ramdhanfirdaus
commited on
Commit
•
373475e
1
Parent(s):
7811983
Training in progress, step 3200, 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:db773136b976b1474997d83fa2f13532f3fc351edb5440d0eb4b78c89ea6bf8e
|
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 151032837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc0d0baf4dc93c907e37268bbe54e68c34f017055a32d5510e142a2991c511d0
|
3 |
size 151032837
|
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:eefe083b6454775aee01bb69e64bad53187f7b97719dea614c013fe397ac511b
|
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 sha256:50b57a34df83b700e2c13775ff734b4569b74ce7e20da3479db76577bb4e906e
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.175557017326355,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3000",
|
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,
|
@@ -441,13 +441,27 @@
|
|
441 |
"eval_samples_per_second": 18.361,
|
442 |
"eval_steps_per_second": 2.297,
|
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.
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
453 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.175557017326355,
|
3 |
"best_model_checkpoint": "./outputs/checkpoint-3000",
|
4 |
+
"epoch": 2.33224043715847,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 3200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
441 |
"eval_samples_per_second": 18.361,
|
442 |
"eval_steps_per_second": 2.297,
|
443 |
"step": 3100
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 2.33,
|
447 |
+
"learning_rate": 0.0002,
|
448 |
+
"loss": 1.1452,
|
449 |
+
"step": 3200
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 2.33,
|
453 |
+
"eval_loss": 1.1769670248031616,
|
454 |
+
"eval_runtime": 341.7617,
|
455 |
+
"eval_samples_per_second": 18.358,
|
456 |
+
"eval_steps_per_second": 2.297,
|
457 |
+
"step": 3200
|
458 |
}
|
459 |
],
|
460 |
"logging_steps": 100,
|
461 |
"max_steps": 4116,
|
462 |
"num_train_epochs": 3,
|
463 |
"save_steps": 100,
|
464 |
+
"total_flos": 1.0375860307626947e+18,
|
465 |
"trial_name": null,
|
466 |
"trial_params": null
|
467 |
}
|