Training in progress, step 4580, 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:ecf3d832aa6b584cd96ef6961c2976ac7757a40847e5eecb52ffb2af5ba7e723
|
| 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 sha256:63a347e67787a41ca55bcd5588649346a8b055efd464c84f8f55635c6070ecbd
|
| 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 sha256:3f54f39a371c50895b5183c8700eedca764b4b56a2526d6a3a956a8e10b86171
|
| 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": 35.
|
| 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,
|
|
@@ -8234,6 +8234,24 @@
|
|
| 8234 |
"mean_token_accuracy": 0.6659534931182861,
|
| 8235 |
"num_tokens": 16668179.0,
|
| 8236 |
"step": 4570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8237 |
}
|
| 8238 |
],
|
| 8239 |
"logging_steps": 5,
|
|
@@ -8253,7 +8271,7 @@
|
|
| 8253 |
"attributes": {}
|
| 8254 |
}
|
| 8255 |
},
|
| 8256 |
-
"total_flos": 8.
|
| 8257 |
"train_batch_size": 4,
|
| 8258 |
"trial_name": null,
|
| 8259 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 35.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8234 |
"mean_token_accuracy": 0.6659534931182861,
|
| 8235 |
"num_tokens": 16668179.0,
|
| 8236 |
"step": 4570
|
| 8237 |
+
},
|
| 8238 |
+
{
|
| 8239 |
+
"epoch": 35.19230769230769,
|
| 8240 |
+
"grad_norm": 0.0,
|
| 8241 |
+
"learning_rate": 2.713e-05,
|
| 8242 |
+
"loss": 1.7469,
|
| 8243 |
+
"mean_token_accuracy": 0.6515377521514892,
|
| 8244 |
+
"num_tokens": 16686202.0,
|
| 8245 |
+
"step": 4575
|
| 8246 |
+
},
|
| 8247 |
+
{
|
| 8248 |
+
"epoch": 35.23076923076923,
|
| 8249 |
+
"grad_norm": 0.0,
|
| 8250 |
+
"learning_rate": 2.7105000000000002e-05,
|
| 8251 |
+
"loss": 1.758,
|
| 8252 |
+
"mean_token_accuracy": 0.6510407030582428,
|
| 8253 |
+
"num_tokens": 16704566.0,
|
| 8254 |
+
"step": 4580
|
| 8255 |
}
|
| 8256 |
],
|
| 8257 |
"logging_steps": 5,
|
|
|
|
| 8271 |
"attributes": {}
|
| 8272 |
}
|
| 8273 |
},
|
| 8274 |
+
"total_flos": 8.46618346708992e+17,
|
| 8275 |
"train_batch_size": 4,
|
| 8276 |
"trial_name": null,
|
| 8277 |
"trial_params": null
|