Training in progress, step 70, 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 sha256:715fdfc3b72e43250d66ed21735dbbf45fa7586f2584927d0b4468e37a6a7466
|
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 sha256:701ae6f2c83a7141ca44f63fc387a03422e235cec3a6a27bf3f80f32dfc51fe2
|
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:c270112259dc0921624c59fb7c82b4ff8da4610d18711e9de53343f3771b5741
|
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,
|
@@ -490,6 +490,13 @@
|
|
490 |
"learning_rate": 0.000138,
|
491 |
"loss": 1.3201,
|
492 |
"step": 69
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
493 |
}
|
494 |
],
|
495 |
"logging_steps": 1,
|
@@ -509,7 +516,7 @@
|
|
509 |
"attributes": {}
|
510 |
}
|
511 |
},
|
512 |
-
"total_flos": 8.
|
513 |
"train_batch_size": 4,
|
514 |
"trial_name": null,
|
515 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.19204389574759945,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 70,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
490 |
"learning_rate": 0.000138,
|
491 |
"loss": 1.3201,
|
492 |
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.19204389574759945,
|
496 |
+
"grad_norm": 0.09785107523202896,
|
497 |
+
"learning_rate": 0.00014,
|
498 |
+
"loss": 1.2413,
|
499 |
+
"step": 70
|
500 |
}
|
501 |
],
|
502 |
"logging_steps": 1,
|
|
|
516 |
"attributes": {}
|
517 |
}
|
518 |
},
|
519 |
+
"total_flos": 8.664968652500582e+16,
|
520 |
"train_batch_size": 4,
|
521 |
"trial_name": null,
|
522 |
"trial_params": null
|