Instructions to use abdouaziiz/soraberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdouaziiz/soraberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="abdouaziiz/soraberta")# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("abdouaziiz/soraberta") model = AutoModelForMaskedLM.from_pretrained("abdouaziiz/soraberta") - Notebooks
- Google Colab
- Kaggle
Commit ·
c3732e7
1
Parent(s): e33b0fc
Upload trainer_state.json
Browse files- trainer_state.json +688 -0
trainer_state.json
ADDED
|
@@ -0,0 +1,688 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 375.83892617449663,
|
| 5 |
+
"global_step": 56000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 3.36,
|
| 12 |
+
"learning_rate": 4.956305928411633e-05,
|
| 13 |
+
"loss": 6.8613,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 6.71,
|
| 18 |
+
"learning_rate": 4.912611856823266e-05,
|
| 19 |
+
"loss": 6.0182,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 10.07,
|
| 24 |
+
"learning_rate": 4.868917785234899e-05,
|
| 25 |
+
"loss": 5.8106,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 13.42,
|
| 30 |
+
"learning_rate": 4.825223713646533e-05,
|
| 31 |
+
"loss": 5.6038,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 16.78,
|
| 36 |
+
"learning_rate": 4.781529642058166e-05,
|
| 37 |
+
"loss": 5.3695,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 20.13,
|
| 42 |
+
"learning_rate": 4.737835570469799e-05,
|
| 43 |
+
"loss": 5.1081,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 23.49,
|
| 48 |
+
"learning_rate": 4.694141498881432e-05,
|
| 49 |
+
"loss": 4.84,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 26.85,
|
| 54 |
+
"learning_rate": 4.6504474272930655e-05,
|
| 55 |
+
"loss": 4.6172,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 30.2,
|
| 60 |
+
"learning_rate": 4.6067533557046985e-05,
|
| 61 |
+
"loss": 4.4057,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 33.56,
|
| 66 |
+
"learning_rate": 4.563059284116331e-05,
|
| 67 |
+
"loss": 4.2367,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 36.91,
|
| 72 |
+
"learning_rate": 4.5193652125279645e-05,
|
| 73 |
+
"loss": 4.0491,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 40.27,
|
| 78 |
+
"learning_rate": 4.4756711409395975e-05,
|
| 79 |
+
"loss": 3.9008,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 43.62,
|
| 84 |
+
"learning_rate": 4.4319770693512305e-05,
|
| 85 |
+
"loss": 3.7661,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 46.98,
|
| 90 |
+
"learning_rate": 4.3882829977628635e-05,
|
| 91 |
+
"loss": 3.6335,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 50.34,
|
| 96 |
+
"learning_rate": 4.344588926174497e-05,
|
| 97 |
+
"loss": 3.4885,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 53.69,
|
| 102 |
+
"learning_rate": 4.30089485458613e-05,
|
| 103 |
+
"loss": 3.377,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 57.05,
|
| 108 |
+
"learning_rate": 4.257200782997763e-05,
|
| 109 |
+
"loss": 3.275,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 60.4,
|
| 114 |
+
"learning_rate": 4.213506711409396e-05,
|
| 115 |
+
"loss": 3.1363,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 63.76,
|
| 120 |
+
"learning_rate": 4.169812639821029e-05,
|
| 121 |
+
"loss": 3.0257,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 67.11,
|
| 126 |
+
"learning_rate": 4.126118568232663e-05,
|
| 127 |
+
"loss": 2.9229,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 70.47,
|
| 132 |
+
"learning_rate": 4.082424496644295e-05,
|
| 133 |
+
"loss": 2.8369,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 73.83,
|
| 138 |
+
"learning_rate": 4.038730425055929e-05,
|
| 139 |
+
"loss": 2.7189,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 77.18,
|
| 144 |
+
"learning_rate": 3.995036353467562e-05,
|
| 145 |
+
"loss": 2.6285,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 80.54,
|
| 150 |
+
"learning_rate": 3.951342281879195e-05,
|
| 151 |
+
"loss": 2.5286,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 83.89,
|
| 156 |
+
"learning_rate": 3.907648210290828e-05,
|
| 157 |
+
"loss": 2.4418,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 87.25,
|
| 162 |
+
