End of training
Browse files- README.md +3 -3
- all_results.json +11 -6
- eval_results.json +8 -0
- runs/Nov26_07-42-22_c0788ea2aa74/events.out.tfevents.1700985649.c0788ea2aa74.27844.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +348 -33
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 1.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.5625
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 1.3141
|
| 36 |
+
- Accuracy: 0.5625
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,8 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 27.83,
|
| 3 |
+
"eval_accuracy": 0.5625,
|
| 4 |
+
"eval_loss": 1.314065933227539,
|
| 5 |
+
"eval_runtime": 1.1151,
|
| 6 |
+
"eval_samples_per_second": 71.743,
|
| 7 |
+
"eval_steps_per_second": 2.69,
|
| 8 |
+
"total_flos": 1.5536429521628037e+18,
|
| 9 |
+
"train_loss": 0.7970057874917984,
|
| 10 |
+
"train_runtime": 905.2766,
|
| 11 |
+
"train_samples_per_second": 25.451,
|
| 12 |
+
"train_steps_per_second": 0.177
|
| 13 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 27.83,
|
| 3 |
+
"eval_accuracy": 0.5625,
|
| 4 |
+
"eval_loss": 1.314065933227539,
|
| 5 |
+
"eval_runtime": 1.1151,
|
| 6 |
+
"eval_samples_per_second": 71.743,
|
| 7 |
+
"eval_steps_per_second": 2.69
|
| 8 |
+
}
|
runs/Nov26_07-42-22_c0788ea2aa74/events.out.tfevents.1700985649.c0788ea2aa74.27844.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e05e264be752fba8b082ba70f077830371f1ec5f4a2ff16706bbbca0448301e
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss":
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 27.83,
|
| 3 |
+
"total_flos": 1.5536429521628037e+18,
|
| 4 |
+
"train_loss": 0.7970057874917984,
|
| 5 |
+
"train_runtime": 905.2766,
|
| 6 |
+
"train_samples_per_second": 25.451,
|
| 7 |
+
"train_steps_per_second": 0.177
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,61 +1,376 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-base-patch16-224-finetuned-Visual-Emotional/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.87,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 2.
|
| 15 |
-
"eval_runtime":
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.74,
|
| 22 |
-
"learning_rate":
|
| 23 |
-
"loss": 2.
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 1.91,
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_loss":
|
| 30 |
-
"eval_runtime": 1.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 2.
|
| 33 |
"step": 11
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 2.
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 1.
|
| 39 |
-
"eval_runtime": 1.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second": 2.
|
| 42 |
-
"step":
|
| 43 |
},
|
| 44 |
{
|
| 45 |
-
"epoch":
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
}
|
| 53 |
],
|
| 54 |
"logging_steps": 10,
|
| 55 |
-
"max_steps":
|
| 56 |
-
"num_train_epochs":
|
| 57 |
"save_steps": 500,
|
| 58 |
-
"total_flos": 1.
|
| 59 |
"trial_name": null,
|
| 60 |
"trial_params": null
|
| 61 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5625,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-finetuned-Visual-Emotional/checkpoint-132",
|
| 4 |
+
"epoch": 27.82608695652174,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 160,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.87,
|
| 13 |
+
"eval_accuracy": 0.15,
|
| 14 |
+
"eval_loss": 2.141930341720581,
|
| 15 |
+
"eval_runtime": 1.0932,
|
| 16 |
+
"eval_samples_per_second": 73.177,
|
| 17 |
+
"eval_steps_per_second": 2.744,
|
| 18 |
"step": 5
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.74,
|
| 22 |
+
"learning_rate": 3.125e-05,
|
| 23 |
