Training in progress, step 2580, 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 sha256:90bb7cf5b29ef203e712e496ebf7197d7101a98e0c3a879c0583b2a2b4f2cdb2
|
| 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 sha256:3171765a543b644d5c034c75f1041d503aafaec1b63f9b09187bab17600e7d7e
|
| 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:b9fa0b7c37aa2263926594b23b2fdac907e882d475cdb6ed500061229da43b26
|
| 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": 19.
|
| 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,
|
|
@@ -4634,6 +4634,24 @@
|
|
| 4634 |
"mean_token_accuracy": 0.6545383244752884,
|
| 4635 |
"num_tokens": 9373351.0,
|
| 4636 |
"step": 2570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4637 |
}
|
| 4638 |
],
|
| 4639 |
"logging_steps": 5,
|
|
@@ -4653,7 +4671,7 @@
|
|
| 4653 |
"attributes": {}
|
| 4654 |
}
|
| 4655 |
},
|
| 4656 |
-
"total_flos": 4.
|
| 4657 |
"train_batch_size": 4,
|
| 4658 |
"trial_name": null,
|
| 4659 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4634 |
"mean_token_accuracy": 0.6545383244752884,
|
| 4635 |
"num_tokens": 9373351.0,
|
| 4636 |
"step": 2570
|
| 4637 |
+
},
|
| 4638 |
+
{
|
| 4639 |
+
"epoch": 19.807692307692307,
|
| 4640 |
+
"grad_norm": 0.0,
|
| 4641 |
+
"learning_rate": 3.7130000000000005e-05,
|
| 4642 |
+
"loss": 1.7363,
|
| 4643 |
+
"mean_token_accuracy": 0.6508906304836273,
|
| 4644 |
+
"num_tokens": 9391237.0,
|
| 4645 |
+
"step": 2575
|
| 4646 |
+
},
|
| 4647 |
+
{
|
| 4648 |
+
"epoch": 19.846153846153847,
|
| 4649 |
+
"grad_norm": 0.0,
|
| 4650 |
+
"learning_rate": 3.7105e-05,
|
| 4651 |
+
"loss": 1.6926,
|
| 4652 |
+
"mean_token_accuracy": 0.6579229325056076,
|
| 4653 |
+
"num_tokens": 9409658.0,
|
| 4654 |
+
"step": 2580
|
| 4655 |
}
|
| 4656 |
],
|
| 4657 |
"logging_steps": 5,
|
|
|
|
| 4671 |
"attributes": {}
|
| 4672 |
}
|
| 4673 |
},
|
| 4674 |
+
"total_flos": 4.7697001483862016e+17,
|
| 4675 |
"train_batch_size": 4,
|
| 4676 |
"trial_name": null,
|
| 4677 |
"trial_params": null
|