"learning_rate": 3.863954138702461e-05,
|
| 163 |
+
"loss": 2.3471,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 90.6,
|
| 168 |
+
"learning_rate": 3.8202600671140944e-05,
|
| 169 |
+
"loss": 2.2438,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 93.96,
|
| 174 |
+
"learning_rate": 3.7765659955257274e-05,
|
| 175 |
+
"loss": 2.1722,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 97.32,
|
| 180 |
+
"learning_rate": 3.7328719239373604e-05,
|
| 181 |
+
"loss": 2.0995,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 100.67,
|
| 186 |
+
"learning_rate": 3.6891778523489934e-05,
|
| 187 |
+
"loss": 2.0343,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 104.03,
|
| 192 |
+
"learning_rate": 3.645483780760627e-05,
|
| 193 |
+
"loss": 1.9535,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 107.38,
|
| 198 |
+
"learning_rate": 3.6017897091722594e-05,
|
| 199 |
+
"loss": 1.8755,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 110.74,
|
| 204 |
+
"learning_rate": 3.5580956375838924e-05,
|
| 205 |
+
"loss": 1.8003,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 114.09,
|
| 210 |
+
"learning_rate": 3.514401565995526e-05,
|
| 211 |
+
"loss": 1.7354,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 117.45,
|
| 216 |
+
"learning_rate": 3.470707494407159e-05,
|
| 217 |
+
"loss": 1.666,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 120.81,
|
| 222 |
+
"learning_rate": 3.427013422818792e-05,
|
| 223 |
+
"loss": 1.6116,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 124.16,
|
| 228 |
+
"learning_rate": 3.383319351230425e-05,
|
| 229 |
+
"loss": 1.5483,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 127.52,
|
| 234 |
+
"learning_rate": 3.339625279642059e-05,
|
| 235 |
+
"loss": 1.4874,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 130.87,
|
| 240 |
+
"learning_rate": 3.295931208053692e-05,
|
| 241 |
+
"loss": 1.4294,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 134.23,
|
| 246 |
+
"learning_rate": 3.252237136465325e-05,
|
| 247 |
+
"loss": 1.3839,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 137.58,
|
| 252 |
+
"learning_rate": 3.2085430648769577e-05,
|
| 253 |
+
"loss": 1.32,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 140.94,
|
| 258 |
+
"learning_rate": 3.1648489932885906e-05,
|
| 259 |
+
"loss": 1.2635,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 144.3,
|
| 264 |
+
"learning_rate": 3.1211549217002236e-05,
|
| 265 |
+
"loss": 1.2201,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 147.65,
|
| 270 |
+
"learning_rate": 3.0774608501118566e-05,
|
| 271 |
+
"loss": 1.1751,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 151.01,
|
| 276 |
+
"learning_rate": 3.0337667785234903e-05,
|
| 277 |
+
"loss": 1.1269,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 154.36,
|
| 282 |
+
"learning_rate": 2.990072706935123e-05,
|
| 283 |
+
"loss": 1.087,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 157.72,
|
| 288 |
+
"learning_rate": 2.9463786353467566e-05,
|
| 289 |
+
"loss": 1.0491,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 161.07,
|
| 294 |
+
"learning_rate": 2.9026845637583893e-05,
|
| 295 |
+
"loss": 1.0008,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 164.43,
|
| 300 |
+
"learning_rate": 2.8589904921700223e-05,
|
| 301 |
+
"loss": 0.9718,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 167.79,
|
| 306 |
+
"learning_rate": 2.8152964205816556e-05,
|
| 307 |
+
"loss": 0.9386,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 171.14,
|
| 312 |
+
"learning_rate": 2.7716023489932886e-05,
|
| 313 |
+
"loss": 0.8923,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 174.5,
|
| 318 |
+
"learning_rate": 2.727908277404922e-05,
|
| 319 |
+
"loss": 0.8642,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 177.85,
|
| 324 |
+
"learning_rate": 2.684214205816555e-05,
|
| 325 |
+
"loss": 0.8361,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 181.21,
|
| 330 |
+
"learning_rate": 2.6405201342281882e-05,
|
| 331 |
+
"loss": 0.8075,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 184.56,
|
| 336 |
+
"learning_rate": 2.5968260626398212e-05,
|
| 337 |
+
