Training in progress, step 3420, 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 sha256:52e1c1d2ae29c7116988a9cb5a8a6053bf8a17a9d71cc9e22485f3d77ccf2106
|
| 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:beb85f2a6f4afa9f00ca4304388b913a177f9b325e91df4c5cc98caa58369086
|
| 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 sha256:9a57e7c6b61484ba9db2e4269f2a229909c246942b959e88aebd117ef3f79ff7
|
| 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": 26.
|
| 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,
|
|
@@ -6146,6 +6146,24 @@
|
|
| 6146 |
"mean_token_accuracy": 0.6598240792751312,
|
| 6147 |
"num_tokens": 12436367.0,
|
| 6148 |
"step": 3410
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6149 |
}
|
| 6150 |
],
|
| 6151 |
"logging_steps": 5,
|
|
@@ -6165,7 +6183,7 @@
|
|
| 6165 |
"attributes": {}
|
| 6166 |
}
|
| 6167 |
},
|
| 6168 |
-
"total_flos": 6.
|
| 6169 |
"train_batch_size": 4,
|
| 6170 |
"trial_name": null,
|
| 6171 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3420,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6146 |
"mean_token_accuracy": 0.6598240792751312,
|
| 6147 |
"num_tokens": 12436367.0,
|
| 6148 |
"step": 3410
|
| 6149 |
+
},
|
| 6150 |
+
{
|
| 6151 |
+
"epoch": 26.26923076923077,
|
| 6152 |
+
"grad_norm": 0.0,
|
| 6153 |
+
"learning_rate": 3.293e-05,
|
| 6154 |
+
"loss": 1.7437,
|
| 6155 |
+
"mean_token_accuracy": 0.6541768878698349,
|
| 6156 |
+
"num_tokens": 12454372.0,
|
| 6157 |
+
"step": 3415
|
| 6158 |
+
},
|
| 6159 |
+
{
|
| 6160 |
+
"epoch": 26.307692307692307,
|
| 6161 |
+
"grad_norm": 0.0,
|
| 6162 |
+
"learning_rate": 3.2905000000000004e-05,
|
| 6163 |
+
"loss": 1.7304,
|
| 6164 |
+
"mean_token_accuracy": 0.6505888134241105,
|
| 6165 |
+
"num_tokens": 12472148.0,
|
| 6166 |
+
"step": 3420
|
| 6167 |
}
|
| 6168 |
],
|
| 6169 |
"logging_steps": 5,
|
|
|
|
| 6183 |
"attributes": {}
|
| 6184 |
}
|
| 6185 |
},
|
| 6186 |
+
"total_flos": 6.318725682231706e+17,
|
| 6187 |
"train_batch_size": 4,
|
| 6188 |
"trial_name": null,
|
| 6189 |
"trial_params": null
|