Training in progress, step 9380, 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 sha256:2c2de650dded1c11aef2a505b1709893f298b5753af92b095325815f1dbee0b5
|
| 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:ff2cf4d3651d89af65f28ba58f1842eabbad64a073789ecd9dec3a505d9e3d73
|
| 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 sha256:18145bb876517b912b47b3e83a2c1a9d205590f22e6b7a0093b8dae751488fa7
|
| 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": 72.
|
| 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,
|
|
@@ -16874,6 +16874,24 @@
|
|
| 16874 |
"mean_token_accuracy": 0.6482025504112243,
|
| 16875 |
"num_tokens": 34172147.0,
|
| 16876 |
"step": 9370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16877 |
}
|
| 16878 |
],
|
| 16879 |
"logging_steps": 5,
|
|
@@ -16893,7 +16911,7 @@
|
|
| 16893 |
"attributes": {}
|
| 16894 |
}
|
| 16895 |
},
|
| 16896 |
-
"total_flos": 1.
|
| 16897 |
"train_batch_size": 4,
|
| 16898 |
"trial_name": null,
|
| 16899 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16874 |
"mean_token_accuracy": 0.6482025504112243,
|
| 16875 |
"num_tokens": 34172147.0,
|
| 16876 |
"step": 9370
|
| 16877 |
+
},
|
| 16878 |
+
{
|
| 16879 |
+
"epoch": 72.11538461538461,
|
| 16880 |
+
"grad_norm": 0.0,
|
| 16881 |
+
"learning_rate": 3.13e-06,
|
| 16882 |
+
"loss": 1.7281,
|
| 16883 |
+
"mean_token_accuracy": 0.6510056018829345,
|
| 16884 |
+
"num_tokens": 34191430.0,
|
| 16885 |
+
"step": 9375
|
| 16886 |
+
},
|
| 16887 |
+
{
|
| 16888 |
+
"epoch": 72.15384615384616,
|
| 16889 |
+
"grad_norm": 0.0,
|
| 16890 |
+
"learning_rate": 3.1050000000000003e-06,
|
| 16891 |
+
"loss": 1.725,
|
| 16892 |
+
"mean_token_accuracy": 0.6562888383865356,
|
| 16893 |
+
"num_tokens": 34209348.0,
|
| 16894 |
+
"step": 9380
|
| 16895 |
}
|
| 16896 |
],
|
| 16897 |
"logging_steps": 5,
|
|
|
|
| 16911 |
"attributes": {}
|
| 16912 |
}
|
| 16913 |
},
|
| 16914 |
+
"total_flos": 1.734659473426514e+18,
|
| 16915 |
"train_batch_size": 4,
|
| 16916 |
"trial_name": null,
|
| 16917 |
"trial_params": null
|