Training in progress, step 1250, 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 sha256:14906306fc02d6084e2ccc9d08010ef054937a1c75c45f42b6850e18e3828e35
|
| 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:ef7b7422b31b2326ee8a25d67530d9aca3748ecf371bcdbfab75eb2e43c67919
|
| 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 sha256:3fa4c5aa0228ea20f971e4081c5b1c844a1bcce82dbbf1565a2c91da048d8e48
|
| 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,
|
|
@@ -2240,6 +2240,24 @@
|
|
| 2240 |
"mean_token_accuracy": 0.650190019607544,
|
| 2241 |
"num_tokens": 4522905.0,
|
| 2242 |
"step": 1240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2243 |
}
|
| 2244 |
],
|
| 2245 |
"logging_steps": 5,
|
|
@@ -2259,7 +2277,7 @@
|
|
| 2259 |
"attributes": {}
|
| 2260 |
}
|
| 2261 |
},
|
| 2262 |
-
"total_flos": 2.
|
| 2263 |
"train_batch_size": 4,
|
| 2264 |
"trial_name": null,
|
| 2265 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2240 |
"mean_token_accuracy": 0.650190019607544,
|
| 2241 |
"num_tokens": 4522905.0,
|
| 2242 |
"step": 1240
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 9.576923076923077,
|
| 2246 |
+
"grad_norm": 0.0,
|
| 2247 |
+
"learning_rate": 4.3780000000000004e-05,
|
| 2248 |
+
"loss": 1.7429,
|
| 2249 |
+
"mean_token_accuracy": 0.6522337943315506,
|
| 2250 |
+
"num_tokens": 4541124.0,
|
| 2251 |
+
"step": 1245
|
| 2252 |
+
},
|
| 2253 |
+
{
|
| 2254 |
+
"epoch": 9.615384615384615,
|
| 2255 |
+
"grad_norm": 0.0,
|
| 2256 |
+
"learning_rate": 4.3755000000000004e-05,
|
| 2257 |
+
"loss": 1.6859,
|
| 2258 |
+
"mean_token_accuracy": 0.6608754128217698,
|
| 2259 |
+
"num_tokens": 4560264.0,
|
| 2260 |
+
"step": 1250
|
| 2261 |
}
|
| 2262 |
],
|
| 2263 |
"logging_steps": 5,
|
|
|
|
| 2277 |
"attributes": {}
|
| 2278 |
}
|
| 2279 |
},
|
| 2280 |
+
"total_flos": 2.3116703534825472e+17,
|
| 2281 |
"train_batch_size": 4,
|
| 2282 |
"trial_name": null,
|
| 2283 |
"trial_params": null
|