Training in progress, step 2670, 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 sha256:6aee21e8d56ec6fd789831aa42e07b531d3a1602f13c0535544554517f0b40bc
|
| 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:d1efb149d8804fc076acf8c4ac5a5b2cef08eda5c4f43826b1e76877076ff558
|
| 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 sha256:9b6bf2126ab0c42e10dca5bdc5845a2e51c1475644f830e11ec7c0c26b5af1b0
|
| 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,
|
|
@@ -4796,6 +4796,24 @@
|
|
| 4796 |
"mean_token_accuracy": 0.6423662751913071,
|
| 4797 |
"num_tokens": 9698951.0,
|
| 4798 |
"step": 2660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4799 |
}
|
| 4800 |
],
|
| 4801 |
"logging_steps": 5,
|
|
@@ -4815,7 +4833,7 @@
|
|
| 4815 |
"attributes": {}
|
| 4816 |
}
|
| 4817 |
},
|
| 4818 |
-
"total_flos": 4.
|
| 4819 |
"train_batch_size": 4,
|
| 4820 |
"trial_name": null,
|
| 4821 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2670,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4796 |
"mean_token_accuracy": 0.6423662751913071,
|
| 4797 |
"num_tokens": 9698951.0,
|
| 4798 |
"step": 2660
|
| 4799 |
+
},
|
| 4800 |
+
{
|
| 4801 |
+
"epoch": 20.5,
|
| 4802 |
+
"grad_norm": 0.0,
|
| 4803 |
+
"learning_rate": 3.668e-05,
|
| 4804 |
+
"loss": 1.7479,
|
| 4805 |
+
"mean_token_accuracy": 0.6455884456634522,
|
| 4806 |
+
"num_tokens": 9716798.0,
|
| 4807 |
+
"step": 2665
|
| 4808 |
+
},
|
| 4809 |
+
{
|
| 4810 |
+
"epoch": 20.53846153846154,
|
| 4811 |
+
"grad_norm": 0.0,
|
| 4812 |
+
"learning_rate": 3.6655e-05,
|
| 4813 |
+
"loss": 1.6967,
|
| 4814 |
+
"mean_token_accuracy": 0.6592382907867431,
|
| 4815 |
+
"num_tokens": 9735601.0,
|
| 4816 |
+
"step": 2670
|
| 4817 |
}
|
| 4818 |
],
|
| 4819 |
"logging_steps": 5,
|
|
|
|
| 4833 |
"attributes": {}
|
| 4834 |
}
|
| 4835 |
},
|
| 4836 |
+
"total_flos": 4.9332855393828864e+17,
|
| 4837 |
"train_batch_size": 4,
|
| 4838 |
"trial_name": null,
|
| 4839 |
"trial_params": null
|