End of training
Browse files- README.md +1 -1
- all_results.json +12 -0
- eval_results.json +8 -0
- runs/Dec02_21-16-32_DESKTOP-SKBE9FB/events.out.tfevents.1733196014.DESKTOP-SKBE9FB.16940.1 +3 -0
- train_results.json +7 -0
- trainer_state.json +417 -0
README.md
CHANGED
|
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss:
|
| 36 |
- Accuracy: 0.1087
|
| 37 |
|
| 38 |
## Model description
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 7.9427
|
| 36 |
- Accuracy: 0.1087
|
| 37 |
|
| 38 |
## Model description
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.29,
|
| 3 |
+
"eval_accuracy": 0.10869565217391304,
|
| 4 |
+
"eval_loss": 7.94273042678833,
|
| 5 |
+
"eval_runtime": 0.8337,
|
| 6 |
+
"eval_samples_per_second": 55.174,
|
| 7 |
+
"eval_steps_per_second": 3.598,
|
| 8 |
+
"train_loss": 7.123055585225424,
|
| 9 |
+
"train_runtime": 193.127,
|
| 10 |
+
"train_samples_per_second": 44.116,
|
| 11 |
+
"train_steps_per_second": 0.621
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.29,
|
| 3 |
+
"eval_accuracy": 0.10869565217391304,
|
| 4 |
+
"eval_loss": 7.94273042678833,
|
| 5 |
+
"eval_runtime": 0.8337,
|
| 6 |
+
"eval_samples_per_second": 55.174,
|
| 7 |
+
"eval_steps_per_second": 3.598
|
| 8 |
+
}
|
runs/Dec02_21-16-32_DESKTOP-SKBE9FB/events.out.tfevents.1733196014.DESKTOP-SKBE9FB.16940.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5a88a23bf86fec5b8cac524bebea0ff9133e665caa4ef777861c6c64512e9d7
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.29,
|
| 3 |
+
"train_loss": 7.123055585225424,
|
| 4 |
+
"train_runtime": 193.127,
|
| 5 |
+
"train_samples_per_second": 44.116,
|
| 6 |
+
"train_steps_per_second": 0.621
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,417 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.10869565217391304,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-DMAE-8e-6\\checkpoint-3",
|
| 4 |
+
"epoch": 34.285714285714285,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 120,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.86,
|
| 13 |
+
"eval_accuracy": 0.10869565217391304,
|
| 14 |
+
"eval_loss": 7.94273042678833,
|
| 15 |
+
"eval_runtime": 0.6742,
|
| 16 |
+
"eval_samples_per_second": 68.233,
|
| 17 |
+
"eval_steps_per_second": 4.45,
|
| 18 |
+
"step": 3
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.10869565217391304,
|
| 23 |
+
"eval_loss": 7.938077926635742,
|
| 24 |
+
"eval_runtime": 0.7182,
|
| 25 |
+
"eval_samples_per_second": 64.052,
|
| 26 |
+
"eval_steps_per_second": 4.177,
|
| 27 |
+
"step": 7
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.86,
|
| 31 |
+
"learning_rate": 6.666666666666667e-06,
|
| 32 |
+
"loss": 7.9636,
|
| 33 |
+
"step": 10
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.86,
|
| 37 |
+
"eval_accuracy": 0.10869565217391304,
|
| 38 |
+
"eval_loss": 7.930100917816162,
|
| 39 |
+
"eval_runtime": 0.6504,
|
| 40 |
+
"eval_samples_per_second": 70.725,
|
| 41 |
+
"eval_steps_per_second": 4.612,
|
| 42 |
+
"step": 10
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 4.0,
|
| 46 |
+
"eval_accuracy": 0.10869565217391304,
|
| 47 |
+
"eval_loss": 7.908843517303467,
|
| 48 |
+
"eval_runtime": 0.6571,
|
| 49 |
+
"eval_samples_per_second": 70.0,
|
| 50 |
+
"eval_steps_per_second": 4.565,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.86,
|
| 55 |
+
"eval_accuracy": 0.10869565217391304,
|
| 56 |
+
"eval_loss": 7.885687828063965,
|
| 57 |
+
"eval_runtime": 0.6511,
|
| 58 |
+
"eval_samples_per_second": 70.645,
|
| 59 |
+
"eval_steps_per_second": 4.607,
|
| 60 |
+
"step": 17
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 5.71,
|
| 64 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 65 |
+
"loss": 7.8732,
|
| 66 |
+
"step": 20
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 6.0,
