Training in progress, step 7790, 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 sha256:7d3d5046f8166490466a2240ca1b42c8010afe133cbd240ec33180ea5fcb9ed1
|
| 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:a20ef5b9fdbfa68a808af6a2be9c0f845ee00bc654282e021974177703899656
|
| 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 sha256:2f5cb706354ab22cb6fac8efa3e55093c316ead63bd9960d0419d04658306734
|
| 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": 59.
|
| 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,
|
|
@@ -14012,6 +14012,24 @@
|
|
| 14012 |
"mean_token_accuracy": 0.6550350069999695,
|
| 14013 |
"num_tokens": 28374046.0,
|
| 14014 |
"step": 7780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14015 |
}
|
| 14016 |
],
|
| 14017 |
"logging_steps": 5,
|
|
@@ -14031,7 +14049,7 @@
|
|
| 14031 |
"attributes": {}
|
| 14032 |
}
|
| 14033 |
},
|
| 14034 |
-
"total_flos": 1.
|
| 14035 |
"train_batch_size": 4,
|
| 14036 |
"trial_name": null,
|
| 14037 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 59.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7790,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14012 |
"mean_token_accuracy": 0.6550350069999695,
|
| 14013 |
"num_tokens": 28374046.0,
|
| 14014 |
"step": 7780
|
| 14015 |
+
},
|
| 14016 |
+
{
|
| 14017 |
+
"epoch": 59.88461538461539,
|
| 14018 |
+
"grad_norm": 0.0,
|
| 14019 |
+
"learning_rate": 1.108e-05,
|
| 14020 |
+
"loss": 1.7463,
|
| 14021 |
+
"mean_token_accuracy": 0.6461563289165497,
|
| 14022 |
+
"num_tokens": 28392669.0,
|
| 14023 |
+
"step": 7785
|
| 14024 |
+
},
|
| 14025 |
+
{
|
| 14026 |
+
"epoch": 59.92307692307692,
|
| 14027 |
+
"grad_norm": 0.0,
|
| 14028 |
+
"learning_rate": 1.1055e-05,
|
| 14029 |
+
"loss": 1.7571,
|
| 14030 |
+
"mean_token_accuracy": 0.6455042749643326,
|
| 14031 |
+
"num_tokens": 28410567.0,
|
| 14032 |
+
"step": 7790
|
| 14033 |
}
|
| 14034 |
],
|
| 14035 |
"logging_steps": 5,
|
|
|
|
| 14049 |
"attributes": {}
|
| 14050 |
}
|
| 14051 |
},
|
| 14052 |
+
"total_flos": 1.4405685799816397e+18,
|
| 14053 |
"train_batch_size": 4,
|
| 14054 |
"trial_name": null,
|
| 14055 |
"trial_params": null
|