Training in progress, step 3490, 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 sha256:6d9fb4373b113a892362814da85c250b9e9611d3edb9a2909563908ab3fd1ed3
|
| 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 sha256:2e6ccd7e2387b1854e37bf6006946eef66da8542c52cd2a2f9d2b7d9fec649fc
|
| 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 sha256:491095b68c1b7737caba646490411c967c37853451e47b96522023987d46fe97
|
| 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": 26.
|
| 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,
|
|
@@ -6272,6 +6272,24 @@
|
|
| 6272 |
"mean_token_accuracy": 0.6486168265342712,
|
| 6273 |
"num_tokens": 12693239.0,
|
| 6274 |
"step": 3480
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6275 |
}
|
| 6276 |
],
|
| 6277 |
"logging_steps": 5,
|
|
@@ -6291,7 +6309,7 @@
|
|
| 6291 |
"attributes": {}
|
| 6292 |
}
|
| 6293 |
},
|
| 6294 |
-
"total_flos": 6.
|
| 6295 |
"train_batch_size": 4,
|
| 6296 |
"trial_name": null,
|
| 6297 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3490,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6272 |
"mean_token_accuracy": 0.6486168265342712,
|
| 6273 |
"num_tokens": 12693239.0,
|
| 6274 |
"step": 3480
|
| 6275 |
+
},
|
| 6276 |
+
{
|
| 6277 |
+
"epoch": 26.807692307692307,
|
| 6278 |
+
"grad_norm": 0.0,
|
| 6279 |
+
"learning_rate": 3.2579999999999996e-05,
|
| 6280 |
+
"loss": 1.6658,
|
| 6281 |
+
"mean_token_accuracy": 0.6676429510116577,
|
| 6282 |
+
"num_tokens": 12712177.0,
|
| 6283 |
+
"step": 3485
|
| 6284 |
+
},
|
| 6285 |
+
{
|
| 6286 |
+
"epoch": 26.846153846153847,
|
| 6287 |
+
"grad_norm": 0.0,
|
| 6288 |
+
"learning_rate": 3.2555e-05,
|
| 6289 |
+
"loss": 1.789,
|
| 6290 |
+
"mean_token_accuracy": 0.6442992717027665,
|
| 6291 |
+
"num_tokens": 12729550.0,
|
| 6292 |
+
"step": 3490
|
| 6293 |
}
|
| 6294 |
],
|
| 6295 |
"logging_steps": 5,
|
|
|
|
| 6309 |
"attributes": {}
|
| 6310 |
}
|
| 6311 |
},
|
| 6312 |
+
"total_flos": 6.450115425745306e+17,
|
| 6313 |
"train_batch_size": 4,
|
| 6314 |
"trial_name": null,
|
| 6315 |
"trial_params": null
|