End of training
Browse files- README.md +1 -1
- all_results.json +10 -10
- eval_results.json +5 -5
- train_results.json +6 -6
- trainer_state.json +2880 -104
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# e3-sft
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [CMU-AIRe/e3-1.7B](https://huggingface.co/CMU-AIRe/e3-1.7B) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6364
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
# e3-sft
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [CMU-AIRe/e3-1.7B](https://huggingface.co/CMU-AIRe/e3-1.7B) on the hardmath_sft_2 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6364
|
| 22 |
|
all_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime": 0.
|
| 5 |
-
"eval_samples_per_second": 16.
|
| 6 |
-
"eval_steps_per_second": 16.
|
| 7 |
-
"total_flos": 1.
|
| 8 |
-
"train_loss": 0.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples_per_second": 3.
|
| 11 |
-
"train_steps_per_second": 0.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.6363555192947388,
|
| 4 |
+
"eval_runtime": 0.7771,
|
| 5 |
+
"eval_samples_per_second": 16.728,
|
| 6 |
+
"eval_steps_per_second": 16.728,
|
| 7 |
+
"total_flos": 1.34153286008832e+17,
|
| 8 |
+
"train_loss": 0.7119150696694851,
|
| 9 |
+
"train_runtime": 2950.0217,
|
| 10 |
+
"train_samples_per_second": 3.729,
|
| 11 |
+
"train_steps_per_second": 0.136
|
| 12 |
}
|
eval_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_runtime": 0.
|
| 5 |
-
"eval_samples_per_second": 16.
|
| 6 |
-
"eval_steps_per_second": 16.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"eval_loss": 0.6363555192947388,
|
| 4 |
+
"eval_runtime": 0.7771,
|
| 5 |
+
"eval_samples_per_second": 16.728,
|
| 6 |
+
"eval_steps_per_second": 16.728
|
| 7 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 3.
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 100.0,
|
| 3 |
+
"total_flos": 1.34153286008832e+17,
|
| 4 |
+
"train_loss": 0.7119150696694851,
|
| 5 |
+
"train_runtime": 2950.0217,
|
| 6 |
+
"train_samples_per_second": 3.729,
|
| 7 |
+
"train_steps_per_second": 0.136
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -2,251 +2,3027 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch":
|
| 6 |
-
"eval_steps":
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.2909090909090909,
|
| 14 |
-
"grad_norm": 10.
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
"loss": 0.7859,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.5818181818181818,
|
| 21 |
-
"grad_norm": 9.
|
| 22 |
-
"learning_rate": 2.5e-
|
| 23 |
"loss": 0.7965,
|
| 24 |
"step": 2
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.8727272727272727,
|
| 28 |
-
"grad_norm": 10.
|
| 29 |
-
"learning_rate": 5e-
|
| 30 |
"loss": 0.7893,
|
| 31 |
"step": 3
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
-
"grad_norm": 12.
|
| 36 |
-
"learning_rate": 7.5e-
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 4
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 1.290909090909091,
|
| 42 |
-
"grad_norm": 10.
|
| 43 |
-
"learning_rate": 1e-
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 5
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 1.5818181818181818,
|
| 49 |
-
"grad_norm": 9.
|
| 50 |
-
"learning_rate":
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 6
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 1.8727272727272726,
|
| 56 |
-
"grad_norm": 10.
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 7
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 2.0,
|
| 63 |
-
"grad_norm": 11.
|
| 64 |
-
"learning_rate":
|
| 65 |
-
"loss": 0.
|
| 66 |
"step": 8
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 2.290909090909091,
|
| 70 |
-
"grad_norm": 9.
|
| 71 |
-
"learning_rate":
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 9
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 2.581818181818182,
|
| 77 |
-
"grad_norm": 11.
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 10
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 2.8727272727272726,
|
| 84 |
-
"grad_norm": 10.
|
| 85 |
-
"learning_rate":
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 11
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 3.0,
|
| 91 |
-
"grad_norm": 11.
|
| 92 |
-
"learning_rate":
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 12
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 3.290909090909091,
|
| 98 |
-
"grad_norm": 10.
|
| 99 |
-
"learning_rate":
|
| 100 |
-
"loss": 0.
|
| 101 |
"step": 13
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 3.581818181818182,
|
| 105 |
-
"grad_norm": 10.
|
| 106 |
-
"learning_rate":
|
| 107 |
-
"loss": 0.
|
| 108 |
"step": 14
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 3.8727272727272726,
|
| 112 |
-
"grad_norm": 9.
|
| 113 |
-
"learning_rate":
|
| 114 |
-
"loss": 0.
|
| 115 |
"step": 15
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 4.0,
|
| 119 |
-
"grad_norm": 10.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 122 |
"step": 16
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 4.290909090909091,
|
| 126 |
-
"grad_norm": 9.
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss": 0.
|
| 129 |
"step": 17
|
| 130 |
},
|
| 131 |
{
|
| 132 |
"epoch": 4.581818181818182,
|
| 133 |
-
"grad_norm": 11.
|
| 134 |
-
"learning_rate":
|
| 135 |
-
"loss": 0.
|
| 136 |
"step": 18
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 4.872727272727273,
|
| 140 |
-
"grad_norm": 10.
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss": 0.
|
| 143 |
"step": 19
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 5.0,
|
| 147 |
-
"grad_norm": 10.
|
| 148 |
-
"learning_rate": 4.
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 20
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 5.290909090909091,
|
| 154 |
-
"grad_norm": 9.
|
| 155 |
-
"learning_rate":
|
| 156 |
-
"loss": 0.
|
| 157 |
"step": 21
|
| 158 |
},
|
| 159 |
{
|
| 160 |
"epoch": 5.581818181818182,
|
| 161 |
-
"grad_norm": 10.
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 22
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 5.872727272727273,
|
| 168 |
-
"grad_norm": 10.
|
| 169 |
-
"learning_rate":
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 23
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 6.0,
|
| 175 |
-
"grad_norm":
|
| 176 |
-
"learning_rate":
|
| 177 |
-
"loss": 0.
|
| 178 |
"step": 24
|
| 179 |
},
|
| 180 |
{
|
| 181 |
"epoch": 6.290909090909091,
|
| 182 |
-
"grad_norm": 10.
|
| 183 |
-
"learning_rate":
|
| 184 |
-
"loss": 0.
|
| 185 |
"step": 25
|
| 186 |
},
|
| 187 |
{
|
| 188 |
"epoch": 6.581818181818182,
|
| 189 |
-
"grad_norm": 9.
|
| 190 |
-
"learning_rate":
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 26
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 6.872727272727273,
|
| 196 |
-
"grad_norm": 10.
|
| 197 |
-
"learning_rate":
|
| 198 |
-
"loss": 0.
|
| 199 |
"step": 27
|
| 200 |
},
|
| 201 |
{
|
| 202 |
"epoch": 7.0,
|
| 203 |
-
"grad_norm": 10.
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 28
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 7.290909090909091,
|
| 210 |
-
"grad_norm": 10.
|
| 211 |
-
"learning_rate":
|
| 212 |
-
"loss": 0.
|
| 213 |
"step": 29
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 7.581818181818182,
|
| 217 |
-
"grad_norm": 10.
|
| 218 |
-
"learning_rate":
|
| 219 |
-
"loss": 0.
|
| 220 |
"step": 30
|
| 221 |
},
|
| 222 |
{
|
| 223 |
"epoch": 7.872727272727273,
|
| 224 |
-
"grad_norm": 9.
|
| 225 |
-
"learning_rate":
|
| 226 |
-
"loss": 0.
|
| 227 |
"step": 31
|
| 228 |
},
|
| 229 |
{
|
| 230 |
"epoch": 8.0,
|
| 231 |
-
"grad_norm": 10.
|
| 232 |
-
"learning_rate":
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 32
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 8.0,
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"
|
| 241 |
-
"
|
| 242 |
-
"
|
| 243 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 244 |
}
|
| 245 |
],
|
| 246 |
"logging_steps": 1,
|
| 247 |
-
"max_steps":
|
| 248 |
"num_input_tokens_seen": 0,
|
| 249 |
-
"num_train_epochs":
|
| 250 |
"save_steps": 16,
|
| 251 |
"stateful_callbacks": {
|
| 252 |
"TrainerControl": {
|
|
@@ -260,7 +3036,7 @@
|
|
| 260 |
"attributes": {}
|
| 261 |
}
|
| 262 |
},
|
| 263 |
-
"total_flos": 1.
|
| 264 |
"train_batch_size": 1,
|
| 265 |
"trial_name": null,
|
| 266 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 100.0,
|
| 6 |
+
"eval_steps": 16,
|
| 7 |
+
"global_step": 400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.2909090909090909,
|
| 14 |
+
"grad_norm": 10.451888084411621,
|
| 15 |
"learning_rate": 0.0,
|
| 16 |
"loss": 0.7859,
|
| 17 |
"step": 1
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.5818181818181818,
|
| 21 |
+
"grad_norm": 9.886292457580566,
|
| 22 |
+
"learning_rate": 2.5e-09,
|
| 23 |
"loss": 0.7965,
|
| 24 |
"step": 2
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.8727272727272727,
|
| 28 |
+
"grad_norm": 10.406240463256836,
|
| 29 |
+
"learning_rate": 5e-09,
|
| 30 |
"loss": 0.7893,
|
| 31 |
"step": 3
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
+
"grad_norm": 12.746437072753906,
|
| 36 |
+
"learning_rate": 7.5e-09,
|
| 37 |
+
"loss": 0.8702,
|
| 38 |
"step": 4
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 1.290909090909091,
|
| 42 |
+
"grad_norm": 10.291970252990723,
|
| 43 |
+
"learning_rate": 1e-08,
|
| 44 |
+
"loss": 0.7785,
|
| 45 |
"step": 5
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 1.5818181818181818,
|
| 49 |
+
"grad_norm": 9.746875762939453,
|
| 50 |
+
"learning_rate": 1.25e-08,
|
| 51 |
+
"loss": 0.759,
|
| 52 |
"step": 6
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 1.8727272727272726,
|
| 56 |
+
"grad_norm": 10.920265197753906,
|
| 57 |
+
"learning_rate": 1.5e-08,
|
| 58 |
+
"loss": 0.8308,
|
| 59 |
"step": 7
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 2.0,
|
| 63 |
+
"grad_norm": 11.265154838562012,
|
| 64 |
+
"learning_rate": 1.7499999999999998e-08,
|
| 65 |
+
"loss": 0.8828,
|
| 66 |
"step": 8
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 2.290909090909091,
|
| 70 |
+
"grad_norm": 9.750505447387695,
|
| 71 |
+
"learning_rate": 2e-08,
|
| 72 |
+
"loss": 0.8004,
|
| 73 |
"step": 9
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 2.581818181818182,
|
| 77 |
+
"grad_norm": 11.47065544128418,
|
| 78 |
+
"learning_rate": 2.25e-08,
|
| 79 |
+
"loss": 0.8204,
|
| 80 |
"step": 10
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 2.8727272727272726,
|
| 84 |
+
"grad_norm": 10.275605201721191,
|
| 85 |
+
"learning_rate": 2.5e-08,
|
| 86 |
+
"loss": 0.7771,
|
| 87 |
"step": 11
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 3.0,
|
| 91 |
+
"grad_norm": 11.604477882385254,
|
| 92 |
+
"learning_rate": 2.75e-08,
|
| 93 |
+
"loss": 0.8295,
|
| 94 |
"step": 12
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 3.290909090909091,
|
| 98 |
+
"grad_norm": 10.712018966674805,
|
| 99 |
+
"learning_rate": 3e-08,
|
| 100 |
+
"loss": 0.8378,
|
| 101 |
"step": 13
|
| 102 |
},
|
| 103 |
{
|
| 104 |
"epoch": 3.581818181818182,
|
| 105 |
+
"grad_norm": 10.54987907409668,
|
| 106 |
+
"learning_rate": 3.25e-08,
|
| 107 |
+
"loss": 0.8398,
|
| 108 |
"step": 14
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 3.8727272727272726,
|
| 112 |
+
"grad_norm": 9.999624252319336,
|
| 113 |
+
"learning_rate": 3.4999999999999996e-08,
|
| 114 |
+
"loss": 0.773,
|
| 115 |
"step": 15
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 4.0,
|
| 119 |
+
"grad_norm": 10.562870979309082,
|
| 120 |
+
"learning_rate": 3.75e-08,
|
| 121 |
+
"loss": 0.7025,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.0,
|
| 126 |
+
"eval_loss": 0.760595977306366,
|
| 127 |
+
"eval_runtime": 0.722,
|
| 128 |
+
"eval_samples_per_second": 18.005,
|
| 129 |
+
"eval_steps_per_second": 18.005,
|
| 130 |
"step": 16
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 4.290909090909091,
|
| 134 |
+
"grad_norm": 9.95614242553711,
|
| 135 |
+
"learning_rate": 4e-08,
|
| 136 |
+
"loss": 0.7785,
|
| 137 |
"step": 17
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 4.581818181818182,
|
| 141 |
+
"grad_norm": 11.356291770935059,
|
| 142 |
+
"learning_rate": 4.25e-08,
|
| 143 |
+
"loss": 0.8645,
|
| 144 |
"step": 18
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 4.872727272727273,
|
| 148 |
+
"grad_norm": 10.108142852783203,
|
| 149 |
+
"learning_rate": 4.5e-08,
|
| 150 |
+
"loss": 0.7834,
|
| 151 |
"step": 19
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 5.0,
|
| 155 |
+
"grad_norm": 10.209877014160156,
|
| 156 |
+
"learning_rate": 4.7499999999999995e-08,
|
| 157 |
+
"loss": 0.7744,
|
| 158 |
"step": 20
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 5.290909090909091,
|
| 162 |
+
"grad_norm": 9.586356163024902,
|
| 163 |
+
"learning_rate": 5e-08,
|
| 164 |
+
"loss": 0.7433,
|
| 165 |
"step": 21
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 5.581818181818182,
