Training in progress, step 6770, 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:c243dc2e48327286cdc5fd7d67464267d7180fefe10ad00445f105049260822b
|
| 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:c92d15563c7f5ad96c77b3160994df5480c59910247f2af06d1cc03ca403ae9e
|
| 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:a80d0f5dd8e37b7b95ef809bcb6331fd2e19913fddec416bef71a7bce89a9f8e
|
| 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": 52.
|
| 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,
|
|
@@ -12176,6 +12176,24 @@
|
|
| 12176 |
"mean_token_accuracy": 0.6327983260154724,
|
| 12177 |
"num_tokens": 24653460.0,
|
| 12178 |
"step": 6760
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12179 |
}
|
| 12180 |
],
|
| 12181 |
"logging_steps": 5,
|
|
@@ -12195,7 +12213,7 @@
|
|
| 12195 |
"attributes": {}
|
| 12196 |
}
|
| 12197 |
},
|
| 12198 |
-
"total_flos": 1.
|
| 12199 |
"train_batch_size": 4,
|
| 12200 |
"trial_name": null,
|
| 12201 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 52.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6770,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12176 |
"mean_token_accuracy": 0.6327983260154724,
|
| 12177 |
"num_tokens": 24653460.0,
|
| 12178 |
"step": 6760
|
| 12179 |
+
},
|
| 12180 |
+
{
|
| 12181 |
+
"epoch": 52.03846153846154,
|
| 12182 |
+
"grad_norm": 0.0,
|
| 12183 |
+
"learning_rate": 1.618e-05,
|
| 12184 |
+
"loss": 1.6387,
|
| 12185 |
+
"mean_token_accuracy": 0.6734457373619079,
|
| 12186 |
+
"num_tokens": 24672969.0,
|
| 12187 |
+
"step": 6765
|
| 12188 |
+
},
|
| 12189 |
+
{
|
| 12190 |
+
"epoch": 52.07692307692308,
|
| 12191 |
+
"grad_norm": 0.0,
|
| 12192 |
+
"learning_rate": 1.6155e-05,
|
| 12193 |
+
"loss": 1.7751,
|
| 12194 |
+
"mean_token_accuracy": 0.6482141762971878,
|
| 12195 |
+
"num_tokens": 24690768.0,
|
| 12196 |
+
"step": 6770
|
| 12197 |
}
|
| 12198 |
],
|
| 12199 |
"logging_steps": 5,
|
|
|
|
| 12213 |
"attributes": {}
|
| 12214 |
}
|
| 12215 |
},
|
| 12216 |
+
"total_flos": 1.2518771891606323e+18,
|
| 12217 |
"train_batch_size": 4,
|
| 12218 |
"trial_name": null,
|
| 12219 |
"trial_params": null
|