Training in progress, step 6630, 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 sha256:1993adbe98d600c9641e8f72f79a398139f0fc0a44faab363d253c35a51df318
|
| 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 sha256:6ca13d54fd1ef87891592b25f4cbaf21167c7d9eec52d0ffc22ecf42201ee77d
|
| 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 sha256:797530067fccccdf2fa9c27fb907e1c2ee861b95a99915b9a99772f5a98cd424
|
| 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,
|
|
@@ -11924,6 +11924,24 @@
|
|
| 11924 |
"mean_token_accuracy": 0.6567032128572464,
|
| 11925 |
"num_tokens": 24142871.0,
|
| 11926 |
"step": 6620
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11927 |
}
|
| 11928 |
],
|
| 11929 |
"logging_steps": 5,
|
|
@@ -11943,7 +11961,7 @@
|
|
| 11943 |
"attributes": {}
|
| 11944 |
}
|
| 11945 |
},
|
| 11946 |
-
"total_flos": 1.
|
| 11947 |
"train_batch_size": 4,
|
| 11948 |
"trial_name": null,
|
| 11949 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6630,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11924 |
"mean_token_accuracy": 0.6567032128572464,
|
| 11925 |
"num_tokens": 24142871.0,
|
| 11926 |
"step": 6620
|
| 11927 |
+
},
|
| 11928 |
+
{
|
| 11929 |
+
"epoch": 50.96153846153846,
|
| 11930 |
+
"grad_norm": 0.0,
|
| 11931 |
+
"learning_rate": 1.688e-05,
|
| 11932 |
+
"loss": 1.6891,
|
| 11933 |
+
"mean_token_accuracy": 0.6616051197052002,
|
| 11934 |
+
"num_tokens": 24161666.0,
|
| 11935 |
+
"step": 6625
|
| 11936 |
+
},
|
| 11937 |
+
{
|
| 11938 |
+
"epoch": 51.0,
|
| 11939 |
+
"grad_norm": 0.0,
|
| 11940 |
+
"learning_rate": 1.6855e-05,
|
| 11941 |
+
"loss": 1.7768,
|
| 11942 |
+
"mean_token_accuracy": 0.6428048938512803,
|
| 11943 |
+
"num_tokens": 24179355.0,
|
| 11944 |
+
"step": 6630
|
| 11945 |
}
|
| 11946 |
],
|
| 11947 |
"logging_steps": 5,
|
|
|
|
| 11961 |
"attributes": {}
|
| 11962 |
}
|
| 11963 |
},
|
| 11964 |
+
"total_flos": 1.225903302522962e+18,
|
| 11965 |
"train_batch_size": 4,
|
| 11966 |
"trial_name": null,
|
| 11967 |
"trial_params": null
|