Training in progress, step 5870, 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:fd833be88a5153c2af3e7d9ec76bcdf3bb0f61688e17955c9bae001550ec3d5e
|
| 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 sha256:7cfc88c683ce06fc6e51c056279242f7df7cea4a7dc385aa5853e904eccfad67
|
| 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:d50169c1f37417a68ab0ed0ef24691fbd371ac1ab2d5d84a208b09c082f20e31
|
| 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": 45.
|
| 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,
|
|
@@ -10556,6 +10556,24 @@
|
|
| 10556 |
"mean_token_accuracy": 0.6628474831581116,
|
| 10557 |
"num_tokens": 21371719.0,
|
| 10558 |
"step": 5860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10559 |
}
|
| 10560 |
],
|
| 10561 |
"logging_steps": 5,
|
|
@@ -10575,7 +10593,7 @@
|
|
| 10575 |
"attributes": {}
|
| 10576 |
}
|
| 10577 |
},
|
| 10578 |
-
"total_flos": 1.
|
| 10579 |
"train_batch_size": 4,
|
| 10580 |
"trial_name": null,
|
| 10581 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 45.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10556 |
"mean_token_accuracy": 0.6628474831581116,
|
| 10557 |
"num_tokens": 21371719.0,
|
| 10558 |
"step": 5860
|
| 10559 |
+
},
|
| 10560 |
+
{
|
| 10561 |
+
"epoch": 45.11538461538461,
|
| 10562 |
+
"grad_norm": 0.0,
|
| 10563 |
+
"learning_rate": 2.0680000000000002e-05,
|
| 10564 |
+
"loss": 1.7366,
|
| 10565 |
+
"mean_token_accuracy": 0.6500916868448258,
|
| 10566 |
+
"num_tokens": 21390734.0,
|
| 10567 |
+
"step": 5865
|
| 10568 |
+
},
|
| 10569 |
+
{
|
| 10570 |
+
"epoch": 45.15384615384615,
|
| 10571 |
+
"grad_norm": 0.0,
|
| 10572 |
+
"learning_rate": 2.0655e-05,
|
| 10573 |
+
"loss": 1.7111,
|
| 10574 |
+
"mean_token_accuracy": 0.6544335097074508,
|
| 10575 |
+
"num_tokens": 21409214.0,
|
| 10576 |
+
"step": 5870
|
| 10577 |
}
|
| 10578 |
],
|
| 10579 |
"logging_steps": 5,
|
|
|
|
| 10593 |
"attributes": {}
|
| 10594 |
}
|
| 10595 |
},
|
| 10596 |
+
"total_flos": 1.0849024985083085e+18,
|
| 10597 |
"train_batch_size": 4,
|
| 10598 |
"trial_name": null,
|
| 10599 |
"trial_params": null
|