|
| 169 |
+
"grad_norm": 10.589778900146484,
|
| 170 |
+
"learning_rate": 5.25e-08,
|
| 171 |
+
"loss": 0.818,
|
| 172 |
"step": 22
|
| 173 |
},
|
| 174 |
{
|
| 175 |
"epoch": 5.872727272727273,
|
| 176 |
+
"grad_norm": 10.28813362121582,
|
| 177 |
+
"learning_rate": 5.5e-08,
|
| 178 |
+
"loss": 0.8245,
|
| 179 |
"step": 23
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 6.0,
|
| 183 |
+
"grad_norm": 13.027183532714844,
|
| 184 |
+
"learning_rate": 5.749999999999999e-08,
|
| 185 |
+
"loss": 0.8331,
|
| 186 |
"step": 24
|
| 187 |
},
|
| 188 |
{
|
| 189 |
"epoch": 6.290909090909091,
|
| 190 |
+
"grad_norm": 10.363873481750488,
|
| 191 |
+
"learning_rate": 6e-08,
|
| 192 |
+
"loss": 0.8331,
|
| 193 |
"step": 25
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 6.581818181818182,
|
| 197 |
+
"grad_norm": 9.84264850616455,
|
| 198 |
+
"learning_rate": 6.25e-08,
|
| 199 |
+
"loss": 0.755,
|
| 200 |
"step": 26
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 6.872727272727273,
|
| 204 |
+
"grad_norm": 10.973934173583984,
|
| 205 |
+
"learning_rate": 6.5e-08,
|
| 206 |
+
"loss": 0.8372,
|
| 207 |
"step": 27
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 7.0,
|
| 211 |
+
"grad_norm": 10.278410911560059,
|
| 212 |
+
"learning_rate": 6.75e-08,
|
| 213 |
+
"loss": 0.7442,
|
| 214 |
"step": 28
|
| 215 |
},
|
| 216 |
{
|
| 217 |
"epoch": 7.290909090909091,
|
| 218 |
+
"grad_norm": 10.205405235290527,
|
| 219 |
+
"learning_rate": 6.999999999999999e-08,
|
| 220 |
+
"loss": 0.7851,
|
| 221 |
"step": 29
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 7.581818181818182,
|
| 225 |
+
"grad_norm": 10.862798690795898,
|
| 226 |
+
"learning_rate": 7.25e-08,
|
| 227 |
+
"loss": 0.7962,
|
| 228 |
"step": 30
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 7.872727272727273,
|
| 232 |
+
"grad_norm": 9.971634864807129,
|
| 233 |
+
"learning_rate": 7.5e-08,
|
| 234 |
+
"loss": 0.79,
|
| 235 |
"step": 31
|
| 236 |
},
|
| 237 |
{
|
| 238 |
"epoch": 8.0,
|
| 239 |
+
"grad_norm": 10.8460111618042,
|
| 240 |
+
"learning_rate": 7.75e-08,
|
| 241 |
+
"loss": 0.9105,
|
| 242 |
"step": 32
|
| 243 |
},
|
| 244 |
{
|
| 245 |
"epoch": 8.0,
|
| 246 |
+
"eval_loss": 0.7589532136917114,
|
| 247 |
+
"eval_runtime": 0.7554,
|
| 248 |
+
"eval_samples_per_second": 17.21,
|
| 249 |
+
"eval_steps_per_second": 17.21,
|
| 250 |
+
"step": 32
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 8.290909090909091,
|
| 254 |
+
"grad_norm": 10.4276704788208,
|
| 255 |
+
"learning_rate": 8e-08,
|
| 256 |
+
"loss": 0.7914,
|
| 257 |
+
"step": 33
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 8.581818181818182,
|
| 261 |
+
"grad_norm": 9.807103157043457,
|
| 262 |
+
"learning_rate": 8.249999999999999e-08,
|
| 263 |
+
"loss": 0.8344,
|
| 264 |
+
"step": 34
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 8.872727272727273,
|
| 268 |
+
"grad_norm": 9.850166320800781,
|
| 269 |
+
"learning_rate": 8.5e-08,
|
| 270 |
+
"loss": 0.7419,
|
| 271 |
+
"step": 35
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 9.0,
|
| 275 |
+
"grad_norm": 12.547399520874023,
|
| 276 |
+
"learning_rate": 8.75e-08,
|
| 277 |
+
"loss": 0.8597,
|
| 278 |
+
"step": 36
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 9.290909090909091,
|
| 282 |
+
"grad_norm": 10.39106559753418,
|
| 283 |
+
"learning_rate": 9e-08,
|
| 284 |
+
"loss": 0.7911,
|
| 285 |
+
"step": 37
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 9.581818181818182,
|
| 289 |
+
"grad_norm": 10.728227615356445,
|
| 290 |
+
"learning_rate": 9.25e-08,
|
| 291 |
+
"loss": 0.852,
|
| 292 |
+
"step": 38
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 9.872727272727273,
|
| 296 |
+
"grad_norm": 10.104507446289062,
|
| 297 |
+
"learning_rate": 9.499999999999999e-08,
|
| 298 |
+
"loss": 0.7942,
|
| 299 |
+
"step": 39
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.0,
|
| 303 |
+
"grad_norm": 9.163139343261719,
|
| 304 |
+
"learning_rate": 9.749999999999999e-08,
|
| 305 |
+
"loss": 0.7006,
|
| 306 |
+
"step": 40
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.290909090909091,
|
| 310 |
+
"grad_norm": 9.795455932617188,
|
| 311 |
+
"learning_rate": 1e-07,
|
| 312 |
+
"loss": 0.7496,
|
| 313 |
+
"step": 41
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.581818181818182,
|
| 317 |
+
"grad_norm": 9.88698959350586,
|
| 318 |
+
"learning_rate": 9.99982865378877e-08,
|
| 319 |
+
"loss": 0.7978,
|
| 320 |
+
"step": 42
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 10.872727272727273,
|
| 324 |
+
"grad_norm": 10.60831069946289,
|
| 325 |
+
"learning_rate": 9.99931462820376e-08,
|
| 326 |
+
"loss": 0.8437,
|
| 327 |
+
"step": 43
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 11.0,
|
| 331 |
+
"grad_norm": 10.177803039550781,
|
| 332 |
+
"learning_rate": 9.998457962390006e-08,
|
| 333 |
+
"loss": 0.7926,
|
| 334 |
+
"step": 44
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 11.290909090909091,
|
| 338 |
+
"grad_norm": 9.594599723815918,
|
| 339 |
+
"learning_rate": 9.997258721585931e-08,
|
| 340 |
+
"loss": 0.7521,
|
| 341 |
+
"step": 45
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 11.581818181818182,
|
| 345 |
+
"grad_norm": 9.713711738586426,
|
| 346 |
+
"learning_rate": 9.99571699711836e-08,
|
| 347 |
+
"loss": 0.7497,
|
| 348 |
+
"step": 46
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 11.872727272727273,
|
| 352 |
+
"grad_norm": 10.672869682312012,
|
| 353 |
+
"learning_rate": 9.993832906395581e-08,
|
| 354 |
+
"loss": 0.8709,
|
| 355 |
+
"step": 47
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 12.0,
|
| 359 |
+
"grad_norm": 10.758075714111328,
|
| 360 |
+
"learning_rate": 9.991606592898401e-08,
|
| 361 |
+
"loss": 0.8193,
|
| 362 |
+
"step": 48
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 12.0,
|
| 366 |
+
"eval_loss": 0.7549822926521301,
|
| 367 |
+
"eval_runtime": 0.7468,
|
| 368 |
+
"eval_samples_per_second": 17.407,
|
| 369 |
+
"eval_steps_per_second": 17.407,
|
| 370 |
+
"step": 48
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 12.290909090909091,
|
| 374 |
+
"grad_norm": 10.45877742767334,
|
| 375 |
+
"learning_rate": 9.989038226169209e-08,
|
| 376 |
+
"loss": 0.8488,
|
| 377 |
+
"step": 49
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 12.581818181818182,
|
| 381 |
+
"grad_norm": 9.969883918762207,
|
| 382 |
+
"learning_rate": 9.986128001799076e-08,
|
| 383 |
+
"loss": 0.7697,
|
| 384 |
+
"step": 50
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 12.872727272727273,
|
| 388 |
+
"grad_norm": 9.769625663757324,
|
| 389 |
+
"learning_rate": 9.982876141412855e-08,
|
| 390 |
+
"loss": 0.769,
|
| 391 |
+
"step": 51
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 13.0,
|
| 395 |
+
"grad_norm": 10.126288414001465,
|
| 396 |
+
"learning_rate": 9.979282892652304e-08,
|
| 397 |
+
"loss": 0.8111,
|
| 398 |
+
"step": 52
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 13.290909090909091,
|
| 402 |
+
"grad_norm": 10.078240394592285,
|
| 403 |
+
"learning_rate": 9.975348529157229e-08,
|
| 404 |
+
"loss": 0.798,
|
| 405 |
+
"step": 53
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.581818181818182,
|
| 409 |
+
"grad_norm": 10.470067024230957,
|
| 410 |
+
"learning_rate": 9.971073350544643e-08,
|
| 411 |
+
"loss": 0.8011,
|
| 412 |
+
"step": 54
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 13.872727272727273,
|
| 416 |
+
"grad_norm": 9.311027526855469,
|
| 417 |
+
"learning_rate": 9.966457682385949e-08,
|
| 418 |
+
"loss": 0.7109,
|
| 419 |
+
"step": 55
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 14.0,
|
| 423 |
+
"grad_norm": 10.48747730255127,
|
| 424 |
+
"learning_rate": 9.961501876182147e-08,
|
| 425 |
+
"loss": 0.969,
|
| 426 |
+
"step": 56
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 14.290909090909091,
|
| 430 |
+
"grad_norm": 9.95235538482666,
|
| 431 |
+
"learning_rate": 9.956206309337066e-08,
|
| 432 |
+
"loss": 0.7757,
|
| 433 |
+
"step": 57
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 14.581818181818182,
|
| 437 |
+
"grad_norm": 9.8017578125,
|
| 438 |
+
"learning_rate": 9.950571385128625e-08,
|
| 439 |
+
"loss": 0.7974,
|
| 440 |
+
"step": 58
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 14.872727272727273,
|
| 444 |
+
"grad_norm": 10.287720680236816,
|
| 445 |
+
"learning_rate": 9.94459753267812e-08,
|
| 446 |
+
"loss": 0.842,
|
| 447 |
+
"step": 59
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 15.0,
|
| 451 |
+
"grad_norm": 9.790772438049316,
|
| 452 |
+
"learning_rate": 9.938285206917541e-08,
|
| 453 |
+
"loss": 0.7127,
|
| 454 |
+
"step": 60
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 15.290909090909091,
|
| 458 |
+
"grad_norm": 9.698260307312012,
|
| 459 |
+
"learning_rate": 9.931634888554937e-08,
|
| 460 |
+
"loss": 0.7662,
|
| 461 |
+
"step": 61
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 15.581818181818182,
|
| 465 |
+
"grad_norm": 8.966428756713867,
|
| 466 |
+
"learning_rate": 9.924647084037797e-08,
|
| 467 |
+
"loss": 0.7652,
|
| 468 |
+
"step": 62
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 15.872727272727273,
|
| 472 |
+
"grad_norm": 9.97366714477539,
|
| 473 |
+
"learning_rate": 9.917322325514488e-08,
|
| 474 |
+
"loss": 0.854,
|
| 475 |
+
"step": 63
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 16.0,
|
| 479 |
+
"grad_norm": 8.8572359085083,
|
| 480 |
+
"learning_rate": 9.909661170793732e-08,
|
| 481 |
+
"loss": 0.6939,
|
| 482 |
+
"step": 64
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 16.0,
|
| 486 |
+
"eval_loss": 0.7460314631462097,
|
| 487 |
+
"eval_runtime": 0.7685,
|
| 488 |
+
"eval_samples_per_second": 16.917,
|
| 489 |
+
"eval_steps_per_second": 16.917,
|
| 490 |
+
"step": 64
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 16.29090909090909,
|
| 494 |
+
"grad_norm": 9.27105712890625,
|
| 495 |
+
"learning_rate": 9.901664203302125e-08,
|
| 496 |
+
"loss": 0.7894,
|
| 497 |
+
"step": 65
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 16.581818181818182,
|
| 501 |
+
"grad_norm": 9.316947937011719,
|
| 502 |
+
"learning_rate": 9.8933320320397e-08,
|
| 503 |
+
"loss": 0.7476,
|
| 504 |
+
"step": 66
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 16.87272727272727,
|
| 508 |
+
"grad_norm": 9.482162475585938,
|
| 509 |
+
"learning_rate": 9.884665291533559e-08,
|
| 510 |
+
"loss": 0.8294,
|
| 511 |
+
"step": 67
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 17.0,
|
| 515 |
+
"grad_norm": 8.661737442016602,
|
| 516 |
+
"learning_rate": 9.875664641789545e-08,
|
| 517 |
+
"loss": 0.741,
|
| 518 |
+
"step": 68
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 17.29090909090909,
|
| 522 |
+
"grad_norm": 8.976079940795898,
|
| 523 |
+
"learning_rate": 9.866330768241983e-08,
|
| 524 |
+
"loss": 0.7999,
|
| 525 |
+
"step": 69
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 17.581818181818182,
|
| 529 |
+
"grad_norm": 9.500139236450195,
|
| 530 |
+
"learning_rate": 9.856664381701484e-08,
|
| 531 |
+
"loss": 0.8324,
|
| 532 |
+
"step": 70
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 17.87272727272727,
|
| 536 |
+
"grad_norm": 8.916980743408203,
|
| 537 |
+
"learning_rate": 9.846666218300807e-08,
|
| 538 |
+
"loss": 0.7308,
|
| 539 |
+
"step": 71
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 18.0,
|
| 543 |
+
"grad_norm": 9.658391952514648,
|
| 544 |
+
"learning_rate": 9.836337039438803e-08,
|
| 545 |
+
"loss": 0.7691,
|
| 546 |
+
"step": 72
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 18.29090909090909,
|
| 550 |
+
"grad_norm": 9.849284172058105,
|
| 551 |
+
"learning_rate": 9.825677631722435e-08,
|
| 552 |
+
"loss": 0.7804,
|
| 553 |
+
"step": 73
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 18.581818181818182,
|
| 557 |
+
"grad_norm": 9.135872840881348,
|
| 558 |
+
"learning_rate": 9.814688806906868e-08,
|
| 559 |
+
"loss": 0.808,
|
| 560 |
+
"step": 74
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 18.87272727272727,
|
| 564 |
+
"grad_norm": 8.595244407653809,
|
| 565 |
+
"learning_rate": 9.80337140183366e-08,
|
| 566 |
+
"loss": 0.7593,
|
| 567 |
+
"step": 75
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 19.0,
|
| 571 |
+
"grad_norm": 9.557754516601562,
|
| 572 |
+
"learning_rate": 9.791726278367021e-08,
|
| 573 |
+
"loss": 0.795,
|
| 574 |
+
"step": 76
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 19.29090909090909,
|
| 578 |
+
"grad_norm": 9.38132095336914,
|
| 579 |
+
"learning_rate": 9.779754323328191e-08,
|
| 580 |
+
"loss": 0.8303,
|
| 581 |
+
"step": 77
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 19.581818181818182,
|
| 585 |
+
"grad_norm": 9.702839851379395,
|
| 586 |
+
"learning_rate": 9.767456448427896e-08,
|
| 587 |
+
"loss": 0.7404,
|
| 588 |
+
"step": 78
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 19.87272727272727,
|
| 592 |
+
"grad_norm": 8.890022277832031,
|
| 593 |
+
