Training in progress, step 78, 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:fc941af358c41fdacb4643bbfec2e2f6cedd8ccebc8d32a056a9fe1f0067a572
|
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 sha256:171a625f2f946875f946841d317f73ae901bc37acb6617c511d58b5b274af3c6
|
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:a97cd7f079d7f12ed4724344a7cbd6b5515d4008435f2e5a63f0ce71a90c202c
|
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,
|
@@ -546,6 +546,13 @@
|
|
546 |
"learning_rate": 0.000154,
|
547 |
"loss": 1.3226,
|
548 |
"step": 77
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
549 |
}
|
550 |
],
|
551 |
"logging_steps": 1,
|
@@ -565,7 +572,7 @@
|
|
565 |
"attributes": {}
|
566 |
}
|
567 |
},
|
568 |
-
"total_flos": 9.
|
569 |
"train_batch_size": 4,
|
570 |
"trial_name": null,
|
571 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2139917695473251,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 78,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
546 |
"learning_rate": 0.000154,
|
547 |
"loss": 1.3226,
|
548 |
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.2139917695473251,
|
552 |
+
"grad_norm": 0.09259933233261108,
|
553 |
+
"learning_rate": 0.00015600000000000002,
|
554 |
+
"loss": 1.2942,
|
555 |
+
"step": 78
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 1,
|
|
|
572 |
"attributes": {}
|
573 |
}
|
574 |
},
|
575 |
+
"total_flos": 9.669833466976666e+16,
|
576 |
"train_batch_size": 4,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|