Training in progress, step 5830, 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:b6e862bb2578e57999382b1455b3dd38fd79ee9c7caacfec05e6434ee3aa5573
|
| 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:f99b5c20581dbd3cd6cc77ccc8155666fe328c3b5ab13f9a3cef9aa7feb23846
|
| 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 sha256:10065bd1ef3d93be6628131f751d718e1d95309dbf8a6cbe635ffeaa43daee18
|
| 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": 44.
|
| 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,
|
|
@@ -10484,6 +10484,24 @@
|
|
| 10484 |
"mean_token_accuracy": 0.6526555448770524,
|
| 10485 |
"num_tokens": 21225855.0,
|
| 10486 |
"step": 5820
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10487 |
}
|
| 10488 |
],
|
| 10489 |
"logging_steps": 5,
|
|
@@ -10503,7 +10521,7 @@
|
|
| 10503 |
"attributes": {}
|
| 10504 |
}
|
| 10505 |
},
|
| 10506 |
-
"total_flos": 1.
|
| 10507 |
"train_batch_size": 4,
|
| 10508 |
"trial_name": null,
|
| 10509 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5830,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10484 |
"mean_token_accuracy": 0.6526555448770524,
|
| 10485 |
"num_tokens": 21225855.0,
|
| 10486 |
"step": 5820
|
| 10487 |
+
},
|
| 10488 |
+
{
|
| 10489 |
+
"epoch": 44.80769230769231,
|
| 10490 |
+
"grad_norm": 0.0,
|
| 10491 |
+
"learning_rate": 2.0880000000000003e-05,
|
| 10492 |
+
"loss": 1.7651,
|
| 10493 |
+
"mean_token_accuracy": 0.6445731610059738,
|
| 10494 |
+
"num_tokens": 21244188.0,
|
| 10495 |
+
"step": 5825
|
| 10496 |
+
},
|
| 10497 |
+
{
|
| 10498 |
+
"epoch": 44.84615384615385,
|
| 10499 |
+
"grad_norm": 0.0,
|
| 10500 |
+
"learning_rate": 2.0855000000000003e-05,
|
| 10501 |
+
"loss": 1.7282,
|
| 10502 |
+
"mean_token_accuracy": 0.6482422709465027,
|
| 10503 |
+
"num_tokens": 21262701.0,
|
| 10504 |
+
"step": 5830
|
| 10505 |
}
|
| 10506 |
],
|
| 10507 |
"logging_steps": 5,
|
|
|
|
| 10521 |
"attributes": {}
|
| 10522 |
}
|
| 10523 |
},
|
| 10524 |
+
"total_flos": 1.077400501406761e+18,
|
| 10525 |
"train_batch_size": 4,
|
| 10526 |
"trial_name": null,
|
| 10527 |
"trial_params": null
|