Training in progress, step 6940, 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:b6176a03925eb69d564c3f23ddaebc0c0a88369ae1514eb76cf2d09a54c7d0cc
|
| 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 sha256:9ca3858d1a9fd66baedc91566a2c273c1057dcb8c47f518928f9f3e4f852171d
|
| 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 sha256:8fb2c8c23de4d5ba94be02cd4456b3d20e90d516c090235c2011db7feac94378
|
| 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": 53.
|
| 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,
|
|
@@ -12482,6 +12482,24 @@
|
|
| 12482 |
"mean_token_accuracy": 0.6471881836652755,
|
| 12483 |
"num_tokens": 25273909.0,
|
| 12484 |
"step": 6930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12485 |
}
|
| 12486 |
],
|
| 12487 |
"logging_steps": 5,
|
|
@@ -12501,7 +12519,7 @@
|
|
| 12501 |
"attributes": {}
|
| 12502 |
}
|
| 12503 |
},
|
| 12504 |
-
"total_flos": 1.
|
| 12505 |
"train_batch_size": 4,
|
| 12506 |
"trial_name": null,
|
| 12507 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 53.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12482 |
"mean_token_accuracy": 0.6471881836652755,
|
| 12483 |
"num_tokens": 25273909.0,
|
| 12484 |
"step": 6930
|
| 12485 |
+
},
|
| 12486 |
+
{
|
| 12487 |
+
"epoch": 53.34615384615385,
|
| 12488 |
+
"grad_norm": 0.0,
|
| 12489 |
+
"learning_rate": 1.533e-05,
|
| 12490 |
+
"loss": 1.7417,
|
| 12491 |
+
"mean_token_accuracy": 0.6538171172142029,
|
| 12492 |
+
"num_tokens": 25291903.0,
|
| 12493 |
+
"step": 6935
|
| 12494 |
+
},
|
| 12495 |
+
{
|
| 12496 |
+
"epoch": 53.38461538461539,
|
| 12497 |
+
"grad_norm": 0.0,
|
| 12498 |
+
"learning_rate": 1.5305e-05,
|
| 12499 |
+
"loss": 1.7168,
|
| 12500 |
+
"mean_token_accuracy": 0.654968672990799,
|
| 12501 |
+
"num_tokens": 25310540.0,
|
| 12502 |
+
"step": 6940
|
| 12503 |
}
|
| 12504 |
],
|
| 12505 |
"logging_steps": 5,
|
|
|
|
| 12519 |
"attributes": {}
|
| 12520 |
}
|
| 12521 |
},
|
| 12522 |
+
"total_flos": 1.283296724176896e+18,
|
| 12523 |
"train_batch_size": 4,
|
| 12524 |
"trial_name": null,
|
| 12525 |
"trial_params": null
|