Training in progress, step 3550, 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 sha256:231a866590b85dfc8d6c032fce70b4daacb4bc5068d19fc746cf0defb2bc9539
|
| 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 sha256:841e3fe4ef480d25f011fcbf0c908136f523e2e633b8c9b4146073ac7cd336b9
|
| 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 sha256:957d4846b0308ad71444dd9d45daf0368f86639bc3865ab9f4956a48b9688c28
|
| 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,
|
|
@@ -1418,6 +1418,16 @@
|
|
| 1418 |
"mean_token_accuracy": 0.943871192932129,
|
| 1419 |
"num_tokens": 1228868.0,
|
| 1420 |
"step": 3525
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1421 |
}
|
| 1422 |
],
|
| 1423 |
"logging_steps": 25,
|
|
@@ -1437,7 +1447,7 @@
|
|
| 1437 |
"attributes": {}
|
| 1438 |
}
|
| 1439 |
},
|
| 1440 |
-
"total_flos": 3.
|
| 1441 |
"train_batch_size": 4,
|
| 1442 |
"trial_name": null,
|
| 1443 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8070015912707433,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 3550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1418 |
"mean_token_accuracy": 0.943871192932129,
|
| 1419 |
"num_tokens": 1228868.0,
|
| 1420 |
"step": 3525
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"entropy": 0.1653268790245056,
|
| 1424 |
+
"epoch": 0.8070015912707433,
|
| 1425 |
+
"grad_norm": 0.18932081758975983,
|
| 1426 |
+
"learning_rate": 0.0002,
|
| 1427 |
+
"loss": 0.16573875427246093,
|
| 1428 |
+
"mean_token_accuracy": 0.94473468542099,
|
| 1429 |
+
"num_tokens": 1259226.0,
|
| 1430 |
+
"step": 3550
|
| 1431 |
}
|
| 1432 |
],
|
| 1433 |
"logging_steps": 25,
|
|
|
|
| 1447 |
"attributes": {}
|
| 1448 |
}
|
| 1449 |
},
|
| 1450 |
+
"total_flos": 3.163241641250611e+17,
|
| 1451 |
"train_batch_size": 4,
|
| 1452 |
"trial_name": null,
|
| 1453 |
"trial_params": null
|