Training in progress, step 8840, 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 sha256:62c201be99e1a74e4f48f52246c9e134a30745e58042c489a7a44bacdf50b676
|
| 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:dc8fa511801090a081395bfe623c88d6b4d340a80b079dcfe9f18095015278cb
|
| 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:acecfbed16ebec4ea015dddd4b41cd62884848f512e95afb61ecaba640fe891b
|
| 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":
|
| 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,
|
|
@@ -15902,6 +15902,24 @@
|
|
| 15902 |
"mean_token_accuracy": 0.6364179074764251,
|
| 15903 |
"num_tokens": 32202532.0,
|
| 15904 |
"step": 8830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15905 |
}
|
| 15906 |
],
|
| 15907 |
"logging_steps": 5,
|
|
@@ -15921,7 +15939,7 @@
|
|
| 15921 |
"attributes": {}
|
| 15922 |
}
|
| 15923 |
},
|
| 15924 |
-
"total_flos": 1.
|
| 15925 |
"train_batch_size": 4,
|
| 15926 |
"trial_name": null,
|
| 15927 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15902 |
"mean_token_accuracy": 0.6364179074764251,
|
| 15903 |
"num_tokens": 32202532.0,
|
| 15904 |
"step": 8830
|
| 15905 |
+
},
|
| 15906 |
+
{
|
| 15907 |
+
"epoch": 67.96153846153847,
|
| 15908 |
+
"grad_norm": 0.0,
|
| 15909 |
+
"learning_rate": 5.83e-06,
|
| 15910 |
+
"loss": 1.842,
|
| 15911 |
+
"mean_token_accuracy": 0.629499414563179,
|
| 15912 |
+
"num_tokens": 32219939.0,
|
| 15913 |
+
"step": 8835
|
| 15914 |
+
},
|
| 15915 |
+
{
|
| 15916 |
+
"epoch": 68.0,
|
| 15917 |
+
"grad_norm": 0.0,
|
| 15918 |
+
"learning_rate": 5.805e-06,
|
| 15919 |
+
"loss": 1.7138,
|
| 15920 |
+
"mean_token_accuracy": 0.651302108168602,
|
| 15921 |
+
"num_tokens": 32239140.0,
|
| 15922 |
+
"step": 8840
|
| 15923 |
}
|
| 15924 |
],
|
| 15925 |
"logging_steps": 5,
|
|
|
|
| 15939 |
"attributes": {}
|
| 15940 |
}
|
| 15941 |
},
|
| 15942 |
+
"total_flos": 1.634717368838062e+18,
|
| 15943 |
"train_batch_size": 4,
|
| 15944 |
"trial_name": null,
|
| 15945 |
"trial_params": null
|