re-trained age classifier with new prefix
Browse files- all_results.json +5 -5
- train_results.json +0 -9
- trainer_state.json +8 -8
- training_args.bin +0 -0
all_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
"train_samples": 10842,
|
| 7 |
-
"train_samples_per_second": 23.
|
| 8 |
-
"train_steps_per_second": 2.
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 2.0,
|
| 3 |
+
"total_flos": 3504393242025984.0,
|
| 4 |
+
"train_loss": 1.7561454885477161,
|
| 5 |
+
"train_runtime": 923.5466,
|
| 6 |
"train_samples": 10842,
|
| 7 |
+
"train_samples_per_second": 23.479,
|
| 8 |
+
"train_steps_per_second": 2.937
|
| 9 |
}
|
train_results.json
DELETED
|
@@ -1,9 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.0,
|
| 3 |
-
"total_flos": 3524249494757376.0,
|
| 4 |
-
"train_loss": 1.206946437689407,
|
| 5 |
-
"train_runtime": 917.4346,
|
| 6 |
-
"train_samples": 10842,
|
| 7 |
-
"train_samples_per_second": 23.635,
|
| 8 |
-
"train_steps_per_second": 2.956
|
| 9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
trainer_state.json
CHANGED
|
@@ -10,28 +10,28 @@
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
"learning_rate": 5e-06,
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 1356
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 2.0,
|
| 18 |
"learning_rate": 0.0,
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 2712
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 2.0,
|
| 24 |
"step": 2712,
|
| 25 |
-
"total_flos":
|
| 26 |
-
"train_loss": 1.
|
| 27 |
-
"train_runtime":
|
| 28 |
-
"train_samples_per_second": 23.
|
| 29 |
-
"train_steps_per_second": 2.
|
| 30 |
}
|
| 31 |
],
|
| 32 |
"max_steps": 2712,
|
| 33 |
"num_train_epochs": 2,
|
| 34 |
-
"total_flos":
|
| 35 |
"trial_name": null,
|
| 36 |
"trial_params": null
|
| 37 |
}
|
|
|
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 2.8275,
|
| 14 |
"step": 1356
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 2.0,
|
| 18 |
"learning_rate": 0.0,
|
| 19 |
+
"loss": 0.6848,
|
| 20 |
"step": 2712
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 2.0,
|
| 24 |
"step": 2712,
|
| 25 |
+
"total_flos": 3504393242025984.0,
|
| 26 |
+
"train_loss": 1.7561454885477161,
|
| 27 |
+
"train_runtime": 923.5466,
|
| 28 |
+
"train_samples_per_second": 23.479,
|
| 29 |
+
"train_steps_per_second": 2.937
|
| 30 |
}
|
| 31 |
],
|
| 32 |
"max_steps": 2712,
|
| 33 |
"num_train_epochs": 2,
|
| 34 |
+
"total_flos": 3504393242025984.0,
|
| 35 |
"trial_name": null,
|
| 36 |
"trial_params": null
|
| 37 |
}
|
training_args.bin
CHANGED
|
Binary files a/training_args.bin and b/training_args.bin differ
|
|
|