Training in progress, step 7400, 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 sha256:75be62931ca89f23de7c2c6c483ee19c4f2ef138d655a65379af228b82b161dc
|
| 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 sha256:8dba0480e4ca5555afa0bf7b62139d4c19532c4b78abe6342a2c4d08071b8212
|
| 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 sha256:4aa5b9d71d5524022fdb89355036b4bd30d92891556b751a47429b9fe2b2efba
|
| 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 sha256:381e8c3b4c5347a5e5a8c54712ad5f2c5ede6fb03b4178c4cda7398bba55a45a
|
| 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": 14.
|
| 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,
|
|
@@ -630,6 +630,13 @@
|
|
| 630 |
"learning_rate": 5.133333333333333e-05,
|
| 631 |
"loss": 1.2374,
|
| 632 |
"step": 7300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 633 |
}
|
| 634 |
],
|
| 635 |
"logging_steps": 100,
|
|
@@ -649,7 +656,7 @@
|
|
| 649 |
"attributes": {}
|
| 650 |
}
|
| 651 |
},
|
| 652 |
-
"total_flos": 1.
|
| 653 |
"train_batch_size": 8,
|
| 654 |
"trial_name": null,
|
| 655 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.797687861271676,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 7400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 630 |
"learning_rate": 5.133333333333333e-05,
|
| 631 |
"loss": 1.2374,
|
| 632 |
"step": 7300
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 14.797687861271676,
|
| 636 |
+
"grad_norm": 0.21324670314788818,
|
| 637 |
+
"learning_rate": 5.0666666666666674e-05,
|
| 638 |
+
"loss": 1.2382,
|
| 639 |
+
"step": 7400
|
| 640 |
}
|
| 641 |
],
|
| 642 |
"logging_steps": 100,
|
|
|
|
| 656 |
"attributes": {}
|
| 657 |
}
|
| 658 |
},
|
| 659 |
+
"total_flos": 1.1549419671740482e+19,
|
| 660 |
"train_batch_size": 8,
|
| 661 |
"trial_name": null,
|
| 662 |
"trial_params": null
|