Training in progress, step 4900, 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 sha256:831e5c604cf01e3ab1999b5a7b505df8728c74d60e2e4988fd1b18310fba60d3
|
| 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:cff87507ea8cfcd613c0fc0e0118a56c1a6c693edc6aa799b80281149e304b6e
|
| 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 sha256:2b3fda08d2118fb71ac93436a955d1b35b185d1af28e907a9bc65f372f4910db
|
| 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": 37.
|
| 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,
|
|
@@ -8810,6 +8810,24 @@
|
|
| 8810 |
"mean_token_accuracy": 0.641741332411766,
|
| 8811 |
"num_tokens": 17833805.0,
|
| 8812 |
"step": 4890
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8813 |
}
|
| 8814 |
],
|
| 8815 |
"logging_steps": 5,
|
|
@@ -8829,7 +8847,7 @@
|
|
| 8829 |
"attributes": {}
|
| 8830 |
}
|
| 8831 |
},
|
| 8832 |
-
"total_flos": 9.
|
| 8833 |
"train_batch_size": 4,
|
| 8834 |
"trial_name": null,
|
| 8835 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4900,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8810 |
"mean_token_accuracy": 0.641741332411766,
|
| 8811 |
"num_tokens": 17833805.0,
|
| 8812 |
"step": 4890
|
| 8813 |
+
},
|
| 8814 |
+
{
|
| 8815 |
+
"epoch": 37.65384615384615,
|
| 8816 |
+
"grad_norm": 0.0,
|
| 8817 |
+
"learning_rate": 2.5530000000000005e-05,
|
| 8818 |
+
"loss": 1.7906,
|
| 8819 |
+
"mean_token_accuracy": 0.6406534284353256,
|
| 8820 |
+
"num_tokens": 17851648.0,
|
| 8821 |
+
"step": 4895
|
| 8822 |
+
},
|
| 8823 |
+
{
|
| 8824 |
+
"epoch": 37.69230769230769,
|
| 8825 |
+
"grad_norm": 0.0,
|
| 8826 |
+
"learning_rate": 2.5505e-05,
|
| 8827 |
+
"loss": 1.7484,
|
| 8828 |
+
"mean_token_accuracy": 0.650345778465271,
|
| 8829 |
+
"num_tokens": 17869722.0,
|
| 8830 |
+
"step": 4900
|
| 8831 |
}
|
| 8832 |
],
|
| 8833 |
"logging_steps": 5,
|
|
|
|
| 8847 |
"attributes": {}
|
| 8848 |
}
|
| 8849 |
},
|
| 8850 |
+
"total_flos": 9.055792360946074e+17,
|
| 8851 |
"train_batch_size": 4,
|
| 8852 |
"trial_name": null,
|
| 8853 |
"trial_params": null
|