End of training
Browse files- README.md +3 -3
- all_results.json +8 -0
- runs/May29_10-36-16_0ff75122c46e/events.out.tfevents.1716985000.0ff75122c46e.24.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +505 -0
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 [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8886904761904761
|
| 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 [facebook/convnextv2-tiny-1k-224](https://huggingface.co/facebook/convnextv2-tiny-1k-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4027
|
| 36 |
+
- Accuracy: 0.8887
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 4.4284716808619213e+18,
|
| 4 |
+
"train_loss": 0.8922947484796697,
|
| 5 |
+
"train_runtime": 5842.588,
|
| 6 |
+
"train_samples_per_second": 30.091,
|
| 7 |
+
"train_steps_per_second": 0.941
|
| 8 |
+
}
|
runs/May29_10-36-16_0ff75122c46e/events.out.tfevents.1716985000.0ff75122c46e.24.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35c1b939b88e31ca5063a89fb8a6ecb3760200af3bf30302286ac8815a983021
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"total_flos": 4.4284716808619213e+18,
|
| 4 |
+
"train_loss": 0.8922947484796697,
|
| 5 |
+
"train_runtime": 5842.588,
|
| 6 |
+
"train_samples_per_second": 30.091,
|
| 7 |
+
"train_steps_per_second": 0.941
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,505 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.42871516942977905,
|
| 3 |
+
"best_model_checkpoint": "./convnext-tiny-upgrade-1k-224-batch-32/checkpoint-5500",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18,
|
| 13 |
+
"grad_norm": 9.459319114685059,
|
| 14 |
+
"learning_rate": 2.9975536558892034e-05,
|
| 15 |
+
"loss": 3.1737,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.36,
|
| 20 |
+
"grad_norm": 15.453875541687012,
|
| 21 |
+
"learning_rate": 2.9902226030228252e-05,
|
| 22 |
+
"loss": 2.5523,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.55,
|
| 27 |
+
"grad_norm": 14.928990364074707,
|
| 28 |
+
"learning_rate": 2.9780307537715396e-05,
|
| 29 |
+
"loss": 2.0438,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.73,
|
| 34 |
+
"grad_norm": 14.474929809570312,
|
| 35 |
+
"learning_rate": 2.9610178754135005e-05,
|
| 36 |
+
"loss": 1.7769,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.91,
|
| 41 |
+
"grad_norm": 16.29086685180664,
|
| 42 |
+
"learning_rate": 2.939239460421746e-05,
|
| 43 |
+
"loss": 1.5523,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.7009940357852883,
|
| 49 |
+
"eval_loss": 1.2082535028457642,
|
| 50 |
+
"eval_runtime": 49.3679,
|
| 51 |
+
"eval_samples_per_second": 50.944,
|
| 52 |
+
"eval_steps_per_second": 1.6,
|
| 53 |
+
"step": 550
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.09,
|
| 57 |
+
"grad_norm": 23.075525283813477,
|
| 58 |
+
"learning_rate": 2.9127665454592872e-05,
|
| 59 |
+
"loss": 1.448,
|
| 60 |
+
"step": 600
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.27,
|
| 64 |
+
"grad_norm": 22.86272430419922,
|
| 65 |
+
"learning_rate": 2.8816854796722754e-05,
|
| 66 |
+
"loss": 1.2812,
|
| 67 |
+
"step": 700
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.45,
|
| 71 |
+
"grad_norm": 18.48836898803711,
|
| 72 |
+
"learning_rate": 2.8460976430370375e-05,
|
| 73 |
+
"loss": 1.2282,
|
| 74 |
+
"step": 800
