Training in progress, step 870, 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:d867695bb338d5ee33a78a98060567a24e20e48b17f0257656b1997cb1ae596b
|
| 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 sha256:7281141612f3ebc1457e422895e3d07c68ab228bd46811b652c69d1910e1ece6
|
| 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 sha256:384c885d0c4fbcc82117a3ae43d1e0ddbf2d89c9ad8f08eca9dd6788b6f65bc3
|
| 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,
|
|
@@ -1556,6 +1556,24 @@
|
|
| 1556 |
"mean_token_accuracy": 0.6611418306827546,
|
| 1557 |
"num_tokens": 3136818.0,
|
| 1558 |
"step": 860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1559 |
}
|
| 1560 |
],
|
| 1561 |
"logging_steps": 5,
|
|
@@ -1575,7 +1593,7 @@
|
|
| 1575 |
"attributes": {}
|
| 1576 |
}
|
| 1577 |
},
|
| 1578 |
-
"total_flos": 1.
|
| 1579 |
"train_batch_size": 4,
|
| 1580 |
"trial_name": null,
|
| 1581 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.6923076923076925,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1556 |
"mean_token_accuracy": 0.6611418306827546,
|
| 1557 |
"num_tokens": 3136818.0,
|
| 1558 |
"step": 860
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 6.653846153846154,
|
| 1562 |
+
"grad_norm": 0.0,
|
| 1563 |
+
"learning_rate": 4.568e-05,
|
| 1564 |
+
"loss": 1.6901,
|
| 1565 |
+
"mean_token_accuracy": 0.6592308074235916,
|
| 1566 |
+
"num_tokens": 3156269.0,
|
| 1567 |
+
"step": 865
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 6.6923076923076925,
|
| 1571 |
+
"grad_norm": 0.0,
|
| 1572 |
+
"learning_rate": 4.5655e-05,
|
| 1573 |
+
"loss": 1.7783,
|
| 1574 |
+
"mean_token_accuracy": 0.6404279589653015,
|
| 1575 |
+
"num_tokens": 3174097.0,
|
| 1576 |
+
"step": 870
|
| 1577 |
}
|
| 1578 |
],
|
| 1579 |
"logging_steps": 5,
|
|
|
|
| 1593 |
"attributes": {}
|
| 1594 |
}
|
| 1595 |
},
|
| 1596 |
+
"total_flos": 1.608424812453888e+17,
|
| 1597 |
"train_batch_size": 4,
|
| 1598 |
"trial_name": null,
|
| 1599 |
"trial_params": null
|