+
"loss": 2.1722,
|
| 24 |
"step": 10
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 1.91,
|
| 28 |
+
"eval_accuracy": 0.1625,
|
| 29 |
+
"eval_loss": 2.038079023361206,
|
| 30 |
+
"eval_runtime": 1.0792,
|
| 31 |
+
"eval_samples_per_second": 74.126,
|
| 32 |
+
"eval_steps_per_second": 2.78,
|
| 33 |
"step": 11
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 2.96,
|
| 37 |
+
"eval_accuracy": 0.3,
|
| 38 |
+
"eval_loss": 1.8728723526000977,
|
| 39 |
+
"eval_runtime": 1.0061,
|
| 40 |
+
"eval_samples_per_second": 79.518,
|
| 41 |
+
"eval_steps_per_second": 2.982,
|
| 42 |
+
"step": 17
|
| 43 |
},
|
| 44 |
{
|
| 45 |
+
"epoch": 3.48,
|
| 46 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 47 |
+
"loss": 1.8696,
|
| 48 |
+
"step": 20
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.3625,
|
| 53 |
+
"eval_loss": 1.6683166027069092,
|
| 54 |
+
"eval_runtime": 1.0334,
|
| 55 |
+
"eval_samples_per_second": 77.411,
|
| 56 |
+
"eval_steps_per_second": 2.903,
|
| 57 |
+
"step": 23
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.87,
|
| 61 |
+
"eval_accuracy": 0.4,
|
| 62 |
+
"eval_loss": 1.5172284841537476,
|
| 63 |
+
"eval_runtime": 1.0518,
|
| 64 |
+
"eval_samples_per_second": 76.061,
|
| 65 |
+
"eval_steps_per_second": 2.852,
|
| 66 |
+
"step": 28
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.22,
|
| 70 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 71 |
+
"loss": 1.4531,
|
| 72 |
+
"step": 30
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 5.91,
|
| 76 |
+
"eval_accuracy": 0.4625,
|
| 77 |
+
"eval_loss": 1.3959767818450928,
|
| 78 |
+
"eval_runtime": 1.1351,
|
| 79 |
+
"eval_samples_per_second": 70.478,
|
| 80 |
+
"eval_steps_per_second": 2.643,
|
| 81 |
+
"step": 34
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.96,
|
| 85 |
+
"learning_rate": 4.166666666666667e-05,
|
| 86 |
+
"loss": 1.1483,
|
| 87 |
+
"step": 40
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.96,
|
| 91 |
+
"eval_accuracy": 0.45,
|
| 92 |
+
"eval_loss": 1.378754734992981,
|
| 93 |
+
"eval_runtime": 1.1386,
|
| 94 |
+
"eval_samples_per_second": 70.26,
|
| 95 |
+
"eval_steps_per_second": 2.635,
|
| 96 |
+
"step": 40
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 8.0,
|
| 100 |
+
"eval_accuracy": 0.5125,
|
| 101 |
+
"eval_loss": 1.318593144416809,
|
| 102 |
+
"eval_runtime": 1.0875,
|
| 103 |
+
"eval_samples_per_second": 73.565,
|
| 104 |
+
"eval_steps_per_second": 2.759,
|
| 105 |
+
"step": 46
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.7,
|
| 109 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 110 |
+
"loss": 0.955,
|
| 111 |
+
"step": 50
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.87,
|
| 115 |
+
"eval_accuracy": 0.475,
|
| 116 |
+
"eval_loss": 1.2741286754608154,
|
| 117 |
+
"eval_runtime": 1.0684,
|
| 118 |
+
"eval_samples_per_second": 74.879,
|
| 119 |
+
"eval_steps_per_second": 2.808,
|
| 120 |
+
"step": 51
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 9.91,
|
| 124 |
+
"eval_accuracy": 0.5,
|
| 125 |
+
"eval_loss": 1.2990485429763794,
|
| 126 |
+
"eval_runtime": 1.0705,
|
| 127 |
+
"eval_samples_per_second": 74.731,
|
| 128 |
+
"eval_steps_per_second": 2.802,
|
| 129 |
+
"step": 57
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 10.43,
|
| 133 |
+
"learning_rate": 3.472222222222222e-05,
|
| 134 |
+
"loss": 0.7894,
|
| 135 |
+
"step": 60
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.96,
|
| 139 |
+
"eval_accuracy": 0.475,
|
| 140 |
+
"eval_loss": 1.246220588684082,
|
| 141 |
+
"eval_runtime": 1.0689,
|
| 142 |
+
"eval_samples_per_second": 74.845,
|
| 143 |
+
