Training in progress, step 3100, 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 sha256:078afd492697b57aa1b447670acac98b9e5830bf1cc1f3d2a5e1129300d6fe00
|
| 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:ede1896f75f08cf575d9e0204b3c8c19fbbd7929d4d62b3a7880ffc17626358c
|
| 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:d0e726d5ed30c9502b2e0b36440e56dd2f085437864c1ee2d475cc7711e0533c
|
| 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": 23.
|
| 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,
|
|
@@ -5570,6 +5570,24 @@
|
|
| 5570 |
"mean_token_accuracy": 0.6431278616189957,
|
| 5571 |
"num_tokens": 11268887.0,
|
| 5572 |
"step": 3090
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5573 |
}
|
| 5574 |
],
|
| 5575 |
"logging_steps": 5,
|
|
@@ -5589,7 +5607,7 @@
|
|
| 5589 |
"attributes": {}
|
| 5590 |
}
|
| 5591 |
},
|
| 5592 |
-
"total_flos": 5.
|
| 5593 |
"train_batch_size": 4,
|
| 5594 |
"trial_name": null,
|
| 5595 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 23.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5570 |
"mean_token_accuracy": 0.6431278616189957,
|
| 5571 |
"num_tokens": 11268887.0,
|
| 5572 |
"step": 3090
|
| 5573 |
+
},
|
| 5574 |
+
{
|
| 5575 |
+
"epoch": 23.807692307692307,
|
| 5576 |
+
"grad_norm": 0.0,
|
| 5577 |
+
"learning_rate": 3.453e-05,
|
| 5578 |
+
"loss": 1.6927,
|
| 5579 |
+
"mean_token_accuracy": 0.6590600997209549,
|
| 5580 |
+
"num_tokens": 11287728.0,
|
| 5581 |
+
"step": 3095
|
| 5582 |
+
},
|
| 5583 |
+
{
|
| 5584 |
+
"epoch": 23.846153846153847,
|
| 5585 |
+
"grad_norm": 0.0,
|
| 5586 |
+
"learning_rate": 3.4505e-05,
|
| 5587 |
+
"loss": 1.6928,
|
| 5588 |
+
"mean_token_accuracy": 0.6589304953813553,
|
| 5589 |
+
"num_tokens": 11306559.0,
|
| 5590 |
+
"step": 3100
|
| 5591 |
}
|
| 5592 |
],
|
| 5593 |
"logging_steps": 5,
|
|
|
|
| 5607 |
"attributes": {}
|
| 5608 |
}
|
| 5609 |
},
|
| 5610 |
+
"total_flos": 5.7291469564133376e+17,
|
| 5611 |
"train_batch_size": 4,
|
| 5612 |
"trial_name": null,
|
| 5613 |
"trial_params": null
|