Training in progress, step 4340, 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:a3e75814f66d7d0d3981f4c02cc4a4de75ad8263a3beb72df4aacafdd89b3646
|
| 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:efb6c236c862fc5bb06263387577c4dfb9f126f6649edb4c3196396a5717cdcb
|
| 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 sha256:6ddc1f0ef9e948eee4bb18178a44f0fae0f4258b098304fe5aa093b85da6504a
|
| 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": 33.
|
| 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,
|
|
@@ -7802,6 +7802,24 @@
|
|
| 7802 |
"mean_token_accuracy": 0.6550895661115647,
|
| 7803 |
"num_tokens": 15792876.0,
|
| 7804 |
"step": 4330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7805 |
}
|
| 7806 |
],
|
| 7807 |
"logging_steps": 5,
|
|
@@ -7821,7 +7839,7 @@
|
|
| 7821 |
"attributes": {}
|
| 7822 |
}
|
| 7823 |
},
|
| 7824 |
-
"total_flos": 8.
|
| 7825 |
"train_batch_size": 4,
|
| 7826 |
"trial_name": null,
|
| 7827 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7802 |
"mean_token_accuracy": 0.6550895661115647,
|
| 7803 |
"num_tokens": 15792876.0,
|
| 7804 |
"step": 4330
|
| 7805 |
+
},
|
| 7806 |
+
{
|
| 7807 |
+
"epoch": 33.34615384615385,
|
| 7808 |
+
"grad_norm": 0.0,
|
| 7809 |
+
"learning_rate": 2.833e-05,
|
| 7810 |
+
"loss": 1.6975,
|
| 7811 |
+
"mean_token_accuracy": 0.6590204060077667,
|
| 7812 |
+
"num_tokens": 15811378.0,
|
| 7813 |
+
"step": 4335
|
| 7814 |
+
},
|
| 7815 |
+
{
|
| 7816 |
+
"epoch": 33.38461538461539,
|
| 7817 |
+
"grad_norm": 0.0,
|
| 7818 |
+
"learning_rate": 2.8305000000000004e-05,
|
| 7819 |
+
"loss": 1.7203,
|
| 7820 |
+
"mean_token_accuracy": 0.6554653912782669,
|
| 7821 |
+
"num_tokens": 15829656.0,
|
| 7822 |
+
"step": 4340
|
| 7823 |
}
|
| 7824 |
],
|
| 7825 |
"logging_steps": 5,
|
|
|
|
| 7839 |
"attributes": {}
|
| 7840 |
}
|
| 7841 |
},
|
| 7842 |
+
"total_flos": 8.022062317142016e+17,
|
| 7843 |
"train_batch_size": 4,
|
| 7844 |
"trial_name": null,
|
| 7845 |
"trial_params": null
|