Training in progress, step 5300, 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:c18bf22da50ee7e621053083f197766e32e004389d73ee642b168a9743bd93f3
|
| 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:bddaa93ad22a96ad4c306a5057d1244a3c06ab340e36b9872a4b49b80cddcdbc
|
| 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 sha256:5fa4756020fa5980ff5a63fa7658f43b2bfa6af01ca36c8e11fa1866fca196d4
|
| 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 sha256:58b3b470bfc7be4867e68290c747de33d63c74880aa25662880b5df50a1bd0fc
|
| 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": 10.
|
| 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,
|
|
@@ -451,6 +451,13 @@
|
|
| 451 |
"learning_rate": 6.533333333333334e-05,
|
| 452 |
"loss": 1.2466,
|
| 453 |
"step": 5200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 454 |
}
|
| 455 |
],
|
| 456 |
"logging_steps": 100,
|
|
@@ -470,7 +477,7 @@
|
|
| 470 |
"attributes": {}
|
| 471 |
}
|
| 472 |
},
|
| 473 |
-
"total_flos": 8.
|
| 474 |
"train_batch_size": 8,
|
| 475 |
"trial_name": null,
|
| 476 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.598344008748633,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5300,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 451 |
"learning_rate": 6.533333333333334e-05,
|
| 452 |
"loss": 1.2466,
|
| 453 |
"step": 5200
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 10.598344008748633,
|
| 457 |
+
"grad_norm": 0.19761793315410614,
|
| 458 |
+
"learning_rate": 6.466666666666666e-05,
|
| 459 |
+
"loss": 1.2471,
|
| 460 |
+
"step": 5300
|
| 461 |
}
|
| 462 |
],
|
| 463 |
"logging_steps": 100,
|
|
|
|
| 477 |
"attributes": {}
|
| 478 |
}
|
| 479 |
},
|
| 480 |
+
"total_flos": 8.271881904270082e+18,
|
| 481 |
"train_batch_size": 8,
|
| 482 |
"trial_name": null,
|
| 483 |
"trial_params": null
|