Training in progress, step 3240, 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 sha256:4c2de1d4bbc97bac066bd4d1bfad9e5e0b5ce0a7a2ab92841131b4ae564adae4
|
| 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 sha256:2e5f6cac7dba1a11252bdf6fb371a1b3445b59f6516b08f0494aa93ebed14151
|
| 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:b6c6ebd81d726582af0889e91562592065b7c3dc09548c3703eb995929f35cad
|
| 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": 24.
|
| 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,
|
|
@@ -5822,6 +5822,24 @@
|
|
| 5822 |
"mean_token_accuracy": 0.6536848098039627,
|
| 5823 |
"num_tokens": 11778672.0,
|
| 5824 |
"step": 3230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5825 |
}
|
| 5826 |
],
|
| 5827 |
"logging_steps": 5,
|
|
@@ -5841,7 +5859,7 @@
|
|
| 5841 |
"attributes": {}
|
| 5842 |
}
|
| 5843 |
},
|
| 5844 |
-
"total_flos": 5.
|
| 5845 |
"train_batch_size": 4,
|
| 5846 |
"trial_name": null,
|
| 5847 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 24.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5822 |
"mean_token_accuracy": 0.6536848098039627,
|
| 5823 |
"num_tokens": 11778672.0,
|
| 5824 |
"step": 3230
|
| 5825 |
+
},
|
| 5826 |
+
{
|
| 5827 |
+
"epoch": 24.884615384615383,
|
| 5828 |
+
"grad_norm": 0.0,
|
| 5829 |
+
"learning_rate": 3.383e-05,
|
| 5830 |
+
"loss": 1.6997,
|
| 5831 |
+
"mean_token_accuracy": 0.6613029778003693,
|
| 5832 |
+
"num_tokens": 11797888.0,
|
| 5833 |
+
"step": 3235
|
| 5834 |
+
},
|
| 5835 |
+
{
|
| 5836 |
+
"epoch": 24.923076923076923,
|
| 5837 |
+
"grad_norm": 0.0,
|
| 5838 |
+
"learning_rate": 3.3805000000000006e-05,
|
| 5839 |
+
"loss": 1.6657,
|
| 5840 |
+
"mean_token_accuracy": 0.6732263565063477,
|
| 5841 |
+
"num_tokens": 11816590.0,
|
| 5842 |
+
"step": 3240
|
| 5843 |
}
|
| 5844 |
],
|
| 5845 |
"logging_steps": 5,
|
|
|
|
| 5859 |
"attributes": {}
|
| 5860 |
}
|
| 5861 |
},
|
| 5862 |
+
"total_flos": 5.987379008692224e+17,
|
| 5863 |
"train_batch_size": 4,
|
| 5864 |
"trial_name": null,
|
| 5865 |
"trial_params": null
|