ramdhanfirdaus
commited on
Commit
•
5fd9841
1
Parent(s):
d0ba825
Training in progress, step 3100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73454161117257a6eadf951d72a89a7fbd44621ac88cc94b3925c5e99db69f97
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:883300515096f663a55a666a62892f0941b8d1f96d149713b704ce98c7bc0be6
|
3 |
size 100693001
|
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 sha256:6e42983a0941a5ea3ab8dd356cda0bea564cad32d8e894b126d9bb07e48e1e57
|
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": 43.689,
|
428 |
"eval_steps_per_second": 5.466,
|
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": 1.3265715837478638,
|
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": 43.689,
|
428 |
"eval_steps_per_second": 5.466,
|
429 |
"step": 3000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 2.26,
|
433 |
+
"learning_rate": 0.0002,
|
434 |
+
"loss": 1.2964,
|
435 |
+
"step": 3100
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 2.26,
|
439 |
+
"eval_loss": 1.3265715837478638,
|
440 |
+
"eval_runtime": 143.6034,
|
441 |
+
"eval_samples_per_second": 43.69,
|
442 |
+
"eval_steps_per_second": 5.466,
|
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": 1.847919861143716e+17,
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|