Training in progress, step 7260, 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:def4ab477602ff2136edb301de1b5e22a247c84e2a457c7511103446b20d7546
|
| 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 sha256:6fbd8842f608f73ce2faa8f5a8b5b0d34fe30b78a5fc0ea1c301473632b2b654
|
| 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 sha256:02e5d4ff994f72a203c79180d0ecef5877b83f585747bc4f99f2ab10c8a788b7
|
| 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": 55.
|
| 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,
|
|
@@ -13058,6 +13058,24 @@
|
|
| 13058 |
"mean_token_accuracy": 0.6388367056846619,
|
| 13059 |
"num_tokens": 26440984.0,
|
| 13060 |
"step": 7250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13061 |
}
|
| 13062 |
],
|
| 13063 |
"logging_steps": 5,
|
|
@@ -13077,7 +13095,7 @@
|
|
| 13077 |
"attributes": {}
|
| 13078 |
}
|
| 13079 |
},
|
| 13080 |
-
"total_flos": 1.
|
| 13081 |
"train_batch_size": 4,
|
| 13082 |
"trial_name": null,
|
| 13083 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13058 |
"mean_token_accuracy": 0.6388367056846619,
|
| 13059 |
"num_tokens": 26440984.0,
|
| 13060 |
"step": 7250
|
| 13061 |
+
},
|
| 13062 |
+
{
|
| 13063 |
+
"epoch": 55.80769230769231,
|
| 13064 |
+
"grad_norm": 0.0,
|
| 13065 |
+
"learning_rate": 1.373e-05,
|
| 13066 |
+
"loss": 1.7501,
|
| 13067 |
+
"mean_token_accuracy": 0.6547516256570816,
|
| 13068 |
+
"num_tokens": 26459173.0,
|
| 13069 |
+
"step": 7255
|
| 13070 |
+
},
|
| 13071 |
+
{
|
| 13072 |
+
"epoch": 55.84615384615385,
|
| 13073 |
+
"grad_norm": 0.0,
|
| 13074 |
+
"learning_rate": 1.3705000000000002e-05,
|
| 13075 |
+
"loss": 1.7926,
|
| 13076 |
+
"mean_token_accuracy": 0.6436378836631775,
|
| 13077 |
+
"num_tokens": 26477032.0,
|
| 13078 |
+
"step": 7260
|
| 13079 |
}
|
| 13080 |
],
|
| 13081 |
"logging_steps": 5,
|
|
|
|
| 13095 |
"attributes": {}
|
| 13096 |
}
|
| 13097 |
},
|
| 13098 |
+
"total_flos": 1.342492924257239e+18,
|
| 13099 |
"train_batch_size": 4,
|
| 13100 |
"trial_name": null,
|
| 13101 |
"trial_params": null
|