"learning_rate": 9.754833590196926e-08,
|
| 594 |
+
"loss": 0.8152,
|
| 595 |
+
"step": 79
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 20.0,
|
| 599 |
+
"grad_norm": 8.762577056884766,
|
| 600 |
+
"learning_rate": 9.741886709914803e-08,
|
| 601 |
+
"loss": 0.6623,
|
| 602 |
+
"step": 80
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 20.0,
|
| 606 |
+
"eval_loss": 0.7418057918548584,
|
| 607 |
+
"eval_runtime": 0.7512,
|
| 608 |
+
"eval_samples_per_second": 17.305,
|
| 609 |
+
"eval_steps_per_second": 17.305,
|
| 610 |
+
"step": 80
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 20.29090909090909,
|
| 614 |
+
"grad_norm": 9.43545913696289,
|
| 615 |
+
"learning_rate": 9.728616793536587e-08,
|
| 616 |
+
"loss": 0.726,
|
| 617 |
+
"step": 81
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 20.581818181818182,
|
| 621 |
+
"grad_norm": 8.36042308807373,
|
| 622 |
+
"learning_rate": 9.715024851617789e-08,
|
| 623 |
+
"loss": 0.7908,
|
| 624 |
+
"step": 82
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 20.87272727272727,
|
| 628 |
+
"grad_norm": 9.46149730682373,
|
| 629 |
+
"learning_rate": 9.701111919237408e-08,
|
| 630 |
+
"loss": 0.8219,
|
| 631 |
+
"step": 83
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 21.0,
|
| 635 |
+
"grad_norm": 9.277331352233887,
|
| 636 |
+
"learning_rate": 9.68687905591911e-08,
|
| 637 |
+
"loss": 0.7955,
|
| 638 |
+
"step": 84
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 21.29090909090909,
|
| 642 |
+
"grad_norm": 9.980899810791016,
|
| 643 |
+
"learning_rate": 9.672327345550542e-08,
|
| 644 |
+
"loss": 0.8459,
|
| 645 |
+
"step": 85
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 21.581818181818182,
|
| 649 |
+
"grad_norm": 8.734892845153809,
|
| 650 |
+
"learning_rate": 9.65745789630079e-08,
|
| 651 |
+
"loss": 0.7952,
|
| 652 |
+
"step": 86
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 21.87272727272727,
|
| 656 |
+
"grad_norm": 7.979213714599609,
|
| 657 |
+
"learning_rate": 9.642271840535982e-08,
|
| 658 |
+
"loss": 0.6928,
|
| 659 |
+
"step": 87
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 22.0,
|
| 663 |
+
"grad_norm": 9.570889472961426,
|
| 664 |
+
"learning_rate": 9.626770334733058e-08,
|
| 665 |
+
"loss": 0.7813,
|
| 666 |
+
"step": 88
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 22.29090909090909,
|
| 670 |
+
"grad_norm": 9.478497505187988,
|
| 671 |
+
"learning_rate": 9.610954559391703e-08,
|
| 672 |
+
"loss": 0.783,
|
| 673 |
+
"step": 89
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 22.581818181818182,
|
| 677 |
+
"grad_norm": 8.57199478149414,
|
| 678 |
+
"learning_rate": 9.594825718944444e-08,
|
| 679 |
+
"loss": 0.7859,
|
| 680 |
+
"step": 90
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 22.87272727272727,
|
| 684 |
+
"grad_norm": 8.782203674316406,
|
| 685 |
+
"learning_rate": 9.578385041664925e-08,
|
| 686 |
+
"loss": 0.7784,
|
| 687 |
+
"step": 91
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 23.0,
|
| 691 |
+
"grad_norm": 9.160470008850098,
|
| 692 |
+
"learning_rate": 9.561633779574373e-08,
|
| 693 |
+
"loss": 0.7613,
|
| 694 |
+
"step": 92
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 23.29090909090909,
|
| 698 |
+
"grad_norm": 8.80034065246582,
|
| 699 |
+
"learning_rate": 9.544573208346251e-08,
|
| 700 |
+
"loss": 0.7708,
|
| 701 |
+
"step": 93
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 23.581818181818182,
|
| 705 |
+
"grad_norm": 9.001204490661621,
|
| 706 |
+
"learning_rate": 9.527204627209113e-08,
|
| 707 |
+
"loss": 0.7975,
|
| 708 |
+
"step": 94
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 23.87272727272727,
|
| 712 |
+
"grad_norm": 8.64294147491455,
|
| 713 |
+
"learning_rate": 9.509529358847655e-08,
|
| 714 |
+
"loss": 0.7533,
|
| 715 |
+
"step": 95
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 24.0,
|
| 719 |
+
"grad_norm": 9.539164543151855,
|
| 720 |
+
"learning_rate": 9.491548749301997e-08,
|
| 721 |
+
"loss": 0.8112,
|
| 722 |
+
"step": 96
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 24.0,
|
| 726 |
+
"eval_loss": 0.7388671040534973,
|
| 727 |
+
"eval_runtime": 0.7379,
|
| 728 |
+
"eval_samples_per_second": 17.617,
|
| 729 |
+
"eval_steps_per_second": 17.617,
|
| 730 |
+
"step": 96
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 24.29090909090909,
|
| 734 |
+
"grad_norm": 8.564647674560547,
|
| 735 |
+
"learning_rate": 9.473264167865172e-08,
|
| 736 |
+
"loss": 0.779,
|
| 737 |
+
"step": 97
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 24.581818181818182,
|
| 741 |
+
"grad_norm": 8.466269493103027,
|
| 742 |
+
"learning_rate": 9.454677006978843e-08,
|
| 743 |
+
"loss": 0.7427,
|
| 744 |
+
"step": 98
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 24.87272727272727,
|
| 748 |
+
"grad_norm": 9.549156188964844,
|
| 749 |
+
"learning_rate": 9.435788682127281e-08,
|
| 750 |
+
"loss": 0.7749,
|
| 751 |
+
"step": 99
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 25.0,
|
| 755 |
+
"grad_norm": 8.791007041931152,
|
| 756 |
+
"learning_rate": 9.416600631729548e-08,
|
| 757 |
+
"loss": 0.8413,
|
| 758 |
+
"step": 100
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 25.29090909090909,
|
| 762 |
+
"grad_norm": 8.481273651123047,
|
| 763 |
+
"learning_rate": 9.397114317029974e-08,
|
| 764 |
+
"loss": 0.7987,
|
| 765 |
+
"step": 101
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 25.581818181818182,
|
| 769 |
+
"grad_norm": 7.957334518432617,
|
| 770 |
+
"learning_rate": 9.377331221986867e-08,
|
| 771 |
+
"loss": 0.7579,
|
| 772 |
+
"step": 102
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 25.87272727272727,
|
| 776 |
+
"grad_norm": 7.695952415466309,
|
| 777 |
+
"learning_rate": 9.357252853159505e-08,
|
| 778 |
+
"loss": 0.7138,
|
| 779 |
+
"step": 103
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 26.0,
|
| 783 |
+
"grad_norm": 8.535294532775879,
|
| 784 |
+
"learning_rate": 9.336880739593415e-08,
|
| 785 |
+
"loss": 0.8143,
|
| 786 |
+
"step": 104
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 26.29090909090909,
|
| 790 |
+
"grad_norm": 7.785234451293945,
|
| 791 |
+
"learning_rate": 9.316216432703917e-08,
|
| 792 |
+
"loss": 0.7595,
|
| 793 |
+
"step": 105
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 26.581818181818182,
|
| 797 |
+
"grad_norm": 7.210692882537842,
|
| 798 |
+
"learning_rate": 9.295261506157986e-08,
|
| 799 |
+
"loss": 0.6892,
|
| 800 |
+
"step": 106
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 26.87272727272727,
|
| 804 |
+
"grad_norm": 7.439105033874512,
|
| 805 |
+
"learning_rate": 9.274017555754408e-08,
|
| 806 |
+
"loss": 0.7828,
|
| 807 |
+
"step": 107
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 27.0,
|
| 811 |
+
"grad_norm": 8.5601167678833,
|
| 812 |
+
"learning_rate": 9.252486199302256e-08,
|
| 813 |
+
"loss": 0.8267,
|
| 814 |
+
"step": 108
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 27.29090909090909,
|
| 818 |
+
"grad_norm": 7.751751899719238,
|
| 819 |
+
"learning_rate": 9.230669076497686e-08,
|
| 820 |
+
"loss": 0.7837,
|
| 821 |
+
"step": 109
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 27.581818181818182,
|
| 825 |
+
"grad_norm": 7.58750057220459,
|
| 826 |
+
"learning_rate": 9.20856784879907e-08,
|
| 827 |
+
"loss": 0.7629,
|
| 828 |
+
"step": 110
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 27.87272727272727,
|
| 832 |
+
"grad_norm": 7.078155040740967,
|
| 833 |
+
"learning_rate": 9.186184199300463e-08,
|
| 834 |
+
"loss": 0.732,
|
| 835 |
+
"step": 111
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 28.0,
|
| 839 |
+
"grad_norm": 7.075254440307617,
|
| 840 |
+
"learning_rate": 9.163519832603437e-08,
|
| 841 |
+
"loss": 0.708,
|
| 842 |
+
"step": 112
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 28.0,
|
| 846 |
+
"eval_loss": 0.7153984904289246,
|
| 847 |
+
"eval_runtime": 0.7384,
|
| 848 |
+
"eval_samples_per_second": 17.605,
|
| 849 |
+
"eval_steps_per_second": 17.605,
|
| 850 |
+
"step": 112
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 28.29090909090909,
|
| 854 |
+
"grad_norm": 7.660149097442627,
|
| 855 |
+
"learning_rate": 9.140576474687262e-08,
|
| 856 |
+
"loss": 0.7923,
|
| 857 |
+
"step": 113
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 28.581818181818182,
|
| 861 |
+
"grad_norm": 6.516578674316406,
|
| 862 |
+
"learning_rate": 9.117355872777476e-08,
|
| 863 |
+
"loss": 0.6965,
|
| 864 |
+
"step": 114
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 28.87272727272727,
|
| 868 |
+
"grad_norm": 6.818985462188721,
|
| 869 |
+
"learning_rate": 9.093859795212817e-08,
|
| 870 |
+
"loss": 0.7564,
|
| 871 |
+
"step": 115
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 29.0,
|
| 875 |
+
"grad_norm": 9.244476318359375,
|
| 876 |
+
"learning_rate": 9.070090031310558e-08,
|
| 877 |
+
"loss": 0.7325,
|
| 878 |
+
"step": 116
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 29.29090909090909,
|
| 882 |
+
"grad_norm": 7.331173419952393,
|
| 883 |
+
"learning_rate": 9.046048391230248e-08,
|
| 884 |
+
"loss": 0.6957,
|
| 885 |
+
"step": 117
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 29.581818181818182,
|
| 889 |
+
"grad_norm": 7.235352993011475,
|
| 890 |
+
"learning_rate": 9.021736705835861e-08,
|
| 891 |
+
"loss": 0.8011,
|
| 892 |
+
"step": 118
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 29.87272727272727,
|
| 896 |
+
"grad_norm": 7.370168209075928,
|
| 897 |
+
"learning_rate": 8.997156826556369e-08,
|
| 898 |
+
"loss": 0.7767,
|
| 899 |
+
"step": 119
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 30.0,
|
| 903 |
+
"grad_norm": 6.547177314758301,
|
| 904 |
+
"learning_rate": 8.97231062524474e-08,
|
| 905 |
+
"loss": 0.6864,
|
| 906 |
+
"step": 120
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 30.29090909090909,
|
| 910 |
+
"grad_norm": 6.999849796295166,
|
| 911 |
+
"learning_rate": 8.9471999940354e-08,
|
| 912 |
+
"loss": 0.757,
|
| 913 |
+
"step": 121
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 30.581818181818182,
|
| 917 |
+
"grad_norm": 7.369142055511475,
|
| 918 |
+
"learning_rate": 8.921826845200139e-08,
|
| 919 |
+
"loss": 0.7184,
|
| 920 |
+
"step": 122
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 30.87272727272727,
|
| 924 |
+
"grad_norm": 7.147704601287842,
|
| 925 |
+
"learning_rate": 8.896193111002475e-08,
|
| 926 |
+
"loss": 0.8074,
|
| 927 |
+
"step": 123
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 31.0,
|
| 931 |
+
"grad_norm": 6.590007305145264,
|
| 932 |
+
"learning_rate": 8.87030074355051e-08,
|
| 933 |
+
"loss": 0.666,
|
| 934 |
+
"step": 124
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 31.29090909090909,
|
| 938 |
+
"grad_norm": 6.5022711753845215,
|
| 939 |
+
"learning_rate": 8.844151714648274e-08,
|
| 940 |
+
"loss": 0.7109,
|
| 941 |
+
"step": 125
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 31.581818181818182,
|
| 945 |
+
"grad_norm": 7.46487283706665,
|
| 946 |
+
"learning_rate": 8.817748015645558e-08,
|
| 947 |
+
"loss": 0.7848,
|
| 948 |
+
"step": 126
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 31.87272727272727,
|
| 952 |
+
"grad_norm": 7.2371721267700195,
|
| 953 |
+
"learning_rate": 8.791091657286267e-08,
|
| 954 |
+
"loss": 0.7756,
|
| 955 |
+
"step": 127
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 32.0,
|
| 959 |
+
"grad_norm": 6.450557708740234,
|
| 960 |
+
"learning_rate": 8.764184669555293e-08,
|
| 961 |
+
"loss": 0.6471,
|
| 962 |
+
"step": 128
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 32.0,
|
| 966 |
+
"eval_loss": 0.7097088694572449,
|
| 967 |
+
"eval_runtime": 0.7853,
|
| 968 |
+
"eval_samples_per_second": 16.554,
|
| 969 |
+
"eval_steps_per_second": 16.554,
|
| 970 |
+
"step": 128
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 32.29090909090909,
|
| 974 |
+
"grad_norm": 7.1595611572265625,
|
| 975 |
+
"learning_rate": 8.737029101523929e-08,
|
| 976 |
+
"loss": 0.7418,
|
| 977 |
+
"step": 129
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 32.58181818181818,
|
| 981 |
+
"grad_norm": 7.2520294189453125,
|
| 982 |
+
"learning_rate": 8.709627021193817e-08,
|
| 983 |
+
"loss": 0.7407,
|
| 984 |
+
"step": 130
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 32.872727272727275,
|
| 988 |
+
"grad_norm": 6.757298469543457,
|
| 989 |
+
"learning_rate": 8.681980515339464e-08,
|
| 990 |
+
"loss": 0.7486,
|
| 991 |
+
"step": 131
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 33.0,
|
| 995 |
+
"grad_norm": 6.70634651184082,
|
| 996 |
+
"learning_rate": 8.65409168934933e-08,
|
| 997 |
+
"loss": 0.7381,
|
| 998 |
+
"step": 132
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 33.29090909090909,
|
| 1002 |
+
"grad_norm": 8.267258644104004,
|
| 1003 |
+
"learning_rate": 8.625962667065488e-08,
|
| 1004 |
+
"loss": 0.8277,
|
| 1005 |
+
"step": 133
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 33.58181818181818,
