Training in progress, step 8580, 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 sha256:47a0e4b5cc866f765c880319747c93d98e6b39b409ba2214606b6adc3a2f0c77
|
| 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 sha256:2335464f1c502db5d15a56ac8210a5ac0815f3b986aa938b62f6fc61c1af5b0b
|
| 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:c7d106feb4678c78a75cd3b1cfe8cbbc2d437e09a0f8758c1381b1a5ea68b53c
|
| 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,
|
|
@@ -15434,6 +15434,24 @@
|
|
| 15434 |
"mean_token_accuracy": 0.6507874131202698,
|
| 15435 |
"num_tokens": 31255303.0,
|
| 15436 |
"step": 8570
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15437 |
}
|
| 15438 |
],
|
| 15439 |
"logging_steps": 5,
|
|
@@ -15453,7 +15471,7 @@
|
|
| 15453 |
"attributes": {}
|
| 15454 |
}
|
| 15455 |
},
|
| 15456 |
-
"total_flos": 1.
|
| 15457 |
"train_batch_size": 4,
|
| 15458 |
"trial_name": null,
|
| 15459 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8580,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15434 |
"mean_token_accuracy": 0.6507874131202698,
|
| 15435 |
"num_tokens": 31255303.0,
|
| 15436 |
"step": 8570
|
| 15437 |
+
},
|
| 15438 |
+
{
|
| 15439 |
+
"epoch": 65.96153846153847,
|
| 15440 |
+
"grad_norm": 0.0,
|
| 15441 |
+
"learning_rate": 7.13e-06,
|
| 15442 |
+
"loss": 1.7875,
|
| 15443 |
+
"mean_token_accuracy": 0.6378930985927582,
|
| 15444 |
+
"num_tokens": 31273030.0,
|
| 15445 |
+
"step": 8575
|
| 15446 |
+
},
|
| 15447 |
+
{
|
| 15448 |
+
"epoch": 66.0,
|
| 15449 |
+
"grad_norm": 0.0,
|
| 15450 |
+
"learning_rate": 7.105000000000001e-06,
|
| 15451 |
+
"loss": 1.7661,
|
| 15452 |
+
"mean_token_accuracy": 0.6479190230369568,
|
| 15453 |
+
"num_tokens": 31290930.0,
|
| 15454 |
+
"step": 8580
|
| 15455 |
}
|
| 15456 |
],
|
| 15457 |
"logging_steps": 5,
|
|
|
|
| 15471 |
"attributes": {}
|
| 15472 |
}
|
| 15473 |
},
|
| 15474 |
+
"total_flos": 1.5866249120125747e+18,
|
| 15475 |
"train_batch_size": 4,
|
| 15476 |
"trial_name": null,
|
| 15477 |
"trial_params": null
|