Training in progress, step 5070, 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 sha256:0c9fd91325d146f6f99377c60c5b16ad21b4b5eb52c7b05e8f5d051256bbad1d
|
| 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 sha256:5b2f7e62a6890e3ca448b1ea721127d781e5bffd595689c429ea83e262946906
|
| 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 sha256:6ea7872f6e3892a4498aa8b61d8b6a5903f033bc1b3af4b7503f42904960ac4b
|
| 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,
|
|
@@ -9116,6 +9116,24 @@
|
|
| 9116 |
"mean_token_accuracy": 0.6524721384048462,
|
| 9117 |
"num_tokens": 18453025.0,
|
| 9118 |
"step": 5060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9119 |
}
|
| 9120 |
],
|
| 9121 |
"logging_steps": 5,
|
|
@@ -9135,7 +9153,7 @@
|
|
| 9135 |
"attributes": {}
|
| 9136 |
}
|
| 9137 |
},
|
| 9138 |
-
"total_flos": 9.
|
| 9139 |
"train_batch_size": 4,
|
| 9140 |
"trial_name": null,
|
| 9141 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9116 |
"mean_token_accuracy": 0.6524721384048462,
|
| 9117 |
"num_tokens": 18453025.0,
|
| 9118 |
"step": 5060
|
| 9119 |
+
},
|
| 9120 |
+
{
|
| 9121 |
+
"epoch": 38.96153846153846,
|
| 9122 |
+
"grad_norm": 0.0,
|
| 9123 |
+
"learning_rate": 2.468e-05,
|
| 9124 |
+
"loss": 1.7789,
|
| 9125 |
+
"mean_token_accuracy": 0.6459534347057343,
|
| 9126 |
+
"num_tokens": 18470888.0,
|
| 9127 |
+
"step": 5065
|
| 9128 |
+
},
|
| 9129 |
+
{
|
| 9130 |
+
"epoch": 39.0,
|
| 9131 |
+
"grad_norm": 0.0,
|
| 9132 |
+
"learning_rate": 2.4655e-05,
|
| 9133 |
+
"loss": 1.6775,
|
| 9134 |
+
"mean_token_accuracy": 0.6582199364900589,
|
| 9135 |
+
"num_tokens": 18490095.0,
|
| 9136 |
+
"step": 5070
|
| 9137 |
}
|
| 9138 |
],
|
| 9139 |
"logging_steps": 5,
|
|
|
|
| 9153 |
"attributes": {}
|
| 9154 |
}
|
| 9155 |
},
|
| 9156 |
+
"total_flos": 9.369311311945728e+17,
|
| 9157 |
"train_batch_size": 4,
|
| 9158 |
"trial_name": null,
|
| 9159 |
"trial_params": null
|