Training in progress, step 4025, 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 sha256:08fd1d9e69b87ed55af2bfb5c0277f778e41841bc7e43b30933439e8a44ae393
|
| 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 sha256:9e5f4e3337496b71a03246bbba7700125da76e199fb1e32779f7ed77d6a4c5ef
|
| 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 sha256:76360d024f2c5ba84197ea89b28d17ea3771be1d987b8d4b18e6189070eceea2
|
| 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,
|
|
@@ -1608,6 +1608,16 @@
|
|
| 1608 |
"mean_token_accuracy": 0.948661367893219,
|
| 1609 |
"num_tokens": 550288.0,
|
| 1610 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1611 |
}
|
| 1612 |
],
|
| 1613 |
"logging_steps": 25,
|
|
@@ -1627,7 +1637,7 @@
|
|
| 1627 |
"attributes": {}
|
| 1628 |
}
|
| 1629 |
},
|
| 1630 |
-
"total_flos": 3.
|
| 1631 |
"train_batch_size": 4,
|
| 1632 |
"trial_name": null,
|
| 1633 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9149806774266879,
|
| 6 |
"eval_steps": 300,
|
| 7 |
+
"global_step": 4025,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1608 |
"mean_token_accuracy": 0.948661367893219,
|
| 1609 |
"num_tokens": 550288.0,
|
| 1610 |
"step": 4000
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"entropy": 0.16860369294881822,
|
| 1614 |
+
"epoch": 0.9149806774266879,
|
| 1615 |
+
"grad_norm": 0.22995591163635254,
|
| 1616 |
+
"learning_rate": 0.0002,
|
| 1617 |
+
"loss": 0.17189517974853516,
|
| 1618 |
+
"mean_token_accuracy": 0.9441352486610413,
|
| 1619 |
+
"num_tokens": 580804.0,
|
| 1620 |
+
"step": 4025
|
| 1621 |
}
|
| 1622 |
],
|
| 1623 |
"logging_steps": 25,
|
|
|
|
| 1637 |
"attributes": {}
|
| 1638 |
}
|
| 1639 |
},
|
| 1640 |
+
"total_flos": 3.497034200465326e+17,
|
| 1641 |
"train_batch_size": 4,
|
| 1642 |
"trial_name": null,
|
| 1643 |
"trial_params": null
|