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.64,
|
| 78 |
+
"grad_norm": 32.918296813964844,
|
| 79 |
+
"learning_rate": 2.8061191156796658e-05,
|
| 80 |
+
"loss": 1.2056,
|
| 81 |
+
"step": 900
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.82,
|
| 85 |
+
"grad_norm": 19.546428680419922,
|
| 86 |
+
"learning_rate": 2.7618802992467718e-05,
|
| 87 |
+
"loss": 1.1179,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.0,
|
| 92 |
+
"grad_norm": 39.9352912902832,
|
| 93 |
+
"learning_rate": 2.7135254915624213e-05,
|
| 94 |
+
"loss": 1.0852,
|
| 95 |
+
"step": 1100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.0,
|
| 99 |
+
"eval_accuracy": 0.7960238568588469,
|
| 100 |
+
"eval_loss": 0.7955119013786316,
|
| 101 |
+
"eval_runtime": 49.699,
|
| 102 |
+
"eval_samples_per_second": 50.605,
|
| 103 |
+
"eval_steps_per_second": 1.59,
|
| 104 |
+
"step": 1100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.18,
|
| 108 |
+
"grad_norm": 31.628759384155273,
|
| 109 |
+
"learning_rate": 2.661212415958624e-05,
|
| 110 |
+
"loss": 1.0018,
|
| 111 |
+
"step": 1200
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.36,
|
| 115 |
+
"grad_norm": 20.639881134033203,
|
| 116 |
+
"learning_rate": 2.6051117068146073e-05,
|
| 117 |
+
"loss": 1.0004,
|
| 118 |
+
"step": 1300
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.55,
|
| 122 |
+
"grad_norm": 34.07547378540039,
|
| 123 |
+
"learning_rate": 2.5454063529829405e-05,
|
| 124 |
+
"loss": 0.9302,
|
| 125 |
+
"step": 1400
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.73,
|
| 129 |
+
"grad_norm": 21.45457649230957,
|
| 130 |
+
"learning_rate": 2.482291100917928e-05,
|
| 131 |
+
"loss": 0.9218,
|
| 132 |
+
"step": 1500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.91,
|
| 136 |
+
"grad_norm": 16.903533935546875,
|
| 137 |
+
"learning_rate": 2.4159718194531573e-05,
|
| 138 |
+
"loss": 0.9179,
|
| 139 |
+
"step": 1600
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 3.0,
|
| 143 |
+
"eval_accuracy": 0.8258449304174951,
|
| 144 |
+
"eval_loss": 0.6425434947013855,
|
| 145 |
+
"eval_runtime": 50.6126,
|
| 146 |
+
"eval_samples_per_second": 49.691,
|
| 147 |
+
"eval_steps_per_second": 1.561,
|
| 148 |
+
"step": 1650
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.09,
|
| 152 |
+
"grad_norm": 20.296306610107422,
|
| 153 |
+
"learning_rate": 2.3466648283001542e-05,
|
| 154 |
+
"loss": 0.8552,
|
| 155 |
+
"step": 1700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.27,
|
| 159 |
+
"grad_norm": 25.9653263092041,
|
| 160 |
+
"learning_rate": 2.274596192458443e-05,
|
| 161 |
+
"loss": 0.8283,
|
| 162 |
+
"step": 1800
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.45,
|
| 166 |
+
"grad_norm": 14.738792419433594,
|
| 167 |
+
"learning_rate": 2.2000009848385107e-05,
|
| 168 |
+
"loss": 0.8234,
|
| 169 |
+
"step": 1900
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.64,
|
| 173 |
+
"grad_norm": 17.272687911987305,
|
| 174 |
+
"learning_rate": 2.12312251950283e-05,
|
| 175 |
+
"loss": 0.8101,
|
| 176 |
+
"step": 2000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.82,
|
| 180 |
+
"grad_norm": 19.54085922241211,
|
| 181 |
+
"learning_rate": 2.0442115580259615e-05,
|
| 182 |
+
"loss": 0.8235,
|
| 183 |
+
"step": 2100
