Training in progress, step 1240, 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:bb507d8c36c5e58793edfa78910171de4bbdccc0313f7906979dc3c32c1eafff
|
| 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:d31d38caa5671bbdf83536352c495273c0732a2ca43fd4afb37f7276dc967308
|
| 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 sha256:7a4efed661028c2c90990d3f7bc6f59a0c066719a5c69c181a834d069d639311
|
| 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": 9.
|
| 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,
|
|
@@ -2222,6 +2222,24 @@
|
|
| 2222 |
"mean_token_accuracy": 0.6529223084449768,
|
| 2223 |
"num_tokens": 4487471.0,
|
| 2224 |
"step": 1230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2225 |
}
|
| 2226 |
],
|
| 2227 |
"logging_steps": 5,
|
|
@@ -2241,7 +2259,7 @@
|
|
| 2241 |
"attributes": {}
|
| 2242 |
}
|
| 2243 |
},
|
| 2244 |
-
"total_flos": 2.
|
| 2245 |
"train_batch_size": 4,
|
| 2246 |
"trial_name": null,
|
| 2247 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.538461538461538,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2222 |
"mean_token_accuracy": 0.6529223084449768,
|
| 2223 |
"num_tokens": 4487471.0,
|
| 2224 |
"step": 1230
|
| 2225 |
+
},
|
| 2226 |
+
{
|
| 2227 |
+
"epoch": 9.5,
|
| 2228 |
+
"grad_norm": 0.0,
|
| 2229 |
+
"learning_rate": 4.3830000000000006e-05,
|
| 2230 |
+
"loss": 1.7984,
|
| 2231 |
+
"mean_token_accuracy": 0.6414839684963226,
|
| 2232 |
+
"num_tokens": 4504876.0,
|
| 2233 |
+
"step": 1235
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 9.538461538461538,
|
| 2237 |
+
"grad_norm": 0.0,
|
| 2238 |
+
"learning_rate": 4.3805000000000005e-05,
|
| 2239 |
+
"loss": 1.7501,
|
| 2240 |
+
"mean_token_accuracy": 0.650190019607544,
|
| 2241 |
+
"num_tokens": 4522905.0,
|
| 2242 |
+
"step": 1240
|
| 2243 |
}
|
| 2244 |
],
|
| 2245 |
"logging_steps": 5,
|
|
|
|
| 2259 |
"attributes": {}
|
| 2260 |
}
|
| 2261 |
},
|
| 2262 |
+
"total_flos": 2.2927645205397504e+17,
|
| 2263 |
"train_batch_size": 4,
|
| 2264 |
"trial_name": null,
|
| 2265 |
"trial_params": null
|