Training in progress, step 1890, 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:c9a68b9429a53a2549e8c7d2696736ec9bf45b3c0d7ebaaee390420137974753
|
| 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 sha256:3b7e2b791ac31f1d172de2f53f507dd0c370316b52472ecdbbc6f4c4bc977cd8
|
| 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 sha256:90115e9448be81f6140ec80813cb244c76159679c2d4565d04257fd501b6661a
|
| 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,
|
|
@@ -3392,6 +3392,24 @@
|
|
| 3392 |
"mean_token_accuracy": 0.6461942523717881,
|
| 3393 |
"num_tokens": 6857208.0,
|
| 3394 |
"step": 1880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3395 |
}
|
| 3396 |
],
|
| 3397 |
"logging_steps": 5,
|
|
@@ -3411,7 +3429,7 @@
|
|
| 3411 |
"attributes": {}
|
| 3412 |
}
|
| 3413 |
},
|
| 3414 |
-
"total_flos": 3.
|
| 3415 |
"train_batch_size": 4,
|
| 3416 |
"trial_name": null,
|
| 3417 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3392 |
"mean_token_accuracy": 0.6461942523717881,
|
| 3393 |
"num_tokens": 6857208.0,
|
| 3394 |
"step": 1880
|
| 3395 |
+
},
|
| 3396 |
+
{
|
| 3397 |
+
"epoch": 14.5,
|
| 3398 |
+
"grad_norm": 0.0,
|
| 3399 |
+
"learning_rate": 4.058e-05,
|
| 3400 |
+
"loss": 1.7463,
|
| 3401 |
+
"mean_token_accuracy": 0.6480780661106109,
|
| 3402 |
+
"num_tokens": 6875091.0,
|
| 3403 |
+
"step": 1885
|
| 3404 |
+
},
|
| 3405 |
+
{
|
| 3406 |
+
"epoch": 14.538461538461538,
|
| 3407 |
+
"grad_norm": 0.0,
|
| 3408 |
+
"learning_rate": 4.055500000000001e-05,
|
| 3409 |
+
"loss": 1.745,
|
| 3410 |
+
"mean_token_accuracy": 0.6500824391841888,
|
| 3411 |
+
"num_tokens": 6893171.0,
|
| 3412 |
+
"step": 1890
|
| 3413 |
}
|
| 3414 |
],
|
| 3415 |
"logging_steps": 5,
|
|
|
|
| 3429 |
"attributes": {}
|
| 3430 |
}
|
| 3431 |
},
|
| 3432 |
+
"total_flos": 3.493072942247117e+17,
|
| 3433 |
"train_batch_size": 4,
|
| 3434 |
"trial_name": null,
|
| 3435 |
"trial_params": null
|