Training in progress, step 1820, 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 sha256:7888448d78875461048f44497dd160369286bdce9dc4aca1e8cc1e4dbdcffc43
|
| 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:ada9dccc5a82708679e4754a1b0aa86dd2ecc25826c4b9c0d7beed114fc43bea
|
| 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:d646bbba5264c8188df18915ccaa038a18410fb624e631b465f79c042cbccb5d
|
| 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,
|
|
@@ -3266,6 +3266,24 @@
|
|
| 3266 |
"mean_token_accuracy": 0.6494243443012238,
|
| 3267 |
"num_tokens": 6600126.0,
|
| 3268 |
"step": 1810
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3269 |
}
|
| 3270 |
],
|
| 3271 |
"logging_steps": 5,
|
|
@@ -3285,7 +3303,7 @@
|
|
| 3285 |
"attributes": {}
|
| 3286 |
}
|
| 3287 |
},
|
| 3288 |
-
"total_flos": 3.
|
| 3289 |
"train_batch_size": 4,
|
| 3290 |
"trial_name": null,
|
| 3291 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 14.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1820,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3266 |
"mean_token_accuracy": 0.6494243443012238,
|
| 3267 |
"num_tokens": 6600126.0,
|
| 3268 |
"step": 1810
|
| 3269 |
+
},
|
| 3270 |
+
{
|
| 3271 |
+
"epoch": 13.961538461538462,
|
| 3272 |
+
"grad_norm": 0.0,
|
| 3273 |
+
"learning_rate": 4.093e-05,
|
| 3274 |
+
"loss": 1.7329,
|
| 3275 |
+
"mean_token_accuracy": 0.6540934264659881,
|
| 3276 |
+
"num_tokens": 6618707.0,
|
| 3277 |
+
"step": 1815
|
| 3278 |
+
},
|
| 3279 |
+
{
|
| 3280 |
+
"epoch": 14.0,
|
| 3281 |
+
"grad_norm": 0.0,
|
| 3282 |
+
"learning_rate": 4.0905e-05,
|
| 3283 |
+
"loss": 1.7251,
|
| 3284 |
+
"mean_token_accuracy": 0.6513684660196304,
|
| 3285 |
+
"num_tokens": 6637470.0,
|
| 3286 |
+
"step": 1820
|
| 3287 |
}
|
| 3288 |
],
|
| 3289 |
"logging_steps": 5,
|
|
|
|
| 3303 |
"attributes": {}
|
| 3304 |
}
|
| 3305 |
},
|
| 3306 |
+
"total_flos": 3.362651751525581e+17,
|
| 3307 |
"train_batch_size": 4,
|
| 3308 |
"trial_name": null,
|
| 3309 |
"trial_params": null
|