Training in progress, step 50000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +2 -2
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- 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 sha256:5aab534a941de846cd5acb29f0cac50eed51613e2cbe9b058b2cef36db3ca849
|
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 sha256:5dec19b920534a5898acdfc98e79e9b70791428c6bd7a25c13bcdf61c6645ec5
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9736a584cb8ae3d7bd8ffe95a660707985f449648611e3cc9b4d825e5958e568
|
3 |
+
size 14439
|
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:ef650477065ab5caa49e1061409f9f0faf9c6cf935e3b3d122d891a44dfd7336
|
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 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2a2ced2ef326c6276aee305dcedbdce1bdac86a7e92e323f89ded2bbda8df1d
|
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 sha256:8434c6987c2b0551e47b946336d0f273a4237d950c380ff8d131694cde1e29a8
|
3 |
+
size 14503
|
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 sha256:5b8d45ebb28c7b9f23a6abeafd90122c1ed22446a846f1cf2ac94e95c51e1adb
|
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,
|
@@ -302,11 +302,85 @@
|
|
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":
|
310 |
"trial_name": null,
|
311 |
"trial_params": null
|
312 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.763510315024356,
|
5 |
+
"global_step": 50000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
302 |
"eval_samples_per_second": 985.598,
|
303 |
"eval_steps_per_second": 15.77,
|
304 |
"step": 40000
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.63,
|
308 |
+
"learning_rate": 0.00012299999999999998,
|
309 |
+
"loss": 0.5163,
|
310 |
+
"step": 41000
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.64,
|
314 |
+
"learning_rate": 0.00012599999999999997,
|
315 |
+
"loss": 0.5126,
|
316 |
+
"step": 42000
|
317 |
+
},
|
318 |
+
{
|
319 |
+
"epoch": 0.66,
|
320 |
+
"learning_rate": 0.000129,
|
321 |
+
"loss": 0.5094,
|
322 |
+
"step": 43000
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.67,
|
326 |
+
"learning_rate": 0.00013199999999999998,
|
327 |
+
"loss": 0.5061,
|
328 |
+
"step": 44000
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.69,
|
332 |
+
"learning_rate": 0.000135,
|
333 |
+
"loss": 0.5036,
|
334 |
+
"step": 45000
|
335 |
+
},
|
336 |
+
{
|
337 |
+
"epoch": 0.69,
|
338 |
+
"eval_runtime": 1.0362,
|
339 |
+
"eval_samples_per_second": 965.067,
|
340 |
+
"eval_steps_per_second": 15.441,
|
341 |
+
"step": 45000
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 0.7,
|
345 |
+
"learning_rate": 0.000138,
|
346 |
+
"loss": 0.4995,
|
347 |
+
"step": 46000
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.72,
|
351 |
+
"learning_rate": 0.00014099999999999998,
|
352 |
+
"loss": 0.4967,
|
353 |
+
"step": 47000
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.73,
|
357 |
+
"learning_rate": 0.00014399999999999998,
|
358 |
+
"loss": 0.4934,
|
359 |
+
"step": 48000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.75,
|
363 |
+
"learning_rate": 0.000147,
|
364 |
+
"loss": 0.4898,
|
365 |
+
"step": 49000
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 0.76,
|
369 |
+
"learning_rate": 0.00015,
|
370 |
+
"loss": 0.4863,
|
371 |
+
"step": 50000
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.76,
|
375 |
+
"eval_runtime": 1.0374,
|
376 |
+
"eval_samples_per_second": 963.96,
|
377 |
+
"eval_steps_per_second": 15.423,
|
378 |
+
"step": 50000
|
379 |
}
|
380 |
],
|
381 |
"max_steps": 1000000,
|
382 |
"num_train_epochs": 16,
|
383 |
+
"total_flos": 3.505013051517357e+21,
|
384 |
"trial_name": null,
|
385 |
"trial_params": null
|
386 |
}
|
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 sha256:5dec19b920534a5898acdfc98e79e9b70791428c6bd7a25c13bcdf61c6645ec5
|
3 |
size 449471589
|