End of training
Browse files- README.md +2 -2
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +374 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# question_generation_model
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 18 |
|
| 19 |
# question_generation_model
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the questions_finetune_train dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.5050
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.5049812197685242,
|
| 4 |
+
"eval_runtime": 45.2794,
|
| 5 |
+
"eval_samples_per_second": 0.375,
|
| 6 |
+
"eval_steps_per_second": 0.375,
|
| 7 |
+
"total_flos": 7437909605990400.0,
|
| 8 |
+
"train_loss": 0.471399851375156,
|
| 9 |
+
"train_runtime": 7246.2151,
|
| 10 |
+
"train_samples_per_second": 0.124,
|
| 11 |
+
"train_steps_per_second": 0.031
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.5049812197685242,
|
| 4 |
+
"eval_runtime": 45.2794,
|
| 5 |
+
"eval_samples_per_second": 0.375,
|
| 6 |
+
"eval_steps_per_second": 0.375
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 7437909605990400.0,
|
| 4 |
+
"train_loss": 0.471399851375156,
|
| 5 |
+
"train_runtime": 7246.2151,
|
| 6 |
+
"train_samples_per_second": 0.124,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,374 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 225,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.06666666666666667,
|
| 14 |
+
"grad_norm": 0.16145890951156616,
|
| 15 |
+
"learning_rate": 8.695652173913044e-05,
|
| 16 |
+
"loss": 0.5835,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.13333333333333333,
|
| 21 |
+
"grad_norm": 0.16309808194637299,
|
| 22 |
+
"learning_rate": 0.0001956521739130435,
|
| 23 |
+
"loss": 0.6482,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.2,
|
| 28 |
+
"grad_norm": 0.13111482560634613,
|
| 29 |
+
"learning_rate": 0.00030434782608695655,
|
| 30 |
+
"loss": 0.566,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.26666666666666666,
|
| 35 |
+
"grad_norm": 0.10666251927614212,
|
| 36 |
+
"learning_rate": 0.0004130434782608696,
|
| 37 |
+
"loss": 0.5803,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3333333333333333,
|
| 42 |
+
"grad_norm": 0.12014622241258621,
|
| 43 |
+
"learning_rate": 0.0004999697658150374,
|
| 44 |
+
"loss": 0.5898,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.4,
|
| 49 |
+
"grad_norm": 0.10439501702785492,
|
| 50 |
+
"learning_rate": 0.0004989123369922546,
|
| 51 |
+
"loss": 0.5948,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4666666666666667,
|
| 56 |
+
"grad_norm": 0.09919652342796326,
|
| 57 |
+
"learning_rate": 0.0004963505038221703,
|
| 58 |
+
"loss": 0.5853,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5333333333333333,
|
| 63 |
+
"grad_norm": 0.08807212114334106,
|
| 64 |
+
"learning_rate": 0.0004922997497999166,
|
| 65 |
+
"loss": 0.5324,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6,
|
| 70 |
+
"grad_norm": 0.1061202809214592,
|
| 71 |
+
"learning_rate": 0.00048678455732775007,
|
| 72 |
+
"loss": 0.554,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.6666666666666666,
|
| 77 |
+
"grad_norm": 0.10958874970674515,
|
| 78 |
+
"learning_rate": 0.00047983825974555906,
|
| 79 |
+
"loss": 0.6044,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.7333333333333333,
|
| 84 |
+
"grad_norm": 0.09531711041927338,
|
| 85 |
+
"learning_rate": 0.0004715028398670787,
|
| 86 |
+
"loss": 0.5653,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8,
|
| 91 |
+
"grad_norm": 0.11301957815885544,
|
| 92 |
+
"learning_rate": 0.00046182867623944434,
|
| 93 |
+
"loss": 0.5539,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.8666666666666667,
|
| 98 |
+
"grad_norm": 0.1083487942814827,
|
| 99 |
+
"learning_rate": 0.00045087423865966894,
|
| 100 |
+
"loss": 0.5267,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.9333333333333333,
|
| 105 |
+
"grad_norm": 0.10189539939165115,
|
| 106 |
+
"learning_rate": 0.0004387057347883143,
