Training in progress, step 4310, 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:c33f99457dd48542d8c26a3a166f74e6c99d05aebd12476f6aad22b9e6181164
|
| 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:b833c53902cf9a99c76596ec13ab328d15c68da8f391cd284446216baa0f328f
|
| 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 sha256:26a1083c5416b7381da0ae6010993b12f2bfbe337275b2fa8e73ee8c1aa73b11
|
| 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": 33.
|
| 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,
|
|
@@ -7748,6 +7748,24 @@
|
|
| 7748 |
"mean_token_accuracy": 0.6503149479627609,
|
| 7749 |
"num_tokens": 15682167.0,
|
| 7750 |
"step": 4300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7751 |
}
|
| 7752 |
],
|
| 7753 |
"logging_steps": 5,
|
|
@@ -7767,7 +7785,7 @@
|
|
| 7767 |
"attributes": {}
|
| 7768 |
}
|
| 7769 |
},
|
| 7770 |
-
"total_flos": 7.
|
| 7771 |
"train_batch_size": 4,
|
| 7772 |
"trial_name": null,
|
| 7773 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7748 |
"mean_token_accuracy": 0.6503149479627609,
|
| 7749 |
"num_tokens": 15682167.0,
|
| 7750 |
"step": 4300
|
| 7751 |
+
},
|
| 7752 |
+
{
|
| 7753 |
+
"epoch": 33.11538461538461,
|
| 7754 |
+
"grad_norm": 0.0,
|
| 7755 |
+
"learning_rate": 2.8480000000000002e-05,
|
| 7756 |
+
"loss": 1.7905,
|
| 7757 |
+
"mean_token_accuracy": 0.6410009592771531,
|
| 7758 |
+
"num_tokens": 15699294.0,
|
| 7759 |
+
"step": 4305
|
| 7760 |
+
},
|
| 7761 |
+
{
|
| 7762 |
+
"epoch": 33.15384615384615,
|
| 7763 |
+
"grad_norm": 0.0,
|
| 7764 |
+
"learning_rate": 2.8455000000000005e-05,
|
| 7765 |
+
"loss": 1.7323,
|
| 7766 |
+
"mean_token_accuracy": 0.6517443567514419,
|
| 7767 |
+
"num_tokens": 15718054.0,
|
| 7768 |
+
"step": 4310
|
| 7769 |
}
|
| 7770 |
],
|
| 7771 |
"logging_steps": 5,
|
|
|
|
| 7785 |
"attributes": {}
|
| 7786 |
}
|
| 7787 |
},
|
| 7788 |
+
"total_flos": 7.965301947944141e+17,
|
| 7789 |
"train_batch_size": 4,
|
| 7790 |
"trial_name": null,
|
| 7791 |
"trial_params": null
|