Training in progress, step 4200, 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:b139c3af7ba25aef920f54fe7349bd8e4882124b95388a03b26c6f01d1cc53d8
|
| 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 sha256:3f6ce14dfda069f0216d6e6498d44b5e58fb7be4666fb787fa22d1ab07e2c201
|
| 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 sha256:8e17cb9a719cb47517f3b78be26174aeb22328ea945d77f7861ca9082c2f1a3b
|
| 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": 32.
|
| 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,
|
|
@@ -7550,6 +7550,24 @@
|
|
| 7550 |
"mean_token_accuracy": 0.6341224372386932,
|
| 7551 |
"num_tokens": 15281071.0,
|
| 7552 |
"step": 4190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7553 |
}
|
| 7554 |
],
|
| 7555 |
"logging_steps": 5,
|
|
@@ -7569,7 +7587,7 @@
|
|
| 7569 |
"attributes": {}
|
| 7570 |
}
|
| 7571 |
},
|
| 7572 |
-
"total_flos": 7.
|
| 7573 |
"train_batch_size": 4,
|
| 7574 |
"trial_name": null,
|
| 7575 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7550 |
"mean_token_accuracy": 0.6341224372386932,
|
| 7551 |
"num_tokens": 15281071.0,
|
| 7552 |
"step": 4190
|
| 7553 |
+
},
|
| 7554 |
+
{
|
| 7555 |
+
"epoch": 32.26923076923077,
|
| 7556 |
+
"grad_norm": 0.0,
|
| 7557 |
+
"learning_rate": 2.903e-05,
|
| 7558 |
+
"loss": 1.7784,
|
| 7559 |
+
"mean_token_accuracy": 0.6433619648218155,
|
| 7560 |
+
"num_tokens": 15299529.0,
|
| 7561 |
+
"step": 4195
|
| 7562 |
+
},
|
| 7563 |
+
{
|
| 7564 |
+
"epoch": 32.30769230769231,
|
| 7565 |
+
"grad_norm": 0.0,
|
| 7566 |
+
"learning_rate": 2.9004999999999998e-05,
|
| 7567 |
+
"loss": 1.7868,
|
| 7568 |
+
"mean_token_accuracy": 0.642947056889534,
|
| 7569 |
+
"num_tokens": 15317120.0,
|
| 7570 |
+
"step": 4200
|
| 7571 |
}
|
| 7572 |
],
|
| 7573 |
"logging_steps": 5,
|
|
|
|
| 7587 |
"attributes": {}
|
| 7588 |
}
|
| 7589 |
},
|
| 7590 |
+
"total_flos": 7.763411087917056e+17,
|
| 7591 |
"train_batch_size": 4,
|
| 7592 |
"trial_name": null,
|
| 7593 |
"trial_params": null
|