|
| 107 |
+
"loss": 0.5533,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.0,
|
| 112 |
+
"grad_norm": 0.09216652810573578,
|
| 113 |
+
"learning_rate": 0.0004253967099961942,
|
| 114 |
+
"loss": 0.5016,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.0666666666666667,
|
| 119 |
+
"grad_norm": 0.10134831815958023,
|
| 120 |
+
"learning_rate": 0.0004110276028625994,
|
| 121 |
+
"loss": 0.4856,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.1333333333333333,
|
| 126 |
+
"grad_norm": 0.1001599058508873,
|
| 127 |
+
"learning_rate": 0.00039568525901157527,
|
| 128 |
+
"loss": 0.4632,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.2,
|
| 133 |
+
"grad_norm": 0.09839078038930893,
|
| 134 |
+
"learning_rate": 0.0003794624062245813,
|
| 135 |
+
"loss": 0.5097,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.2666666666666666,
|
| 140 |
+
"grad_norm": 0.102094367146492,
|
| 141 |
+
"learning_rate": 0.000362457094001909,
|
| 142 |
+
"loss": 0.4476,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.3333333333333333,
|
| 147 |
+
"grad_norm": 0.11247370392084122,
|
| 148 |
+
"learning_rate": 0.00034477210096009486,
|
| 149 |
+
"loss": 0.4919,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.3333333333333333,
|
| 154 |
+
"eval_loss": 0.506523609161377,
|
| 155 |
+
"eval_runtime": 45.0985,
|
| 156 |
+
"eval_samples_per_second": 0.377,
|
| 157 |
+
"eval_steps_per_second": 0.377,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.4,
|
| 162 |
+
"grad_norm": 0.10984684526920319,
|
| 163 |
+
"learning_rate": 0.00032651431364697186,
|
| 164 |
+
"loss": 0.3816,
|
| 165 |
+
"step": 105
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.4666666666666668,
|
| 169 |
+
"grad_norm": 0.10393229871988297,
|
| 170 |
+
"learning_rate": 0.0003077940805287425,
|
| 171 |
+
"loss": 0.4784,
|
| 172 |
+
"step": 110
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.5333333333333332,
|
| 176 |
+
"grad_norm": 0.11296918988227844,
|
| 177 |
+
"learning_rate": 0.00028872454505352117,
|
| 178 |
+
"loss": 0.4422,
|
| 179 |
+
"step": 115
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.6,
|
| 183 |
+
"grad_norm": 0.10333701968193054,
|
| 184 |
+
"learning_rate": 0.0002694209618222516,
|
| 185 |
+
"loss": 0.4828,
|
| 186 |
+
"step": 120
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.6666666666666665,
|
| 190 |
+
"grad_norm": 0.09766612201929092,
|
| 191 |
+
"learning_rate": 0.00025,
|
| 192 |
+
"loss": 0.4853,
|
| 193 |
+
"step": 125
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.7333333333333334,
|
| 197 |
+
"grad_norm": 0.09704718738794327,
|
| 198 |
+
"learning_rate": 0.00023057903817774841,
|
| 199 |
+
"loss": 0.4392,
|
| 200 |
+
"step": 130
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.8,
|
| 204 |
+
"grad_norm": 0.11206477135419846,
|
| 205 |
+
"learning_rate": 0.00021127545494647882,
|
| 206 |
+
"loss": 0.4489,
|
| 207 |
+
"step": 135
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.8666666666666667,
|
| 211 |
+
"grad_norm": 0.11189498007297516,
|
| 212 |
+
"learning_rate": 0.00019220591947125766,
|
| 213 |
+
"loss": 0.4856,
|
| 214 |
+
"step": 140
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.9333333333333333,
|
| 218 |
+
"grad_norm": 0.1053239181637764,
|
| 219 |
+
"learning_rate": 0.0001734856863530282,
|
| 220 |
+
"loss": 0.4406,
|
| 221 |
+
"step": 145
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.0,
|
| 225 |
+
"grad_norm": 0.10603803396224976,
|
| 226 |
+
"learning_rate": 0.0001552278990399052,
|
| 227 |
+
"loss": 0.4405,
|
| 228 |
+
"step": 150
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.066666666666667,
|
| 232 |
+
"grad_norm": 0.1078822985291481,
|
| 233 |
+
"learning_rate": 0.00013754290599809105,
|
| 234 |
+
"loss": 0.3784,
|
| 235 |
+
"step": 155
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.1333333333333333,
|
| 239 |
+
"grad_norm": 0.09372378885746002,
|
| 240 |
+
"learning_rate": 0.00012053759377541865,
