Training in progress, step 9520, 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 sha256:0b8056f2058d23f27a2b17b2966fba531668186aa9f06172b3d07035d43adf71
|
| 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:c7eba582520d2c84084c45bfa0253c0011f900b4b91b89e3ac6c77efa5082ad6
|
| 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 sha256:9dfdcc681bf87342098ed0ff1b114bef44ae3e2fa86b97f368c7c73ebb9a71e5
|
| 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": 73.
|
| 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,
|
|
@@ -17126,6 +17126,24 @@
|
|
| 17126 |
"mean_token_accuracy": 0.664915868639946,
|
| 17127 |
"num_tokens": 34682190.0,
|
| 17128 |
"step": 9510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17129 |
}
|
| 17130 |
],
|
| 17131 |
"logging_steps": 5,
|
|
@@ -17145,7 +17163,7 @@
|
|
| 17145 |
"attributes": {}
|
| 17146 |
}
|
| 17147 |
},
|
| 17148 |
-
"total_flos": 1.
|
| 17149 |
"train_batch_size": 4,
|
| 17150 |
"trial_name": null,
|
| 17151 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17126 |
"mean_token_accuracy": 0.664915868639946,
|
| 17127 |
"num_tokens": 34682190.0,
|
| 17128 |
"step": 9510
|
| 17129 |
+
},
|
| 17130 |
+
{
|
| 17131 |
+
"epoch": 73.1923076923077,
|
| 17132 |
+
"grad_norm": 0.0,
|
| 17133 |
+
"learning_rate": 2.43e-06,
|
| 17134 |
+
"loss": 1.718,
|
| 17135 |
+
"mean_token_accuracy": 0.6526754826307297,
|
| 17136 |
+
"num_tokens": 34700323.0,
|
| 17137 |
+
"step": 9515
|
| 17138 |
+
},
|
| 17139 |
+
{
|
| 17140 |
+
"epoch": 73.23076923076923,
|
| 17141 |
+
"grad_norm": 0.0,
|
| 17142 |
+
"learning_rate": 2.405e-06,
|
| 17143 |
+
"loss": 1.7598,
|
| 17144 |
+
"mean_token_accuracy": 0.648136830329895,
|
| 17145 |
+
"num_tokens": 34718585.0,
|
| 17146 |
+
"step": 9520
|
| 17147 |
}
|
| 17148 |
],
|
| 17149 |
"logging_steps": 5,
|
|
|
|
| 17163 |
"attributes": {}
|
| 17164 |
}
|
| 17165 |
},
|
| 17166 |
+
"total_flos": 1.760566355264471e+18,
|
| 17167 |
"train_batch_size": 4,
|
| 17168 |
"trial_name": null,
|
| 17169 |
"trial_params": null
|