Training in progress, step 6690, 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 sha256:8425203c4f8b28d9afc91bcce935e80c697a6a139176f0ba9da5345b968ac4e8
|
| 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 sha256:44837c310d43eed0aea3b9101585f0d0b69f09effddc63eaf104cc18215e1321
|
| 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:b655e97096b3218357cddd0792a4b7921f363bf5015b73adb77bfe836c306dbc
|
| 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": 51.
|
| 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,
|
|
@@ -12032,6 +12032,24 @@
|
|
| 12032 |
"mean_token_accuracy": 0.6461174368858338,
|
| 12033 |
"num_tokens": 24361431.0,
|
| 12034 |
"step": 6680
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12035 |
}
|
| 12036 |
],
|
| 12037 |
"logging_steps": 5,
|
|
@@ -12051,7 +12069,7 @@
|
|
| 12051 |
"attributes": {}
|
| 12052 |
}
|
| 12053 |
},
|
| 12054 |
-
"total_flos": 1.
|
| 12055 |
"train_batch_size": 4,
|
| 12056 |
"trial_name": null,
|
| 12057 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6690,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12032 |
"mean_token_accuracy": 0.6461174368858338,
|
| 12033 |
"num_tokens": 24361431.0,
|
| 12034 |
"step": 6680
|
| 12035 |
+
},
|
| 12036 |
+
{
|
| 12037 |
+
"epoch": 51.42307692307692,
|
| 12038 |
+
"grad_norm": 0.0,
|
| 12039 |
+
"learning_rate": 1.658e-05,
|
| 12040 |
+
"loss": 1.6647,
|
| 12041 |
+
"mean_token_accuracy": 0.6634925454854965,
|
| 12042 |
+
"num_tokens": 24380890.0,
|
| 12043 |
+
"step": 6685
|
| 12044 |
+
},
|
| 12045 |
+
{
|
| 12046 |
+
"epoch": 51.46153846153846,
|
| 12047 |
+
"grad_norm": 0.0,
|
| 12048 |
+
"learning_rate": 1.6555e-05,
|
| 12049 |
+
"loss": 1.7547,
|
| 12050 |
+
"mean_token_accuracy": 0.650789025425911,
|
| 12051 |
+
"num_tokens": 24398752.0,
|
| 12052 |
+
"step": 6690
|
| 12053 |
}
|
| 12054 |
],
|
| 12055 |
"logging_steps": 5,
|
|
|
|
| 12069 |
"attributes": {}
|
| 12070 |
}
|
| 12071 |
},
|
| 12072 |
+
"total_flos": 1.2369036805536154e+18,
|
| 12073 |
"train_batch_size": 4,
|
| 12074 |
"trial_name": null,
|
| 12075 |
"trial_params": null
|