Training in progress, step 3510, 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:ad4739fd4d76b4ee239e9e6390ae68e966542c4ceef88878b6a28e0e5b6480f5
|
| 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 sha256:7720f5785bac8e40b46db0597bd1128ef8edc8054bc56e274d4008edc94fb715
|
| 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 sha256:2c08f1c217caa856ff5992cdd49da41a2af7f29d19208c5527782e80545f64d4
|
| 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,
|
|
@@ -6308,6 +6308,24 @@
|
|
| 6308 |
"mean_token_accuracy": 0.6475391507148742,
|
| 6309 |
"num_tokens": 12765847.0,
|
| 6310 |
"step": 3500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6311 |
}
|
| 6312 |
],
|
| 6313 |
"logging_steps": 5,
|
|
@@ -6327,7 +6345,7 @@
|
|
| 6327 |
"attributes": {}
|
| 6328 |
}
|
| 6329 |
},
|
| 6330 |
-
"total_flos": 6.
|
| 6331 |
"train_batch_size": 4,
|
| 6332 |
"trial_name": null,
|
| 6333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 27.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6308 |
"mean_token_accuracy": 0.6475391507148742,
|
| 6309 |
"num_tokens": 12765847.0,
|
| 6310 |
"step": 3500
|
| 6311 |
+
},
|
| 6312 |
+
{
|
| 6313 |
+
"epoch": 26.96153846153846,
|
| 6314 |
+
"grad_norm": 0.0,
|
| 6315 |
+
"learning_rate": 3.248e-05,
|
| 6316 |
+
"loss": 1.7987,
|
| 6317 |
+
"mean_token_accuracy": 0.6450091898441315,
|
| 6318 |
+
"num_tokens": 12783426.0,
|
| 6319 |
+
"step": 3505
|
| 6320 |
+
},
|
| 6321 |
+
{
|
| 6322 |
+
"epoch": 27.0,
|
| 6323 |
+
"grad_norm": 0.0,
|
| 6324 |
+
"learning_rate": 3.2455e-05,
|
| 6325 |
+
"loss": 1.8088,
|
| 6326 |
+
"mean_token_accuracy": 0.6360502719879151,
|
| 6327 |
+
"num_tokens": 12800835.0,
|
| 6328 |
+
"step": 3510
|
| 6329 |
}
|
| 6330 |
],
|
| 6331 |
"logging_steps": 5,
|
|
|
|
| 6345 |
"attributes": {}
|
| 6346 |
}
|
| 6347 |
},
|
| 6348 |
+
"total_flos": 6.485527938731213e+17,
|
| 6349 |
"train_batch_size": 4,
|
| 6350 |
"trial_name": null,
|
| 6351 |
"trial_params": null
|