Commit
·
831dda3
1
Parent(s):
102047b
Training in progress, step 100, 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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c480283f652ea6b0a6277170ad479fdcbfa1ee41d8b0ebb6ca0da87695bc026c
|
| 3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42545748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7fc5f4ccb6b8974b5b2dd6e323a346d15361c1223affd585e12001f7482f76b
|
| 3 |
size 42545748
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cf2042332884d26b423c910e7e944b9fb3bdc6234db05b1536b08f0d4fc221f
|
| 3 |
size 14244
|
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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 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": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -547,13 +547,73 @@
|
|
| 547 |
"learning_rate": 2.105263157894737e-05,
|
| 548 |
"loss": 1.7966,
|
| 549 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 550 |
}
|
| 551 |
],
|
| 552 |
"logging_steps": 1,
|
| 553 |
"max_steps": 100,
|
| 554 |
"num_train_epochs": 1,
|
| 555 |
"save_steps": 10,
|
| 556 |
-
"total_flos":
|
| 557 |
"trial_name": null,
|
| 558 |
"trial_params": null
|
| 559 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.04,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 547 |
"learning_rate": 2.105263157894737e-05,
|
| 548 |
"loss": 1.7966,
|
| 549 |
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.04,
|
| 553 |
+
"learning_rate": 1.8947368421052634e-05,
|
| 554 |
+
"loss": 1.4885,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.04,
|
| 559 |
+
"learning_rate": 1.6842105263157896e-05,
|
| 560 |
+
"loss": 1.0934,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.04,
|
| 565 |
+
"learning_rate": 1.4736842105263157e-05,
|
| 566 |
+
"loss": 1.5674,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.04,
|
| 571 |
+
"learning_rate": 1.2631578947368422e-05,
|
| 572 |
+
"loss": 2.0261,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.04,
|
| 577 |
+
"learning_rate": 1.0526315789473684e-05,
|
| 578 |
+
"loss": 1.5099,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.04,
|
| 583 |
+
"learning_rate": 8.421052631578948e-06,
|
| 584 |
+
"loss": 1.4694,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.04,
|
| 589 |
+
"learning_rate": 6.315789473684211e-06,
|
| 590 |
+
"loss": 1.675,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.04,
|
| 595 |
+
"learning_rate": 4.210526315789474e-06,
|
| 596 |
+
"loss": 1.6133,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.04,
|
| 601 |
+
"learning_rate": 2.105263157894737e-06,
|
| 602 |
+
"loss": 1.6722,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.04,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 1.4913,
|
| 609 |
+
"step": 100
|
| 610 |
}
|
| 611 |
],
|
| 612 |
"logging_steps": 1,
|
| 613 |
"max_steps": 100,
|
| 614 |
"num_train_epochs": 1,
|
| 615 |
"save_steps": 10,
|
| 616 |
+
"total_flos": 6616414021533696.0,
|
| 617 |
"trial_name": null,
|
| 618 |
"trial_params": null
|
| 619 |
}
|