|
| 1009 |
+
"grad_norm": 6.568601608276367,
|
| 1010 |
+
"learning_rate": 8.597595590621892e-08,
|
| 1011 |
+
"loss": 0.7345,
|
| 1012 |
+
"step": 134
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 33.872727272727275,
|
| 1016 |
+
"grad_norm": 6.368529796600342,
|
| 1017 |
+
"learning_rate": 8.568992620281244e-08,
|
| 1018 |
+
"loss": 0.6949,
|
| 1019 |
+
"step": 135
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 34.0,
|
| 1023 |
+
"grad_norm": 6.077971458435059,
|
| 1024 |
+
"learning_rate": 8.540155934270471e-08,
|
| 1025 |
+
"loss": 0.6427,
|
| 1026 |
+
"step": 136
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 34.29090909090909,
|
| 1030 |
+
"grad_norm": 6.2005743980407715,
|
| 1031 |
+
"learning_rate": 8.511087728614862e-08,
|
| 1032 |
+
"loss": 0.7113,
|
| 1033 |
+
"step": 137
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 34.58181818181818,
|
| 1037 |
+
"grad_norm": 6.390923023223877,
|
| 1038 |
+
"learning_rate": 8.481790216970819e-08,
|
| 1039 |
+
"loss": 0.7422,
|
| 1040 |
+
"step": 138
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 34.872727272727275,
|
| 1044 |
+
"grad_norm": 7.773628234863281,
|
| 1045 |
+
"learning_rate": 8.452265630457283e-08,
|
| 1046 |
+
"loss": 0.7829,
|
| 1047 |
+
"step": 139
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 35.0,
|
| 1051 |
+
"grad_norm": 7.676466941833496,
|
| 1052 |
+
"learning_rate": 8.422516217485826e-08,
|
| 1053 |
+
"loss": 0.718,
|
| 1054 |
+
"step": 140
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 35.29090909090909,
|
| 1058 |
+
"grad_norm": 6.630233287811279,
|
| 1059 |
+
"learning_rate": 8.392544243589427e-08,
|
| 1060 |
+
"loss": 0.7046,
|
| 1061 |
+
"step": 141
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 35.58181818181818,
|
| 1065 |
+
"grad_norm": 6.816230297088623,
|
| 1066 |
+
"learning_rate": 8.362351991249938e-08,
|
| 1067 |
+
"loss": 0.7685,
|
| 1068 |
+
"step": 142
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 35.872727272727275,
|
| 1072 |
+
"grad_norm": 6.341788291931152,
|
| 1073 |
+
"learning_rate": 8.331941759724268e-08,
|
| 1074 |
+
"loss": 0.6774,
|
| 1075 |
+
"step": 143
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 36.0,
|
| 1079 |
+
"grad_norm": 8.306670188903809,
|
| 1080 |
+
"learning_rate": 8.301315864869288e-08,
|
| 1081 |
+
"loss": 0.9019,
|
| 1082 |
+
"step": 144
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 36.0,
|
| 1086 |
+
"eval_loss": 0.7050113677978516,
|
| 1087 |
+
"eval_runtime": 0.7541,
|
| 1088 |
+
"eval_samples_per_second": 17.239,
|
| 1089 |
+
"eval_steps_per_second": 17.239,
|
| 1090 |
+
"step": 144
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 36.29090909090909,
|
| 1094 |
+
"grad_norm": 6.883708953857422,
|
| 1095 |
+
"learning_rate": 8.270476638965461e-08,
|
| 1096 |
+
"loss": 0.7921,
|
| 1097 |
+
"step": 145
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 36.58181818181818,
|
| 1101 |
+
"grad_norm": 6.389072418212891,
|
| 1102 |
+
"learning_rate": 8.239426430539243e-08,
|
| 1103 |
+
"loss": 0.6827,
|
| 1104 |
+
"step": 146
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 36.872727272727275,
|
| 1108 |
+
"grad_norm": 6.924624443054199,
|
| 1109 |
+
"learning_rate": 8.208167604184218e-08,
|
| 1110 |
+
"loss": 0.7774,
|
| 1111 |
+
"step": 147
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 37.0,
|
| 1115 |
+
"grad_norm": 6.5363450050354,
|
| 1116 |
+
"learning_rate": 8.176702540381035e-08,
|
| 1117 |
+
"loss": 0.6709,
|
| 1118 |
+
"step": 148
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 37.29090909090909,
|
| 1122 |
+
"grad_norm": 6.154909610748291,
|
| 1123 |
+
"learning_rate": 8.145033635316129e-08,
|
| 1124 |
+
"loss": 0.7302,
|
| 1125 |
+
"step": 149
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 37.58181818181818,
|
| 1129 |
+
"grad_norm": 6.3788676261901855,
|
| 1130 |
+
"learning_rate": 8.113163300699229e-08,
|
| 1131 |
+
"loss": 0.7301,
|
| 1132 |
+
"step": 150
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 37.872727272727275,
|
| 1136 |
+
"grad_norm": 7.089733600616455,
|
| 1137 |
+
"learning_rate": 8.081093963579708e-08,
|
| 1138 |
+
"loss": 0.7223,
|
| 1139 |
+
"step": 151
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 38.0,
|
| 1143 |
+
"grad_norm": 7.056278228759766,
|
| 1144 |
+
"learning_rate": 8.048828066161747e-08,
|
| 1145 |
+
"loss": 0.7989,
|
| 1146 |
+
"step": 152
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 38.29090909090909,
|
| 1150 |
+
"grad_norm": 5.888208389282227,
|
| 1151 |
+
"learning_rate": 8.016368065618359e-08,
|
| 1152 |
+
"loss": 0.6768,
|
| 1153 |
+
"step": 153
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 38.58181818181818,
|
| 1157 |
+
"grad_norm": 7.345203399658203,
|
| 1158 |
+
"learning_rate": 7.983716433904262e-08,
|
| 1159 |
+
"loss": 0.7454,
|
| 1160 |
+
"step": 154
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 38.872727272727275,
|
| 1164 |
+
"grad_norm": 6.323718070983887,
|
| 1165 |
+
"learning_rate": 7.950875657567622e-08,
|
| 1166 |
+
"loss": 0.7511,
|
| 1167 |
+
"step": 155
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 39.0,
|
| 1171 |
+
"grad_norm": 7.311026096343994,
|
| 1172 |
+
"learning_rate": 7.917848237560708e-08,
|
| 1173 |
+
"loss": 0.8113,
|
| 1174 |
+
"step": 156
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 39.29090909090909,
|
| 1178 |
+
"grad_norm": 6.139308452606201,
|
| 1179 |
+
"learning_rate": 7.884636689049422e-08,
|
| 1180 |
+
"loss": 0.7076,
|
| 1181 |
+
"step": 157
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 39.58181818181818,
|
| 1185 |
+
"grad_norm": 6.485006809234619,
|
| 1186 |
+
"learning_rate": 7.851243541221769e-08,
|
| 1187 |
+
"loss": 0.7437,
|
| 1188 |
+
"step": 158
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 39.872727272727275,
|
| 1192 |
+
"grad_norm": 6.589916706085205,
|
| 1193 |
+
"learning_rate": 7.817671337095244e-08,
|
| 1194 |
+
"loss": 0.7404,
|
| 1195 |
+
"step": 159
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 40.0,
|
| 1199 |
+
"grad_norm": 6.963124752044678,
|
| 1200 |
+
"learning_rate": 7.78392263332317e-08,
|
| 1201 |
+
"loss": 0.7328,
|
| 1202 |
+
"step": 160
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 40.0,
|
| 1206 |
+
"eval_loss": 0.7006868124008179,
|
| 1207 |
+
"eval_runtime": 0.7566,
|
| 1208 |
+
"eval_samples_per_second": 17.183,
|
| 1209 |
+
"eval_steps_per_second": 17.183,
|
| 1210 |
+
"step": 160
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 40.29090909090909,
|
| 1214 |
+
"grad_norm": 6.547840118408203,
|
| 1215 |
+
"learning_rate": 7.75e-08,
|
| 1216 |
+
"loss": 0.7431,
|
| 1217 |
+
"step": 161
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 40.58181818181818,
|
| 1221 |
+
"grad_norm": 6.299688816070557,
|
| 1222 |
+
"learning_rate": 7.715906020465603e-08,
|
| 1223 |
+
"loss": 0.7585,
|
| 1224 |
+
"step": 162
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 40.872727272727275,
|
| 1228 |
+
"grad_norm": 6.586760997772217,
|
| 1229 |
+
"learning_rate": 7.681643291108518e-08,
|
| 1230 |
+
"loss": 0.7324,
|
| 1231 |
+
"step": 163
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 41.0,
|
| 1235 |
+
"grad_norm": 6.389430999755859,
|
| 1236 |
+
"learning_rate": 7.647214421168238e-08,
|
| 1237 |
+
"loss": 0.6533,
|
| 1238 |
+
"step": 164
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 41.29090909090909,
|
| 1242 |
+
"grad_norm": 6.027109146118164,
|
| 1243 |
+
"learning_rate": 7.612622032536508e-08,
|
| 1244 |
+
"loss": 0.7135,
|
| 1245 |
+
"step": 165
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 41.58181818181818,
|
| 1249 |
+
"grad_norm": 6.719674110412598,
|
| 1250 |
+
"learning_rate": 7.577868759557654e-08,
|
| 1251 |
+
"loss": 0.7597,
|
| 1252 |
+
"step": 166
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 41.872727272727275,
|
| 1256 |
+
"grad_norm": 6.458725929260254,
|
| 1257 |
+
"learning_rate": 7.54295724882796e-08,
|
| 1258 |
+
"loss": 0.7109,
|
| 1259 |
+
"step": 167
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 42.0,
|
| 1263 |
+
"grad_norm": 6.904190540313721,
|
| 1264 |
+
"learning_rate": 7.507890158994139e-08,
|
| 1265 |
+
"loss": 0.7504,
|
| 1266 |
+
"step": 168
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 42.29090909090909,
|
| 1270 |
+
"grad_norm": 6.580723285675049,
|
| 1271 |
+
"learning_rate": 7.472670160550848e-08,
|
| 1272 |
+
"loss": 0.7096,
|
| 1273 |
+
"step": 169
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 42.58181818181818,
|
| 1277 |
+
"grad_norm": 6.410011291503906,
|
| 1278 |
+
"learning_rate": 7.437299935637328e-08,
|
| 1279 |
+
"loss": 0.7692,
|
| 1280 |
+
"step": 170
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 42.872727272727275,
|
| 1284 |
+
"grad_norm": 6.3067827224731445,
|
| 1285 |
+
"learning_rate": 7.401782177833146e-08,
|
| 1286 |
+
"loss": 0.7346,
|
| 1287 |
+
"step": 171
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 43.0,
|
| 1291 |
+
"grad_norm": 5.755003929138184,
|
| 1292 |
+
"learning_rate": 7.366119591953075e-08,
|
| 1293 |
+
"loss": 0.6633,
|
| 1294 |
+
"step": 172
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 43.29090909090909,
|
| 1298 |
+
"grad_norm": 6.46678352355957,
|
| 1299 |
+
"learning_rate": 7.3303148938411e-08,
|
| 1300 |
+
"loss": 0.7365,
|
| 1301 |
+
"step": 173
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 43.58181818181818,
|
| 1305 |
+
"grad_norm": 6.622053623199463,
|
| 1306 |
+
"learning_rate": 7.294370810163607e-08,
|
| 1307 |
+
"loss": 0.7511,
|
| 1308 |
+
"step": 174
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 43.872727272727275,
|
| 1312 |
+
"grad_norm": 5.266422748565674,
|
| 1313 |
+
"learning_rate": 7.258290078201731e-08,
|
| 1314 |
+
"loss": 0.6481,
|
| 1315 |
+
"step": 175
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 44.0,
|
| 1319 |
+
"grad_norm": 7.341455936431885,
|
| 1320 |
+
"learning_rate": 7.222075445642904e-08,
|
| 1321 |
+
"loss": 0.8191,
|
| 1322 |
+
"step": 176
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 44.0,
|
| 1326 |
+
"eval_loss": 0.6937930583953857,
|
| 1327 |
+
"eval_runtime": 0.7725,
|
| 1328 |
+
"eval_samples_per_second": 16.828,
|
| 1329 |
+
"eval_steps_per_second": 16.828,
|
| 1330 |
+
"step": 176
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 44.29090909090909,
|
| 1334 |
+
"grad_norm": 6.314858436584473,
|
| 1335 |
+
"learning_rate": 7.185729670371604e-08,
|
| 1336 |
+
"loss": 0.7001,
|
| 1337 |
+
"step": 177
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 44.58181818181818,
|
| 1341 |
+
"grad_norm": 6.364148139953613,
|
| 1342 |
+
"learning_rate": 7.149255520259337e-08,
|
| 1343 |
+
"loss": 0.786,
|
| 1344 |
+
"step": 178
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 44.872727272727275,
|
| 1348 |
+
"grad_norm": 5.679451942443848,
|
| 1349 |
+
"learning_rate": 7.11265577295385e-08,
|
| 1350 |
+
"loss": 0.6767,
|
| 1351 |
+
"step": 179
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 45.0,
|
| 1355 |
+
"grad_norm": 6.4454216957092285,
|
| 1356 |
+
"learning_rate": 7.075933215667603e-08,
|
| 1357 |
+
"loss": 0.7351,
|
| 1358 |
+
"step": 180
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 45.29090909090909,
|
| 1362 |
+
"grad_norm": 5.991427421569824,
|
| 1363 |
+
"learning_rate": 7.039090644965509e-08,
|
| 1364 |
+
"loss": 0.7047,
|
| 1365 |
+
"step": 181
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 45.58181818181818,
|
| 1369 |
+
"grad_norm": 5.386115550994873,
|
| 1370 |
+
"learning_rate": 7.002130866551968e-08,
|
| 1371 |
+
"loss": 0.7113,
|
| 1372 |
+
"step": 182
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 45.872727272727275,
|
| 1376 |
+
"grad_norm": 6.815364360809326,
|
| 1377 |
+
"learning_rate": 6.965056695057204e-08,
|
| 1378 |
+
"loss": 0.7255,
|
| 1379 |
+
"step": 183
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 46.0,
|
| 1383 |
+
"grad_norm": 6.38714599609375,
|
| 1384 |
+
"learning_rate": 6.927870953822915e-08,
|
| 1385 |
+
"loss": 0.7503,
|
| 1386 |
+
"step": 184
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 46.29090909090909,
|
| 1390 |
+
"grad_norm": 5.759856224060059,
|
| 1391 |
+
"learning_rate": 6.890576474687262e-08,
|
| 1392 |
+
"loss": 0.7008,
|
| 1393 |
+
"step": 185
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 46.58181818181818,
|
| 1397 |
+
"grad_norm": 5.1396918296813965,
|
| 1398 |
+
"learning_rate": 6.853176097769228e-08,
|
| 1399 |
+
"loss": 0.6925,
|
| 1400 |
+
"step": 186
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 46.872727272727275,
|
| 1404 |
+
"grad_norm": 5.9070539474487305,
|
| 1405 |
+
"learning_rate": 6.815672671252315e-08,
|
| 1406 |
+
"loss": 0.7409,
|
| 1407 |
+
"step": 187
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 47.0,
|
| 1411 |
+
"grad_norm": 5.90541410446167,
|
| 1412 |
+
"learning_rate": 6.778069051167653e-08,
|
| 1413 |
+
"loss": 0.702,
|
| 1414 |
+
"step": 188
