Training in progress, step 6760, 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:da7254401648b02230a0a977d1892a2f55ca5adac31bef145b394ba3eab7c27b
|
| 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:f932c824d1f6c8987ab03e55620d00aaf2a9dc93e790fafa56585d89867da253
|
| 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 sha256:718e5446de195256fed2a57966092328e02b65d9af249bf50e14aef92bc87d69
|
| 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":
|
| 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,
|
|
@@ -12158,6 +12158,24 @@
|
|
| 12158 |
"mean_token_accuracy": 0.6468292713165283,
|
| 12159 |
"num_tokens": 24617539.0,
|
| 12160 |
"step": 6750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12161 |
}
|
| 12162 |
],
|
| 12163 |
"logging_steps": 5,
|
|
@@ -12177,7 +12195,7 @@
|
|
| 12177 |
"attributes": {}
|
| 12178 |
}
|
| 12179 |
},
|
| 12180 |
-
"total_flos": 1.
|
| 12181 |
"train_batch_size": 4,
|
| 12182 |
"trial_name": null,
|
| 12183 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12158 |
"mean_token_accuracy": 0.6468292713165283,
|
| 12159 |
"num_tokens": 24617539.0,
|
| 12160 |
"step": 6750
|
| 12161 |
+
},
|
| 12162 |
+
{
|
| 12163 |
+
"epoch": 51.96153846153846,
|
| 12164 |
+
"grad_norm": 0.0,
|
| 12165 |
+
"learning_rate": 1.6230000000000002e-05,
|
| 12166 |
+
"loss": 1.7414,
|
| 12167 |
+
"mean_token_accuracy": 0.653847748041153,
|
| 12168 |
+
"num_tokens": 24635357.0,
|
| 12169 |
+
"step": 6755
|
| 12170 |
+
},
|
| 12171 |
+
{
|
| 12172 |
+
"epoch": 52.0,
|
| 12173 |
+
"grad_norm": 0.0,
|
| 12174 |
+
"learning_rate": 1.6205e-05,
|
| 12175 |
+
"loss": 1.7919,
|
| 12176 |
+
"mean_token_accuracy": 0.6327983260154724,
|
| 12177 |
+
"num_tokens": 24653460.0,
|
| 12178 |
+
"step": 6760
|
| 12179 |
}
|
| 12180 |
],
|
| 12181 |
"logging_steps": 5,
|
|
|
|
| 12195 |
"attributes": {}
|
| 12196 |
}
|
| 12197 |
},
|
| 12198 |
+
"total_flos": 1.2499731096389222e+18,
|
| 12199 |
"train_batch_size": 4,
|
| 12200 |
"trial_name": null,
|
| 12201 |
"trial_params": null
|