Training in progress, step 5400, 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 sha256:014fee06c40abe14189555c9ed4b025e6ee8cd4e072236a6535f45528f8d6229
|
| 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:cd913717e7a6e4112d3543f341b7a262c1da4ae52ac1ad2834e5b246991f9026
|
| 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 sha256:924549db5c8fa7c6722b2717239f1aff8fd1b5bfacb8266579f90ebe96787e6a
|
| 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 sha256:80145150a24a2d588a25fa8b47e99a841735b6543ce3ee2a1cf42f0c87555d79
|
| 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,
|
|
@@ -458,6 +458,13 @@
|
|
| 458 |
"learning_rate": 6.466666666666666e-05,
|
| 459 |
"loss": 1.2471,
|
| 460 |
"step": 5300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 461 |
}
|
| 462 |
],
|
| 463 |
"logging_steps": 100,
|
|
@@ -477,7 +484,7 @@
|
|
| 477 |
"attributes": {}
|
| 478 |
}
|
| 479 |
},
|
| 480 |
-
"total_flos": 8.
|
| 481 |
"train_batch_size": 8,
|
| 482 |
"trial_name": null,
|
| 483 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.798312763630683,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 458 |
"learning_rate": 6.466666666666666e-05,
|
| 459 |
"loss": 1.2471,
|
| 460 |
"step": 5300
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 10.798312763630683,
|
| 464 |
+
"grad_norm": 0.20083682239055634,
|
| 465 |
+
"learning_rate": 6.400000000000001e-05,
|
| 466 |
+
"loss": 1.2461,
|
| 467 |
+
"step": 5400
|
| 468 |
}
|
| 469 |
],
|
| 470 |
"logging_steps": 100,
|
|
|
|
| 484 |
"attributes": {}
|
| 485 |
}
|
| 486 |
},
|
| 487 |
+
"total_flos": 8.427956875458249e+18,
|
| 488 |
"train_batch_size": 8,
|
| 489 |
"trial_name": null,
|
| 490 |
"trial_params": null
|