Training in progress, step 40000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +2 -2
- last-checkpoint/rng_state_3.pth +2 -2
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +77 -3
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 893438545
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b79098aba355edf15cdcc2ba65841e59d94f2195e6563e00db7a5b77d0de1b0
|
3 |
size 893438545
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56c9245179e00ecfc159536796459f1277956357c9ae2eeba259fdadb204bca4
|
3 |
size 449471589
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dab27e02a841889dd406a61f3825c3bf16e995606299fd6ab9fd7db009ed4e68
|
3 |
size 14503
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:783ce381375b60e783f2e4204fc7d9689e81e56991f92e086a503c69636e5046
|
3 |
size 14503
|
last-checkpoint/rng_state_2.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 sha256:59eabe2e991b1516dd6b66887718520f904de193e569a87238bb2d8904706701
|
3 |
+
size 14503
|
last-checkpoint/rng_state_3.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 sha256:24b999227318d7857e7c42c9ad2f2208b186825e80265bff7952618efa8d3e7e
|
3 |
+
size 14439
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06b5c694b40cd5a966b5116288c30b2f19979f1058d82965ee57335ae5f1e596
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -228,11 +228,85 @@
|
|
228 |
"eval_samples_per_second": 990.512,
|
229 |
"eval_steps_per_second": 15.848,
|
230 |
"step": 30000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
231 |
}
|
232 |
],
|
233 |
"max_steps": 1000000,
|
234 |
"num_train_epochs": 16,
|
235 |
-
"total_flos": 2.
|
236 |
"trial_name": null,
|
237 |
"trial_params": null
|
238 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6108082520194847,
|
5 |
+
"global_step": 40000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
228 |
"eval_samples_per_second": 990.512,
|
229 |
"eval_steps_per_second": 15.848,
|
230 |
"step": 30000
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.47,
|
234 |
+
"learning_rate": 9.3e-05,
|
235 |
+
"loss": 0.5536,
|
236 |
+
"step": 31000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.49,
|
240 |
+
"learning_rate": 9.599999999999999e-05,
|
241 |
+
"loss": 0.5496,
|
242 |
+
"step": 32000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.5,
|
246 |
+
"learning_rate": 9.9e-05,
|
247 |
+
"loss": 0.5458,
|
248 |
+
"step": 33000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.52,
|
252 |
+
"learning_rate": 0.000102,
|
253 |
+
"loss": 0.5426,
|
254 |
+
"step": 34000
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.53,
|
258 |
+
"learning_rate": 0.00010499999999999999,
|
259 |
+
"loss": 0.5394,
|
260 |
+
"step": 35000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 0.53,
|
264 |
+
"eval_runtime": 1.3102,
|
265 |
+
"eval_samples_per_second": 763.27,
|
266 |
+
"eval_steps_per_second": 12.212,
|
267 |
+
"step": 35000
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.55,
|
271 |
+
"learning_rate": 0.00010799999999999998,
|
272 |
+
"loss": 0.5345,
|
273 |
+
"step": 36000
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.56,
|
277 |
+
"learning_rate": 0.00011099999999999999,
|
278 |
+
"loss": 0.5302,
|
279 |
+
"step": 37000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.58,
|
283 |
+
"learning_rate": 0.00011399999999999999,
|
284 |
+
"loss": 0.527,
|
285 |
+
"step": 38000
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.6,
|
289 |
+
"learning_rate": 0.000117,
|
290 |
+
"loss": 0.5232,
|
291 |
+
"step": 39000
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.61,
|
295 |
+
"learning_rate": 0.00011999999999999999,
|
296 |
+
"loss": 0.5202,
|
297 |
+
"step": 40000
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.61,
|
301 |
+
"eval_runtime": 1.0146,
|
302 |
+
"eval_samples_per_second": 985.598,
|
303 |
+
"eval_steps_per_second": 15.77,
|
304 |
+
"step": 40000
|
305 |
}
|
306 |
],
|
307 |
"max_steps": 1000000,
|
308 |
"num_train_epochs": 16,
|
309 |
+
"total_flos": 2.804010441213886e+21,
|
310 |
"trial_name": null,
|
311 |
"trial_params": null
|
312 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 449471589
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56c9245179e00ecfc159536796459f1277956357c9ae2eeba259fdadb204bca4
|
3 |
size 449471589
|