Training in progress, step 830, 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:e51c84ea0f8b2d80a5273f7f3ed3f4a9ede4a77f0ff8435ff690fb86a529ddfe
|
| 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 sha256:5db708c704ea025c4d52f71a2366ace7fc9d6802c46da205ed4da9df7cf09aec
|
| 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 sha256:536dc0882c387104f0c982a18835bc93cc52625550df9859fb767a840b84c217
|
| 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,
|
|
@@ -1484,6 +1484,24 @@
|
|
| 1484 |
"mean_token_accuracy": 0.6741865813732147,
|
| 1485 |
"num_tokens": 2990306.0,
|
| 1486 |
"step": 820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1487 |
}
|
| 1488 |
],
|
| 1489 |
"logging_steps": 5,
|
|
@@ -1503,7 +1521,7 @@
|
|
| 1503 |
"attributes": {}
|
| 1504 |
}
|
| 1505 |
},
|
| 1506 |
-
"total_flos": 1.
|
| 1507 |
"train_batch_size": 4,
|
| 1508 |
"trial_name": null,
|
| 1509 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1484 |
"mean_token_accuracy": 0.6741865813732147,
|
| 1485 |
"num_tokens": 2990306.0,
|
| 1486 |
"step": 820
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 6.346153846153846,
|
| 1490 |
+
"grad_norm": 0.0,
|
| 1491 |
+
"learning_rate": 4.588e-05,
|
| 1492 |
+
"loss": 1.7449,
|
| 1493 |
+
"mean_token_accuracy": 0.6494547843933105,
|
| 1494 |
+
"num_tokens": 3008827.0,
|
| 1495 |
+
"step": 825
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 6.384615384615385,
|
| 1499 |
+
"grad_norm": 0.0,
|
| 1500 |
+
"learning_rate": 4.5855e-05,
|
| 1501 |
+
"loss": 1.716,
|
| 1502 |
+
"mean_token_accuracy": 0.6559219211339951,
|
| 1503 |
+
"num_tokens": 3027465.0,
|
| 1504 |
+
"step": 830
|
| 1505 |
}
|
| 1506 |
],
|
| 1507 |
"logging_steps": 5,
|
|
|
|
| 1521 |
"attributes": {}
|
| 1522 |
}
|
| 1523 |
},
|
| 1524 |
+
"total_flos": 1.534465486135296e+17,
|
| 1525 |
"train_batch_size": 4,
|
| 1526 |
"trial_name": null,
|
| 1527 |
"trial_params": null
|