|
| 70 |
+
"eval_accuracy": 0.10869565217391304,
|
| 71 |
+
"eval_loss": 7.8449907302856445,
|
| 72 |
+
"eval_runtime": 0.6802,
|
| 73 |
+
"eval_samples_per_second": 67.632,
|
| 74 |
+
"eval_steps_per_second": 4.411,
|
| 75 |
+
"step": 21
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.86,
|
| 79 |
+
"eval_accuracy": 0.10869565217391304,
|
| 80 |
+
"eval_loss": 7.804883003234863,
|
| 81 |
+
"eval_runtime": 0.6691,
|
| 82 |
+
"eval_samples_per_second": 68.744,
|
| 83 |
+
"eval_steps_per_second": 4.483,
|
| 84 |
+
"step": 24
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 8.0,
|
| 88 |
+
"eval_accuracy": 0.10869565217391304,
|
| 89 |
+
"eval_loss": 7.737576007843018,
|
| 90 |
+
"eval_runtime": 0.6657,
|
| 91 |
+
"eval_samples_per_second": 69.104,
|
| 92 |
+
"eval_steps_per_second": 4.507,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.57,
|
| 97 |
+
"learning_rate": 6.666666666666667e-06,
|
| 98 |
+
"loss": 7.6568,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 8.86,
|
| 103 |
+
"eval_accuracy": 0.10869565217391304,
|
| 104 |
+
"eval_loss": 7.678272247314453,
|
| 105 |
+
"eval_runtime": 0.6862,
|
| 106 |
+
"eval_samples_per_second": 67.04,
|
| 107 |
+
"eval_steps_per_second": 4.372,
|
| 108 |
+
"step": 31
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 10.0,
|
| 112 |
+
"eval_accuracy": 0.10869565217391304,
|
| 113 |
+
"eval_loss": 7.594333648681641,
|
| 114 |
+
"eval_runtime": 0.6459,
|
| 115 |
+
"eval_samples_per_second": 71.215,
|
| 116 |
+
"eval_steps_per_second": 4.644,
|
| 117 |
+
"step": 35
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 10.86,
|
| 121 |
+
"eval_accuracy": 0.10869565217391304,
|
| 122 |
+
"eval_loss": 7.528815746307373,
|
| 123 |
+
"eval_runtime": 0.6537,
|
| 124 |
+
"eval_samples_per_second": 70.373,
|
| 125 |
+
"eval_steps_per_second": 4.59,
|
| 126 |
+
"step": 38
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 11.43,
|
| 130 |
+
"learning_rate": 5.925925925925925e-06,
|
| 131 |
+
"loss": 7.7458,
|
| 132 |
+
"step": 40
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 12.0,
|
| 136 |
+
"eval_accuracy": 0.10869565217391304,
|
| 137 |
+
"eval_loss": 7.435303211212158,
|
| 138 |
+
"eval_runtime": 0.6387,
|
| 139 |
+
"eval_samples_per_second": 72.025,
|
| 140 |
+
"eval_steps_per_second": 4.697,
|
| 141 |
+
"step": 42
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 12.86,
|
| 145 |
+
"eval_accuracy": 0.10869565217391304,
|
| 146 |
+
"eval_loss": 7.361030101776123,
|
| 147 |
+
"eval_runtime": 0.6672,
|
| 148 |
+
"eval_samples_per_second": 68.947,
|
| 149 |
+
"eval_steps_per_second": 4.497,
|
| 150 |
+
"step": 45
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 14.0,
|
| 154 |
+
"eval_accuracy": 0.10869565217391304,
|
| 155 |
+
"eval_loss": 7.261359214782715,
|
| 156 |
+
"eval_runtime": 0.6457,
|
| 157 |
+
"eval_samples_per_second": 71.241,
|
| 158 |
+
"eval_steps_per_second": 4.646,
|
| 159 |
+
"step": 49
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 14.29,
|
| 163 |
+
"learning_rate": 5.185185185185185e-06,
|
| 164 |
+
"loss": 7.3025,
|
| 165 |
+
"step": 50
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 14.86,
|
| 169 |
+
"eval_accuracy": 0.10869565217391304,
|
| 170 |
+
"eval_loss": 7.189355373382568,
|
| 171 |
+
"eval_runtime": 0.6962,
|
| 172 |
+
"eval_samples_per_second": 66.077,
|
| 173 |
+
"eval_steps_per_second": 4.309,
|
| 174 |
+
"step": 52
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 16.0,
|
| 178 |
+
"eval_accuracy": 0.10869565217391304,
|
| 179 |
+
"eval_loss": 7.099257946014404,
|
| 180 |
+
"eval_runtime": 0.6592,
|
| 181 |
+
"eval_samples_per_second": 69.786,
|
| 182 |
+
"eval_steps_per_second": 4.551,
|
| 183 |
+
"step": 56
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 16.86,