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 4.0,
|
| 187 |
+
"grad_norm": 30.610021591186523,
|
| 188 |
+
"learning_rate": 1.963525491562421e-05,
|
| 189 |
+
"loss": 0.7621,
|
| 190 |
+
"step": 2200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 4.0,
|
| 194 |
+
"eval_accuracy": 0.8548707753479126,
|
| 195 |
+
"eval_loss": 0.5425807237625122,
|
| 196 |
+
"eval_runtime": 49.9135,
|
| 197 |
+
"eval_samples_per_second": 50.387,
|
| 198 |
+
"eval_steps_per_second": 1.583,
|
| 199 |
+
"step": 2200
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.18,
|
| 203 |
+
"grad_norm": 17.56275749206543,
|
| 204 |
+
"learning_rate": 1.8813275012902307e-05,
|
| 205 |
+
"loss": 0.743,
|
| 206 |
+
"step": 2300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 4.36,
|
| 210 |
+
"grad_norm": 21.964000701904297,
|
| 211 |
+
"learning_rate": 1.7978856999686182e-05,
|
| 212 |
+
"loss": 0.7278,
|
| 213 |
+
"step": 2400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.55,
|
| 217 |
+
"grad_norm": 19.241918563842773,
|
| 218 |
+
"learning_rate": 1.713472257409928e-05,
|
| 219 |
+
"loss": 0.7047,
|
| 220 |
+
"step": 2500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.73,
|
| 224 |
+
"grad_norm": 30.8186092376709,
|
| 225 |
+
"learning_rate": 1.6283625127182596e-05,
|
| 226 |
+
"loss": 0.7558,
|
| 227 |
+
"step": 2600
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.91,
|
| 231 |
+
"grad_norm": 16.47164535522461,
|
| 232 |
+
"learning_rate": 1.5428340761905444e-05,
|
| 233 |
+
"loss": 0.7506,
|
| 234 |
+
"step": 2700
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.0,
|
| 238 |
+
"eval_accuracy": 0.8624254473161034,
|
| 239 |
+
"eval_loss": 0.5018457770347595,
|
| 240 |
+
"eval_runtime": 49.7681,
|
| 241 |
+
"eval_samples_per_second": 50.534,
|
| 242 |
+
"eval_steps_per_second": 1.587,
|
| 243 |
+
"step": 2750
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 5.09,
|
| 247 |
+
"grad_norm": 21.695837020874023,
|
| 248 |
+
"learning_rate": 1.4571659238094557e-05,
|
| 249 |
+
"loss": 0.693,
|
| 250 |
+
"step": 2800
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 5.27,
|
| 254 |
+
"grad_norm": 19.108768463134766,
|
| 255 |
+
"learning_rate": 1.3716374872817408e-05,
|
| 256 |
+
"loss": 0.6944,
|
| 257 |
+
"step": 2900
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 5.45,
|
| 261 |
+
"grad_norm": 19.964969635009766,
|
| 262 |
+
"learning_rate": 1.2865277425900725e-05,
|
| 263 |
+
"loss": 0.656,
|
| 264 |
+
"step": 3000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.64,
|
| 268 |
+
"grad_norm": 17.055917739868164,
|
| 269 |
+
"learning_rate": 1.2021143000313822e-05,
|
| 270 |
+
"loss": 0.6643,
|
| 271 |
+
"step": 3100
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 5.82,
|
| 275 |
+
"grad_norm": 15.315804481506348,
|
| 276 |
+
"learning_rate": 1.11867249870977e-05,
|
| 277 |
+
"loss": 0.6955,
|
| 278 |
+
"step": 3200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 6.0,
|
| 282 |
+
"grad_norm": 33.08659744262695,
|
| 283 |
+
"learning_rate": 1.036474508437579e-05,
|
| 284 |
+
"loss": 0.6774,
|
| 285 |
+
"step": 3300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 6.0,
|
| 289 |
+
"eval_accuracy": 0.868389662027833,
|
| 290 |
+
"eval_loss": 0.4792053699493408,
|
| 291 |
+
"eval_runtime": 49.8325,
|
