Training in progress, step 9610, 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 sha256:1d9d60f87fa1ed154b8d5c453bdb5bb3b9943386a25af4b0124d9b1be7dd8b7b
|
| 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:e7ca6338723730b38f3084c22e58b2e124d074c0c5adf46895eadc2dd4c4b497
|
| 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:a73b20d16af2d8cc9b0996cba4388b48c2be03fc36e8a92f9c4df64b9ed9a7db
|
| 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": 73.
|
| 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,
|
|
@@ -17288,6 +17288,24 @@
|
|
| 17288 |
"mean_token_accuracy": 0.6461809724569321,
|
| 17289 |
"num_tokens": 35010375.0,
|
| 17290 |
"step": 9600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17291 |
}
|
| 17292 |
],
|
| 17293 |
"logging_steps": 5,
|
|
@@ -17307,7 +17325,7 @@
|
|
| 17307 |
"attributes": {}
|
| 17308 |
}
|
| 17309 |
},
|
| 17310 |
-
"total_flos": 1.
|
| 17311 |
"train_batch_size": 4,
|
| 17312 |
"trial_name": null,
|
| 17313 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 73.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9610,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17288 |
"mean_token_accuracy": 0.6461809724569321,
|
| 17289 |
"num_tokens": 35010375.0,
|
| 17290 |
"step": 9600
|
| 17291 |
+
},
|
| 17292 |
+
{
|
| 17293 |
+
"epoch": 73.88461538461539,
|
| 17294 |
+
"grad_norm": 0.0,
|
| 17295 |
+
"learning_rate": 1.98e-06,
|
| 17296 |
+
"loss": 1.7652,
|
| 17297 |
+
"mean_token_accuracy": 0.6461312264204025,
|
| 17298 |
+
"num_tokens": 35028006.0,
|
| 17299 |
+
"step": 9605
|
| 17300 |
+
},
|
| 17301 |
+
{
|
| 17302 |
+
"epoch": 73.92307692307692,
|
| 17303 |
+
"grad_norm": 0.0,
|
| 17304 |
+
"learning_rate": 1.9550000000000003e-06,
|
| 17305 |
+
"loss": 1.7037,
|
| 17306 |
+
"mean_token_accuracy": 0.656490358710289,
|
| 17307 |
+
"num_tokens": 35046822.0,
|
| 17308 |
+
"step": 9610
|
| 17309 |
}
|
| 17310 |
],
|
| 17311 |
"logging_steps": 5,
|
|
|
|
| 17325 |
"attributes": {}
|
| 17326 |
}
|
| 17327 |
},
|
| 17328 |
+
"total_flos": 1.777330733861929e+18,
|
| 17329 |
"train_batch_size": 4,
|
| 17330 |
"trial_name": null,
|
| 17331 |
"trial_params": null
|