Training in progress, step 3525, 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 108113968
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5971123d89e36bf98d701f41f8c7a50ed5bd3da805c7b515ed16fb93d602b195
|
| 3 |
size 108113968
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57081771
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52e66d4bbae0259dd3d0a2a41d71609bd2879217ae74b50944c502dda9393117
|
| 3 |
size 57081771
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b00fa73066df26c04546a3e4e0bd3ca92a9cedad3c19e3246c0cf5b9c0ed4d7d
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 300,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1408,6 +1408,16 @@
|
|
| 1408 |
"mean_token_accuracy": 0.9428420805931091,
|
| 1409 |
"num_tokens": 1198369.0,
|
| 1410 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1411 |
}
|
| 1412 |
],
|
| 1413 |
"logging_steps": 25,
|
|
@@ -1427,7 +1437,7 @@
|
|
| 1427 |
"attributes": {}
|
| 1428 |
}
|
| 1429 |
},
|
| 1430 |
-
"total_flos": 3.
|
| 1431 |
"train_batch_size": 4,
|
| 1432 |
"trial_name": null,
|
| 1433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8013184814730621,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 3525,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1408 |
"mean_token_accuracy": 0.9428420805931091,
|
| 1409 |
"num_tokens": 1198369.0,
|
| 1410 |
"step": 3500
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy": 0.16919010490179062,
|
| 1414 |
+
"epoch": 0.8013184814730621,
|
| 1415 |
+
"grad_norm": 0.21531875431537628,
|
| 1416 |
+
"learning_rate": 0.0002,
|
| 1417 |
+
"loss": 0.17262735366821289,
|
| 1418 |
+
"mean_token_accuracy": 0.943871192932129,
|
| 1419 |
+
"num_tokens": 1228868.0,
|
| 1420 |
+
"step": 3525
|
| 1421 |
}
|
| 1422 |
],
|
| 1423 |
"logging_steps": 25,
|
|
|
|
| 1437 |
"attributes": {}
|
| 1438 |
}
|
| 1439 |
},
|
| 1440 |
+
"total_flos": 3.14599522134955e+17,
|
| 1441 |
"train_batch_size": 4,
|
| 1442 |
"trial_name": null,
|
| 1443 |
"trial_params": null
|