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 47.29090909090909,
|
| 1418 |
+
"grad_norm": 5.474076747894287,
|
| 1419 |
+
"learning_rate": 6.740368101176495e-08,
|
| 1420 |
+
"loss": 0.7085,
|
| 1421 |
+
"step": 189
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 47.58181818181818,
|
| 1425 |
+
"grad_norm": 5.111520767211914,
|
| 1426 |
+
"learning_rate": 6.702572692352155e-08,
|
| 1427 |
+
"loss": 0.685,
|
| 1428 |
+
"step": 190
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 47.872727272727275,
|
| 1432 |
+
"grad_norm": 5.618140697479248,
|
| 1433 |
+
"learning_rate": 6.664685702961344e-08,
|
| 1434 |
+
"loss": 0.7551,
|
| 1435 |
+
"step": 191
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 48.0,
|
| 1439 |
+
"grad_norm": 4.961245059967041,
|
| 1440 |
+
"learning_rate": 6.626710018244986e-08,
|
| 1441 |
+
"loss": 0.6327,
|
| 1442 |
+
"step": 192
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 48.0,
|
| 1446 |
+
"eval_loss": 0.6752312183380127,
|
| 1447 |
+
"eval_runtime": 0.7832,
|
| 1448 |
+
"eval_samples_per_second": 16.599,
|
| 1449 |
+
"eval_steps_per_second": 16.599,
|
| 1450 |
+
"step": 192
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 48.29090909090909,
|
| 1454 |
+
"grad_norm": 5.36975622177124,
|
| 1455 |
+
"learning_rate": 6.588648530198504e-08,
|
| 1456 |
+
"loss": 0.7312,
|
| 1457 |
+
"step": 193
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 48.58181818181818,
|
| 1461 |
+
"grad_norm": 5.021007061004639,
|
| 1462 |
+
"learning_rate": 6.550504137351574e-08,
|
| 1463 |
+
"loss": 0.7467,
|
| 1464 |
+
"step": 194
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 48.872727272727275,
|
| 1468 |
+
"grad_norm": 4.721583843231201,
|
| 1469 |
+
"learning_rate": 6.512279744547392e-08,
|
| 1470 |
+
"loss": 0.6271,
|
| 1471 |
+
"step": 195
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 49.0,
|
| 1475 |
+
"grad_norm": 5.531439304351807,
|
| 1476 |
+
"learning_rate": 6.473978262721462e-08,
|
| 1477 |
+
"loss": 0.7127,
|
| 1478 |
+
"step": 196
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 49.29090909090909,
|
| 1482 |
+
"grad_norm": 5.3525309562683105,
|
| 1483 |
+
"learning_rate": 6.435602608679917e-08,
|
| 1484 |
+
"loss": 0.7255,
|
| 1485 |
+
"step": 197
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 49.58181818181818,
|
| 1489 |
+
"grad_norm": 4.411137104034424,
|
| 1490 |
+
"learning_rate": 6.397155704877387e-08,
|
| 1491 |
+
"loss": 0.6177,
|
| 1492 |
+
"step": 198
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 49.872727272727275,
|
| 1496 |
+
"grad_norm": 4.907252788543701,
|
| 1497 |
+
"learning_rate": 6.358640479194451e-08,
|
| 1498 |
+
"loss": 0.7295,
|
| 1499 |
+
"step": 199
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 50.0,
|
| 1503 |
+
"grad_norm": 4.626101493835449,
|
| 1504 |
+
"learning_rate": 6.320059864714664e-08,
|
| 1505 |
+
"loss": 0.7091,
|
| 1506 |
+
"step": 200
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 50.29090909090909,
|
| 1510 |
+
"grad_norm": 4.853626728057861,
|
| 1511 |
+
"learning_rate": 6.281416799501187e-08,
|
| 1512 |
+
"loss": 0.7432,
|
| 1513 |
+
"step": 201
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 50.58181818181818,
|
| 1517 |
+
"grad_norm": 4.439899921417236,
|
| 1518 |
+
"learning_rate": 6.242714226373049e-08,
|
| 1519 |
+
"loss": 0.676,
|
| 1520 |
+
"step": 202
|
| 1521 |
+
},
|
| 1522 |
+
{
|
| 1523 |
+
"epoch": 50.872727272727275,
|
| 1524 |
+
"grad_norm": 4.5280985832214355,
|
| 1525 |
+
"learning_rate": 6.203955092681039e-08,
|
| 1526 |
+
"loss": 0.7086,
|
| 1527 |
+
"step": 203
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 51.0,
|
| 1531 |
+
"grad_norm": 4.414018154144287,
|
| 1532 |
+
"learning_rate": 6.165142350083249e-08,
|
| 1533 |
+
"loss": 0.5264,
|
| 1534 |
+
"step": 204
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 51.29090909090909,
|
| 1538 |
+
"grad_norm": 4.17572021484375,
|
| 1539 |
+
"learning_rate": 6.126278954320294e-08,
|
| 1540 |
+
"loss": 0.7346,
|
| 1541 |
+
"step": 205
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 51.58181818181818,
|
| 1545 |
+
"grad_norm": 4.015255928039551,
|
| 1546 |
+
"learning_rate": 6.087367864990232e-08,
|
| 1547 |
+
"loss": 0.6239,
|
| 1548 |
+
"step": 206
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 51.872727272727275,
|
| 1552 |
+
"grad_norm": 4.698182582855225,
|
| 1553 |
+
"learning_rate": 6.048412045323163e-08,
|
| 1554 |
+
"loss": 0.688,
|
| 1555 |
+
"step": 207
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 52.0,
|
| 1559 |
+
"grad_norm": 5.5075297355651855,
|
| 1560 |
+
"learning_rate": 6.00941446195558e-08,
|
| 1561 |
+
"loss": 0.6903,
|
| 1562 |
+
"step": 208
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 52.0,
|
| 1566 |
+
"eval_loss": 0.6604220271110535,
|
| 1567 |
+
"eval_runtime": 0.6915,
|
| 1568 |
+
"eval_samples_per_second": 18.8,
|
| 1569 |
+
"eval_steps_per_second": 18.8,
|
| 1570 |
+
"step": 208
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 52.29090909090909,
|
| 1574 |
+
"grad_norm": 3.8842809200286865,
|
| 1575 |
+
"learning_rate": 5.970378084704441e-08,
|
| 1576 |
+
"loss": 0.6428,
|
| 1577 |
+
"step": 209
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 52.58181818181818,
|
| 1581 |
+
"grad_norm": 4.9067301750183105,
|
| 1582 |
+
"learning_rate": 5.931305886341008e-08,
|
| 1583 |
+
"loss": 0.7572,
|
| 1584 |
+
"step": 210
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 52.872727272727275,
|
| 1588 |
+
"grad_norm": 4.025907516479492,
|
| 1589 |
+
"learning_rate": 5.892200842364462e-08,
|
| 1590 |
+
"loss": 0.6545,
|
| 1591 |
+
"step": 211
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 53.0,
|
| 1595 |
+
"grad_norm": 4.105547904968262,
|
| 1596 |
+
"learning_rate": 5.853065930775303e-08,
|
| 1597 |
+
"loss": 0.6439,
|
| 1598 |
+
"step": 212
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 53.29090909090909,
|
| 1602 |
+
"grad_norm": 3.7520296573638916,
|
| 1603 |
+
"learning_rate": 5.813904131848564e-08,
|
| 1604 |
+
"loss": 0.677,
|
| 1605 |
+
"step": 213
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 53.58181818181818,
|
| 1609 |
+
"grad_norm": 3.975045680999756,
|
| 1610 |
+
"learning_rate": 5.7747184279068564e-08,
|
| 1611 |
+
"loss": 0.6321,
|
| 1612 |
+
"step": 214
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 53.872727272727275,
|
| 1616 |
+
"grad_norm": 4.536473274230957,
|
| 1617 |
+
"learning_rate": 5.735511803093248e-08,
|
| 1618 |
+
"loss": 0.7326,
|
| 1619 |
+
"step": 215
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 54.0,
|
| 1623 |
+
"grad_norm": 5.148712158203125,
|
| 1624 |
+
"learning_rate": 5.696287243144012e-08,
|
| 1625 |
+
"loss": 0.6819,
|
| 1626 |
+
"step": 216
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 54.29090909090909,
|
| 1630 |
+
"grad_norm": 3.6721999645233154,
|
| 1631 |
+
"learning_rate": 5.6570477351612554e-08,
|
| 1632 |
+
"loss": 0.6655,
|
| 1633 |
+
"step": 217
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 54.58181818181818,
|
| 1637 |
+
"grad_norm": 4.29323148727417,
|
| 1638 |
+
"learning_rate": 5.61779626738543e-08,
|
| 1639 |
+
"loss": 0.6743,
|
| 1640 |
+
"step": 218
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 54.872727272727275,
|
| 1644 |
+
"grad_norm": 4.018572807312012,
|
| 1645 |
+
"learning_rate": 5.5785358289677765e-08,
|
| 1646 |
+
"loss": 0.711,
|
| 1647 |
+
"step": 219
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 55.0,
|
| 1651 |
+
"grad_norm": 4.6550445556640625,
|
| 1652 |
+
"learning_rate": 5.539269409742683e-08,
|
| 1653 |
+
"loss": 0.6398,
|
| 1654 |
+
"step": 220
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 55.29090909090909,
|
| 1658 |
+
"grad_norm": 4.599621295928955,
|
| 1659 |
+
"learning_rate": 5.5e-08,
|
| 1660 |
+
"loss": 0.6885,
|
| 1661 |
+
"step": 221
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 55.58181818181818,
|
| 1665 |
+
"grad_norm": 3.6876866817474365,
|
| 1666 |
+
"learning_rate": 5.460730590257318e-08,
|
| 1667 |
+
"loss": 0.6391,
|
| 1668 |
+
"step": 222
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 55.872727272727275,
|
| 1672 |
+
"grad_norm": 3.641345262527466,
|
| 1673 |
+
"learning_rate": 5.421464171032224e-08,
|
| 1674 |
+
"loss": 0.6684,
|
| 1675 |
+
"step": 223
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 56.0,
|
| 1679 |
+
"grad_norm": 4.325244903564453,
|
| 1680 |
+
"learning_rate": 5.382203732614572e-08,
|
| 1681 |
+
"loss": 0.7467,
|
| 1682 |
+
"step": 224
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 56.0,
|
| 1686 |
+
"eval_loss": 0.6532977819442749,
|
| 1687 |
+
"eval_runtime": 0.746,
|
| 1688 |
+
"eval_samples_per_second": 17.427,
|
| 1689 |
+
"eval_steps_per_second": 17.427,
|
| 1690 |
+
"step": 224
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 56.29090909090909,
|
| 1694 |
+
"grad_norm": 4.434227466583252,
|
| 1695 |
+
"learning_rate": 5.342952264838747e-08,
|
| 1696 |
+
"loss": 0.7395,
|
| 1697 |
+
"step": 225
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 56.58181818181818,
|
| 1701 |
+
"grad_norm": 4.03561544418335,
|
| 1702 |
+
"learning_rate": 5.303712756855988e-08,
|
| 1703 |
+
"loss": 0.7176,
|
| 1704 |
+
"step": 226
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 56.872727272727275,
|
| 1708 |
+
"grad_norm": 3.4329726696014404,
|
| 1709 |
+
"learning_rate": 5.264488196906752e-08,
|
| 1710 |
+
"loss": 0.5565,
|
| 1711 |
+
"step": 227
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 57.0,
|
| 1715 |
+
"grad_norm": 3.6157584190368652,
|
| 1716 |
+
"learning_rate": 5.225281572093143e-08,
|
| 1717 |
+
"loss": 0.7052,
|
| 1718 |
+
"step": 228
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 57.29090909090909,
|
| 1722 |
+
"grad_norm": 3.654561996459961,
|
| 1723 |
+
"learning_rate": 5.1860958681514355e-08,
|
| 1724 |
+
"loss": 0.6931,
|
| 1725 |
+
"step": 229
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 57.58181818181818,
|
| 1729 |
+
"grad_norm": 3.4616754055023193,
|
| 1730 |
+
"learning_rate": 5.1469340692246985e-08,
|
| 1731 |
+
"loss": 0.6126,
|
| 1732 |
+
"step": 230
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 57.872727272727275,
|
| 1736 |
+
"grad_norm": 4.538090229034424,
|
| 1737 |
+
"learning_rate": 5.107799157635537e-08,
|
| 1738 |
+
"loss": 0.7149,
|
| 1739 |
+
"step": 231
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 58.0,
|
| 1743 |
+
"grad_norm": 3.8424854278564453,
|
| 1744 |
+
"learning_rate": 5.068694113658992e-08,
|
| 1745 |
+
"loss": 0.6564,
|
| 1746 |
+
"step": 232
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 58.29090909090909,
|
| 1750 |
+
"grad_norm": 3.360053777694702,
|
| 1751 |
+
"learning_rate": 5.02962191529556e-08,
|
| 1752 |
+
"loss": 0.6657,
|
| 1753 |
+
"step": 233
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 58.58181818181818,
|
| 1757 |
+
"grad_norm": 4.166203022003174,
|
| 1758 |
+
"learning_rate": 4.9905855380444194e-08,
|
| 1759 |
+
"loss": 0.7461,
|
| 1760 |
+
"step": 234
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 58.872727272727275,
|
| 1764 |
+
"grad_norm": 3.4333815574645996,
|
| 1765 |
+
"learning_rate": 4.9515879546768366e-08,
|
| 1766 |
+
"loss": 0.5924,
|
| 1767 |
+
"step": 235
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 59.0,
|
| 1771 |
+
"grad_norm": 4.719890594482422,
|
| 1772 |
+
"learning_rate": 4.912632135009769e-08,
|
| 1773 |
+
"loss": 0.6793,
|
| 1774 |
+
"step": 236
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 59.29090909090909,
|
| 1778 |
+
"grad_norm": 3.6366472244262695,
|
| 1779 |
+
"learning_rate": 4.873721045679706e-08,
|
| 1780 |
+
"loss": 0.6648,
|
| 1781 |
+
"step": 237
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 59.58181818181818,
|
| 1785 |
+
"grad_norm": 4.29836893081665,
|
| 1786 |
+
"learning_rate": 4.8348576499167516e-08,
|
| 1787 |
+
"loss": 0.6871,
|
| 1788 |
+
"step": 238
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 59.872727272727275,
|
| 1792 |
+
"grad_norm": 3.3436715602874756,
|
| 1793 |
+
"learning_rate": 4.7960449073189604e-08,
|
| 1794 |
+
"loss": 0.6136,
|
| 1795 |
+
"step": 239
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 60.0,
|
| 1799 |
+
"grad_norm": 3.974397897720337,
|
| 1800 |
+
"learning_rate": 4.75728577362695e-08,
|
| 1801 |
+
"loss": 0.7364,
|
| 1802 |
+
"step": 240
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 60.0,
|
| 1806 |
+
"eval_loss": 0.6488688588142395,
|
| 1807 |
+
"eval_runtime": 0.7429,
|
| 1808 |
+
"eval_samples_per_second": 17.5,
|
| 1809 |
+
"eval_steps_per_second": 17.5,
|
| 1810 |
+
"step": 240
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 60.29090909090909,
|
| 1814 |
+
"grad_norm": 4.133732318878174,
|
| 1815 |
+
"learning_rate": 4.718583200498813e-08,
|
| 1816 |
+
"loss": 0.7386,
|
| 1817 |
+
"step": 241
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 60.58181818181818,
|
| 1821 |
+
