Training in progress, step 6120, 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 sha256:53498973f82d5aacdb2a4d9c3d1c81cdab587547f52d23a1741307040f03a4c1
|
| 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:c8d393cab783c3501c5c2cf9495d91773f3b8a9f258c0e9af25a1b135cfd1fb0
|
| 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 sha256:28d839dab6a84ef87de107ed3314e6fb7bc36be0867e637c6150343d88c3fc3b
|
| 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": 47.
|
| 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,
|
|
@@ -11006,6 +11006,24 @@
|
|
| 11006 |
"mean_token_accuracy": 0.6506162971258164,
|
| 11007 |
"num_tokens": 22282935.0,
|
| 11008 |
"step": 6110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11009 |
}
|
| 11010 |
],
|
| 11011 |
"logging_steps": 5,
|
|
@@ -11025,7 +11043,7 @@
|
|
| 11025 |
"attributes": {}
|
| 11026 |
}
|
| 11027 |
},
|
| 11028 |
-
"total_flos": 1.
|
| 11029 |
"train_batch_size": 4,
|
| 11030 |
"trial_name": null,
|
| 11031 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11006 |
"mean_token_accuracy": 0.6506162971258164,
|
| 11007 |
"num_tokens": 22282935.0,
|
| 11008 |
"step": 6110
|
| 11009 |
+
},
|
| 11010 |
+
{
|
| 11011 |
+
"epoch": 47.03846153846154,
|
| 11012 |
+
"grad_norm": 0.0,
|
| 11013 |
+
"learning_rate": 1.9430000000000002e-05,
|
| 11014 |
+
"loss": 1.7305,
|
| 11015 |
+
"mean_token_accuracy": 0.6571007430553436,
|
| 11016 |
+
"num_tokens": 22301303.0,
|
| 11017 |
+
"step": 6115
|
| 11018 |
+
},
|
| 11019 |
+
{
|
| 11020 |
+
"epoch": 47.07692307692308,
|
| 11021 |
+
"grad_norm": 0.0,
|
| 11022 |
+
"learning_rate": 1.9405e-05,
|
| 11023 |
+
"loss": 1.6624,
|
| 11024 |
+
"mean_token_accuracy": 0.6648898661136627,
|
| 11025 |
+
"num_tokens": 22320863.0,
|
| 11026 |
+
"step": 6120
|
| 11027 |
}
|
| 11028 |
],
|
| 11029 |
"logging_steps": 5,
|
|
|
|
| 11043 |
"attributes": {}
|
| 11044 |
}
|
| 11045 |
},
|
| 11046 |
+
"total_flos": 1.1312698199098982e+18,
|
| 11047 |
"train_batch_size": 4,
|
| 11048 |
"trial_name": null,
|
| 11049 |
"trial_params": null
|