Training in progress, step 6070, 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 sha256:7d7e9740d0844b786654059a2b22495a7c9eb97da2c7f5fa8c372df2bdbefd67
|
| 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 sha256:290842b14fe071e4139ca1f896378288a3b7fa89b6f8579351566d570d7a6d82
|
| 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:c0c273c6e6bced3bce15c08d1748793621f325cdf51c026a1f761ecf7bfff163
|
| 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": 46.
|
| 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,
|
|
@@ -10916,6 +10916,24 @@
|
|
| 10916 |
"mean_token_accuracy": 0.6389273494482041,
|
| 10917 |
"num_tokens": 22100180.0,
|
| 10918 |
"step": 6060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10919 |
}
|
| 10920 |
],
|
| 10921 |
"logging_steps": 5,
|
|
@@ -10935,7 +10953,7 @@
|
|
| 10935 |
"attributes": {}
|
| 10936 |
}
|
| 10937 |
},
|
| 10938 |
-
"total_flos": 1.
|
| 10939 |
"train_batch_size": 4,
|
| 10940 |
"trial_name": null,
|
| 10941 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10916 |
"mean_token_accuracy": 0.6389273494482041,
|
| 10917 |
"num_tokens": 22100180.0,
|
| 10918 |
"step": 6060
|
| 10919 |
+
},
|
| 10920 |
+
{
|
| 10921 |
+
"epoch": 46.65384615384615,
|
| 10922 |
+
"grad_norm": 0.0,
|
| 10923 |
+
"learning_rate": 1.968e-05,
|
| 10924 |
+
"loss": 1.7366,
|
| 10925 |
+
"mean_token_accuracy": 0.6541613578796387,
|
| 10926 |
+
"num_tokens": 22118685.0,
|
| 10927 |
+
"step": 6065
|
| 10928 |
+
},
|
| 10929 |
+
{
|
| 10930 |
+
"epoch": 46.69230769230769,
|
| 10931 |
+
"grad_norm": 0.0,
|
| 10932 |
+
"learning_rate": 1.9655e-05,
|
| 10933 |
+
"loss": 1.7336,
|
| 10934 |
+
"mean_token_accuracy": 0.6524038523435592,
|
| 10935 |
+
"num_tokens": 22136815.0,
|
| 10936 |
+
"step": 6070
|
| 10937 |
}
|
| 10938 |
],
|
| 10939 |
"logging_steps": 5,
|
|
|
|
| 10953 |
"attributes": {}
|
| 10954 |
}
|
| 10955 |
},
|
| 10956 |
+
"total_flos": 1.1218486592677478e+18,
|
| 10957 |
"train_batch_size": 4,
|
| 10958 |
"trial_name": null,
|
| 10959 |
"trial_params": null
|