Training in progress, step 8590, 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 sha256:2dce9ea148eff9d027fad08436e458a030e6b262764067a369a78071eba70bd6
|
| 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 sha256:42ebdd5ba30a66e1283c27ea4144b7e9f3d9bea044d9342f49596ecbe7afdd90
|
| 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:ae9a18a622eb3b6d40691c04a293424f89faa7e4debeb32f8c6e2ffb59b95e8e
|
| 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": 66.
|
| 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,
|
|
@@ -15452,6 +15452,24 @@
|
|
| 15452 |
"mean_token_accuracy": 0.6479190230369568,
|
| 15453 |
"num_tokens": 31290930.0,
|
| 15454 |
"step": 8580
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15455 |
}
|
| 15456 |
],
|
| 15457 |
"logging_steps": 5,
|
|
@@ -15471,7 +15489,7 @@
|
|
| 15471 |
"attributes": {}
|
| 15472 |
}
|
| 15473 |
},
|
| 15474 |
-
"total_flos": 1.
|
| 15475 |
"train_batch_size": 4,
|
| 15476 |
"trial_name": null,
|
| 15477 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 66.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8590,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15452 |
"mean_token_accuracy": 0.6479190230369568,
|
| 15453 |
"num_tokens": 31290930.0,
|
| 15454 |
"step": 8580
|
| 15455 |
+
},
|
| 15456 |
+
{
|
| 15457 |
+
"epoch": 66.03846153846153,
|
| 15458 |
+
"grad_norm": 0.0,
|
| 15459 |
+
"learning_rate": 7.080000000000001e-06,
|
| 15460 |
+
"loss": 1.694,
|
| 15461 |
+
"mean_token_accuracy": 0.6604873329401016,
|
| 15462 |
+
"num_tokens": 31309688.0,
|
| 15463 |
+
"step": 8585
|
| 15464 |
+
},
|
| 15465 |
+
{
|
| 15466 |
+
"epoch": 66.07692307692308,
|
| 15467 |
+
"grad_norm": 0.0,
|
| 15468 |
+
"learning_rate": 7.055e-06,
|
| 15469 |
+
"loss": 1.768,
|
| 15470 |
+
"mean_token_accuracy": 0.6487796038389206,
|
| 15471 |
+
"num_tokens": 31327646.0,
|
| 15472 |
+
"step": 8590
|
| 15473 |
}
|
| 15474 |
],
|
| 15475 |
"logging_steps": 5,
|
|
|
|
| 15489 |
"attributes": {}
|
| 15490 |
}
|
| 15491 |
},
|
| 15492 |
+
"total_flos": 1.5884853272690688e+18,
|
| 15493 |
"train_batch_size": 4,
|
| 15494 |
"trial_name": null,
|
| 15495 |
"trial_params": null
|