Training in progress, step 4400, 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:fd6feb44fd4a371f3ab74ee5e57d06e2a75ac597305502b24b8d8f5195dde52e
|
| 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:b9e3539775f402b4864f77f2f9b6ebf37e513ae8441a708b0d7377ff9f022dc4
|
| 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 sha256:3c9eff77540dede028973a3a7d3de45171bd5bb15fa08b7884c1e9297e1e115a
|
| 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 sha256:0ae3d58e23bb299295105e102ba554966b77b6c0b683658ad76c5839a4c22e52
|
| 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": 8.
|
| 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,
|
|
@@ -372,6 +372,13 @@
|
|
| 372 |
"learning_rate": 7.133333333333334e-05,
|
| 373 |
"loss": 1.2594,
|
| 374 |
"step": 4300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 375 |
}
|
| 376 |
],
|
| 377 |
"logging_steps": 100,
|
|
@@ -391,7 +398,7 @@
|
|
| 391 |
"attributes": {}
|
| 392 |
}
|
| 393 |
},
|
| 394 |
-
"total_flos": 6.
|
| 395 |
"train_batch_size": 8,
|
| 396 |
"trial_name": null,
|
| 397 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.798625214810185,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 4400,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 372 |
"learning_rate": 7.133333333333334e-05,
|
| 373 |
"loss": 1.2594,
|
| 374 |
"step": 4300
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.798625214810185,
|
| 378 |
+
"grad_norm": 0.19417451322078705,
|
| 379 |
+
"learning_rate": 7.066666666666667e-05,
|
| 380 |
+
"loss": 1.2548,
|
| 381 |
+
"step": 4400
|
| 382 |
}
|
| 383 |
],
|
| 384 |
"logging_steps": 100,
|
|
|
|
| 398 |
"attributes": {}
|
| 399 |
}
|
| 400 |
},
|
| 401 |
+
"total_flos": 6.867225477317132e+18,
|
| 402 |
"train_batch_size": 8,
|
| 403 |
"trial_name": null,
|
| 404 |
"trial_params": null
|