Training in progress, step 6400, 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 sha256:0fcdddb3205fc39b0d17b0a66929c147bb81190e9ec07b5b74cb7108475c7b60
|
| 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:f02ce76f7e5243520f7149be6fe498ba53c9585449492dc5dbe009d8f83af6e3
|
| 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:abfd33050a9eea1b4c3b053077d50de96001d65a09fdb39807cdb294b78e59e1
|
| 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": 49.
|
| 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,
|
|
@@ -11510,6 +11510,24 @@
|
|
| 11510 |
"mean_token_accuracy": 0.6448217332363129,
|
| 11511 |
"num_tokens": 23304489.0,
|
| 11512 |
"step": 6390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11513 |
}
|
| 11514 |
],
|
| 11515 |
"logging_steps": 5,
|
|
@@ -11529,7 +11547,7 @@
|
|
| 11529 |
"attributes": {}
|
| 11530 |
}
|
| 11531 |
},
|
| 11532 |
-
"total_flos": 1.
|
| 11533 |
"train_batch_size": 4,
|
| 11534 |
"trial_name": null,
|
| 11535 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11510 |
"mean_token_accuracy": 0.6448217332363129,
|
| 11511 |
"num_tokens": 23304489.0,
|
| 11512 |
"step": 6390
|
| 11513 |
+
},
|
| 11514 |
+
{
|
| 11515 |
+
"epoch": 49.19230769230769,
|
| 11516 |
+
"grad_norm": 0.0,
|
| 11517 |
+
"learning_rate": 1.803e-05,
|
| 11518 |
+
"loss": 1.7013,
|
| 11519 |
+
"mean_token_accuracy": 0.6568325966596603,
|
| 11520 |
+
"num_tokens": 23323802.0,
|
| 11521 |
+
"step": 6395
|
| 11522 |
+
},
|
| 11523 |
+
{
|
| 11524 |
+
"epoch": 49.23076923076923,
|
| 11525 |
+
"grad_norm": 0.0,
|
| 11526 |
+
"learning_rate": 1.8005e-05,
|
| 11527 |
+
"loss": 1.6943,
|
| 11528 |
+
"mean_token_accuracy": 0.6581353217363357,
|
| 11529 |
+
"num_tokens": 23342349.0,
|
| 11530 |
+
"step": 6400
|
| 11531 |
}
|
| 11532 |
],
|
| 11533 |
"logging_steps": 5,
|
|
|
|
| 11547 |
"attributes": {}
|
| 11548 |
}
|
| 11549 |
},
|
| 11550 |
+
"total_flos": 1.1833092087526195e+18,
|
| 11551 |
"train_batch_size": 4,
|
| 11552 |
"trial_name": null,
|
| 11553 |
"trial_params": null
|