Training in progress, step 9130, 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 sha256:144d8dc24162221c68e69bd9c6fa4a11f3ee37e8872106cbe96ecd1bec254189
|
| 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 sha256:5d3d03f7d57cfd3110cc64751ca4941a21e4b4674d3b1aa04bd78a942030ce2e
|
| 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 sha256:51145f02caaaed6a77db2bf6b07d817d12e1e841ebfa217e918532c191544ecd
|
| 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": 70.
|
| 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,
|
|
@@ -16424,6 +16424,24 @@
|
|
| 16424 |
"mean_token_accuracy": 0.6556406348943711,
|
| 16425 |
"num_tokens": 33261667.0,
|
| 16426 |
"step": 9120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16427 |
}
|
| 16428 |
],
|
| 16429 |
"logging_steps": 5,
|
|
@@ -16443,7 +16461,7 @@
|
|
| 16443 |
"attributes": {}
|
| 16444 |
}
|
| 16445 |
},
|
| 16446 |
-
"total_flos": 1.
|
| 16447 |
"train_batch_size": 4,
|
| 16448 |
"trial_name": null,
|
| 16449 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9130,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16424 |
"mean_token_accuracy": 0.6556406348943711,
|
| 16425 |
"num_tokens": 33261667.0,
|
| 16426 |
"step": 9120
|
| 16427 |
+
},
|
| 16428 |
+
{
|
| 16429 |
+
"epoch": 70.1923076923077,
|
| 16430 |
+
"grad_norm": 0.0,
|
| 16431 |
+
"learning_rate": 4.38e-06,
|
| 16432 |
+
"loss": 1.7115,
|
| 16433 |
+
"mean_token_accuracy": 0.6550081551074982,
|
| 16434 |
+
"num_tokens": 33280058.0,
|
| 16435 |
+
"step": 9125
|
| 16436 |
+
},
|
| 16437 |
+
{
|
| 16438 |
+
"epoch": 70.23076923076923,
|
| 16439 |
+
"grad_norm": 0.0,
|
| 16440 |
+
"learning_rate": 4.355e-06,
|
| 16441 |
+
"loss": 1.6983,
|
| 16442 |
+
"mean_token_accuracy": 0.6546464413404465,
|
| 16443 |
+
"num_tokens": 33299469.0,
|
| 16444 |
+
"step": 9130
|
| 16445 |
}
|
| 16446 |
],
|
| 16447 |
"logging_steps": 5,
|
|
|
|
| 16461 |
"attributes": {}
|
| 16462 |
}
|
| 16463 |
},
|
| 16464 |
+
"total_flos": 1.6885733498929152e+18,
|
| 16465 |
"train_batch_size": 4,
|
| 16466 |
"trial_name": null,
|
| 16467 |
"trial_params": null
|