Training in progress, step 1680, 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:d69e3528114ad73a5be3244f66f5fdd101cad790c946bf2deb3d78c9599e03ae
|
| 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:b7203ac4000667b012e8979a922d8244ff786ba35cce4687d4de37db5d5572db
|
| 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 sha256:31b0b29b20c544055bbfc5f546278f1646ba18727aeeadf28c9f8a28735c05f4
|
| 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": 12.
|
| 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,
|
|
@@ -3014,6 +3014,24 @@
|
|
| 3014 |
"mean_token_accuracy": 0.6513452738523483,
|
| 3015 |
"num_tokens": 6090024.0,
|
| 3016 |
"step": 1670
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3017 |
}
|
| 3018 |
],
|
| 3019 |
"logging_steps": 5,
|
|
@@ -3033,7 +3051,7 @@
|
|
| 3033 |
"attributes": {}
|
| 3034 |
}
|
| 3035 |
},
|
| 3036 |
-
"total_flos": 3.
|
| 3037 |
"train_batch_size": 4,
|
| 3038 |
"trial_name": null,
|
| 3039 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1680,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3014 |
"mean_token_accuracy": 0.6513452738523483,
|
| 3015 |
"num_tokens": 6090024.0,
|
| 3016 |
"step": 1670
|
| 3017 |
+
},
|
| 3018 |
+
{
|
| 3019 |
+
"epoch": 12.884615384615385,
|
| 3020 |
+
"grad_norm": 0.0,
|
| 3021 |
+
"learning_rate": 4.163e-05,
|
| 3022 |
+
"loss": 1.7536,
|
| 3023 |
+
"mean_token_accuracy": 0.6504515618085861,
|
| 3024 |
+
"num_tokens": 6108154.0,
|
| 3025 |
+
"step": 1675
|
| 3026 |
+
},
|
| 3027 |
+
{
|
| 3028 |
+
"epoch": 12.923076923076923,
|
| 3029 |
+
"grad_norm": 0.0,
|
| 3030 |
+
"learning_rate": 4.1605e-05,
|
| 3031 |
+
"loss": 1.7592,
|
| 3032 |
+
"mean_token_accuracy": 0.6449838757514954,
|
| 3033 |
+
"num_tokens": 6126273.0,
|
| 3034 |
+
"step": 1680
|
| 3035 |
}
|
| 3036 |
],
|
| 3037 |
"logging_steps": 5,
|
|
|
|
| 3051 |
"attributes": {}
|
| 3052 |
}
|
| 3053 |
},
|
| 3054 |
+
"total_flos": 3.103366993507123e+17,
|
| 3055 |
"train_batch_size": 4,
|
| 3056 |
"trial_name": null,
|
| 3057 |
"trial_params": null
|