Training in progress, step 4350, 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:dba7b28566a851dca50592a077251c0b479b740365c7f4832c132a3e69037df6
|
| 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:a66f884546ae3d7655ddeec5c3ed6f35d03fc0a5b50dae1ce8b71e509e031c5d
|
| 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 sha256:28edd482f189b30911953eafe1f65ecb9f9add1df7167c0ca2d2336869f6343e
|
| 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,
|
|
@@ -7820,6 +7820,24 @@
|
|
| 7820 |
"mean_token_accuracy": 0.6554653912782669,
|
| 7821 |
"num_tokens": 15829656.0,
|
| 7822 |
"step": 4340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7823 |
}
|
| 7824 |
],
|
| 7825 |
"logging_steps": 5,
|
|
@@ -7839,7 +7857,7 @@
|
|
| 7839 |
"attributes": {}
|
| 7840 |
}
|
| 7841 |
},
|
| 7842 |
-
"total_flos": 8.
|
| 7843 |
"train_batch_size": 4,
|
| 7844 |
"trial_name": null,
|
| 7845 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7820 |
"mean_token_accuracy": 0.6554653912782669,
|
| 7821 |
"num_tokens": 15829656.0,
|
| 7822 |
"step": 4340
|
| 7823 |
+
},
|
| 7824 |
+
{
|
| 7825 |
+
"epoch": 33.42307692307692,
|
| 7826 |
+
"grad_norm": 0.0,
|
| 7827 |
+
"learning_rate": 2.828e-05,
|
| 7828 |
+
"loss": 1.7643,
|
| 7829 |
+
"mean_token_accuracy": 0.6414321035146713,
|
| 7830 |
+
"num_tokens": 15847703.0,
|
| 7831 |
+
"step": 4345
|
| 7832 |
+
},
|
| 7833 |
+
{
|
| 7834 |
+
"epoch": 33.46153846153846,
|
| 7835 |
+
"grad_norm": 0.0,
|
| 7836 |
+
"learning_rate": 2.8255000000000003e-05,
|
| 7837 |
+
"loss": 1.6511,
|
| 7838 |
+
"mean_token_accuracy": 0.667979073524475,
|
| 7839 |
+
"num_tokens": 15867134.0,
|
| 7840 |
+
"step": 4350
|
| 7841 |
}
|
| 7842 |
],
|
| 7843 |
"logging_steps": 5,
|
|
|
|
| 7857 |
"attributes": {}
|
| 7858 |
}
|
| 7859 |
},
|
| 7860 |
+
"total_flos": 8.04172076323799e+17,
|
| 7861 |
"train_batch_size": 4,
|
| 7862 |
"trial_name": null,
|
| 7863 |
"trial_params": null
|