Training in progress, step 880, 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 sha256:6bbe2b086bbba79a4c494dccc0f77f38a9bdbbfa5116b12a5903c0d739e1c682
|
| 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 sha256:75e91112ab516ad9c782088be345d40dd390d159c77f592bab30518f3de209f2
|
| 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 sha256:3116cb00a7c29d008877be1554f6cd0519c32877c74589ad4305cada0fa571b7
|
| 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,
|
|
@@ -1574,6 +1574,24 @@
|
|
| 1574 |
"mean_token_accuracy": 0.6404279589653015,
|
| 1575 |
"num_tokens": 3174097.0,
|
| 1576 |
"step": 870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1577 |
}
|
| 1578 |
],
|
| 1579 |
"logging_steps": 5,
|
|
@@ -1593,7 +1611,7 @@
|
|
| 1593 |
"attributes": {}
|
| 1594 |
}
|
| 1595 |
},
|
| 1596 |
-
"total_flos": 1.
|
| 1597 |
"train_batch_size": 4,
|
| 1598 |
"trial_name": null,
|
| 1599 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.769230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1574 |
"mean_token_accuracy": 0.6404279589653015,
|
| 1575 |
"num_tokens": 3174097.0,
|
| 1576 |
"step": 870
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 6.730769230769231,
|
| 1580 |
+
"grad_norm": 0.0,
|
| 1581 |
+
"learning_rate": 4.563e-05,
|
| 1582 |
+
"loss": 1.7347,
|
| 1583 |
+
"mean_token_accuracy": 0.649324044585228,
|
| 1584 |
+
"num_tokens": 3192152.0,
|
| 1585 |
+
"step": 875
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 6.769230769230769,
|
| 1589 |
+
"grad_norm": 0.0,
|
| 1590 |
+
"learning_rate": 4.5605e-05,
|
| 1591 |
+
"loss": 1.7318,
|
| 1592 |
+
"mean_token_accuracy": 0.6562680333852768,
|
| 1593 |
+
"num_tokens": 3210441.0,
|
| 1594 |
+
"step": 880
|
| 1595 |
}
|
| 1596 |
],
|
| 1597 |
"logging_steps": 5,
|
|
|
|
| 1611 |
"attributes": {}
|
| 1612 |
}
|
| 1613 |
},
|
| 1614 |
+
"total_flos": 1.6269448120713216e+17,
|
| 1615 |
"train_batch_size": 4,
|
| 1616 |
"trial_name": null,
|
| 1617 |
"trial_params": null
|