|
| 187 |
+
"eval_accuracy": 0.10869565217391304,
|
| 188 |
+
"eval_loss": 7.034775257110596,
|
| 189 |
+
"eval_runtime": 0.6762,
|
| 190 |
+
"eval_samples_per_second": 68.032,
|
| 191 |
+
"eval_steps_per_second": 4.437,
|
| 192 |
+
"step": 59
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 17.14,
|
| 196 |
+
"learning_rate": 4.444444444444444e-06,
|
| 197 |
+
"loss": 7.0862,
|
| 198 |
+
"step": 60
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 18.0,
|
| 202 |
+
"eval_accuracy": 0.10869565217391304,
|
| 203 |
+
"eval_loss": 6.95252799987793,
|
| 204 |
+
"eval_runtime": 0.6451,
|
| 205 |
+
"eval_samples_per_second": 71.302,
|
| 206 |
+
"eval_steps_per_second": 4.65,
|
| 207 |
+
"step": 63
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 18.86,
|
| 211 |
+
"eval_accuracy": 0.10869565217391304,
|
| 212 |
+
"eval_loss": 6.894467353820801,
|
| 213 |
+
"eval_runtime": 0.6837,
|
| 214 |
+
"eval_samples_per_second": 67.285,
|
| 215 |
+
"eval_steps_per_second": 4.388,
|
| 216 |
+
"step": 66
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 20.0,
|
| 220 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 221 |
+
"loss": 6.9553,
|
| 222 |
+
"step": 70
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 20.0,
|
| 226 |
+
"eval_accuracy": 0.10869565217391304,
|
| 227 |
+
"eval_loss": 6.825292110443115,
|
| 228 |
+
"eval_runtime": 0.6427,
|
| 229 |
+
"eval_samples_per_second": 71.578,
|
| 230 |
+
"eval_steps_per_second": 4.668,
|
| 231 |
+
"step": 70
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 20.86,
|
| 235 |
+
"eval_accuracy": 0.10869565217391304,
|
| 236 |
+
"eval_loss": 6.779515743255615,
|
| 237 |
+
"eval_runtime": 0.6441,
|
| 238 |
+
"eval_samples_per_second": 71.413,
|
| 239 |
+
"eval_steps_per_second": 4.657,
|
| 240 |
+
"step": 73
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 22.0,
|
| 244 |
+
"eval_accuracy": 0.10869565217391304,
|
| 245 |
+
"eval_loss": 6.7202067375183105,
|
| 246 |
+
"eval_runtime": 0.6361,
|
| 247 |
+
"eval_samples_per_second": 72.311,
|
| 248 |
+
"eval_steps_per_second": 4.716,
|
| 249 |
+
"step": 77
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 22.86,
|
| 253 |
+
"learning_rate": 2.9629629629629625e-06,
|
| 254 |
+
"loss": 6.8024,
|
| 255 |
+
"step": 80
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 22.86,
|
| 259 |
+
"eval_accuracy": 0.10869565217391304,
|
| 260 |
+
"eval_loss": 6.675656318664551,
|
| 261 |
+
"eval_runtime": 0.6491,
|
| 262 |
+
"eval_samples_per_second": 70.862,
|
| 263 |
+
"eval_steps_per_second": 4.621,
|
| 264 |
+
"step": 80
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 24.0,
|
| 268 |
+
"eval_accuracy": 0.10869565217391304,
|
| 269 |
+
"eval_loss": 6.621024131774902,
|
| 270 |
+
"eval_runtime": 0.6807,
|
| 271 |
+
"eval_samples_per_second": 67.581,
|
| 272 |
+
"eval_steps_per_second": 4.407,
|
| 273 |
+
"step": 84
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 24.86,
|
| 277 |
+
"eval_accuracy": 0.10869565217391304,
|
| 278 |
+
"eval_loss": 6.578530311584473,
|
| 279 |
+
"eval_runtime": 0.6592,
|
| 280 |
+
"eval_samples_per_second": 69.785,
|
| 281 |
+
"eval_steps_per_second": 4.551,
|
| 282 |
+
"step": 87
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 25.71,
|
| 286 |
+
"learning_rate": 2.222222222222222e-06,
|
| 287 |
+
"loss": 6.6652,
|
| 288 |
+
"step": 90
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 26.0,
|
| 292 |
+
"eval_accuracy": 0.10869565217391304,
|
| 293 |
+
"eval_loss": 6.5274739265441895,
|
| 294 |
+
"eval_runtime": 0.6592,
|
| 295 |
+
"eval_samples_per_second": 69.785,
|
| 296 |
+
"eval_steps_per_second": 4.551,
|
| 297 |
+
"step": 91
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 26.86,
|
| 301 |
+
"eval_accuracy": 0.10869565217391304,
|
| 302 |
+
