Training in progress, step 570, 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:c9695c544ec017d04c76c1d57dce185be9c6ede4cbaca7b10427402f09c9b889
|
| 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 sha256:555f9a79cac721b73d3248c947ea8ea9c5fa554d8db3455c2ee689adcf9b9db6
|
| 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:b1fef65992aa63a14b0144efe1ccb618dadccb88eb526d7e4ff70ce554abaf1d
|
| 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": 4.
|
| 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,
|
|
@@ -1016,6 +1016,24 @@
|
|
| 1016 |
"mean_token_accuracy": 0.6540951490402221,
|
| 1017 |
"num_tokens": 2042349.0,
|
| 1018 |
"step": 560
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1019 |
}
|
| 1020 |
],
|
| 1021 |
"logging_steps": 5,
|
|
@@ -1035,7 +1053,7 @@
|
|
| 1035 |
"attributes": {}
|
| 1036 |
}
|
| 1037 |
},
|
| 1038 |
-
"total_flos": 1.
|
| 1039 |
"train_batch_size": 4,
|
| 1040 |
"trial_name": null,
|
| 1041 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.384615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 570,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1016 |
"mean_token_accuracy": 0.6540951490402221,
|
| 1017 |
"num_tokens": 2042349.0,
|
| 1018 |
"step": 560
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 4.346153846153846,
|
| 1022 |
+
"grad_norm": 0.0,
|
| 1023 |
+
"learning_rate": 4.718e-05,
|
| 1024 |
+
"loss": 1.7127,
|
| 1025 |
+
"mean_token_accuracy": 0.6528139978647232,
|
| 1026 |
+
"num_tokens": 2060824.0,
|
| 1027 |
+
"step": 565
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 4.384615384615385,
|
| 1031 |
+
"grad_norm": 0.0,
|
| 1032 |
+
"learning_rate": 4.7155000000000005e-05,
|
| 1033 |
+
"loss": 1.7282,
|
| 1034 |
+
"mean_token_accuracy": 0.6538840979337692,
|
| 1035 |
+
"num_tokens": 2079449.0,
|
| 1036 |
+
"step": 570
|
| 1037 |
}
|
| 1038 |
],
|
| 1039 |
"logging_steps": 5,
|
|
|
|
| 1053 |
"attributes": {}
|
| 1054 |
}
|
| 1055 |
},
|
| 1056 |
+
"total_flos": 1.0532154206306304e+17,
|
| 1057 |
"train_batch_size": 4,
|
| 1058 |
"trial_name": null,
|
| 1059 |
"trial_params": null
|