Training in progress, step 8490, 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:dddd3ec20bb20ffb82b290e3a39a69b3e4b84286cd00477bdf4200ffb65a642c
|
| 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 sha256:27dfca58eded1bdd88970696f17f8279ac088c3deab69092ebba58d39edc6268
|
| 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 sha256:24c3b0ce3c94d01441acd0143c9bed9d59ef37be622bf9daea2edd9e309090f5
|
| 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": 65.
|
| 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,
|
|
@@ -15272,6 +15272,24 @@
|
|
| 15272 |
"mean_token_accuracy": 0.667791223526001,
|
| 15273 |
"num_tokens": 30928442.0,
|
| 15274 |
"step": 8480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15275 |
}
|
| 15276 |
],
|
| 15277 |
"logging_steps": 5,
|
|
@@ -15291,7 +15309,7 @@
|
|
| 15291 |
"attributes": {}
|
| 15292 |
}
|
| 15293 |
},
|
| 15294 |
-
"total_flos": 1.
|
| 15295 |
"train_batch_size": 4,
|
| 15296 |
"trial_name": null,
|
| 15297 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 65.3076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15272 |
"mean_token_accuracy": 0.667791223526001,
|
| 15273 |
"num_tokens": 30928442.0,
|
| 15274 |
"step": 8480
|
| 15275 |
+
},
|
| 15276 |
+
{
|
| 15277 |
+
"epoch": 65.26923076923077,
|
| 15278 |
+
"grad_norm": 0.0,
|
| 15279 |
+
"learning_rate": 7.580000000000001e-06,
|
| 15280 |
+
"loss": 1.7272,
|
| 15281 |
+
"mean_token_accuracy": 0.6559307098388671,
|
| 15282 |
+
"num_tokens": 30946632.0,
|
| 15283 |
+
"step": 8485
|
| 15284 |
+
},
|
| 15285 |
+
{
|
| 15286 |
+
"epoch": 65.3076923076923,
|
| 15287 |
+
"grad_norm": 0.0,
|
| 15288 |
+
"learning_rate": 7.555000000000001e-06,
|
| 15289 |
+
"loss": 1.7644,
|
| 15290 |
+
"mean_token_accuracy": 0.6492012023925782,
|
| 15291 |
+
"num_tokens": 30964389.0,
|
| 15292 |
+
"step": 8490
|
| 15293 |
}
|
| 15294 |
],
|
| 15295 |
"logging_steps": 5,
|
|
|
|
| 15309 |
"attributes": {}
|
| 15310 |
}
|
| 15311 |
},
|
| 15312 |
+
"total_flos": 1.5699616757312717e+18,
|
| 15313 |
"train_batch_size": 4,
|
| 15314 |
"trial_name": null,
|
| 15315 |
"trial_params": null
|