Training in progress, step 5290, 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 sha256:2f29b44dab115cae3941a86ed5c564c63def82a5cb9bb6ca4778cd242fa4ad1e
|
| 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 sha256:7d6468e24f610ab8187f09d807850bf6f6f0b1abf4395c0b690a1b1d95c1cfd3
|
| 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:bdb933e98db4a1d9853de935d5996834f335dca3927c7c88868feb5e4d0250dc
|
| 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": 40.
|
| 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,
|
|
@@ -9512,6 +9512,24 @@
|
|
| 9512 |
"mean_token_accuracy": 0.664988386631012,
|
| 9513 |
"num_tokens": 19254738.0,
|
| 9514 |
"step": 5280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9515 |
}
|
| 9516 |
],
|
| 9517 |
"logging_steps": 5,
|
|
@@ -9531,7 +9549,7 @@
|
|
| 9531 |
"attributes": {}
|
| 9532 |
}
|
| 9533 |
},
|
| 9534 |
-
"total_flos": 9.
|
| 9535 |
"train_batch_size": 4,
|
| 9536 |
"trial_name": null,
|
| 9537 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9512 |
"mean_token_accuracy": 0.664988386631012,
|
| 9513 |
"num_tokens": 19254738.0,
|
| 9514 |
"step": 5280
|
| 9515 |
+
},
|
| 9516 |
+
{
|
| 9517 |
+
"epoch": 40.65384615384615,
|
| 9518 |
+
"grad_norm": 0.0,
|
| 9519 |
+
"learning_rate": 2.358e-05,
|
| 9520 |
+
"loss": 1.7453,
|
| 9521 |
+
"mean_token_accuracy": 0.6468230724334717,
|
| 9522 |
+
"num_tokens": 19273467.0,
|
| 9523 |
+
"step": 5285
|
| 9524 |
+
},
|
| 9525 |
+
{
|
| 9526 |
+
"epoch": 40.69230769230769,
|
| 9527 |
+
"grad_norm": 0.0,
|
| 9528 |
+
"learning_rate": 2.3555e-05,
|
| 9529 |
+
"loss": 1.7231,
|
| 9530 |
+
"mean_token_accuracy": 0.6521205425262451,
|
| 9531 |
+
"num_tokens": 19292138.0,
|
| 9532 |
+
"step": 5290
|
| 9533 |
}
|
| 9534 |
],
|
| 9535 |
"logging_steps": 5,
|
|
|
|
| 9549 |
"attributes": {}
|
| 9550 |
}
|
| 9551 |
},
|
| 9552 |
+
"total_flos": 9.775401680786227e+17,
|
| 9553 |
"train_batch_size": 4,
|
| 9554 |
"trial_name": null,
|
| 9555 |
"trial_params": null
|