Training in progress, step 8090, 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 sha256:7a45f7a96793c601fecd2bc60f3c912ed08970437b83115cd8246f07ac159023
|
| 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:e36962cf5cbbbb1e16596da90c24ce8f512a77a6a5daeb2be1b0d8f2c5d8acd7
|
| 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 sha256:90d543d57624dee48f9d9a41507eae49f5a2dccaf63ca6db368c2bc01cec6633
|
| 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": 62.
|
| 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,
|
|
@@ -14552,6 +14552,24 @@
|
|
| 14552 |
"mean_token_accuracy": 0.6442840725183487,
|
| 14553 |
"num_tokens": 29466357.0,
|
| 14554 |
"step": 8080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14555 |
}
|
| 14556 |
],
|
| 14557 |
"logging_steps": 5,
|
|
@@ -14571,7 +14589,7 @@
|
|
| 14571 |
"attributes": {}
|
| 14572 |
}
|
| 14573 |
},
|
| 14574 |
-
"total_flos": 1.
|
| 14575 |
"train_batch_size": 4,
|
| 14576 |
"trial_name": null,
|
| 14577 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14552 |
"mean_token_accuracy": 0.6442840725183487,
|
| 14553 |
"num_tokens": 29466357.0,
|
| 14554 |
"step": 8080
|
| 14555 |
+
},
|
| 14556 |
+
{
|
| 14557 |
+
"epoch": 62.19230769230769,
|
| 14558 |
+
"grad_norm": 0.0,
|
| 14559 |
+
"learning_rate": 9.58e-06,
|
| 14560 |
+
"loss": 1.7854,
|
| 14561 |
+
"mean_token_accuracy": 0.6450077176094056,
|
| 14562 |
+
"num_tokens": 29484406.0,
|
| 14563 |
+
"step": 8085
|
| 14564 |
+
},
|
| 14565 |
+
{
|
| 14566 |
+
"epoch": 62.23076923076923,
|
| 14567 |
+
"grad_norm": 0.0,
|
| 14568 |
+
"learning_rate": 9.555e-06,
|
| 14569 |
+
"loss": 1.6738,
|
| 14570 |
+
"mean_token_accuracy": 0.6603300988674163,
|
| 14571 |
+
"num_tokens": 29503619.0,
|
| 14572 |
+
"step": 8090
|
| 14573 |
}
|
| 14574 |
],
|
| 14575 |
"logging_steps": 5,
|
|
|
|
| 14589 |
"attributes": {}
|
| 14590 |
}
|
| 14591 |
},
|
| 14592 |
+
"total_flos": 1.4959104162870067e+18,
|
| 14593 |
"train_batch_size": 4,
|
| 14594 |
"trial_name": null,
|
| 14595 |
"trial_params": null
|