| 292 |
+
"eval_samples_per_second": 50.469,
|
| 293 |
+
"eval_steps_per_second": 1.585,
|
| 294 |
+
"step": 3300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.18,
|
| 298 |
+
"grad_norm": 20.445402145385742,
|
| 299 |
+
"learning_rate": 9.557884419740387e-06,
|
| 300 |
+
"loss": 0.6568,
|
| 301 |
+
"step": 3400
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 6.36,
|
| 305 |
+
"grad_norm": 15.636629104614258,
|
| 306 |
+
"learning_rate": 8.768774804971705e-06,
|
| 307 |
+
"loss": 0.606,
|
| 308 |
+
"step": 3500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.55,
|
| 312 |
+
"grad_norm": 18.987926483154297,
|
| 313 |
+
"learning_rate": 7.999990151614895e-06,
|
| 314 |
+
"loss": 0.663,
|
| 315 |
+
"step": 3600
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.73,
|
| 319 |
+
"grad_norm": 14.477697372436523,
|
| 320 |
+
"learning_rate": 7.254038075415573e-06,
|
| 321 |
+
"loss": 0.6101,
|
| 322 |
+
"step": 3700
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 6.91,
|
| 326 |
+
"grad_norm": 24.2838191986084,
|
| 327 |
+
"learning_rate": 6.533351716998466e-06,
|
| 328 |
+
"loss": 0.6364,
|
| 329 |
+
"step": 3800
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 7.0,
|
| 333 |
+
"eval_accuracy": 0.8743538767395627,
|
| 334 |
+
"eval_loss": 0.4525967836380005,
|
| 335 |
+
"eval_runtime": 49.992,
|
| 336 |
+
"eval_samples_per_second": 50.308,
|
| 337 |
+
"eval_steps_per_second": 1.58,
|
| 338 |
+
"step": 3850
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.09,
|
| 342 |
+
"grad_norm": 23.1962947845459,
|
| 343 |
+
"learning_rate": 5.840281805468427e-06,
|
| 344 |
+
"loss": 0.5968,
|
| 345 |
+
"step": 3900
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.27,
|
| 349 |
+
"grad_norm": 21.290063858032227,
|
| 350 |
+
"learning_rate": 5.177088990820725e-06,
|
| 351 |
+
"loss": 0.6077,
|
| 352 |
+
"step": 4000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.45,
|
| 356 |
+
"grad_norm": 25.02341079711914,
|
| 357 |
+
"learning_rate": 4.5459364701706e-06,
|
| 358 |
+
"loss": 0.6175,
|
| 359 |
+
"step": 4100
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.64,
|
| 363 |
+
"grad_norm": 21.104934692382812,
|
| 364 |
+
"learning_rate": 3.948882931853924e-06,
|
| 365 |
+
"loss": 0.5993,
|
| 366 |
+
"step": 4200
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 7.82,
|
| 370 |
+
"grad_norm": 17.36994171142578,
|
| 371 |
+
"learning_rate": 3.3878758404137627e-06,
|
| 372 |
+
"loss": 0.607,
|
| 373 |
+
"step": 4300
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.0,
|
| 377 |
+
"grad_norm": 35.08428955078125,
|
| 378 |
+
"learning_rate": 2.86474508437579e-06,
|
| 379 |
+
"loss": 0.5961,
|
| 380 |
+
"step": 4400
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.0,
|
| 384 |
+
"eval_accuracy": 0.8799204771371769,
|
| 385 |
+
"eval_loss": 0.4362061619758606,
|
| 386 |
+
"eval_runtime": 49.5582,
|
| 387 |
+
"eval_samples_per_second": 50.748,
|
| 388 |
+
"eval_steps_per_second": 1.594,
|
| 389 |
+
"step": 4400
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 8.18,
|
| 393 |
+
"grad_norm": 20.05402183532715,
|
| 394 |
+
"learning_rate": 2.38119700753228e-06,
|
| 395 |
+
"loss": 0.5695,
|
| 396 |
+
"step": 4500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.36,
|
| 400 |
+
