Training in progress, step 820, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:616b5f04f36ab114fa9500fea120f1a8d66c0bb5ef2b978e32f6450c6c0e843e
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0f5422fc53447a1903fe92d6625379a97edfd1171e3221a8140fbfdfbaa293d
|
| 3 |
size 14709
|
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 sha256:32d797907dfa61e81aa221070eb057253e40924d2c06ab2e8cd85227dbe64129
|
| 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": 6.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1466,6 +1466,24 @@
|
|
| 1466 |
"mean_token_accuracy": 0.64379281103611,
|
| 1467 |
"num_tokens": 2953207.0,
|
| 1468 |
"step": 810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1469 |
}
|
| 1470 |
],
|
| 1471 |
"logging_steps": 5,
|
|
@@ -1485,7 +1503,7 @@
|
|
| 1485 |
"attributes": {}
|
| 1486 |
}
|
| 1487 |
},
|
| 1488 |
-
"total_flos": 1.
|
| 1489 |
"train_batch_size": 4,
|
| 1490 |
"trial_name": null,
|
| 1491 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.3076923076923075,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1466 |
"mean_token_accuracy": 0.64379281103611,
|
| 1467 |
"num_tokens": 2953207.0,
|
| 1468 |
"step": 810
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 6.269230769230769,
|
| 1472 |
+
"grad_norm": 0.0,
|
| 1473 |
+
"learning_rate": 4.593e-05,
|
| 1474 |
+
"loss": 1.7694,
|
| 1475 |
+
"mean_token_accuracy": 0.6440808981657028,
|
| 1476 |
+
"num_tokens": 2971018.0,
|
| 1477 |
+
"step": 815
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 6.3076923076923075,
|
| 1481 |
+
"grad_norm": 0.0,
|
| 1482 |
+
"learning_rate": 4.5905e-05,
|
| 1483 |
+
"loss": 1.6246,
|
| 1484 |
+
"mean_token_accuracy": 0.6741865813732147,
|
| 1485 |
+
"num_tokens": 2990306.0,
|
| 1486 |
+
"step": 820
|
| 1487 |
}
|
| 1488 |
],
|
| 1489 |
"logging_steps": 5,
|
|
|
|
| 1503 |
"attributes": {}
|
| 1504 |
}
|
| 1505 |
},
|
| 1506 |
+
"total_flos": 1.5160423417970688e+17,
|
| 1507 |
"train_batch_size": 4,
|
| 1508 |
"trial_name": null,
|
| 1509 |
"trial_params": null
|