Training in progress, step 6100, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ae47b2faf42c719a68011b1b0b100bc24d2508f678c6fd2a00513e66f8e8759
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bf3dbad8d8f520d7840428f2b63fa52ef5cab515cccd2ee33e720f454611248
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e01e8e28d486c8806cf9cd9a5e40dda893d11ceafcc0f649340bad06dda0abb1
|
| 3 |
size 15006
|
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:dc99665b99c1c35052797f774c28787563395e7697d40291ce1c84eedb8a5e76
|
| 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":
|
| 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,
|
|
@@ -523,6 +523,13 @@
|
|
| 523 |
"eval_samples_per_second": 19.861,
|
| 524 |
"eval_steps_per_second": 2.484,
|
| 525 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 526 |
}
|
| 527 |
],
|
| 528 |
"logging_steps": 100,
|
|
@@ -542,7 +549,7 @@
|
|
| 542 |
"attributes": {}
|
| 543 |
}
|
| 544 |
},
|
| 545 |
-
"total_flos": 9.
|
| 546 |
"train_batch_size": 8,
|
| 547 |
"trial_name": null,
|
| 548 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.19809404780503,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 6100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 523 |
"eval_samples_per_second": 19.861,
|
| 524 |
"eval_steps_per_second": 2.484,
|
| 525 |
"step": 6000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 12.19809404780503,
|
| 529 |
+
"grad_norm": 0.20758041739463806,
|
| 530 |
+
"learning_rate": 5.9333333333333343e-05,
|
| 531 |
+
"loss": 1.2475,
|
| 532 |
+
"step": 6100
|
| 533 |
}
|
| 534 |
],
|
| 535 |
"logging_steps": 100,
|
|
|
|
| 549 |
"attributes": {}
|
| 550 |
}
|
| 551 |
},
|
| 552 |
+
"total_flos": 9.520463360034865e+18,
|
| 553 |
"train_batch_size": 8,
|
| 554 |
"trial_name": null,
|
| 555 |
"trial_params": null
|