"grad_norm": 30.20684242248535,
|
| 401 |
+
"learning_rate": 1.9388088432033446e-06,
|
| 402 |
+
"loss": 0.5647,
|
| 403 |
+
"step": 4600
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 8.55,
|
| 407 |
+
"grad_norm": 21.600929260253906,
|
| 408 |
+
"learning_rate": 1.5390235696296268e-06,
|
| 409 |
+
"loss": 0.5637,
|
| 410 |
+
"step": 4700
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 8.73,
|
| 414 |
+
"grad_norm": 32.336669921875,
|
| 415 |
+
"learning_rate": 1.1831452032772499e-06,
|
| 416 |
+
"loss": 0.5916,
|
| 417 |
+
"step": 4800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.91,
|
| 421 |
+
"grad_norm": 14.266773223876953,
|
| 422 |
+
"learning_rate": 8.723345454071308e-07,
|
| 423 |
+
"loss": 0.602,
|
| 424 |
+
"step": 4900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.0,
|
| 428 |
+
"eval_accuracy": 0.882703777335984,
|
| 429 |
+
"eval_loss": 0.43156278133392334,
|
| 430 |
+
"eval_runtime": 50.0221,
|
| 431 |
+
"eval_samples_per_second": 50.278,
|
| 432 |
+
"eval_steps_per_second": 1.579,
|
| 433 |
+
"step": 4950
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 9.09,
|
| 437 |
+
"grad_norm": 27.497398376464844,
|
| 438 |
+
"learning_rate": 6.076053957825411e-07,
|
| 439 |
+
"loss": 0.5848,
|
| 440 |
+
"step": 5000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.27,
|
| 444 |
+
"grad_norm": 17.4595890045166,
|
| 445 |
+
"learning_rate": 3.8982124586499804e-07,
|
| 446 |
+
"loss": 0.5724,
|
| 447 |
+
"step": 5100
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 9.45,
|
| 451 |
+
"grad_norm": 30.596479415893555,
|
| 452 |
+
"learning_rate": 2.1969246228460526e-07,
|
| 453 |
+
"loss": 0.5712,
|
| 454 |
+
"step": 5200
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 9.64,
|
| 458 |
+
"grad_norm": 17.515758514404297,
|
| 459 |
+
"learning_rate": 9.777396977174668e-08,
|
| 460 |
+
"loss": 0.5994,
|
| 461 |
+
"step": 5300
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 9.82,
|
| 465 |
+
"grad_norm": 25.090110778808594,
|
| 466 |
+
"learning_rate": 2.4463441107965278e-08,
|
| 467 |
+
"loss": 0.5685,
|
| 468 |
+
"step": 5400
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 10.0,
|
| 472 |
+
"grad_norm": 22.852954864501953,
|
| 473 |
+
"learning_rate": 0.0,
|
| 474 |
+
"loss": 0.5896,
|
| 475 |
+
"step": 5500
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 10.0,
|
| 479 |
+
"eval_accuracy": 0.8850894632206759,
|
| 480 |
+
"eval_loss": 0.42871516942977905,
|
| 481 |
+
"eval_runtime": 49.9143,
|
| 482 |
+
"eval_samples_per_second": 50.386,
|
| 483 |
+
"eval_steps_per_second": 1.583,
|
| 484 |
+
"step": 5500
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 10.0,
|
| 488 |
+
"step": 5500,
|
| 489 |
+
"total_flos": 4.4284716808619213e+18,
|
| 490 |
+
"train_loss": 0.8922947484796697,
|
| 491 |
+
"train_runtime": 5842.588,
|
| 492 |
+
"train_samples_per_second": 30.091,
|
| 493 |
+
"train_steps_per_second": 0.941
|
| 494 |
+
}
|
| 495 |
+
],
|
| 496 |
+
"logging_steps": 100,
|
| 497 |
+
"max_steps": 5500,
|
| 498 |
+
"num_input_tokens_seen": 0,
|
| 499 |
+
"num_train_epochs": 10,
|
| 500 |
+
"save_steps": 500,
|
| 501 |
+
"total_flos": 4.4284716808619213e+18,
|
| 502 |
+
"train_batch_size": 32,
|
| 503 |
+
"trial_name": null,
|
| 504 |
+
"trial_params": null
|
| 505 |
+
}
|