"grad_norm": 3.358363151550293,
|
| 1822 |
+
"learning_rate": 4.6799401352853365e-08,
|
| 1823 |
+
"loss": 0.6255,
|
| 1824 |
+
"step": 242
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 60.872727272727275,
|
| 1828 |
+
"grad_norm": 3.73943829536438,
|
| 1829 |
+
"learning_rate": 4.641359520805548e-08,
|
| 1830 |
+
"loss": 0.6834,
|
| 1831 |
+
"step": 243
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 61.0,
|
| 1835 |
+
"grad_norm": 3.680448532104492,
|
| 1836 |
+
"learning_rate": 4.6028442951226135e-08,
|
| 1837 |
+
"loss": 0.5903,
|
| 1838 |
+
"step": 244
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 61.29090909090909,
|
| 1842 |
+
"grad_norm": 3.3045241832733154,
|
| 1843 |
+
"learning_rate": 4.564397391320084e-08,
|
| 1844 |
+
"loss": 0.5871,
|
| 1845 |
+
"step": 245
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 61.58181818181818,
|
| 1849 |
+
"grad_norm": 3.690742015838623,
|
| 1850 |
+
"learning_rate": 4.526021737278537e-08,
|
| 1851 |
+
"loss": 0.6913,
|
| 1852 |
+
"step": 246
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 61.872727272727275,
|
| 1856 |
+
"grad_norm": 4.233401775360107,
|
| 1857 |
+
"learning_rate": 4.4877202554526084e-08,
|
| 1858 |
+
"loss": 0.7115,
|
| 1859 |
+
"step": 247
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 62.0,
|
| 1863 |
+
"grad_norm": 3.5080771446228027,
|
| 1864 |
+
"learning_rate": 4.449495862648427e-08,
|
| 1865 |
+
"loss": 0.687,
|
| 1866 |
+
"step": 248
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 62.29090909090909,
|
| 1870 |
+
"grad_norm": 3.3871119022369385,
|
| 1871 |
+
"learning_rate": 4.4113514698014955e-08,
|
| 1872 |
+
"loss": 0.6901,
|
| 1873 |
+
"step": 249
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 62.58181818181818,
|
| 1877 |
+
"grad_norm": 3.6088693141937256,
|
| 1878 |
+
"learning_rate": 4.373289981755013e-08,
|
| 1879 |
+
"loss": 0.631,
|
| 1880 |
+
"step": 250
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 62.872727272727275,
|
| 1884 |
+
"grad_norm": 3.743149518966675,
|
| 1885 |
+
"learning_rate": 4.335314297038656e-08,
|
| 1886 |
+
"loss": 0.6351,
|
| 1887 |
+
"step": 251
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 63.0,
|
| 1891 |
+
"grad_norm": 4.030084133148193,
|
| 1892 |
+
"learning_rate": 4.297427307647844e-08,
|
| 1893 |
+
"loss": 0.7212,
|
| 1894 |
+
"step": 252
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 63.29090909090909,
|
| 1898 |
+
"grad_norm": 3.458228349685669,
|
| 1899 |
+
"learning_rate": 4.2596318988235035e-08,
|
| 1900 |
+
"loss": 0.629,
|
| 1901 |
+
"step": 253
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 63.58181818181818,
|
| 1905 |
+
"grad_norm": 4.063506126403809,
|
| 1906 |
+
"learning_rate": 4.2219309488323486e-08,
|
| 1907 |
+
"loss": 0.6565,
|
| 1908 |
+
"step": 254
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 63.872727272727275,
|
| 1912 |
+
"grad_norm": 3.257892370223999,
|
| 1913 |
+
"learning_rate": 4.184327328747685e-08,
|
| 1914 |
+
"loss": 0.6644,
|
| 1915 |
+
"step": 255
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 64.0,
|
| 1919 |
+
"grad_norm": 3.964184284210205,
|
| 1920 |
+
"learning_rate": 4.1468239022307716e-08,
|
| 1921 |
+
"loss": 0.7706,
|
| 1922 |
+
"step": 256
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 64.0,
|
| 1926 |
+
"eval_loss": 0.6460027694702148,
|
| 1927 |
+
"eval_runtime": 0.7572,
|
| 1928 |
+
"eval_samples_per_second": 17.168,
|
| 1929 |
+
"eval_steps_per_second": 17.168,
|
| 1930 |
+
"step": 256
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 64.2909090909091,
|
| 1934 |
+
"grad_norm": 3.444884777069092,
|
| 1935 |
+
"learning_rate": 4.1094235253127375e-08,
|
| 1936 |
+
"loss": 0.5848,
|
| 1937 |
+
"step": 257
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 64.58181818181818,
|
| 1941 |
+
"grad_norm": 3.34226131439209,
|
| 1942 |
+
"learning_rate": 4.072129046177086e-08,
|
| 1943 |
+
"loss": 0.6438,
|
| 1944 |
+
"step": 258
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 64.87272727272727,
|
| 1948 |
+
"grad_norm": 4.081578254699707,
|
| 1949 |
+
"learning_rate": 4.034943304942796e-08,
|
| 1950 |
+
"loss": 0.7825,
|
| 1951 |
+
"step": 259
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 65.0,
|
| 1955 |
+
"grad_norm": 3.9306929111480713,
|
| 1956 |
+
"learning_rate": 3.997869133448031e-08,
|
| 1957 |
+
"loss": 0.7003,
|
| 1958 |
+
"step": 260
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 65.2909090909091,
|
| 1962 |
+
"grad_norm": 3.3377864360809326,
|
| 1963 |
+
"learning_rate": 3.960909355034491e-08,
|
| 1964 |
+
"loss": 0.6723,
|
| 1965 |
+
"step": 261
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 65.58181818181818,
|
| 1969 |
+
"grad_norm": 4.126795291900635,
|
| 1970 |
+
"learning_rate": 3.924066784332396e-08,
|
| 1971 |
+
"loss": 0.6778,
|
| 1972 |
+
"step": 262
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 65.87272727272727,
|
| 1976 |
+
"grad_norm": 3.283628225326538,
|
| 1977 |
+
"learning_rate": 3.8873442270461487e-08,
|
| 1978 |
+
"loss": 0.6196,
|
| 1979 |
+
"step": 263
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 66.0,
|
| 1983 |
+
"grad_norm": 3.599966526031494,
|
| 1984 |
+
"learning_rate": 3.850744479740663e-08,
|
| 1985 |
+
"loss": 0.7125,
|
| 1986 |
+
"step": 264
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 66.2909090909091,
|
| 1990 |
+
"grad_norm": 3.398857831954956,
|
| 1991 |
+
"learning_rate": 3.814270329628395e-08,
|
| 1992 |
+
"loss": 0.6958,
|
| 1993 |
+
"step": 265
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 66.58181818181818,
|
| 1997 |
+
"grad_norm": 3.538728952407837,
|
| 1998 |
+
"learning_rate": 3.777924554357096e-08,
|
| 1999 |
+
"loss": 0.6089,
|
| 2000 |
+
"step": 266
|
| 2001 |
+
},
|
| 2002 |
+
{
|
| 2003 |
+
"epoch": 66.87272727272727,
|
| 2004 |
+
"grad_norm": 3.549941062927246,
|
| 2005 |
+
"learning_rate": 3.7417099217982684e-08,
|
| 2006 |
+
"loss": 0.6794,
|
| 2007 |
+
"step": 267
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"epoch": 67.0,
|
| 2011 |
+
"grad_norm": 3.7104790210723877,
|
| 2012 |
+
"learning_rate": 3.7056291898363926e-08,
|
| 2013 |
+
"loss": 0.6845,
|
| 2014 |
+
"step": 268
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 67.2909090909091,
|
| 2018 |
+
"grad_norm": 3.7661495208740234,
|
| 2019 |
+
"learning_rate": 3.669685106158899e-08,
|
| 2020 |
+
"loss": 0.6726,
|
| 2021 |
+
"step": 269
|
| 2022 |
+
},
|
| 2023 |
+
{
|
| 2024 |
+
"epoch": 67.58181818181818,
|
| 2025 |
+
"grad_norm": 3.2654290199279785,
|
| 2026 |
+
"learning_rate": 3.633880408046926e-08,
|
| 2027 |
+
"loss": 0.6597,
|
| 2028 |
+
"step": 270
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 67.87272727272727,
|
| 2032 |
+
"grad_norm": 3.3389344215393066,
|
| 2033 |
+
"learning_rate": 3.598217822166854e-08,
|
| 2034 |
+
"loss": 0.5967,
|
| 2035 |
+
"step": 271
|
| 2036 |
+
},
|
| 2037 |
+
{
|
| 2038 |
+
"epoch": 68.0,
|
| 2039 |
+
"grad_norm": 4.037345886230469,
|
| 2040 |
+
"learning_rate": 3.5627000643626705e-08,
|
| 2041 |
+
"loss": 0.7777,
|
| 2042 |
+
"step": 272
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 68.0,
|
| 2046 |
+
"eval_loss": 0.6440867185592651,
|
| 2047 |
+
"eval_runtime": 0.7501,
|
| 2048 |
+
"eval_samples_per_second": 17.331,
|
| 2049 |
+
"eval_steps_per_second": 17.331,
|
| 2050 |
+
"step": 272
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 68.2909090909091,
|
| 2054 |
+
"grad_norm": 3.359079360961914,
|
| 2055 |
+
"learning_rate": 3.527329839449151e-08,
|
| 2056 |
+
"loss": 0.6824,
|
| 2057 |
+
"step": 273
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 68.58181818181818,
|
| 2061 |
+
"grad_norm": 3.1845285892486572,
|
| 2062 |
+
"learning_rate": 3.49210984100586e-08,
|
| 2063 |
+
"loss": 0.5956,
|
| 2064 |
+
"step": 274
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 68.87272727272727,
|
| 2068 |
+
"grad_norm": 3.564899206161499,
|
| 2069 |
+
"learning_rate": 3.4570427511720395e-08,
|
| 2070 |
+
"loss": 0.679,
|
| 2071 |
+
"step": 275
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 69.0,
|
| 2075 |
+
"grad_norm": 5.116268157958984,
|
| 2076 |
+
"learning_rate": 3.4221312404423483e-08,
|
| 2077 |
+
"loss": 0.7194,
|
| 2078 |
+
"step": 276
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 69.2909090909091,
|
| 2082 |
+
"grad_norm": 3.2692816257476807,
|
| 2083 |
+
"learning_rate": 3.387377967463493e-08,
|
| 2084 |
+
"loss": 0.5994,
|
| 2085 |
+
"step": 277
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 69.58181818181818,
|
| 2089 |
+
"grad_norm": 3.1827392578125,
|
| 2090 |
+
"learning_rate": 3.3527855788317614e-08,
|
| 2091 |
+
"loss": 0.6582,
|
| 2092 |
+
"step": 278
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 69.87272727272727,
|
| 2096 |
+
"grad_norm": 3.776779890060425,
|
| 2097 |
+
"learning_rate": 3.3183567088914834e-08,
|
| 2098 |
+
"loss": 0.7129,
|
| 2099 |
+
"step": 279
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 70.0,
|
| 2103 |
+
"grad_norm": 4.038694381713867,
|
| 2104 |
+
"learning_rate": 3.2840939795343986e-08,
|
| 2105 |
+
"loss": 0.7197,
|
| 2106 |
+
"step": 280
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 70.2909090909091,
|
| 2110 |
+
"grad_norm": 4.152867317199707,
|
| 2111 |
+
"learning_rate": 3.250000000000001e-08,
|
| 2112 |
+
"loss": 0.6844,
|
| 2113 |
+
"step": 281
|
| 2114 |
+
},
|
| 2115 |
+
{
|
| 2116 |
+
"epoch": 70.58181818181818,
|
| 2117 |
+
"grad_norm": 3.327399492263794,
|
| 2118 |
+
"learning_rate": 3.2160773666768325e-08,
|
| 2119 |
+
"loss": 0.7062,
|
| 2120 |
+
"step": 282
|
| 2121 |
+
},
|
| 2122 |
+
{
|
| 2123 |
+
"epoch": 70.87272727272727,
|
| 2124 |
+
"grad_norm": 3.2052102088928223,
|
| 2125 |
+
"learning_rate": 3.182328662904756e-08,
|
| 2126 |
+
"loss": 0.597,
|
| 2127 |
+
"step": 283
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 71.0,
|
| 2131 |
+
"grad_norm": 3.528104305267334,
|
| 2132 |
+
"learning_rate": 3.14875645877823e-08,
|
| 2133 |
+
"loss": 0.6592,
|
| 2134 |
+
"step": 284
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 71.2909090909091,
|
| 2138 |
+
"grad_norm": 3.380600929260254,
|
| 2139 |
+
"learning_rate": 3.1153633109505784e-08,
|
| 2140 |
+
"loss": 0.6398,
|
| 2141 |
+
"step": 285
|
| 2142 |
+
},
|
| 2143 |
+
{
|
| 2144 |
+
"epoch": 71.58181818181818,
|
| 2145 |
+
"grad_norm": 3.3184642791748047,
|
| 2146 |
+
"learning_rate": 3.082151762439292e-08,
|
| 2147 |
+
"loss": 0.6979,
|
| 2148 |
+
"step": 286
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 71.87272727272727,
|
| 2152 |
+
"grad_norm": 3.4902994632720947,
|
| 2153 |
+
"learning_rate": 3.049124342432378e-08,
|
| 2154 |
+
"loss": 0.6352,
|
| 2155 |
+
"step": 287
|
| 2156 |
+
},
|
| 2157 |
+
{
|
| 2158 |
+
"epoch": 72.0,
|
| 2159 |
+
"grad_norm": 3.682870388031006,
|
| 2160 |
+
"learning_rate": 3.0162835660957385e-08,
|
| 2161 |
+
"loss": 0.6391,
|
| 2162 |
+
"step": 288
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 72.0,
|
| 2166 |
+
"eval_loss": 0.641921877861023,
|
| 2167 |
+
"eval_runtime": 0.7653,
|
| 2168 |
+
"eval_samples_per_second": 16.986,
|
| 2169 |
+
"eval_steps_per_second": 16.986,
|
| 2170 |
+
"step": 288
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 72.2909090909091,
|
| 2174 |
+
"grad_norm": 3.4279274940490723,
|
| 2175 |
+
"learning_rate": 2.983631934381639e-08,
|
| 2176 |
+
"loss": 0.6219,
|
| 2177 |
+
"step": 289
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 72.58181818181818,
|
| 2181 |
+
"grad_norm": 3.627363681793213,
|
| 2182 |
+
"learning_rate": 2.9511719338382535e-08,
|
| 2183 |
+
"loss": 0.6635,
|
| 2184 |
+
"step": 290
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 72.87272727272727,
|
| 2188 |
+
"grad_norm": 3.1634864807128906,
|
| 2189 |
+
"learning_rate": 2.918906036420294e-08,
|
| 2190 |
+
"loss": 0.6377,
|
| 2191 |
+
"step": 291
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 73.0,
|
| 2195 |
+
"grad_norm": 3.896449327468872,
|
| 2196 |
+
"learning_rate": 2.886836699300771e-08,
|
| 2197 |
+
"loss": 0.7822,
|
| 2198 |
+
"step": 292
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 73.2909090909091,
|
| 2202 |
+
"grad_norm": 3.168968677520752,
|
| 2203 |
+
"learning_rate": 2.8549663646838718e-08,
|
| 2204 |
+
"loss": 0.609,
|
| 2205 |
+
"step": 293
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 73.58181818181818,
|
| 2209 |
+
"grad_norm": 3.3781349658966064,
|
| 2210 |
+
"learning_rate": 2.8232974596189653e-08,
|
| 2211 |
+
"loss": 0.6728,
|
| 2212 |
+
"step": 294
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 73.87272727272727,
|
| 2216 |
+
"grad_norm": 3.41473650932312,
|
| 2217 |
+
"learning_rate": 2.791832395815782e-08,
|
| 2218 |
+
"loss": 0.7013,
|
| 2219 |
+
"step": 295
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 74.0,
|
| 2223 |
+
"grad_norm": 3.771911859512329,
|
| 2224 |
+
"learning_rate": 2.760573569460757e-08,
|
| 2225 |
+
"loss": 0.6343,
|
| 2226 |
+
"step": 296
