.5228,
|
224 |
+
"eval_qnli-contrastive_samples_per_second": 351.933,
|
225 |
+
"eval_qnli-contrastive_steps_per_second": 22.032,
|
226 |
+
"step": 12299
|
227 |
},
|
228 |
{
|
229 |
"epoch": 0.8,
|
230 |
+
"grad_norm": 0.6044542193412781,
|
231 |
+
"learning_rate": 7.994308480364257e-06,
|
232 |
+
"loss": 0.5737,
|
233 |
+
"step": 14056
|
234 |
},
|
235 |
{
|
236 |
"epoch": 0.8,
|
237 |
+
"eval_nli-pairs_loss": 0.5019380450248718,
|
238 |
+
"eval_nli-pairs_runtime": 23.0659,
|
239 |
+
"eval_nli-pairs_samples_per_second": 295.154,
|
240 |
+
"eval_nli-pairs_steps_per_second": 18.469,
|
241 |
+
"step": 14056
|
242 |
},
|
243 |
{
|
244 |
"epoch": 0.8,
|
245 |
+
"eval_scitail-pairs-pos_loss": 0.49418017268180847,
|
246 |
+
"eval_scitail-pairs-pos_runtime": 5.2457,
|
247 |
+
"eval_scitail-pairs-pos_samples_per_second": 248.585,
|
248 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.632,
|
249 |
+
"step": 14056
|
250 |
},
|
251 |
{
|
252 |
"epoch": 0.8,
|
253 |
+
"eval_qnli-contrastive_loss": 0.14995019137859344,
|
254 |
+
"eval_qnli-contrastive_runtime": 15.7177,
|
255 |
+
"eval_qnli-contrastive_samples_per_second": 347.57,
|
256 |
+
"eval_qnli-contrastive_steps_per_second": 21.759,
|
257 |
+
"step": 14056
|
258 |
},
|
259 |
{
|
260 |
"epoch": 0.9,
|
261 |
+
"grad_norm": 0.4454790949821472,
|
262 |
+
"learning_rate": 8.993739328400684e-06,
|
263 |
+
"loss": 0.5896,
|
264 |
+
"step": 15813
|
265 |
},
|
266 |
{
|
267 |
"epoch": 0.9,
|
268 |
+
"eval_nli-pairs_loss": 0.4803747236728668,
|
269 |
+
"eval_nli-pairs_runtime": 23.0746,
|
270 |
+
"eval_nli-pairs_samples_per_second": 295.043,
|
271 |
+
"eval_nli-pairs_steps_per_second": 18.462,
|
272 |
+
"step": 15813
|
273 |
},
|
274 |
{
|
275 |
"epoch": 0.9,
|
276 |
+
"eval_scitail-pairs-pos_loss": 0.47568026185035706,
|
277 |
+
"eval_scitail-pairs-pos_runtime": 5.2076,
|
278 |
+
"eval_scitail-pairs-pos_samples_per_second": 250.402,
|
279 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.746,
|
280 |
+
"step": 15813
|
281 |
},
|
282 |
{
|
283 |
"epoch": 0.9,
|
284 |
+
"eval_qnli-contrastive_loss": 0.14648529887199402,
|
285 |
+
"eval_qnli-contrastive_runtime": 15.5997,
|
286 |
+
"eval_qnli-contrastive_samples_per_second": 350.199,
|
287 |
+
"eval_qnli-contrastive_steps_per_second": 21.924,
|
288 |
+
"step": 15813
|
289 |
},
|
290 |
{
|
291 |
"epoch": 1.0,
|
292 |
+
"grad_norm": 196.14842224121094,
|
293 |
+
"learning_rate": 9.993739328400683e-06,
|
294 |
+
"loss": 0.5174,
|
295 |
+
"step": 17570
|
296 |
},
|
297 |
{
|
298 |
"epoch": 1.0,
|
299 |
+
"eval_nli-pairs_loss": 0.4586646258831024,
|
300 |
+
"eval_nli-pairs_runtime": 22.8967,
|
301 |
+
"eval_nli-pairs_samples_per_second": 297.336,
|
302 |
+
"eval_nli-pairs_steps_per_second": 18.605,
|
303 |
+
"step": 17570
|
304 |
},
|
305 |
{
|
306 |
"epoch": 1.0,
|
307 |
+
"eval_scitail-pairs-pos_loss": 0.5253121256828308,
|
308 |
+
"eval_scitail-pairs-pos_runtime": 5.1603,
|
309 |
+
"eval_scitail-pairs-pos_samples_per_second": 252.699,
|
310 |
+
"eval_scitail-pairs-pos_steps_per_second": 15.891,
|
311 |
+
"step": 17570
|
312 |
},
|
313 |
{
|
314 |
"epoch": 1.0,
|
315 |
+
"eval_qnli-contrastive_loss": 0.0533733032643795,
|
316 |
+
"eval_qnli-contrastive_runtime": 15.5083,
|
317 |
+
"eval_qnli-contrastive_samples_per_second": 352.263,
|
318 |
+
"eval_qnli-contrastive_steps_per_second": 22.053,
|
319 |
+
"step": 17570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
320 |
}
|
321 |
],
|
322 |
+
"logging_steps": 1757,
|
323 |
+
"max_steps": 35140,
|
324 |
"num_input_tokens_seen": 0,
|
325 |
"num_train_epochs": 2,
|
326 |
+
"save_steps": 17570,
|
327 |
"stateful_callbacks": {
|
328 |
"TrainerControl": {
|
329 |
"args": {
|
|
|
331 |
"should_evaluate": false,
|
332 |
"should_log": false,
|
333 |
"should_save": true,
|
334 |
+
"should_training_stop": false
|
335 |
},
|
336 |
"attributes": {}
|
337 |
}
|
338 |
},
|
339 |
"total_flos": 0.0,
|
340 |
+
"train_batch_size": 30,
|
341 |
"trial_name": null,
|
342 |
"trial_params": null
|
343 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c38dee2f127b66af8ba487f944d12fc981b321ee21bbaee37696724257596800
|
3 |
size 5624
|