Training in progress, step 9410, 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 sha256:4f4f9477b4630d82a614795977a9008d386dd6228f8bb188f856c495e3bdb230
|
| 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:de7f9ecd38a35b4abfc67c152350ff3fc8cd20afe39647087278ed32192f636f
|
| 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:d4c74c01a7d78a8bd8ef1baec477227c0e90d8f1923411c58c545cb6dda338a8
|
| 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": 72.
|
| 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,
|
|
@@ -16928,6 +16928,24 @@
|
|
| 16928 |
"mean_token_accuracy": 0.6492182224988937,
|
| 16929 |
"num_tokens": 34283311.0,
|
| 16930 |
"step": 9400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16931 |
}
|
| 16932 |
],
|
| 16933 |
"logging_steps": 5,
|
|
@@ -16947,7 +16965,7 @@
|
|
| 16947 |
"attributes": {}
|
| 16948 |
}
|
| 16949 |
},
|
| 16950 |
-
"total_flos": 1.
|
| 16951 |
"train_batch_size": 4,
|
| 16952 |
"trial_name": null,
|
| 16953 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16928 |
"mean_token_accuracy": 0.6492182224988937,
|
| 16929 |
"num_tokens": 34283311.0,
|
| 16930 |
"step": 9400
|
| 16931 |
+
},
|
| 16932 |
+
{
|
| 16933 |
+
"epoch": 72.34615384615384,
|
| 16934 |
+
"grad_norm": 0.0,
|
| 16935 |
+
"learning_rate": 2.9800000000000003e-06,
|
| 16936 |
+
"loss": 1.7515,
|
| 16937 |
+
"mean_token_accuracy": 0.6472180843353271,
|
| 16938 |
+
"num_tokens": 34301877.0,
|
| 16939 |
+
"step": 9405
|
| 16940 |
+
},
|
| 16941 |
+
{
|
| 16942 |
+
"epoch": 72.38461538461539,
|
| 16943 |
+
"grad_norm": 0.0,
|
| 16944 |
+
"learning_rate": 2.955e-06,
|
| 16945 |
+
"loss": 1.7565,
|
| 16946 |
+
"mean_token_accuracy": 0.6518394500017166,
|
| 16947 |
+
"num_tokens": 34319958.0,
|
| 16948 |
+
"step": 9410
|
| 16949 |
}
|
| 16950 |
],
|
| 16951 |
"logging_steps": 5,
|
|
|
|
| 16965 |
"attributes": {}
|
| 16966 |
}
|
| 16967 |
},
|
| 16968 |
+
"total_flos": 1.7403745700162765e+18,
|
| 16969 |
"train_batch_size": 4,
|
| 16970 |
"trial_name": null,
|
| 16971 |
"trial_params": null
|