Training in progress, step 1060, 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 sha256:88fddb17268078a91c10eced460e8149dd911ab555909a7c37a9eee2da8ff8e9
|
| 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:ab0afda98fe657751369348e00a89a394cd2afcb8f7cc8b4ecd8c40313c79c8e
|
| 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 sha256:89dcb88a4425a219e453c2b07acce757552635b20e39ac6cc0d1010a34a68566
|
| 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": 8.
|
| 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,
|
|
@@ -1898,6 +1898,24 @@
|
|
| 1898 |
"mean_token_accuracy": 0.6376824468374253,
|
| 1899 |
"num_tokens": 3828269.0,
|
| 1900 |
"step": 1050
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1901 |
}
|
| 1902 |
],
|
| 1903 |
"logging_steps": 5,
|
|
@@ -1917,7 +1935,7 @@
|
|
| 1917 |
"attributes": {}
|
| 1918 |
}
|
| 1919 |
},
|
| 1920 |
-
"total_flos": 1.
|
| 1921 |
"train_batch_size": 4,
|
| 1922 |
"trial_name": null,
|
| 1923 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.153846153846153,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1060,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1898 |
"mean_token_accuracy": 0.6376824468374253,
|
| 1899 |
"num_tokens": 3828269.0,
|
| 1900 |
"step": 1050
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 8.115384615384615,
|
| 1904 |
+
"grad_norm": 0.0,
|
| 1905 |
+
"learning_rate": 4.473e-05,
|
| 1906 |
+
"loss": 1.7313,
|
| 1907 |
+
"mean_token_accuracy": 0.6513699233531952,
|
| 1908 |
+
"num_tokens": 3846785.0,
|
| 1909 |
+
"step": 1055
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 8.153846153846153,
|
| 1913 |
+
"grad_norm": 0.0,
|
| 1914 |
+
"learning_rate": 4.4705e-05,
|
| 1915 |
+
"loss": 1.779,
|
| 1916 |
+
"mean_token_accuracy": 0.6457870662212372,
|
| 1917 |
+
"num_tokens": 3864589.0,
|
| 1918 |
+
"step": 1060
|
| 1919 |
}
|
| 1920 |
],
|
| 1921 |
"logging_steps": 5,
|
|
|
|
| 1935 |
"attributes": {}
|
| 1936 |
}
|
| 1937 |
},
|
| 1938 |
+
"total_flos": 1.959152068583424e+17,
|
| 1939 |
"train_batch_size": 4,
|
| 1940 |
"trial_name": null,
|
| 1941 |
"trial_params": null
|