Training in progress, step 4890, 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:e26e0d067a86fea4a8a425001c510091465cbb1de38ce0e74c862c6f47c9973d
|
| 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:d3dfb640973294cc8de14a5de68d203db9e8e07140701a4ee7588afe413830c4
|
| 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 sha256:88a0a41255532f9b3ff0fef626523371bc4d748c7bbf2976bdd977c10cd58d4a
|
| 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,
|
|
@@ -8792,6 +8792,24 @@
|
|
| 8792 |
"mean_token_accuracy": 0.6469813168048859,
|
| 8793 |
"num_tokens": 17796705.0,
|
| 8794 |
"step": 4880
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8795 |
}
|
| 8796 |
],
|
| 8797 |
"logging_steps": 5,
|
|
@@ -8811,7 +8829,7 @@
|
|
| 8811 |
"attributes": {}
|
| 8812 |
}
|
| 8813 |
},
|
| 8814 |
-
"total_flos": 9.
|
| 8815 |
"train_batch_size": 4,
|
| 8816 |
"trial_name": null,
|
| 8817 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 37.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4890,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8792 |
"mean_token_accuracy": 0.6469813168048859,
|
| 8793 |
"num_tokens": 17796705.0,
|
| 8794 |
"step": 4880
|
| 8795 |
+
},
|
| 8796 |
+
{
|
| 8797 |
+
"epoch": 37.57692307692308,
|
| 8798 |
+
"grad_norm": 0.0,
|
| 8799 |
+
"learning_rate": 2.5580000000000002e-05,
|
| 8800 |
+
"loss": 1.7045,
|
| 8801 |
+
"mean_token_accuracy": 0.6609047919511795,
|
| 8802 |
+
"num_tokens": 17815465.0,
|
| 8803 |
+
"step": 4885
|
| 8804 |
+
},
|
| 8805 |
+
{
|
| 8806 |
+
"epoch": 37.61538461538461,
|
| 8807 |
+
"grad_norm": 0.0,
|
| 8808 |
+
"learning_rate": 2.5555000000000002e-05,
|
| 8809 |
+
"loss": 1.7773,
|
| 8810 |
+
"mean_token_accuracy": 0.641741332411766,
|
| 8811 |
+
"num_tokens": 17833805.0,
|
| 8812 |
+
"step": 4890
|
| 8813 |
}
|
| 8814 |
],
|
| 8815 |
"logging_steps": 5,
|
|
|
|
| 8829 |
"attributes": {}
|
| 8830 |
}
|
| 8831 |
},
|
| 8832 |
+
"total_flos": 9.037466071887053e+17,
|
| 8833 |
"train_batch_size": 4,
|
| 8834 |
"trial_name": null,
|
| 8835 |
"trial_params": null
|