Training in progress, step 32000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- runs/Jun19_11-34-11_fb9ac27c82f8/1687176171.876592/events.out.tfevents.1687176171.fb9ac27c82f8.312.1 +3 -0
- runs/Jun19_11-34-11_fb9ac27c82f8/events.out.tfevents.1687176171.fb9ac27c82f8.312.0 +3 -0
- training_args.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 3871543575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f611e60a127715e4261631fd28cfd6f4d3b7839c79d7770a4c5df62b97ee1297
|
3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3c9e41b7a87c3284eb0fc88dd5895f4279c4f867906e16e409ea8e81e038f92
|
3 |
size 1944201353
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14511
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35d370b4cba5c2c6a402684b8a529973e99067d97b2e6678d8f68b5e7ae9e35a
|
3 |
size 14511
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21ab2a69acbb103eb20b9723abde0da0e608d5e46462106d51c5443c382bd505
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23894f32d4ad94e24b1e071b8cdf3e21ce613f1cf1e99bba2dba49f5d168cec9
|
3 |
size 627
|
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,
|
@@ -342,11 +342,59 @@
|
|
342 |
"learning_rate": 8.246046851412012e-06,
|
343 |
"loss": 1.3244,
|
344 |
"step": 28000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
345 |
}
|
346 |
],
|
347 |
"max_steps": 38148,
|
348 |
"num_train_epochs": 1,
|
349 |
-
"total_flos": 3.
|
350 |
"trial_name": null,
|
351 |
"trial_params": null
|
352 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8388294135533862,
|
5 |
+
"global_step": 32000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
342 |
"learning_rate": 8.246046851412012e-06,
|
343 |
"loss": 1.3244,
|
344 |
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.75,
|
348 |
+
"learning_rate": 7.49641732456094e-06,
|
349 |
+
"loss": 1.3254,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 0.76,
|
354 |
+
"learning_rate": 6.776460820731448e-06,
|
355 |
+
"loss": 1.3128,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.77,
|
360 |
+
"learning_rate": 6.088744358104376e-06,
|
361 |
+
"loss": 1.3184,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.79,
|
366 |
+
"learning_rate": 5.432959190805995e-06,
|
367 |
+
"loss": 1.3254,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.8,
|
372 |
+
"learning_rate": 4.808998495602621e-06,
|
373 |
+
"loss": 1.3187,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.81,
|
378 |
+
"learning_rate": 4.219266681627635e-06,
|
379 |
+
"loss": 1.3044,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.83,
|
384 |
+
"learning_rate": 3.6647634942484356e-06,
|
385 |
+
"loss": 1.3002,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.84,
|
390 |
+
"learning_rate": 3.1474289357030756e-06,
|
391 |
+
"loss": 1.3125,
|
392 |
+
"step": 32000
|
393 |
}
|
394 |
],
|
395 |
"max_steps": 38148,
|
396 |
"num_train_epochs": 1,
|
397 |
+
"total_flos": 3.523288608785203e+16,
|
398 |
"trial_name": null,
|
399 |
"trial_params": null
|
400 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c61bc7996479b3f97a1e5038a5b383af11403402f4cb665dc005b19feff2e4c
|
3 |
size 3771
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3c9e41b7a87c3284eb0fc88dd5895f4279c4f867906e16e409ea8e81e038f92
|
3 |
size 1944201353
|
runs/Jun19_11-34-11_fb9ac27c82f8/1687176171.876592/events.out.tfevents.1687176171.fb9ac27c82f8.312.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f108347c1fdb4a8e2a30b0dbcb68a3e239d936c15c46bd0ba8bf8615c68ccfc7
|
3 |
+
size 6187
|
runs/Jun19_11-34-11_fb9ac27c82f8/events.out.tfevents.1687176171.fb9ac27c82f8.312.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7aa0bd213d6d0c2e47108c730cbf0e7c5476af37883aef4ad3a108c35ef6bd96
|
3 |
+
size 5742
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3771
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c61bc7996479b3f97a1e5038a5b383af11403402f4cb665dc005b19feff2e4c
|
3 |
size 3771
|