Training in progress, step 12000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +19 -3
- pytorch_model.bin +1 -1
- runs/Jun23_09-25-37_e9237c250134/events.out.tfevents.1687513501.e9237c250134.293.0 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2117841669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d5ecb7cea99166e5331fd83af0abf4700f34f8fa7c55069b55e5cc11ef77b6e
|
3 |
size 2117841669
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a95dc90cf2c6fb077a16d6d006d07123ca58d93e9477b64a60af5efde8712c0f
|
3 |
size 2268278205
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60950be020388f13bb3603ac853f8ba2158b6fdee7c4c316c0178e90051ada25
|
3 |
size 14575
|
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:fd884e1d2e2e8520444f4aed44797bb12512ec301ef2843eb0c7f004efc2a56e
|
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": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -414,11 +414,27 @@
|
|
414 |
"eval_samples_per_second": 198.143,
|
415 |
"eval_steps_per_second": 0.775,
|
416 |
"step": 11600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
417 |
}
|
418 |
],
|
419 |
"max_steps": 953000,
|
420 |
"num_train_epochs": 100,
|
421 |
-
"total_flos":
|
422 |
"trial_name": null,
|
423 |
"trial_params": null
|
424 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2591815320041972,
|
5 |
+
"global_step": 12000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
414 |
"eval_samples_per_second": 198.143,
|
415 |
"eval_steps_per_second": 0.775,
|
416 |
"step": 11600
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.26,
|
420 |
+
"learning_rate": 9.874354669464849e-06,
|
421 |
+
"loss": 0.6767,
|
422 |
+
"step": 12000
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.26,
|
426 |
+
"eval_accuracy": 0.8794138913072349,
|
427 |
+
"eval_f1": 0.8799114820136512,
|
428 |
+
"eval_loss": 0.6668325662612915,
|
429 |
+
"eval_runtime": 685.344,
|
430 |
+
"eval_samples_per_second": 197.766,
|
431 |
+
"eval_steps_per_second": 0.773,
|
432 |
+
"step": 12000
|
433 |
}
|
434 |
],
|
435 |
"max_steps": 953000,
|
436 |
"num_train_epochs": 100,
|
437 |
+
"total_flos": 5.0440310829817606e+17,
|
438 |
"trial_name": null,
|
439 |
"trial_params": null
|
440 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a95dc90cf2c6fb077a16d6d006d07123ca58d93e9477b64a60af5efde8712c0f
|
3 |
size 2268278205
|
runs/Jun23_09-25-37_e9237c250134/events.out.tfevents.1687513501.e9237c250134.293.0
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 sha256:8387c9de792de8bcb2c268b6dea65cfaa813ae12c0224dbb4afa22cccdd5097e
|
3 |
+
size 5930
|