ramdhanfirdaus
commited on
Commit
•
d5f8c77
1
Parent(s):
70819e4
Training in progress, step 2600, 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 75507072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70054c456b68316e69f3ecab6cf099dc087f11b350b276053bbbde200fc00444
|
3 |
size 75507072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 151034501
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:365ac8276a568a8917ea5b352da128cd36f4e1855a29c26f57d06cb5d2a1208e
|
3 |
size 151034501
|
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 sha256:442bafcbf0d292ca19eedeb960e51c5d7ecd5eec12507df91524cb8e1081a81b
|
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:ee2eceee28d7a299780008f817c050eb9e87b0d18fb8d8f19062cda68b3e10f9
|
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": 1.
|
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,
|
@@ -357,13 +357,27 @@
|
|
357 |
"eval_samples_per_second": 14.989,
|
358 |
"eval_steps_per_second": 1.875,
|
359 |
"step": 2500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 100,
|
363 |
"max_steps": 4116,
|
364 |
"num_train_epochs": 3,
|
365 |
"save_steps": 100,
|
366 |
-
"total_flos": 8.
|
367 |
"trial_name": null,
|
368 |
"trial_params": null
|
369 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.2160065174102783,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2600",
|
4 |
+
"epoch": 1.8943533697632058,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
357 |
"eval_samples_per_second": 14.989,
|
358 |
"eval_steps_per_second": 1.875,
|
359 |
"step": 2500
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.89,
|
363 |
+
"learning_rate": 0.0002,
|
364 |
+
"loss": 1.2106,
|
365 |
+
"step": 2600
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.89,
|
369 |
+
"eval_loss": 1.2160065174102783,
|
370 |
+
"eval_runtime": 418.6873,
|
371 |
+
"eval_samples_per_second": 14.985,
|
372 |
+
"eval_steps_per_second": 1.875,
|
373 |
+
"step": 2600
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 100,
|
377 |
"max_steps": 4116,
|
378 |
"num_train_epochs": 3,
|
379 |
"save_steps": 100,
|
380 |
+
"total_flos": 8.428488053895383e+17,
|
381 |
"trial_name": null,
|
382 |
"trial_params": null
|
383 |
}
|