"loss": 0.7729,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 187.92,
|
| 342 |
+
"learning_rate": 2.5531319910514546e-05,
|
| 343 |
+
"loss": 0.7429,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 191.28,
|
| 348 |
+
"learning_rate": 2.5094379194630872e-05,
|
| 349 |
+
"loss": 0.7253,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 194.63,
|
| 354 |
+
"learning_rate": 2.4657438478747206e-05,
|
| 355 |
+
"loss": 0.693,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 197.99,
|
| 360 |
+
"learning_rate": 2.4220497762863535e-05,
|
| 361 |
+
"loss": 0.6717,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 201.34,
|
| 366 |
+
"learning_rate": 2.378355704697987e-05,
|
| 367 |
+
"loss": 0.648,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 204.7,
|
| 372 |
+
"learning_rate": 2.3346616331096195e-05,
|
| 373 |
+
"loss": 0.617,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 208.05,
|
| 378 |
+
"learning_rate": 2.290967561521253e-05,
|
| 379 |
+
"loss": 0.6145,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 211.41,
|
| 384 |
+
"learning_rate": 2.247273489932886e-05,
|
| 385 |
+
"loss": 0.5925,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 214.77,
|
| 390 |
+
"learning_rate": 2.2035794183445192e-05,
|
| 391 |
+
"loss": 0.574,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 218.12,
|
| 396 |
+
"learning_rate": 2.1598853467561522e-05,
|
| 397 |
+
"loss": 0.5549,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 221.48,
|
| 402 |
+
"learning_rate": 2.1161912751677855e-05,
|
| 403 |
+
"loss": 0.543,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 224.83,
|
| 408 |
+
"learning_rate": 2.0724972035794185e-05,
|
| 409 |
+
"loss": 0.5261,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 228.19,
|
| 414 |
+
"learning_rate": 2.0288031319910515e-05,
|
| 415 |
+
"loss": 0.5083,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 231.54,
|
| 420 |
+
"learning_rate": 1.9851090604026848e-05,
|
| 421 |
+
"loss": 0.4944,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 234.9,
|
| 426 |
+
"learning_rate": 1.9414149888143178e-05,
|
| 427 |
+
"loss": 0.4789,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 238.26,
|
| 432 |
+
"learning_rate": 1.8977209172259508e-05,
|
| 433 |
+
"loss": 0.4702,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 241.61,
|
| 438 |
+
"learning_rate": 1.8540268456375838e-05,
|
| 439 |
+
"loss": 0.4567,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 244.97,
|
| 444 |
+
"learning_rate": 1.810332774049217e-05,
|
| 445 |
+
"loss": 0.4417,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 248.32,
|
| 450 |
+
"learning_rate": 1.76663870246085e-05,
|
| 451 |
+
"loss": 0.4414,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 251.68,
|
| 456 |
+
"learning_rate": 1.7229446308724834e-05,
|
| 457 |
+
"loss": 0.431,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 255.03,
|
| 462 |
+
"learning_rate": 1.6792505592841164e-05,
|
| 463 |
+
"loss": 0.4134,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 258.39,
|
| 468 |
+
"learning_rate": 1.6355564876957498e-05,
|
| 469 |
+
"loss": 0.4047,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 261.74,
|
| 474 |
+
"learning_rate": 1.5918624161073824e-05,
|
| 475 |
+
"loss": 0.3894,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 265.1,
|
| 480 |
+
"learning_rate": 1.5481683445190158e-05,
|
| 481 |
+
"loss": 0.3924,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 268.46,
|
| 486 |
+
"learning_rate": 1.5044742729306487e-05,
|
| 487 |
+
"loss": 0.3782,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 271.81,
|
| 492 |
+
"learning_rate": 1.4607802013422819e-05,
|
| 493 |
+
"loss": 0.3786,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 275.17,
|
| 498 |
+
"learning_rate": 1.417086129753915e-05,
|
| 499 |
+
"loss": 0.361,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 278.52,
|
| 504 |
+
"learning_rate": 1.3733920581655482e-05,
|
| 505 |
+
"loss": 0.3588,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 281.88,
|
| 510 |
+
"learning_rate": 1.3296979865771814e-05,
|
| 511 |
+
"loss": 0.35,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 285.23,
|
| 516 |
+
