Training in progress, step 2680, 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:f45f2b36ff10f0ca254c2a464a87a1eea57f0d48d518c9d569ca1beca6997f22
|
| 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 sha256:8ef629d67cb2c920febc42ed9f3f09b014c147c506a05fa2fe8386caaad64de5
|
| 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:bf84c93257d12117a045b263d563f809a8255af2d2e557c20ae323365a4375e1
|
| 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": 20.
|
| 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,
|
|
@@ -4814,6 +4814,24 @@
|
|
| 4814 |
"mean_token_accuracy": 0.6592382907867431,
|
| 4815 |
"num_tokens": 9735601.0,
|
| 4816 |
"step": 2670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4817 |
}
|
| 4818 |
],
|
| 4819 |
"logging_steps": 5,
|
|
@@ -4833,7 +4851,7 @@
|
|
| 4833 |
"attributes": {}
|
| 4834 |
}
|
| 4835 |
},
|
| 4836 |
-
"total_flos": 4.
|
| 4837 |
"train_batch_size": 4,
|
| 4838 |
"trial_name": null,
|
| 4839 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4814 |
"mean_token_accuracy": 0.6592382907867431,
|
| 4815 |
"num_tokens": 9735601.0,
|
| 4816 |
"step": 2670
|
| 4817 |
+
},
|
| 4818 |
+
{
|
| 4819 |
+
"epoch": 20.576923076923077,
|
| 4820 |
+
"grad_norm": 0.0,
|
| 4821 |
+
"learning_rate": 3.663e-05,
|
| 4822 |
+
"loss": 1.7629,
|
| 4823 |
+
"mean_token_accuracy": 0.6453653991222381,
|
| 4824 |
+
"num_tokens": 9753360.0,
|
| 4825 |
+
"step": 2675
|
| 4826 |
+
},
|
| 4827 |
+
{
|
| 4828 |
+
"epoch": 20.615384615384617,
|
| 4829 |
+
"grad_norm": 0.0,
|
| 4830 |
+
"learning_rate": 3.6605e-05,
|
| 4831 |
+
"loss": 1.7007,
|
| 4832 |
+
"mean_token_accuracy": 0.660412722826004,
|
| 4833 |
+
"num_tokens": 9771848.0,
|
| 4834 |
+
"step": 2680
|
| 4835 |
}
|
| 4836 |
],
|
| 4837 |
"logging_steps": 5,
|
|
|
|
| 4851 |
"attributes": {}
|
| 4852 |
}
|
| 4853 |
},
|
| 4854 |
+
"total_flos": 4.951475278376141e+17,
|
| 4855 |
"train_batch_size": 4,
|
| 4856 |
"trial_name": null,
|
| 4857 |
"trial_params": null
|