Training in progress, step 4700, 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:d4d67170782f9253c0f7340ba9213d47c6cc56cf51d9b6b6f68aa259d7392896
|
| 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 sha256:4b79e18f3ae205c2c075b4e64d9ced3380ef383099ada4fa5475be4cc77fc53c
|
| 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:c32f57d141dbe8ed78c62ce866c1838fd2d7ec2d43c7ed9b47c4d519952c1be4
|
| 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 sha256:8a89f947ab8f2b301b2d292fe1e52d38fb71d031c48cac1ceb914ae87899b446
|
| 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": 9.
|
| 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,
|
|
@@ -401,6 +401,13 @@
|
|
| 401 |
"learning_rate": 6.933333333333334e-05,
|
| 402 |
"loss": 1.2599,
|
| 403 |
"step": 4600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 404 |
}
|
| 405 |
],
|
| 406 |
"logging_steps": 100,
|
|
@@ -420,7 +427,7 @@
|
|
| 420 |
"attributes": {}
|
| 421 |
}
|
| 422 |
},
|
| 423 |
-
"total_flos": 7.
|
| 424 |
"train_batch_size": 8,
|
| 425 |
"trial_name": null,
|
| 426 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.398531479456334,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 4700,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 401 |
"learning_rate": 6.933333333333334e-05,
|
| 402 |
"loss": 1.2599,
|
| 403 |
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 9.398531479456334,
|
| 407 |
+
"grad_norm": 0.19702570140361786,
|
| 408 |
+
"learning_rate": 6.866666666666666e-05,
|
| 409 |
+
"loss": 1.2603,
|
| 410 |
+
"step": 4700
|
| 411 |
}
|
| 412 |
],
|
| 413 |
"logging_steps": 100,
|
|
|
|
| 427 |
"attributes": {}
|
| 428 |
}
|
| 429 |
},
|
| 430 |
+
"total_flos": 7.335441234011357e+18,
|
| 431 |
"train_batch_size": 8,
|
| 432 |
"trial_name": null,
|
| 433 |
"trial_params": null
|