Training in progress, step 1610, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18628fff5888b391bc6d563651a70135cf360160b9e4b8c54a931c505add45cb
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:565117ea44dd9d3c592e4adacb279e4ff3cbcab209baeac22bb40b1d188fb170
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:334bc8ec02e58e4ba446fec4b8806a7cb93f1b5dce895a4a76fdea72b35e04c7
|
| 3 |
size 14645
|
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 sha256:8e4a19270e2b79c7632a330b85d9c8b414e7539580876dbcc408ebf95a863643
|
| 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": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -1618,6 +1618,16 @@
|
|
| 1618 |
"mean_token_accuracy": 0.7598425537347794,
|
| 1619 |
"num_tokens": 7439670.0,
|
| 1620 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1621 |
}
|
| 1622 |
],
|
| 1623 |
"logging_steps": 10,
|
|
@@ -1637,7 +1647,7 @@
|
|
| 1637 |
"attributes": {}
|
| 1638 |
}
|
| 1639 |
},
|
| 1640 |
-
"total_flos": 3.
|
| 1641 |
"train_batch_size": 4,
|
| 1642 |
"trial_name": null,
|
| 1643 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.34346666666666664,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1618 |
"mean_token_accuracy": 0.7598425537347794,
|
| 1619 |
"num_tokens": 7439670.0,
|
| 1620 |
"step": 1600
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"entropy": 1.0912248834967613,
|
| 1624 |
+
"epoch": 0.34346666666666664,
|
| 1625 |
+
"grad_norm": 0.2782971262931824,
|
| 1626 |
+
"learning_rate": 9.495469708845701e-05,
|
| 1627 |
+
"loss": 1.1914597511291505,
|
| 1628 |
+
"mean_token_accuracy": 0.7388298735022545,
|
| 1629 |
+
"num_tokens": 7485267.0,
|
| 1630 |
+
"step": 1610
|
| 1631 |
}
|
| 1632 |
],
|
| 1633 |
"logging_steps": 10,
|
|
|
|
| 1647 |
"attributes": {}
|
| 1648 |
}
|
| 1649 |
},
|
| 1650 |
+
"total_flos": 3.5487369026297856e+16,
|
| 1651 |
"train_batch_size": 4,
|
| 1652 |
"trial_name": null,
|
| 1653 |
"trial_params": null
|