Training in progress, step 1910, 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 sha256:6bbae71a191aaa5ff1a40fe41db8a2f1ba8967f65dbf36f56cda024b81c9fba5
|
| 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 sha256:9bb2cbbcc20dbe000bdcfdbdfd89192b36d71a80bc4ca90c8168557e300f2eaa
|
| 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 sha256:0547c235035755408a965992fab8cee37ca3bf04225dec07389bdaea11fd1ce8
|
| 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": 14.
|
| 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,
|
|
@@ -3428,6 +3428,24 @@
|
|
| 3428 |
"mean_token_accuracy": 0.6511125653982163,
|
| 3429 |
"num_tokens": 6930030.0,
|
| 3430 |
"step": 1900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3431 |
}
|
| 3432 |
],
|
| 3433 |
"logging_steps": 5,
|
|
@@ -3447,7 +3465,7 @@
|
|
| 3447 |
"attributes": {}
|
| 3448 |
}
|
| 3449 |
},
|
| 3450 |
-
"total_flos": 3.
|
| 3451 |
"train_batch_size": 4,
|
| 3452 |
"trial_name": null,
|
| 3453 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1910,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3428 |
"mean_token_accuracy": 0.6511125653982163,
|
| 3429 |
"num_tokens": 6930030.0,
|
| 3430 |
"step": 1900
|
| 3431 |
+
},
|
| 3432 |
+
{
|
| 3433 |
+
"epoch": 14.653846153846153,
|
| 3434 |
+
"grad_norm": 0.0,
|
| 3435 |
+
"learning_rate": 4.048e-05,
|
| 3436 |
+
"loss": 1.738,
|
| 3437 |
+
"mean_token_accuracy": 0.6520918369293213,
|
| 3438 |
+
"num_tokens": 6948110.0,
|
| 3439 |
+
"step": 1905
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 14.692307692307692,
|
| 3443 |
+
"grad_norm": 0.0,
|
| 3444 |
+
"learning_rate": 4.0455000000000005e-05,
|
| 3445 |
+
"loss": 1.764,
|
| 3446 |
+
"mean_token_accuracy": 0.6516493141651154,
|
| 3447 |
+
"num_tokens": 6966319.0,
|
| 3448 |
+
"step": 1910
|
| 3449 |
}
|
| 3450 |
],
|
| 3451 |
"logging_steps": 5,
|
|
|
|
| 3465 |
"attributes": {}
|
| 3466 |
}
|
| 3467 |
},
|
| 3468 |
+
"total_flos": 3.530544820759757e+17,
|
| 3469 |
"train_batch_size": 4,
|
| 3470 |
"trial_name": null,
|
| 3471 |
"trial_params": null
|