Training in progress, step 61, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59e53eb8c198a94132f90af234fa8b500f75ed913f4af6d2251c1cefaaba13f9
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d65535f8342dc252acc237d9111b4514a25d297efec1df05d7ace72979286f0b
|
3 |
size 37430836
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1012ac6b588dad3e436237007fabffb59c0c899e6ac8db1225c7337cd1014bf
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -427,6 +427,13 @@
|
|
427 |
"learning_rate": 0.00012,
|
428 |
"loss": 1.3896,
|
429 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
430 |
}
|
431 |
],
|
432 |
"logging_steps": 1,
|
@@ -446,7 +453,7 @@
|
|
446 |
"attributes": {}
|
447 |
}
|
448 |
},
|
449 |
-
"total_flos": 7.
|
450 |
"train_batch_size": 4,
|
451 |
"trial_name": null,
|
452 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1673525377229081,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 61,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
427 |
"learning_rate": 0.00012,
|
428 |
"loss": 1.3896,
|
429 |
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.1673525377229081,
|
433 |
+
"grad_norm": 0.17536282539367676,
|
434 |
+
"learning_rate": 0.000122,
|
435 |
+
"loss": 1.4028,
|
436 |
+
"step": 61
|
437 |
}
|
438 |
],
|
439 |
"logging_steps": 1,
|
|
|
453 |
"attributes": {}
|
454 |
}
|
455 |
},
|
456 |
+
"total_flos": 7.550285148749414e+16,
|
457 |
"train_batch_size": 4,
|
458 |
"trial_name": null,
|
459 |
"trial_params": null
|