Training in progress, step 5650, 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 sha256:62847b2f4ac35bd4fe07311201d87926a586f429d335e948c063084d2ef1d7f9
|
| 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 sha256:7871838c3cc0221c0e4250cf170d0f9188838086f0d231584aefba27b8e601c0
|
| 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 sha256:37c8ee98240a073ef9dc08fdf46b40e50b198de21160a5758740c3c0d24be50a
|
| 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": 43.
|
| 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,
|
|
@@ -10160,6 +10160,24 @@
|
|
| 10160 |
"mean_token_accuracy": 0.6484808444976806,
|
| 10161 |
"num_tokens": 20570987.0,
|
| 10162 |
"step": 5640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10163 |
}
|
| 10164 |
],
|
| 10165 |
"logging_steps": 5,
|
|
@@ -10179,7 +10197,7 @@
|
|
| 10179 |
"attributes": {}
|
| 10180 |
}
|
| 10181 |
},
|
| 10182 |
-
"total_flos": 1.
|
| 10183 |
"train_batch_size": 4,
|
| 10184 |
"trial_name": null,
|
| 10185 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10160 |
"mean_token_accuracy": 0.6484808444976806,
|
| 10161 |
"num_tokens": 20570987.0,
|
| 10162 |
"step": 5640
|
| 10163 |
+
},
|
| 10164 |
+
{
|
| 10165 |
+
"epoch": 43.42307692307692,
|
| 10166 |
+
"grad_norm": 0.0,
|
| 10167 |
+
"learning_rate": 2.178e-05,
|
| 10168 |
+
"loss": 1.7396,
|
| 10169 |
+
"mean_token_accuracy": 0.6534300118684768,
|
| 10170 |
+
"num_tokens": 20589119.0,
|
| 10171 |
+
"step": 5645
|
| 10172 |
+
},
|
| 10173 |
+
{
|
| 10174 |
+
"epoch": 43.46153846153846,
|
| 10175 |
+
"grad_norm": 0.0,
|
| 10176 |
+
"learning_rate": 2.1755e-05,
|
| 10177 |
+
"loss": 1.7263,
|
| 10178 |
+
"mean_token_accuracy": 0.6558996856212616,
|
| 10179 |
+
"num_tokens": 20607573.0,
|
| 10180 |
+
"step": 5650
|
| 10181 |
}
|
| 10182 |
],
|
| 10183 |
"logging_steps": 5,
|
|
|
|
| 10197 |
"attributes": {}
|
| 10198 |
}
|
| 10199 |
},
|
| 10200 |
+
"total_flos": 1.0443456999633715e+18,
|
| 10201 |
"train_batch_size": 4,
|
| 10202 |
"trial_name": null,
|
| 10203 |
"trial_params": null
|