Training in progress, step 890, 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 sha256:5ed54143d34e6393d37be5d2c1b741c59b02807c84b576b5df579e55738fd587
|
| 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:cf695a528bebecb2c85ea558618e19f35de7fff571f05a7bc114e261bc8fa614
|
| 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 sha256:78b960d9bf14791aa503c06b3b13cace285c41803ba7f572cdff1ab53dbb8996
|
| 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,
|
|
@@ -1592,6 +1592,24 @@
|
|
| 1592 |
"mean_token_accuracy": 0.6562680333852768,
|
| 1593 |
"num_tokens": 3210441.0,
|
| 1594 |
"step": 880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1595 |
}
|
| 1596 |
],
|
| 1597 |
"logging_steps": 5,
|
|
@@ -1611,7 +1629,7 @@
|
|
| 1611 |
"attributes": {}
|
| 1612 |
}
|
| 1613 |
},
|
| 1614 |
-
"total_flos": 1.
|
| 1615 |
"train_batch_size": 4,
|
| 1616 |
"trial_name": null,
|
| 1617 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.846153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1592 |
"mean_token_accuracy": 0.6562680333852768,
|
| 1593 |
"num_tokens": 3210441.0,
|
| 1594 |
"step": 880
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 6.8076923076923075,
|
| 1598 |
+
"grad_norm": 0.0,
|
| 1599 |
+
"learning_rate": 4.558e-05,
|
| 1600 |
+
"loss": 1.754,
|
| 1601 |
+
"mean_token_accuracy": 0.6517583757638932,
|
| 1602 |
+
"num_tokens": 3228565.0,
|
| 1603 |
+
"step": 885
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 6.846153846153846,
|
| 1607 |
+
"grad_norm": 0.0,
|
| 1608 |
+
"learning_rate": 4.5555e-05,
|
| 1609 |
+
"loss": 1.719,
|
| 1610 |
+
"mean_token_accuracy": 0.6558358192443847,
|
| 1611 |
+
"num_tokens": 3246686.0,
|
| 1612 |
+
"step": 890
|
| 1613 |
}
|
| 1614 |
],
|
| 1615 |
"logging_steps": 5,
|
|
|
|
| 1629 |
"attributes": {}
|
| 1630 |
}
|
| 1631 |
},
|
| 1632 |
+
"total_flos": 1.6453314372059136e+17,
|
| 1633 |
"train_batch_size": 4,
|
| 1634 |
"trial_name": null,
|
| 1635 |
"trial_params": null
|