Training in progress, step 900, 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:ad8879c8015e1398febba49c58d5db2e155bf87b60a1d10ba49ee43fc2af8053
|
| 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 sha256:367fae4eba5edaf2036f8fa6922072ef7ef203ef1a4e1971cd9342f0e0552ebe
|
| 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 sha256:3f40e0471af3d902fbf987018666a7c873b2cf39973ca0e06436b10f93a3d632
|
| 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,
|
|
@@ -1610,6 +1610,24 @@
|
|
| 1610 |
"mean_token_accuracy": 0.6558358192443847,
|
| 1611 |
"num_tokens": 3246686.0,
|
| 1612 |
"step": 890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1613 |
}
|
| 1614 |
],
|
| 1615 |
"logging_steps": 5,
|
|
@@ -1629,7 +1647,7 @@
|
|
| 1629 |
"attributes": {}
|
| 1630 |
}
|
| 1631 |
},
|
| 1632 |
-
"total_flos": 1.
|
| 1633 |
"train_batch_size": 4,
|
| 1634 |
"trial_name": null,
|
| 1635 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1610 |
"mean_token_accuracy": 0.6558358192443847,
|
| 1611 |
"num_tokens": 3246686.0,
|
| 1612 |
"step": 890
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 6.884615384615385,
|
| 1616 |
+
"grad_norm": 0.0,
|
| 1617 |
+
"learning_rate": 4.553e-05,
|
| 1618 |
+
"loss": 1.7535,
|
| 1619 |
+
"mean_token_accuracy": 0.6434608608484268,
|
| 1620 |
+
"num_tokens": 3264528.0,
|
| 1621 |
+
"step": 895
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 6.923076923076923,
|
| 1625 |
+
"grad_norm": 0.0,
|
| 1626 |
+
"learning_rate": 4.5505000000000006e-05,
|
| 1627 |
+
"loss": 1.7823,
|
| 1628 |
+
"mean_token_accuracy": 0.6435014694929123,
|
| 1629 |
+
"num_tokens": 3282692.0,
|
| 1630 |
+
"step": 900
|
| 1631 |
}
|
| 1632 |
],
|
| 1633 |
"logging_steps": 5,
|
|
|
|
| 1647 |
"attributes": {}
|
| 1648 |
}
|
| 1649 |
},
|
| 1650 |
+
"total_flos": 1.6641356514951168e+17,
|
| 1651 |
"train_batch_size": 4,
|
| 1652 |
"trial_name": null,
|
| 1653 |
"trial_params": null
|