Training in progress, step 9690, 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:eb3e4ff2921cbd64e66be93f1bd3ce7481933c6ae79a99b5ad280c0b06dac04d
|
| 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:d90522edd0540661499c0fa01bc0c4fb6b7a76df072610e992b0a5b3cf06583e
|
| 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:f626f5db9364bdc65381a0d55297162eb190db5f981ba63af178ada20ef4e866
|
| 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": 74.
|
| 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,
|
|
@@ -17432,6 +17432,24 @@
|
|
| 17432 |
"mean_token_accuracy": 0.6488740295171738,
|
| 17433 |
"num_tokens": 35301939.0,
|
| 17434 |
"step": 9680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17435 |
}
|
| 17436 |
],
|
| 17437 |
"logging_steps": 5,
|
|
@@ -17451,7 +17469,7 @@
|
|
| 17451 |
"attributes": {}
|
| 17452 |
}
|
| 17453 |
},
|
| 17454 |
-
"total_flos": 1.
|
| 17455 |
"train_batch_size": 4,
|
| 17456 |
"trial_name": null,
|
| 17457 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 74.53846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17432 |
"mean_token_accuracy": 0.6488740295171738,
|
| 17433 |
"num_tokens": 35301939.0,
|
| 17434 |
"step": 9680
|
| 17435 |
+
},
|
| 17436 |
+
{
|
| 17437 |
+
"epoch": 74.5,
|
| 17438 |
+
"grad_norm": 0.0,
|
| 17439 |
+
"learning_rate": 1.5800000000000003e-06,
|
| 17440 |
+
"loss": 1.6961,
|
| 17441 |
+
"mean_token_accuracy": 0.6596014022827148,
|
| 17442 |
+
"num_tokens": 35320606.0,
|
| 17443 |
+
"step": 9685
|
| 17444 |
+
},
|
| 17445 |
+
{
|
| 17446 |
+
"epoch": 74.53846153846153,
|
| 17447 |
+
"grad_norm": 0.0,
|
| 17448 |
+
"learning_rate": 1.555e-06,
|
| 17449 |
+
"loss": 1.7047,
|
| 17450 |
+
"mean_token_accuracy": 0.6595968753099442,
|
| 17451 |
+
"num_tokens": 35338994.0,
|
| 17452 |
+
"step": 9690
|
| 17453 |
}
|
| 17454 |
],
|
| 17455 |
"logging_steps": 5,
|
|
|
|
| 17469 |
"attributes": {}
|
| 17470 |
}
|
| 17471 |
},
|
| 17472 |
+
"total_flos": 1.7920738539277517e+18,
|
| 17473 |
"train_batch_size": 4,
|
| 17474 |
"trial_name": null,
|
| 17475 |
"trial_params": null
|