Training in progress, step 11600
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:dec2eb057a81f95e4b38c5a7c05a48f7ab6e26f5365038d01808fbe3c89838c0
|
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 sha256:49d2f594746653af81487dba34d362ffda36fd878afa9159ee8ac5213d52ac33
|
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 sha256:6b20b636afc5ec6f2114c8fc9ee568c62fd058690ae4dcb3e69adca1bab819c9
|
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:c900c3ee9e15956ee945abc104e1307cbdf5048311b7dc11a8e787734d35dfae
|
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,
|
@@ -398,11 +398,27 @@
|
|
398 |
"eval_samples_per_second": 197.985,
|
399 |
"eval_steps_per_second": 0.774,
|
400 |
"step": 11200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
401 |
}
|
402 |
],
|
403 |
"max_steps": 953000,
|
404 |
"num_train_epochs": 100,
|
405 |
-
"total_flos": 4.
|
406 |
"trial_name": null,
|
407 |
"trial_params": null
|
408 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.217208814270724,
|
5 |
+
"global_step": 11600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
398 |
"eval_samples_per_second": 197.985,
|
399 |
"eval_steps_per_second": 0.774,
|
400 |
"step": 11200
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 1.21,
|
404 |
+
"learning_rate": 9.8795907660021e-06,
|
405 |
+
"loss": 0.678,
|
406 |
+
"step": 11500
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 1.22,
|
410 |
+
"eval_accuracy": 0.8807862001800233,
|
411 |
+
"eval_f1": 0.8812929844052909,
|
412 |
+
"eval_loss": 0.6662477254867554,
|
413 |
+
"eval_runtime": 684.0407,
|
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": 4.8734693997959686e+17,
|
422 |
"trial_name": null,
|
423 |
"trial_params": null
|
424 |
}
|
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 sha256:49d2f594746653af81487dba34d362ffda36fd878afa9159ee8ac5213d52ac33
|
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 sha256:76baf54d2ecf0db296948b327dff02b7c2b5a993c837b407b04112a3cb288406
|
3 |
+
size 5404
|