Training in progress, step 5640, 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:b67ce832401462acfbbbe738805744a83f56fab6444210ddd90d13c359410090
|
| 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:eca4e0d0a2dbd79b4584fc91d5d4e64b571652d3966751c82e5c032faf6083d2
|
| 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 sha256:7082304a9c359a1e489197fd381e77192265d85282c58126568aa0fd3515dd84
|
| 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,
|
|
@@ -10142,6 +10142,24 @@
|
|
| 10142 |
"mean_token_accuracy": 0.6463449627161026,
|
| 10143 |
"num_tokens": 20533916.0,
|
| 10144 |
"step": 5630
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10145 |
}
|
| 10146 |
],
|
| 10147 |
"logging_steps": 5,
|
|
@@ -10161,7 +10179,7 @@
|
|
| 10161 |
"attributes": {}
|
| 10162 |
}
|
| 10163 |
},
|
| 10164 |
-
"total_flos": 1.
|
| 10165 |
"train_batch_size": 4,
|
| 10166 |
"trial_name": null,
|
| 10167 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 43.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5640,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10142 |
"mean_token_accuracy": 0.6463449627161026,
|
| 10143 |
"num_tokens": 20533916.0,
|
| 10144 |
"step": 5630
|
| 10145 |
+
},
|
| 10146 |
+
{
|
| 10147 |
+
"epoch": 43.34615384615385,
|
| 10148 |
+
"grad_norm": 0.0,
|
| 10149 |
+
"learning_rate": 2.183e-05,
|
| 10150 |
+
"loss": 1.6911,
|
| 10151 |
+
"mean_token_accuracy": 0.6570004016160965,
|
| 10152 |
+
"num_tokens": 20552781.0,
|
| 10153 |
+
"step": 5635
|
| 10154 |
+
},
|
| 10155 |
+
{
|
| 10156 |
+
"epoch": 43.38461538461539,
|
| 10157 |
+
"grad_norm": 0.0,
|
| 10158 |
+
"learning_rate": 2.1805e-05,
|
| 10159 |
+
"loss": 1.7714,
|
| 10160 |
+
"mean_token_accuracy": 0.6484808444976806,
|
| 10161 |
+
"num_tokens": 20570987.0,
|
| 10162 |
+
"step": 5640
|
| 10163 |
}
|
| 10164 |
],
|
| 10165 |
"logging_steps": 5,
|
|
|
|
| 10179 |
"attributes": {}
|
| 10180 |
}
|
| 10181 |
},
|
| 10182 |
+
"total_flos": 1.0424827442405376e+18,
|
| 10183 |
"train_batch_size": 4,
|
| 10184 |
"trial_name": null,
|
| 10185 |
"trial_params": null
|