ramdhanfirdaus
commited on
Commit
•
c4c3e36
1
Parent(s):
31cd891
Training in progress, step 3100, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50349441
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a4bbeb625e4f9b741707e73513aaf9cc3c34946ffe5db8f5b87bd79c9c3a15
|
3 |
size 50349441
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100691721
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bcb64975b4cdbe42c2a24fa97c87b86c990416d66eaa4689a53015eefdff9b8
|
3 |
size 100691721
|
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:e436f91974c8a5934977ecf2e5a240d25a1d333b3c0d40066eacd38dc546eac2
|
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 sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -427,13 +427,27 @@
|
|
427 |
"eval_samples_per_second": 21.18,
|
428 |
"eval_steps_per_second": 2.65,
|
429 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
430 |
}
|
431 |
],
|
432 |
"logging_steps": 100,
|
433 |
"max_steps": 4116,
|
434 |
"num_train_epochs": 3,
|
435 |
"save_steps": 100,
|
436 |
-
"total_flos": 1.
|
437 |
"trial_name": null,
|
438 |
"trial_params": null
|
439 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.311138391494751,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-3100",
|
4 |
+
"epoch": 2.2586520947176685,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
427 |
"eval_samples_per_second": 21.18,
|
428 |
"eval_steps_per_second": 2.65,
|
429 |
"step": 3000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.26,
|
433 |
+
"learning_rate": 0.0002,
|
434 |
+
"loss": 1.2822,
|
435 |
+
"step": 3100
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 2.26,
|
439 |
+
"eval_loss": 1.311138391494751,
|
440 |
+
"eval_runtime": 295.6634,
|
441 |
+
"eval_samples_per_second": 21.22,
|
442 |
+
"eval_steps_per_second": 2.655,
|
443 |
+
"step": 3100
|
444 |
}
|
445 |
],
|
446 |
"logging_steps": 100,
|
447 |
"max_steps": 4116,
|
448 |
"num_train_epochs": 3,
|
449 |
"save_steps": 100,
|
450 |
+
"total_flos": 1.848116374320169e+17,
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|