Training in progress, step 6420, 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 sha256:405c70a139eff0ca9aae67871aac4633a8779ba8308ca559c47b2fddf0d3131c
|
| 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 sha256:2e1d8f660b586881e63a1cd8273a4a9b3e6815abdb247eeee7667c0bde81b771
|
| 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 sha256:63b828365c3020bc227dbda2a67f9f891751542764bf20db9656627918f50737
|
| 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": 49.
|
| 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,
|
|
@@ -11546,6 +11546,24 @@
|
|
| 11546 |
"mean_token_accuracy": 0.6451392889022827,
|
| 11547 |
"num_tokens": 23378793.0,
|
| 11548 |
"step": 6410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11549 |
}
|
| 11550 |
],
|
| 11551 |
"logging_steps": 5,
|
|
@@ -11565,7 +11583,7 @@
|
|
| 11565 |
"attributes": {}
|
| 11566 |
}
|
| 11567 |
},
|
| 11568 |
-
"total_flos": 1.
|
| 11569 |
"train_batch_size": 4,
|
| 11570 |
"trial_name": null,
|
| 11571 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11546 |
"mean_token_accuracy": 0.6451392889022827,
|
| 11547 |
"num_tokens": 23378793.0,
|
| 11548 |
"step": 6410
|
| 11549 |
+
},
|
| 11550 |
+
{
|
| 11551 |
+
"epoch": 49.34615384615385,
|
| 11552 |
+
"grad_norm": 0.0,
|
| 11553 |
+
"learning_rate": 1.793e-05,
|
| 11554 |
+
"loss": 1.7621,
|
| 11555 |
+
"mean_token_accuracy": 0.6497738718986511,
|
| 11556 |
+
"num_tokens": 23396781.0,
|
| 11557 |
+
"step": 6415
|
| 11558 |
+
},
|
| 11559 |
+
{
|
| 11560 |
+
"epoch": 49.38461538461539,
|
| 11561 |
+
"grad_norm": 0.0,
|
| 11562 |
+
"learning_rate": 1.7905e-05,
|
| 11563 |
+
"loss": 1.7673,
|
| 11564 |
+
"mean_token_accuracy": 0.6516094326972961,
|
| 11565 |
+
"num_tokens": 23413811.0,
|
| 11566 |
+
"step": 6420
|
| 11567 |
}
|
| 11568 |
],
|
| 11569 |
"logging_steps": 5,
|
|
|
|
| 11583 |
"attributes": {}
|
| 11584 |
}
|
| 11585 |
},
|
| 11586 |
+
"total_flos": 1.18687538837717e+18,
|
| 11587 |
"train_batch_size": 4,
|
| 11588 |
"trial_name": null,
|
| 11589 |
"trial_params": null
|