Training in progress, step 6500, 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:ea4f789d1373e25c37d3e5b8bf3c7269c58dfa8b1197dc2887d18dea0bbff5d9
|
| 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 sha256:598a18e3cf3260992e7de76a9806b331dd8209cee0a88161a1156070e42bc134
|
| 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 sha256:29b587cdda06d7add84aaa2017ad50439aa51d1e0c25349381d257ef96b0357a
|
| 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":
|
| 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,
|
|
@@ -11690,6 +11690,24 @@
|
|
| 11690 |
"mean_token_accuracy": 0.6560462713241577,
|
| 11691 |
"num_tokens": 23669731.0,
|
| 11692 |
"step": 6490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11693 |
}
|
| 11694 |
],
|
| 11695 |
"logging_steps": 5,
|
|
@@ -11709,7 +11727,7 @@
|
|
| 11709 |
"attributes": {}
|
| 11710 |
}
|
| 11711 |
},
|
| 11712 |
-
"total_flos": 1.
|
| 11713 |
"train_batch_size": 4,
|
| 11714 |
"trial_name": null,
|
| 11715 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 50.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11690 |
"mean_token_accuracy": 0.6560462713241577,
|
| 11691 |
"num_tokens": 23669731.0,
|
| 11692 |
"step": 6490
|
| 11693 |
+
},
|
| 11694 |
+
{
|
| 11695 |
+
"epoch": 49.96153846153846,
|
| 11696 |
+
"grad_norm": 0.0,
|
| 11697 |
+
"learning_rate": 1.7530000000000003e-05,
|
| 11698 |
+
"loss": 1.817,
|
| 11699 |
+
"mean_token_accuracy": 0.6334926426410675,
|
| 11700 |
+
"num_tokens": 23687316.0,
|
| 11701 |
+
"step": 6495
|
| 11702 |
+
},
|
| 11703 |
+
{
|
| 11704 |
+
"epoch": 50.0,
|
| 11705 |
+
"grad_norm": 0.0,
|
| 11706 |
+
"learning_rate": 1.7505000000000003e-05,
|
| 11707 |
+
"loss": 1.7466,
|
| 11708 |
+
"mean_token_accuracy": 0.6494122266769409,
|
| 11709 |
+
"num_tokens": 23705250.0,
|
| 11710 |
+
"step": 6500
|
| 11711 |
}
|
| 11712 |
],
|
| 11713 |
"logging_steps": 5,
|
|
|
|
| 11727 |
"attributes": {}
|
| 11728 |
}
|
| 11729 |
},
|
| 11730 |
+
"total_flos": 1.2017666493864346e+18,
|
| 11731 |
"train_batch_size": 4,
|
| 11732 |
"trial_name": null,
|
| 11733 |
"trial_params": null
|