Training in progress, step 3610, 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 sha256:79e6da1d83a85be90be96bee4e0b816dda7154c07c22c658ebe407720dc6d5af
|
| 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 sha256:1ff7c163975b8f3171d7f0750faf4432020136cd100b9df8d74ea22bdc454c1f
|
| 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 sha256:906f78a0666e3bd992680cfd6395e030d8b8578fa3bf6b54b6e8e1b471fe2886
|
| 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": 27.
|
| 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,
|
|
@@ -6488,6 +6488,24 @@
|
|
| 6488 |
"mean_token_accuracy": 0.6594361692667008,
|
| 6489 |
"num_tokens": 13128968.0,
|
| 6490 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6491 |
}
|
| 6492 |
],
|
| 6493 |
"logging_steps": 5,
|
|
@@ -6507,7 +6525,7 @@
|
|
| 6507 |
"attributes": {}
|
| 6508 |
}
|
| 6509 |
},
|
| 6510 |
-
"total_flos": 6.
|
| 6511 |
"train_batch_size": 4,
|
| 6512 |
"trial_name": null,
|
| 6513 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6488 |
"mean_token_accuracy": 0.6594361692667008,
|
| 6489 |
"num_tokens": 13128968.0,
|
| 6490 |
"step": 3600
|
| 6491 |
+
},
|
| 6492 |
+
{
|
| 6493 |
+
"epoch": 27.73076923076923,
|
| 6494 |
+
"grad_norm": 0.0,
|
| 6495 |
+
"learning_rate": 3.198e-05,
|
| 6496 |
+
"loss": 1.6991,
|
| 6497 |
+
"mean_token_accuracy": 0.6626447290182114,
|
| 6498 |
+
"num_tokens": 13147908.0,
|
| 6499 |
+
"step": 3605
|
| 6500 |
+
},
|
| 6501 |
+
{
|
| 6502 |
+
"epoch": 27.76923076923077,
|
| 6503 |
+
"grad_norm": 0.0,
|
| 6504 |
+
"learning_rate": 3.1955e-05,
|
| 6505 |
+
"loss": 1.7859,
|
| 6506 |
+
"mean_token_accuracy": 0.6439048200845718,
|
| 6507 |
+
"num_tokens": 13165594.0,
|
| 6508 |
+
"step": 3610
|
| 6509 |
}
|
| 6510 |
],
|
| 6511 |
"logging_steps": 5,
|
|
|
|
| 6525 |
"attributes": {}
|
| 6526 |
}
|
| 6527 |
},
|
| 6528 |
+
"total_flos": 6.67023889513513e+17,
|
| 6529 |
"train_batch_size": 4,
|
| 6530 |
"trial_name": null,
|
| 6531 |
"trial_params": null
|