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 74.2909090909091,
|
| 2230 |
+
"grad_norm": 3.527878761291504,
|
| 2231 |
+
"learning_rate": 2.729523361034538e-08,
|
| 2232 |
+
"loss": 0.6528,
|
| 2233 |
+
"step": 297
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 74.58181818181818,
|
| 2237 |
+
"grad_norm": 3.105755090713501,
|
| 2238 |
+
"learning_rate": 2.6986841351307128e-08,
|
| 2239 |
+
"loss": 0.6243,
|
| 2240 |
+
"step": 298
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 74.87272727272727,
|
| 2244 |
+
"grad_norm": 3.3217263221740723,
|
| 2245 |
+
"learning_rate": 2.6680582402757322e-08,
|
| 2246 |
+
"loss": 0.6658,
|
| 2247 |
+
"step": 299
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 75.0,
|
| 2251 |
+
"grad_norm": 4.193359375,
|
| 2252 |
+
"learning_rate": 2.637648008750062e-08,
|
| 2253 |
+
"loss": 0.7016,
|
| 2254 |
+
"step": 300
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 75.2909090909091,
|
| 2258 |
+
"grad_norm": 3.2874765396118164,
|
| 2259 |
+
"learning_rate": 2.6074557564105726e-08,
|
| 2260 |
+
"loss": 0.6661,
|
| 2261 |
+
"step": 301
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 75.58181818181818,
|
| 2265 |
+
"grad_norm": 3.4806275367736816,
|
| 2266 |
+
"learning_rate": 2.5774837825141737e-08,
|
| 2267 |
+
"loss": 0.6277,
|
| 2268 |
+
"step": 302
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 75.87272727272727,
|
| 2272 |
+
"grad_norm": 3.398120880126953,
|
| 2273 |
+
"learning_rate": 2.547734369542718e-08,
|
| 2274 |
+
"loss": 0.6863,
|
| 2275 |
+
"step": 303
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 76.0,
|
| 2279 |
+
"grad_norm": 3.1762161254882812,
|
| 2280 |
+
"learning_rate": 2.5182097830291825e-08,
|
| 2281 |
+
"loss": 0.648,
|
| 2282 |
+
"step": 304
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 76.0,
|
| 2286 |
+
"eval_loss": 0.6407743096351624,
|
| 2287 |
+
"eval_runtime": 0.7838,
|
| 2288 |
+
"eval_samples_per_second": 16.585,
|
| 2289 |
+
"eval_steps_per_second": 16.585,
|
| 2290 |
+
"step": 304
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 76.2909090909091,
|
| 2294 |
+
"grad_norm": 3.250011444091797,
|
| 2295 |
+
"learning_rate": 2.4889122713851394e-08,
|
| 2296 |
+
"loss": 0.6552,
|
| 2297 |
+
"step": 305
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 76.58181818181818,
|
| 2301 |
+
"grad_norm": 3.1045658588409424,
|
| 2302 |
+
"learning_rate": 2.4598440657295288e-08,
|
| 2303 |
+
"loss": 0.6147,
|
| 2304 |
+
"step": 306
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 76.87272727272727,
|
| 2308 |
+
"grad_norm": 4.007096290588379,
|
| 2309 |
+
"learning_rate": 2.4310073797187574e-08,
|
| 2310 |
+
"loss": 0.7181,
|
| 2311 |
+
"step": 307
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 77.0,
|
| 2315 |
+
"grad_norm": 3.300295829772949,
|
| 2316 |
+
"learning_rate": 2.4024044093781064e-08,
|
| 2317 |
+
"loss": 0.6115,
|
| 2318 |
+
"step": 308
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 77.2909090909091,
|
| 2322 |
+
"grad_norm": 3.376610517501831,
|
| 2323 |
+
"learning_rate": 2.3740373329345117e-08,
|
| 2324 |
+
"loss": 0.7065,
|
| 2325 |
+
"step": 309
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 77.58181818181818,
|
| 2329 |
+
"grad_norm": 3.1987497806549072,
|
| 2330 |
+
"learning_rate": 2.3459083106506712e-08,
|
| 2331 |
+
"loss": 0.6265,
|
| 2332 |
+
"step": 310
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 77.87272727272727,
|
| 2336 |
+
"grad_norm": 3.428140878677368,
|
| 2337 |
+
"learning_rate": 2.3180194846605363e-08,
|
| 2338 |
+
"loss": 0.629,
|
| 2339 |
+
"step": 311
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 78.0,
|
| 2343 |
+
"grad_norm": 3.489027261734009,
|
| 2344 |
+
"learning_rate": 2.2903729788061836e-08,
|
| 2345 |
+
"loss": 0.6626,
|
| 2346 |
+
"step": 312
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 78.2909090909091,
|
| 2350 |
+
"grad_norm": 3.7477946281433105,
|
| 2351 |
+
"learning_rate": 2.2629708984760707e-08,
|
| 2352 |
+
"loss": 0.7006,
|
| 2353 |
+
"step": 313
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 78.58181818181818,
|
| 2357 |
+
"grad_norm": 3.2413809299468994,
|
| 2358 |
+
"learning_rate": 2.2358153304447067e-08,
|
| 2359 |
+
"loss": 0.6363,
|
| 2360 |
+
"step": 314
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 78.87272727272727,
|
| 2364 |
+
"grad_norm": 3.0365958213806152,
|
| 2365 |
+
"learning_rate": 2.2089083427137328e-08,
|
| 2366 |
+
"loss": 0.6307,
|
| 2367 |
+
"step": 315
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 79.0,
|
| 2371 |
+
"grad_norm": 3.5392417907714844,
|
| 2372 |
+
"learning_rate": 2.182251984354442e-08,
|
| 2373 |
+
"loss": 0.6594,
|
| 2374 |
+
"step": 316
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 79.2909090909091,
|
| 2378 |
+
"grad_norm": 3.2169861793518066,
|
| 2379 |
+
"learning_rate": 2.1558482853517254e-08,
|
| 2380 |
+
"loss": 0.6261,
|
| 2381 |
+
"step": 317
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 79.58181818181818,
|
| 2385 |
+
"grad_norm": 3.1975908279418945,
|
| 2386 |
+
"learning_rate": 2.1296992564494903e-08,
|
| 2387 |
+
"loss": 0.6303,
|
| 2388 |
+
"step": 318
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 79.87272727272727,
|
| 2392 |
+
"grad_norm": 3.5037009716033936,
|
| 2393 |
+
"learning_rate": 2.103806888997526e-08,
|
| 2394 |
+
"loss": 0.6847,
|
| 2395 |
+
"step": 319
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 80.0,
|
| 2399 |
+
"grad_norm": 3.49397611618042,
|
| 2400 |
+
"learning_rate": 2.078173154799861e-08,
|
| 2401 |
+
"loss": 0.704,
|
| 2402 |
+
"step": 320
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 80.0,
|
| 2406 |
+
"eval_loss": 0.6397803425788879,
|
| 2407 |
+
"eval_runtime": 0.7407,
|
| 2408 |
+
"eval_samples_per_second": 17.552,
|
| 2409 |
+
"eval_steps_per_second": 17.552,
|
| 2410 |
+
"step": 320
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 80.2909090909091,
|
| 2414 |
+
"grad_norm": 3.312922954559326,
|
| 2415 |
+
"learning_rate": 2.0528000059645996e-08,
|
| 2416 |
+
"loss": 0.6742,
|
| 2417 |
+
"step": 321
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 80.58181818181818,
|
| 2421 |
+
"grad_norm": 3.8569176197052,
|
| 2422 |
+
"learning_rate": 2.027689374755261e-08,
|
| 2423 |
+
"loss": 0.6589,
|
| 2424 |
+
"step": 322
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 80.87272727272727,
|
| 2428 |
+
"grad_norm": 3.100782871246338,
|
| 2429 |
+
"learning_rate": 2.0028431734436306e-08,
|
| 2430 |
+
"loss": 0.6384,
|
| 2431 |
+
"step": 323
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 81.0,
|
| 2435 |
+
"grad_norm": 3.488448143005371,
|
| 2436 |
+
"learning_rate": 1.9782632941641373e-08,
|
| 2437 |
+
"loss": 0.6523,
|
| 2438 |
+
"step": 324
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 81.2909090909091,
|
| 2442 |
+
"grad_norm": 3.713844060897827,
|
| 2443 |
+
"learning_rate": 1.9539516087697516e-08,
|
| 2444 |
+
"loss": 0.7186,
|
| 2445 |
+
"step": 325
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 81.58181818181818,
|
| 2449 |
+
"grad_norm": 3.2771830558776855,
|
| 2450 |
+
"learning_rate": 1.9299099686894422e-08,
|
| 2451 |
+
"loss": 0.7155,
|
| 2452 |
+
"step": 326
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 81.87272727272727,
|
| 2456 |
+
"grad_norm": 3.013705015182495,
|
| 2457 |
+
"learning_rate": 1.9061402047871834e-08,
|
| 2458 |
+
"loss": 0.5796,
|
| 2459 |
+
"step": 327
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 82.0,
|
| 2463 |
+
"grad_norm": 3.9129855632781982,
|
| 2464 |
+
"learning_rate": 1.8826441272225223e-08,
|
| 2465 |
+
"loss": 0.5744,
|
| 2466 |
+
"step": 328
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 82.2909090909091,
|
| 2470 |
+
"grad_norm": 3.432311773300171,
|
| 2471 |
+
"learning_rate": 1.8594235253127372e-08,
|
| 2472 |
+
"loss": 0.6681,
|
| 2473 |
+
"step": 329
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 82.58181818181818,
|
| 2477 |
+
"grad_norm": 3.2865946292877197,
|
| 2478 |
+
"learning_rate": 1.8364801673965642e-08,
|
| 2479 |
+
"loss": 0.7103,
|
| 2480 |
+
"step": 330
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 82.87272727272727,
|
| 2484 |
+
"grad_norm": 3.1664698123931885,
|
| 2485 |
+
"learning_rate": 1.8138158006995365e-08,
|
| 2486 |
+
"loss": 0.5704,
|
| 2487 |
+
"step": 331
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 83.0,
|
| 2491 |
+
"grad_norm": 3.5827629566192627,
|
| 2492 |
+
"learning_rate": 1.7914321512009295e-08,
|
| 2493 |
+
"loss": 0.7128,
|
| 2494 |
+
"step": 332
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 83.2909090909091,
|
| 2498 |
+
"grad_norm": 3.228314161300659,
|
| 2499 |
+
"learning_rate": 1.7693309235023126e-08,
|
| 2500 |
+
"loss": 0.6072,
|
| 2501 |
+
"step": 333
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 83.58181818181818,
|
| 2505 |
+
"grad_norm": 3.2263855934143066,
|
| 2506 |
+
"learning_rate": 1.7475138006977434e-08,
|
| 2507 |
+
"loss": 0.6525,
|
| 2508 |
+
"step": 334
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 83.87272727272727,
|
| 2512 |
+
"grad_norm": 3.2911698818206787,
|
| 2513 |
+
"learning_rate": 1.7259824442455922e-08,
|
| 2514 |
+
"loss": 0.7323,
|
| 2515 |
+
"step": 335
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 84.0,
|
| 2519 |
+
"grad_norm": 3.629072666168213,
|
| 2520 |
+
"learning_rate": 1.704738493842015e-08,
|
| 2521 |
+
"loss": 0.6316,
|
| 2522 |
+
"step": 336
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 84.0,
|
| 2526 |
+
"eval_loss": 0.6387331485748291,
|
| 2527 |
+
"eval_runtime": 0.761,
|
| 2528 |
+
"eval_samples_per_second": 17.082,
|
| 2529 |
+
"eval_steps_per_second": 17.082,
|
| 2530 |
+
"step": 336
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 84.2909090909091,
|
| 2534 |
+
"grad_norm": 3.0507638454437256,
|
| 2535 |
+
"learning_rate": 1.6837835672960833e-08,
|
| 2536 |
+
"loss": 0.6576,
|
| 2537 |
+
"step": 337
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 84.58181818181818,
|
| 2541 |
+
"grad_norm": 3.1356823444366455,
|
| 2542 |
+
"learning_rate": 1.663119260406585e-08,
|
| 2543 |
+
"loss": 0.6216,
|
| 2544 |
+
"step": 338
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 84.87272727272727,
|
| 2548 |
+
"grad_norm": 3.6667861938476562,
|
| 2549 |
+
"learning_rate": 1.642747146840495e-08,
|
| 2550 |
+
"loss": 0.6975,
|
| 2551 |
+
"step": 339
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 85.0,
|
| 2555 |
+
"grad_norm": 3.397160768508911,
|
| 2556 |
+
"learning_rate": 1.6226687780131337e-08,
|
| 2557 |
+
"loss": 0.6022,
|
| 2558 |
+
"step": 340
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 85.2909090909091,
|
| 2562 |
+
"grad_norm": 3.163560152053833,
|
| 2563 |
+
"learning_rate": 1.602885682970026e-08,
|
| 2564 |
+
"loss": 0.6316,
|
| 2565 |
+
"step": 341
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 85.58181818181818,
|
| 2569 |
+
"grad_norm": 3.1787586212158203,
|
| 2570 |
+
"learning_rate": 1.5833993682704515e-08,
|
| 2571 |
+
"loss": 0.6725,
|
| 2572 |
+
"step": 342
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 85.87272727272727,
|
| 2576 |
+
"grad_norm": 3.379927158355713,
|
| 2577 |
+
"learning_rate": 1.5642113178727193e-08,
|
| 2578 |
+
"loss": 0.6319,
|
| 2579 |
+
"step": 343
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 86.0,
|
| 2583 |
+
"grad_norm": 3.783219337463379,
|
| 2584 |
+
"learning_rate": 1.5453229930211566e-08,
|
| 2585 |
+
"loss": 0.72,
|
| 2586 |
+
"step": 344
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 86.2909090909091,
|
| 2590 |
+
"grad_norm": 3.678173065185547,
|
| 2591 |
+
"learning_rate": 1.5267358321348288e-08,
|
| 2592 |
+
"loss": 0.7343,
|
| 2593 |
+
"step": 345
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 86.58181818181818,
|
| 2597 |
+
"grad_norm": 3.0277297496795654,
|
| 2598 |
+
"learning_rate": 1.5084512506980025e-08,
|
| 2599 |
+
"loss": 0.6112,
|
| 2600 |
+
"step": 346
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 86.87272727272727,
|
| 2604 |
+
"grad_norm": 2.9994826316833496,
|
| 2605 |
+
"learning_rate": 1.490470641152345e-08,
|
| 2606 |
+
"loss": 0.6377,
|
| 2607 |
+
"step": 347
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 87.0,
|
| 2611 |
+
"grad_norm": 3.4868507385253906,
|
| 2612 |
+
"learning_rate": 1.4727953727908877e-08,
|
| 2613 |
+
"loss": 0.603,
|
| 2614 |
+
"step": 348
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 87.2909090909091,
|
| 2618 |
+
"grad_norm": 3.3681607246398926,
|
| 2619 |
+
"learning_rate": 1.4554267916537493e-08,
|
| 2620 |
+
"loss": 0.6832,
|
| 2621 |
+
"step": 349
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 87.58181818181818,
|
| 2625 |
+
"grad_norm": 3.123229742050171,
|
| 2626 |
+
"learning_rate": 1.438366220425628e-08,
|
| 2627 |
+
"loss": 0.6086,
|
| 2628 |
+
"step": 350
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 87.87272727272727,
|
| 2632 |
+
