Training in progress, step 4230, 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 sha256:39a2c7e77f016bb9b3375e76286b19e777df3391c19fa9f47514fc98bc1f53d4
|
| 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 sha256:547296ffbb3f464a550f7ae47d97abe3020026b3a3dfe987e4a48ea1cc669b18
|
| 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 sha256:81d809b27a363a2de95c44d79004202c8357efc162f151e41d4c02c61f8fea0e
|
| 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": 32.
|
| 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,
|
|
@@ -7604,6 +7604,24 @@
|
|
| 7604 |
"mean_token_accuracy": 0.6474568367004394,
|
| 7605 |
"num_tokens": 15391589.0,
|
| 7606 |
"step": 4220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7607 |
}
|
| 7608 |
],
|
| 7609 |
"logging_steps": 5,
|
|
@@ -7623,7 +7641,7 @@
|
|
| 7623 |
"attributes": {}
|
| 7624 |
}
|
| 7625 |
},
|
| 7626 |
-
"total_flos": 7.
|
| 7627 |
"train_batch_size": 4,
|
| 7628 |
"trial_name": null,
|
| 7629 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7604 |
"mean_token_accuracy": 0.6474568367004394,
|
| 7605 |
"num_tokens": 15391589.0,
|
| 7606 |
"step": 4220
|
| 7607 |
+
},
|
| 7608 |
+
{
|
| 7609 |
+
"epoch": 32.5,
|
| 7610 |
+
"grad_norm": 0.0,
|
| 7611 |
+
"learning_rate": 2.888e-05,
|
| 7612 |
+
"loss": 1.7877,
|
| 7613 |
+
"mean_token_accuracy": 0.637940239906311,
|
| 7614 |
+
"num_tokens": 15409383.0,
|
| 7615 |
+
"step": 4225
|
| 7616 |
+
},
|
| 7617 |
+
{
|
| 7618 |
+
"epoch": 32.53846153846154,
|
| 7619 |
+
"grad_norm": 0.0,
|
| 7620 |
+
"learning_rate": 2.8854999999999997e-05,
|
| 7621 |
+
"loss": 1.6901,
|
| 7622 |
+
"mean_token_accuracy": 0.6617184728384018,
|
| 7623 |
+
"num_tokens": 15428238.0,
|
| 7624 |
+
"step": 4230
|
| 7625 |
}
|
| 7626 |
],
|
| 7627 |
"logging_steps": 5,
|
|
|
|
| 7641 |
"attributes": {}
|
| 7642 |
}
|
| 7643 |
},
|
| 7644 |
+
"total_flos": 7.819637959183565e+17,
|
| 7645 |
"train_batch_size": 4,
|
| 7646 |
"trial_name": null,
|
| 7647 |
"trial_params": null
|