Training in progress, step 70, 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:bc9f79535dd64d8cdd3d56be843a53c2368923aae37a1e838e07280eeeb57a71
|
| 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 sha256:8c5480873be799d147a6712adaab3b5f8598325f1231a3f3c2b04ca4a0ea1c38
|
| 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 sha256:82d5def62b9eff0f44b403f698405cf8fbfb6d9021a371663410a52cb55306c5
|
| 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": 0.
|
| 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,
|
|
@@ -116,6 +116,24 @@
|
|
| 116 |
"mean_token_accuracy": 0.6453521817922592,
|
| 117 |
"num_tokens": 217701.0,
|
| 118 |
"step": 60
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
}
|
| 120 |
],
|
| 121 |
"logging_steps": 5,
|
|
@@ -135,7 +153,7 @@
|
|
| 135 |
"attributes": {}
|
| 136 |
}
|
| 137 |
},
|
| 138 |
-
"total_flos": 1.
|
| 139 |
"train_batch_size": 4,
|
| 140 |
"trial_name": null,
|
| 141 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5384615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 70,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 116 |
"mean_token_accuracy": 0.6453521817922592,
|
| 117 |
"num_tokens": 217701.0,
|
| 118 |
"step": 60
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.5,
|
| 122 |
+
"grad_norm": 0.0,
|
| 123 |
+
"learning_rate": 4.9680000000000005e-05,
|
| 124 |
+
"loss": 1.7214,
|
| 125 |
+
"mean_token_accuracy": 0.658767506480217,
|
| 126 |
+
"num_tokens": 236196.0,
|
| 127 |
+
"step": 65
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.5384615384615384,
|
| 131 |
+
"grad_norm": 0.0,
|
| 132 |
+
"learning_rate": 4.9655000000000005e-05,
|
| 133 |
+
"loss": 1.7138,
|
| 134 |
+
"mean_token_accuracy": 0.6556680232286454,
|
| 135 |
+
"num_tokens": 254323.0,
|
| 136 |
+
"step": 70
|
| 137 |
}
|
| 138 |
],
|
| 139 |
"logging_steps": 5,
|
|
|
|
| 153 |
"attributes": {}
|
| 154 |
}
|
| 155 |
},
|
| 156 |
+
"total_flos": 1.275044178051072e+16,
|
| 157 |
"train_batch_size": 4,
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|