"grad_norm": 3.2728774547576904,
|
| 2633 |
+
"learning_rate": 1.4216149583350753e-08,
|
| 2634 |
+
"loss": 0.6735,
|
| 2635 |
+
"step": 351
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 88.0,
|
| 2639 |
+
"grad_norm": 3.185558319091797,
|
| 2640 |
+
"learning_rate": 1.405174281055556e-08,
|
| 2641 |
+
"loss": 0.6232,
|
| 2642 |
+
"step": 352
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 88.0,
|
| 2646 |
+
"eval_loss": 0.6380465030670166,
|
| 2647 |
+
"eval_runtime": 0.6934,
|
| 2648 |
+
"eval_samples_per_second": 18.748,
|
| 2649 |
+
"eval_steps_per_second": 18.748,
|
| 2650 |
+
"step": 352
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 88.2909090909091,
|
| 2654 |
+
"grad_norm": 3.0658743381500244,
|
| 2655 |
+
"learning_rate": 1.3890454406082957e-08,
|
| 2656 |
+
"loss": 0.6388,
|
| 2657 |
+
"step": 353
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 88.58181818181818,
|
| 2661 |
+
"grad_norm": 3.2591443061828613,
|
| 2662 |
+
"learning_rate": 1.3732296652669417e-08,
|
| 2663 |
+
"loss": 0.6658,
|
| 2664 |
+
"step": 354
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 88.87272727272727,
|
| 2668 |
+
"grad_norm": 3.252021551132202,
|
| 2669 |
+
"learning_rate": 1.3577281594640182e-08,
|
| 2670 |
+
"loss": 0.6671,
|
| 2671 |
+
"step": 355
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 89.0,
|
| 2675 |
+
"grad_norm": 3.7164716720581055,
|
| 2676 |
+
"learning_rate": 1.3425421036992096e-08,
|
| 2677 |
+
"loss": 0.6185,
|
| 2678 |
+
"step": 356
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 89.2909090909091,
|
| 2682 |
+
"grad_norm": 3.1124889850616455,
|
| 2683 |
+
"learning_rate": 1.327672654449457e-08,
|
| 2684 |
+
"loss": 0.6648,
|
| 2685 |
+
"step": 357
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 89.58181818181818,
|
| 2689 |
+
"grad_norm": 3.4343039989471436,
|
| 2690 |
+
"learning_rate": 1.3131209440808898e-08,
|
| 2691 |
+
"loss": 0.6731,
|
| 2692 |
+
"step": 358
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 89.87272727272727,
|
| 2696 |
+
"grad_norm": 2.8693790435791016,
|
| 2697 |
+
"learning_rate": 1.2988880807625927e-08,
|
| 2698 |
+
"loss": 0.5938,
|
| 2699 |
+
"step": 359
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 90.0,
|
| 2703 |
+
"grad_norm": 4.409383773803711,
|
| 2704 |
+
"learning_rate": 1.284975148382211e-08,
|
| 2705 |
+
"loss": 0.7107,
|
| 2706 |
+
"step": 360
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 90.2909090909091,
|
| 2710 |
+
"grad_norm": 3.080493450164795,
|
| 2711 |
+
"learning_rate": 1.2713832064634124e-08,
|
| 2712 |
+
"loss": 0.6798,
|
| 2713 |
+
"step": 361
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 90.58181818181818,
|
| 2717 |
+
"grad_norm": 2.9749112129211426,
|
| 2718 |
+
"learning_rate": 1.2581132900851971e-08,
|
| 2719 |
+
"loss": 0.6249,
|
| 2720 |
+
"step": 362
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 90.87272727272727,
|
| 2724 |
+
"grad_norm": 3.626858949661255,
|
| 2725 |
+
"learning_rate": 1.2451664098030743e-08,
|
| 2726 |
+
"loss": 0.6616,
|
| 2727 |
+
"step": 363
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 91.0,
|
| 2731 |
+
"grad_norm": 3.859955310821533,
|
| 2732 |
+
"learning_rate": 1.232543551572103e-08,
|
| 2733 |
+
"loss": 0.6418,
|
| 2734 |
+
"step": 364
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 91.2909090909091,
|
| 2738 |
+
"grad_norm": 3.4120571613311768,
|
| 2739 |
+
"learning_rate": 1.2202456766718091e-08,
|
| 2740 |
+
"loss": 0.707,
|
| 2741 |
+
"step": 365
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 91.58181818181818,
|
| 2745 |
+
"grad_norm": 2.8337764739990234,
|
| 2746 |
+
"learning_rate": 1.2082737216329793e-08,
|
| 2747 |
+
"loss": 0.6083,
|
| 2748 |
+
"step": 366
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 91.87272727272727,
|
| 2752 |
+
"grad_norm": 3.1251420974731445,
|
| 2753 |
+
"learning_rate": 1.1966285981663406e-08,
|
| 2754 |
+
"loss": 0.6327,
|
| 2755 |
+
"step": 367
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 92.0,
|
| 2759 |
+
"grad_norm": 4.236498832702637,
|
| 2760 |
+
"learning_rate": 1.1853111930931313e-08,
|
| 2761 |
+
"loss": 0.6545,
|
| 2762 |
+
"step": 368
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 92.0,
|
| 2766 |
+
"eval_loss": 0.6371535062789917,
|
| 2767 |
+
"eval_runtime": 0.7492,
|
| 2768 |
+
"eval_samples_per_second": 17.353,
|
| 2769 |
+
"eval_steps_per_second": 17.353,
|
| 2770 |
+
"step": 368
|
| 2771 |
+
},
|
| 2772 |
+
{
|
| 2773 |
+
"epoch": 92.2909090909091,
|
| 2774 |
+
"grad_norm": 3.1066205501556396,
|
| 2775 |
+
"learning_rate": 1.174322368277565e-08,
|
| 2776 |
+
"loss": 0.5913,
|
| 2777 |
+
"step": 369
|
| 2778 |
+
},
|
| 2779 |
+
{
|
| 2780 |
+
"epoch": 92.58181818181818,
|
| 2781 |
+
"grad_norm": 3.334169626235962,
|
| 2782 |
+
"learning_rate": 1.1636629605611967e-08,
|
| 2783 |
+
"loss": 0.6869,
|
| 2784 |
+
"step": 370
|
| 2785 |
+
},
|
| 2786 |
+
{
|
| 2787 |
+
"epoch": 92.87272727272727,
|
| 2788 |
+
"grad_norm": 3.105184316635132,
|
| 2789 |
+
"learning_rate": 1.1533337816991931e-08,
|
| 2790 |
+
"loss": 0.6699,
|
| 2791 |
+
"step": 371
|
| 2792 |
+
},
|
| 2793 |
+
{
|
| 2794 |
+
"epoch": 93.0,
|
| 2795 |
+
"grad_norm": 3.6188406944274902,
|
| 2796 |
+
"learning_rate": 1.1433356182985158e-08,
|
| 2797 |
+
"loss": 0.658,
|
| 2798 |
+
"step": 372
|
| 2799 |
+
},
|
| 2800 |
+
{
|
| 2801 |
+
"epoch": 93.2909090909091,
|
| 2802 |
+
"grad_norm": 3.376845598220825,
|
| 2803 |
+
"learning_rate": 1.133669231758016e-08,
|
| 2804 |
+
"loss": 0.7064,
|
| 2805 |
+
"step": 373
|
| 2806 |
+
},
|
| 2807 |
+
{
|
| 2808 |
+
"epoch": 93.58181818181818,
|
| 2809 |
+
"grad_norm": 3.327584981918335,
|
| 2810 |
+
"learning_rate": 1.1243353582104555e-08,
|
| 2811 |
+
"loss": 0.6268,
|
| 2812 |
+
"step": 374
|
| 2813 |
+
},
|
| 2814 |
+
{
|
| 2815 |
+
"epoch": 93.87272727272727,
|
| 2816 |
+
"grad_norm": 2.9586260318756104,
|
| 2817 |
+
"learning_rate": 1.115334708466442e-08,
|
| 2818 |
+
"loss": 0.6366,
|
| 2819 |
+
"step": 375
|
| 2820 |
+
},
|
| 2821 |
+
{
|
| 2822 |
+
"epoch": 94.0,
|
| 2823 |
+
"grad_norm": 3.442078113555908,
|
| 2824 |
+
"learning_rate": 1.1066679679602998e-08,
|
| 2825 |
+
"loss": 0.5847,
|
| 2826 |
+
"step": 376
|
| 2827 |
+
},
|
| 2828 |
+
{
|
| 2829 |
+
"epoch": 94.2909090909091,
|
| 2830 |
+
"grad_norm": 2.9368817806243896,
|
| 2831 |
+
"learning_rate": 1.0983357966978745e-08,
|
| 2832 |
+
"loss": 0.6578,
|
| 2833 |
+
"step": 377
|
| 2834 |
+
},
|
| 2835 |
+
{
|
| 2836 |
+
"epoch": 94.58181818181818,
|
| 2837 |
+
"grad_norm": 3.0193896293640137,
|
| 2838 |
+
"learning_rate": 1.0903388292062667e-08,
|
| 2839 |
+
"loss": 0.6523,
|
| 2840 |
+
"step": 378
|
| 2841 |
+
},
|
| 2842 |
+
{
|
| 2843 |
+
"epoch": 94.87272727272727,
|
| 2844 |
+
"grad_norm": 3.727072238922119,
|
| 2845 |
+
"learning_rate": 1.0826776744855121e-08,
|
| 2846 |
+
"loss": 0.6582,
|
| 2847 |
+
"step": 379
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 95.0,
|
| 2851 |
+
"grad_norm": 3.880216598510742,
|
| 2852 |
+
"learning_rate": 1.0753529159622047e-08,
|
| 2853 |
+
"loss": 0.6047,
|
| 2854 |
+
"step": 380
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 95.2909090909091,
|
| 2858 |
+
"grad_norm": 3.0474436283111572,
|
| 2859 |
+
"learning_rate": 1.068365111445064e-08,
|
| 2860 |
+
"loss": 0.6078,
|
| 2861 |
+
"step": 381
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 95.58181818181818,
|
| 2865 |
+
"grad_norm": 3.09653639793396,
|
| 2866 |
+
"learning_rate": 1.0617147930824585e-08,
|
| 2867 |
+
"loss": 0.6347,
|
| 2868 |
+
"step": 382
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 95.87272727272727,
|
| 2872 |
+
"grad_norm": 3.2464277744293213,
|
| 2873 |
+
"learning_rate": 1.0554024673218806e-08,
|
| 2874 |
+
"loss": 0.6709,
|
| 2875 |
+
"step": 383
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 96.0,
|
| 2879 |
+
"grad_norm": 3.866807699203491,
|
| 2880 |
+
"learning_rate": 1.0494286148713743e-08,
|
| 2881 |
+
"loss": 0.7126,
|
| 2882 |
+
"step": 384
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 96.0,
|
| 2886 |
+
"eval_loss": 0.6363654732704163,
|
| 2887 |
+
"eval_runtime": 0.7605,
|
| 2888 |
+
"eval_samples_per_second": 17.094,
|
| 2889 |
+
"eval_steps_per_second": 17.094,
|
| 2890 |
+
"step": 384
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 96.2909090909091,
|
| 2894 |
+
"grad_norm": 3.1493375301361084,
|
| 2895 |
+
"learning_rate": 1.0437936906629333e-08,
|
| 2896 |
+
"loss": 0.5571,
|
| 2897 |
+
"step": 385
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 96.58181818181818,
|
| 2901 |
+
"grad_norm": 3.1544456481933594,
|
| 2902 |
+
"learning_rate": 1.0384981238178533e-08,
|
| 2903 |
+
"loss": 0.7043,
|
| 2904 |
+
"step": 386
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 96.87272727272727,
|
| 2908 |
+
"grad_norm": 3.5196638107299805,
|
| 2909 |
+
"learning_rate": 1.033542317614051e-08,
|
| 2910 |
+
"loss": 0.6956,
|
| 2911 |
+
"step": 387
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 97.0,
|
| 2915 |
+
"grad_norm": 2.829664707183838,
|
| 2916 |
+
"learning_rate": 1.0289266494553564e-08,
|
| 2917 |
+
"loss": 0.5839,
|
| 2918 |
+
"step": 388
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 97.2909090909091,
|
| 2922 |
+
"grad_norm": 3.240220308303833,
|
| 2923 |
+
"learning_rate": 1.0246514708427701e-08,
|
| 2924 |
+
"loss": 0.629,
|
| 2925 |
+
"step": 389
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 97.58181818181818,
|
| 2929 |
+
"grad_norm": 3.419234275817871,
|
| 2930 |
+
"learning_rate": 1.0207171073476952e-08,
|
| 2931 |
+
"loss": 0.7125,
|
| 2932 |
+
"step": 390
|
| 2933 |
+
},
|
| 2934 |
+
{
|
| 2935 |
+
"epoch": 97.87272727272727,
|
| 2936 |
+
"grad_norm": 3.266242742538452,
|
| 2937 |
+
"learning_rate": 1.017123858587145e-08,
|
| 2938 |
+
"loss": 0.7004,
|
| 2939 |
+
"step": 391
|
| 2940 |
+
},
|
| 2941 |
+
{
|
| 2942 |
+
"epoch": 98.0,
|
| 2943 |
+
"grad_norm": 2.8885867595672607,
|
| 2944 |
+
"learning_rate": 1.0138719982009241e-08,
|
| 2945 |
+
"loss": 0.4986,
|
| 2946 |
+
"step": 392
|
| 2947 |
+
},
|
| 2948 |
+
{
|
| 2949 |
+
"epoch": 98.2909090909091,
|
| 2950 |
+
"grad_norm": 3.4574053287506104,
|
| 2951 |
+
"learning_rate": 1.0109617738307912e-08,
|
| 2952 |
+
"loss": 0.7095,
|
| 2953 |
+
"step": 393
|
| 2954 |
+
},
|
| 2955 |
+
{
|
| 2956 |
+
"epoch": 98.58181818181818,
|
| 2957 |
+
"grad_norm": 3.2674267292022705,
|
| 2958 |
+
"learning_rate": 1.0083934071015988e-08,
|
| 2959 |
+
"loss": 0.5806,
|
| 2960 |
+
"step": 394
|
| 2961 |
+
},
|
| 2962 |
+
{
|
| 2963 |
+
"epoch": 98.87272727272727,
|
| 2964 |
+
"grad_norm": 2.897749423980713,
|
| 2965 |
+
"learning_rate": 1.0061670936044179e-08,
|
| 2966 |
+
"loss": 0.6434,
|
| 2967 |
+
"step": 395
|
| 2968 |
+
},
|
| 2969 |
+
{
|
| 2970 |
+
"epoch": 99.0,
|
| 2971 |
+
"grad_norm": 3.9228150844573975,
|
| 2972 |
+
"learning_rate": 1.0042830028816398e-08,
|
| 2973 |
+
"loss": 0.7094,
|
| 2974 |
+
"step": 396
|
| 2975 |
+
},
|
| 2976 |
+
{
|
| 2977 |
+
"epoch": 99.2909090909091,
|
| 2978 |
+
"grad_norm": 2.946876287460327,
|
| 2979 |
+
"learning_rate": 1.002741278414069e-08,
|
| 2980 |
+
"loss": 0.5678,
|
| 2981 |
+
"step": 397
|
| 2982 |
+
},
|
| 2983 |
+
{
|
| 2984 |
+
"epoch": 99.58181818181818,
|
| 2985 |
+
"grad_norm": 2.9825222492218018,
|
| 2986 |
+
"learning_rate": 1.0015420376099922e-08,
|
| 2987 |
+
"loss": 0.6347,
|
| 2988 |
+
"step": 398
|
| 2989 |
+
},
|
| 2990 |
+
{
|
| 2991 |
+
"epoch": 99.87272727272727,
|
| 2992 |
+
"grad_norm": 3.46803879737854,
|
| 2993 |
+
"learning_rate": 1.0006853717962394e-08,
|
| 2994 |
+
"loss": 0.7428,
|
| 2995 |
+
"step": 399
|
| 2996 |
+
},
|
| 2997 |
+
{
|
| 2998 |
+
"epoch": 100.0,
|
| 2999 |
+
"grad_norm": 4.149415969848633,
|
| 3000 |
+
"learning_rate": 1.0001713462112291e-08,
|
| 3001 |
+
"loss": 0.6465,
|
| 3002 |
+
"step": 400
|
| 3003 |
+
},
|
| 3004 |
+
{
|
| 3005 |
+
"epoch": 100.0,
|
| 3006 |
+
"eval_loss": 0.6363555192947388,
|
| 3007 |
+
"eval_runtime": 0.7511,
|
| 3008 |
+
"eval_samples_per_second": 17.308,
|
| 3009 |
+
"eval_steps_per_second": 17.308,
|
| 3010 |
+
"step": 400
|
| 3011 |
+
},
|
| 3012 |
+
{
|
| 3013 |
+
"epoch": 100.0,
|
| 3014 |
+
"step": 400,
|
| 3015 |
+
"total_flos": 1.34153286008832e+17,
|
| 3016 |
+
"train_loss": 0.7119150696694851,
|
| 3017 |
+
"train_runtime": 2950.0217,
|
| 3018 |
+
"train_samples_per_second": 3.729,
|
| 3019 |
+
"train_steps_per_second": 0.136
|
| 3020 |
}
|
| 3021 |
],
|
| 3022 |
"logging_steps": 1,
|
| 3023 |
+
"max_steps": 400,
|
| 3024 |
"num_input_tokens_seen": 0,
|
| 3025 |
+
"num_train_epochs": 100,
|
| 3026 |
"save_steps": 16,
|
| 3027 |
"stateful_callbacks": {
|
| 3028 |
"TrainerControl": {
|
|
|
|
| 3036 |
"attributes": {}
|
| 3037 |
}
|
| 3038 |
},
|
| 3039 |
+
"total_flos": 1.34153286008832e+17,
|
| 3040 |
"train_batch_size": 1,
|
| 3041 |
"trial_name": null,
|
| 3042 |
"trial_params": null
|
training_eval_loss.png
ADDED
|
training_loss.png
CHANGED
|
|