"learning_rate": 1.2860039149888146e-05,
|
| 517 |
+
"loss": 0.349,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 288.59,
|
| 522 |
+
"learning_rate": 1.2423098434004475e-05,
|
| 523 |
+
"loss": 0.344,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 291.95,
|
| 528 |
+
"learning_rate": 1.1986157718120807e-05,
|
| 529 |
+
"loss": 0.3314,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 295.3,
|
| 534 |
+
"learning_rate": 1.1549217002237137e-05,
|
| 535 |
+
"loss": 0.3288,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 298.66,
|
| 540 |
+
"learning_rate": 1.1112276286353469e-05,
|
| 541 |
+
"loss": 0.3259,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 302.01,
|
| 546 |
+
"learning_rate": 1.06753355704698e-05,
|
| 547 |
+
"loss": 0.3161,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 305.37,
|
| 552 |
+
"learning_rate": 1.023839485458613e-05,
|
| 553 |
+
"loss": 0.3108,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 308.72,
|
| 558 |
+
"learning_rate": 9.80145413870246e-06,
|
| 559 |
+
"loss": 0.3141,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 312.08,
|
| 564 |
+
"learning_rate": 9.364513422818792e-06,
|
| 565 |
+
"loss": 0.3022,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 315.44,
|
| 570 |
+
"learning_rate": 8.927572706935123e-06,
|
| 571 |
+
"loss": 0.2995,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 318.79,
|
| 576 |
+
"learning_rate": 8.490631991051455e-06,
|
| 577 |
+
"loss": 0.294,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 322.15,
|
| 582 |
+
"learning_rate": 8.053691275167785e-06,
|
| 583 |
+
"loss": 0.2935,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 325.5,
|
| 588 |
+
"learning_rate": 7.6167505592841164e-06,
|
| 589 |
+
"loss": 0.2906,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 328.86,
|
| 594 |
+
"learning_rate": 7.179809843400448e-06,
|
| 595 |
+
"loss": 0.2854,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 332.21,
|
| 600 |
+
"learning_rate": 6.74286912751678e-06,
|
| 601 |
+
"loss": 0.2768,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 335.57,
|
| 606 |
+
"learning_rate": 6.3059284116331096e-06,
|
| 607 |
+
"loss": 0.2799,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 338.93,
|
| 612 |
+
"learning_rate": 5.868987695749441e-06,
|
| 613 |
+
"loss": 0.2696,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 342.28,
|
| 618 |
+
"learning_rate": 5.432046979865772e-06,
|
| 619 |
+
"loss": 0.2713,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 345.64,
|
| 624 |
+
"learning_rate": 4.995106263982103e-06,
|
| 625 |
+
"loss": 0.2651,
|
| 626 |
+
"step": 51500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 348.99,
|
| 630 |
+
"learning_rate": 4.558165548098434e-06,
|
| 631 |
+
"loss": 0.2651,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 352.35,
|
| 636 |
+
"learning_rate": 4.121224832214765e-06,
|
| 637 |
+
"loss": 0.2621,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 355.7,
|
| 642 |
+
"learning_rate": 3.6842841163310963e-06,
|
| 643 |
+
"loss": 0.2671,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 359.06,
|
| 648 |
+
"learning_rate": 3.247343400447427e-06,
|
| 649 |
+
"loss": 0.2538,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 362.42,
|
| 654 |
+
"learning_rate": 2.8104026845637587e-06,
|
| 655 |
+
"loss": 0.2588,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 365.77,
|
| 660 |
+
"learning_rate": 2.37346196868009e-06,
|
| 661 |
+
"loss": 0.2522,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 369.13,
|
| 666 |
+
"learning_rate": 1.9365212527964206e-06,
|
| 667 |
+
"loss": 0.2577,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 372.48,
|
| 672 |
+
"learning_rate": 1.4995805369127516e-06,
|
| 673 |
+
"loss": 0.244,
|
| 674 |
+
"step": 55500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 375.84,
|
| 678 |
+
"learning_rate": 1.062639821029083e-06,
|
| 679 |
+
"loss": 0.2492,
|
| 680 |
+
"step": 56000
|
| 681 |
+
}
|
| 682 |
+
],
|
| 683 |
+
"max_steps": 57216,
|
| 684 |
+
"num_train_epochs": 384,
|
| 685 |
+
"total_flos": 5.557730674767398e+16,
|
| 686 |
+
"trial_name": null,
|
| 687 |
+
"trial_params": null
|
| 688 |
+
}
|