Training in progress, step 5900, 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 sha256:8045ece01cd2aeb9d499a0320e1f22286bdc8cfcfe61a226664746e07c3c5f60
|
| 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 sha256:005e7de3abb84635dafdee3a8ba79cb585547bd0f0048be0efc20bee6a04b734
|
| 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:cf21107d6237c1a47582df5d14262b3f30a2235c4b055ac43a59cd75f5a56ee5
|
| 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:b174702c9c1953310bc2ab4fc08bf447a0a35d9790cc4ddb43424b44578611a9
|
| 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": 11.
|
| 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,
|
|
@@ -501,6 +501,13 @@
|
|
| 501 |
"learning_rate": 6.133333333333334e-05,
|
| 502 |
"loss": 1.2441,
|
| 503 |
"step": 5800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 504 |
}
|
| 505 |
],
|
| 506 |
"logging_steps": 100,
|
|
@@ -520,7 +527,7 @@
|
|
| 520 |
"attributes": {}
|
| 521 |
}
|
| 522 |
},
|
| 523 |
-
"total_flos": 9.
|
| 524 |
"train_batch_size": 8,
|
| 525 |
"trial_name": null,
|
| 526 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.798156538040931,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 5900,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 501 |
"learning_rate": 6.133333333333334e-05,
|
| 502 |
"loss": 1.2441,
|
| 503 |
"step": 5800
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 11.798156538040931,
|
| 507 |
+
"grad_norm": 0.19492241740226746,
|
| 508 |
+
"learning_rate": 6.066666666666667e-05,
|
| 509 |
+
"loss": 1.25,
|
| 510 |
+
"step": 5900
|
| 511 |
}
|
| 512 |
],
|
| 513 |
"logging_steps": 100,
|
|
|
|
| 527 |
"attributes": {}
|
| 528 |
}
|
| 529 |
},
|
| 530 |
+
"total_flos": 9.208322574528807e+18,
|
| 531 |
"train_batch_size": 8,
|
| 532 |
"trial_name": null,
|
| 533 |
"trial_params": null
|