"eval_steps_per_second": 2.807,
|
| 144 |
+
"step": 63
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 12.0,
|
| 148 |
+
"eval_accuracy": 0.5375,
|
| 149 |
+
"eval_loss": 1.308982491493225,
|
| 150 |
+
"eval_runtime": 1.1406,
|
| 151 |
+
"eval_samples_per_second": 70.141,
|
| 152 |
+
"eval_steps_per_second": 2.63,
|
| 153 |
+
"step": 69
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 12.17,
|
| 157 |
+
"learning_rate": 3.125e-05,
|
| 158 |
+
"loss": 0.6769,
|
| 159 |
+
"step": 70
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.87,
|
| 163 |
+
"eval_accuracy": 0.5125,
|
| 164 |
+
"eval_loss": 1.2809442281723022,
|
| 165 |
+
"eval_runtime": 1.0624,
|
| 166 |
+
"eval_samples_per_second": 75.301,
|
| 167 |
+
"eval_steps_per_second": 2.824,
|
| 168 |
+
"step": 74
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 13.91,
|
| 172 |
+
"learning_rate": 2.777777777777778e-05,
|
| 173 |
+
"loss": 0.5958,
|
| 174 |
+
"step": 80
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 13.91,
|
| 178 |
+
"eval_accuracy": 0.525,
|
| 179 |
+
"eval_loss": 1.30197274684906,
|
| 180 |
+
"eval_runtime": 1.0687,
|
| 181 |
+
"eval_samples_per_second": 74.857,
|
| 182 |
+
"eval_steps_per_second": 2.807,
|
| 183 |
+
"step": 80
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 14.96,
|
| 187 |
+
"eval_accuracy": 0.5,
|
| 188 |
+
"eval_loss": 1.3032042980194092,
|
| 189 |
+
"eval_runtime": 1.1451,
|
| 190 |
+
"eval_samples_per_second": 69.863,
|
| 191 |
+
"eval_steps_per_second": 2.62,
|
| 192 |
+
"step": 86
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 15.65,
|
| 196 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 197 |
+
"loss": 0.5179,
|
| 198 |
+
"step": 90
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 16.0,
|
| 202 |
+
"eval_accuracy": 0.5375,
|
| 203 |
+
"eval_loss": 1.2624261379241943,
|
| 204 |
+
"eval_runtime": 1.0678,
|
| 205 |
+
"eval_samples_per_second": 74.923,
|
| 206 |
+
"eval_steps_per_second": 2.81,
|
| 207 |
+
"step": 92
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.87,
|
| 211 |
+
"eval_accuracy": 0.525,
|
| 212 |
+
"eval_loss": 1.2776085138320923,
|
| 213 |
+
"eval_runtime": 1.0697,
|
| 214 |
+
"eval_samples_per_second": 74.787,
|
| 215 |
+
"eval_steps_per_second": 2.805,
|
| 216 |
+
"step": 97
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 17.39,
|
| 220 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 221 |
+
"loss": 0.4808,
|
| 222 |
+
"step": 100
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 17.91,
|
| 226 |
+
"eval_accuracy": 0.525,
|
| 227 |
+
"eval_loss": 1.2705215215682983,
|
| 228 |
+
"eval_runtime": 1.0793,
|
| 229 |
+
"eval_samples_per_second": 74.121,
|
| 230 |
+
"eval_steps_per_second": 2.78,
|
| 231 |
+
"step": 103
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 18.96,
|
| 235 |
+
"eval_accuracy": 0.5125,
|
| 236 |
+
"eval_loss": 1.2791962623596191,
|
| 237 |
+
"eval_runtime": 1.1606,
|
| 238 |
+
"eval_samples_per_second": 68.927,
|
| 239 |
+
"eval_steps_per_second": 2.585,
|
| 240 |
+
"step": 109
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 19.13,
|
| 244 |
+
"learning_rate": 1.736111111111111e-05,
|
| 245 |
+
"loss": 0.4025,
|
| 246 |
+
"step": 110
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 20.0,
|
| 250 |
+
"eval_accuracy": 0.5375,
|
| 251 |
+
"eval_loss": 1.2922601699829102,
|
| 252 |
+
"eval_runtime": 1.0786,
|
| 253 |
+
"eval_samples_per_second": 74.168,
|
| 254 |
+
"eval_steps_per_second": 2.781,
|
| 255 |
+
"step": 115
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 20.87,
|
| 259 |
+
"learning_rate": 1.388888888888889e-05,
|
| 260 |
+