"eval_loss": 6.494857311248779,
|
| 303 |
+
"eval_runtime": 0.6622,
|
| 304 |
+
"eval_samples_per_second": 69.469,
|
| 305 |
+
"eval_steps_per_second": 4.531,
|
| 306 |
+
"step": 94
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 28.0,
|
| 310 |
+
"eval_accuracy": 0.10869565217391304,
|
| 311 |
+
"eval_loss": 6.458892345428467,
|
| 312 |
+
"eval_runtime": 0.6467,
|
| 313 |
+
"eval_samples_per_second": 71.136,
|
| 314 |
+
"eval_steps_per_second": 4.639,
|
| 315 |
+
"step": 98
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 28.57,
|
| 319 |
+
"learning_rate": 1.4814814814814812e-06,
|
| 320 |
+
"loss": 6.467,
|
| 321 |
+
"step": 100
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 28.86,
|
| 325 |
+
"eval_accuracy": 0.10869565217391304,
|
| 326 |
+
"eval_loss": 6.4354329109191895,
|
| 327 |
+
"eval_runtime": 0.6551,
|
| 328 |
+
"eval_samples_per_second": 70.213,
|
| 329 |
+
"eval_steps_per_second": 4.579,
|
| 330 |
+
"step": 101
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 30.0,
|
| 334 |
+
"eval_accuracy": 0.10869565217391304,
|
| 335 |
+
"eval_loss": 6.409433841705322,
|
| 336 |
+
"eval_runtime": 0.8987,
|
| 337 |
+
"eval_samples_per_second": 51.185,
|
| 338 |
+
"eval_steps_per_second": 3.338,
|
| 339 |
+
"step": 105
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 30.86,
|
| 343 |
+
"eval_accuracy": 0.10869565217391304,
|
| 344 |
+
"eval_loss": 6.39463996887207,
|
| 345 |
+
"eval_runtime": 0.6521,
|
| 346 |
+
"eval_samples_per_second": 70.536,
|
| 347 |
+
"eval_steps_per_second": 4.6,
|
| 348 |
+
"step": 108
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 31.43,
|
| 352 |
+
"learning_rate": 7.407407407407406e-07,
|
| 353 |
+
"loss": 6.4984,
|
| 354 |
+
"step": 110
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 32.0,
|
| 358 |
+
"eval_accuracy": 0.10869565217391304,
|
| 359 |
+
"eval_loss": 6.379604816436768,
|
| 360 |
+
"eval_runtime": 0.6611,
|
| 361 |
+
"eval_samples_per_second": 69.576,
|
| 362 |
+
"eval_steps_per_second": 4.538,
|
| 363 |
+
"step": 112
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 32.86,
|
| 367 |
+
"eval_accuracy": 0.10869565217391304,
|
| 368 |
+
"eval_loss": 6.371899127960205,
|
| 369 |
+
"eval_runtime": 0.6278,
|
| 370 |
+
"eval_samples_per_second": 73.271,
|
| 371 |
+
"eval_steps_per_second": 4.779,
|
| 372 |
+
"step": 115
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 34.0,
|
| 376 |
+
"eval_accuracy": 0.10869565217391304,
|
| 377 |
+
"eval_loss": 6.366767406463623,
|
| 378 |
+
"eval_runtime": 0.6237,
|
| 379 |
+
"eval_samples_per_second": 73.759,
|
| 380 |
+
"eval_steps_per_second": 4.81,
|
| 381 |
+
"step": 119
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 34.29,
|
| 385 |
+
"learning_rate": 0.0,
|
| 386 |
+
"loss": 6.4603,
|
| 387 |
+
"step": 120
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 34.29,
|
| 391 |
+
"eval_accuracy": 0.10869565217391304,
|
| 392 |
+
"eval_loss": 6.366403102874756,
|
| 393 |
+
"eval_runtime": 0.7282,
|
| 394 |
+
"eval_samples_per_second": 63.173,
|
| 395 |
+
"eval_steps_per_second": 4.12,
|
| 396 |
+
"step": 120
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 34.29,
|
| 400 |
+
"step": 120,
|
| 401 |
+
"total_flos": 2.3770905934823424e+17,
|
| 402 |
+
"train_loss": 7.123055585225424,
|
| 403 |
+
"train_runtime": 193.127,
|
| 404 |
+
"train_samples_per_second": 44.116,
|
| 405 |
+
"train_steps_per_second": 0.621
|
| 406 |
+
}
|
| 407 |
+
],
|
| 408 |
+
"logging_steps": 10,
|
| 409 |
+
"max_steps": 120,
|
| 410 |
+
"num_input_tokens_seen": 0,
|
| 411 |
+
"num_train_epochs": 40,
|
| 412 |
+
"save_steps": 500,
|
| 413 |
+
"total_flos": 2.3770905934823424e+17,
|
| 414 |
+
"train_batch_size": 16,
|
| 415 |
+
"trial_name": null,
|
| 416 |
+
"trial_params": null
|
| 417 |
+
}
|