"loss": 0.3908,
|
| 261 |
+
"step": 120
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 20.87,
|
| 265 |
+
"eval_accuracy": 0.525,
|
| 266 |
+
"eval_loss": 1.3156249523162842,
|
| 267 |
+
"eval_runtime": 1.0785,
|
| 268 |
+
"eval_samples_per_second": 74.178,
|
| 269 |
+
"eval_steps_per_second": 2.782,
|
| 270 |
+
"step": 120
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 21.91,
|
| 274 |
+
"eval_accuracy": 0.5375,
|
| 275 |
+
"eval_loss": 1.3289515972137451,
|
| 276 |
+
"eval_runtime": 1.067,
|
| 277 |
+
"eval_samples_per_second": 74.979,
|
| 278 |
+
"eval_steps_per_second": 2.812,
|
| 279 |
+
"step": 126
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 22.61,
|
| 283 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 284 |
+
"loss": 0.3384,
|
| 285 |
+
"step": 130
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 22.96,
|
| 289 |
+
"eval_accuracy": 0.5625,
|
| 290 |
+
"eval_loss": 1.314065933227539,
|
| 291 |
+
"eval_runtime": 1.0756,
|
| 292 |
+
"eval_samples_per_second": 74.377,
|
| 293 |
+
"eval_steps_per_second": 2.789,
|
| 294 |
+
"step": 132
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 24.0,
|
| 298 |
+
"eval_accuracy": 0.55,
|
| 299 |
+
"eval_loss": 1.3252638578414917,
|
| 300 |
+
"eval_runtime": 1.0776,
|
| 301 |
+
"eval_samples_per_second": 74.236,
|
| 302 |
+
"eval_steps_per_second": 2.784,
|
| 303 |
+
"step": 138
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 24.35,
|
| 307 |
+
"learning_rate": 6.944444444444445e-06,
|
| 308 |
+
"loss": 0.3428,
|
| 309 |
+
"step": 140
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 24.87,
|
| 313 |
+
"eval_accuracy": 0.5375,
|
| 314 |
+
"eval_loss": 1.350243330001831,
|
| 315 |
+
"eval_runtime": 1.1571,
|
| 316 |
+
"eval_samples_per_second": 69.139,
|
| 317 |
+
"eval_steps_per_second": 2.593,
|
| 318 |
+
"step": 143
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 25.91,
|
| 322 |
+
"eval_accuracy": 0.525,
|
| 323 |
+
"eval_loss": 1.349756121635437,
|
| 324 |
+
"eval_runtime": 1.0754,
|
| 325 |
+
"eval_samples_per_second": 74.39,
|
| 326 |
+
"eval_steps_per_second": 2.79,
|
| 327 |
+
"step": 149
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 26.09,
|
| 331 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 332 |
+
"loss": 0.3236,
|
| 333 |
+
"step": 150
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 26.96,
|
| 337 |
+
"eval_accuracy": 0.525,
|
| 338 |
+
"eval_loss": 1.3449714183807373,
|
| 339 |
+
"eval_runtime": 1.0921,
|
| 340 |
+
"eval_samples_per_second": 73.256,
|
| 341 |
+
"eval_steps_per_second": 2.747,
|
| 342 |
+
"step": 155
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 27.83,
|
| 346 |
+
"learning_rate": 0.0,
|
| 347 |
+
"loss": 0.2951,
|
| 348 |
+
"step": 160
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 27.83,
|
| 352 |
+
"eval_accuracy": 0.5375,
|
| 353 |
+
"eval_loss": 1.3424607515335083,
|
| 354 |
+
"eval_runtime": 1.0784,
|
| 355 |
+
"eval_samples_per_second": 74.181,
|
| 356 |
+
"eval_steps_per_second": 2.782,
|
| 357 |
+
"step": 160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 27.83,
|
| 361 |
+
"step": 160,
|
| 362 |
+
"total_flos": 1.5536429521628037e+18,
|
| 363 |
+
"train_loss": 0.7970057874917984,
|
| 364 |
+
"train_runtime": 905.2766,
|
| 365 |
+
"train_samples_per_second": 25.451,
|
| 366 |
+
"train_steps_per_second": 0.177
|
| 367 |
}
|
| 368 |
],
|
| 369 |
"logging_steps": 10,
|
| 370 |
+
"max_steps": 160,
|
| 371 |
+
"num_train_epochs": 32,
|
| 372 |
"save_steps": 500,
|
| 373 |
+
"total_flos": 1.5536429521628037e+18,
|
| 374 |
"trial_name": null,
|
| 375 |
"trial_params": null
|
| 376 |
}
|