|
| 241 |
+
"loss": 0.4102,
|
| 242 |
+
"step": 160
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.2,
|
| 246 |
+
"grad_norm": 0.11487775295972824,
|
| 247 |
+
"learning_rate": 0.00010431474098842477,
|
| 248 |
+
"loss": 0.3926,
|
| 249 |
+
"step": 165
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.2666666666666666,
|
| 253 |
+
"grad_norm": 0.110216423869133,
|
| 254 |
+
"learning_rate": 8.897239713740058e-05,
|
| 255 |
+
"loss": 0.4028,
|
| 256 |
+
"step": 170
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.3333333333333335,
|
| 260 |
+
"grad_norm": 0.12020918726921082,
|
| 261 |
+
"learning_rate": 7.460329000380586e-05,
|
| 262 |
+
"loss": 0.4216,
|
| 263 |
+
"step": 175
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.4,
|
| 267 |
+
"grad_norm": 0.11179473251104355,
|
| 268 |
+
"learning_rate": 6.12942652116858e-05,
|
| 269 |
+
"loss": 0.4194,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.466666666666667,
|
| 274 |
+
"grad_norm": 0.1162172257900238,
|
| 275 |
+
"learning_rate": 4.912576134033106e-05,
|
| 276 |
+
"loss": 0.3448,
|
| 277 |
+
"step": 185
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.533333333333333,
|
| 281 |
+
"grad_norm": 0.12591737508773804,
|
| 282 |
+
"learning_rate": 3.8171323760555655e-05,
|
| 283 |
+
"loss": 0.3779,
|
| 284 |
+
"step": 190
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.6,
|
| 288 |
+
"grad_norm": 0.12023098766803741,
|
| 289 |
+
"learning_rate": 2.8497160132921336e-05,
|
| 290 |
+
"loss": 0.3846,
|
| 291 |
+
"step": 195
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.6666666666666665,
|
| 295 |
+
"grad_norm": 0.12184033542871475,
|
| 296 |
+
"learning_rate": 2.0161740254440898e-05,
|
| 297 |
+
"loss": 0.3998,
|
| 298 |
+
"step": 200
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.6666666666666665,
|
| 302 |
+
"eval_loss": 0.5051587224006653,
|
| 303 |
+
"eval_runtime": 45.0327,
|
| 304 |
+
"eval_samples_per_second": 0.378,
|
| 305 |
+
"eval_steps_per_second": 0.378,
|
| 306 |
+
"step": 200
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.7333333333333334,
|
| 310 |
+
"grad_norm": 0.13668841123580933,
|
| 311 |
+
"learning_rate": 1.3215442672249972e-05,
|
| 312 |
+
"loss": 0.4098,
|
| 313 |
+
"step": 205
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.8,
|
| 317 |
+
"grad_norm": 0.11291203647851944,
|
| 318 |
+
"learning_rate": 7.70025020008347e-06,
|
| 319 |
+
"loss": 0.3316,
|
| 320 |
+
"step": 210
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.8666666666666667,
|
| 324 |
+
"grad_norm": 0.1049598902463913,
|
| 325 |
+
"learning_rate": 3.64949617782967e-06,
|
| 326 |
+
"loss": 0.3406,
|
| 327 |
+
"step": 215
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.9333333333333336,
|
| 331 |
+
"grad_norm": 0.10330229252576828,
|
| 332 |
+
"learning_rate": 1.0876630077453487e-06,
|
| 333 |
+
"loss": 0.3846,
|
| 334 |
+
"step": 220
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 3.0,
|
| 338 |
+
"grad_norm": 0.11973880231380463,
|
| 339 |
+
"learning_rate": 3.023418496261865e-08,
|
| 340 |
+
"loss": 0.3517,
|
| 341 |
+
"step": 225
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.0,
|
| 345 |
+
"step": 225,
|
| 346 |
+
"total_flos": 7437909605990400.0,
|
| 347 |
+
"train_loss": 0.471399851375156,
|
| 348 |
+
"train_runtime": 7246.2151,
|
| 349 |
+
"train_samples_per_second": 0.124,
|
| 350 |
+
"train_steps_per_second": 0.031
|
| 351 |
+
}
|
| 352 |
+
],
|
| 353 |
+
"logging_steps": 5,
|
| 354 |
+
"max_steps": 225,
|
| 355 |
+
"num_input_tokens_seen": 0,
|
| 356 |
+
"num_train_epochs": 3,
|
| 357 |
+
"save_steps": 40,
|
| 358 |
+
"stateful_callbacks": {
|
| 359 |
+
"TrainerControl": {
|
| 360 |
+
"args": {
|
| 361 |
+
"should_epoch_stop": false,
|
| 362 |
+
"should_evaluate": false,
|
| 363 |
+
"should_log": false,
|
| 364 |
+
"should_save": true,
|
| 365 |
+
"should_training_stop": true
|
| 366 |
+
},
|
| 367 |
+
"attributes": {}
|
| 368 |
+
}
|
| 369 |
+
},
|
| 370 |
+
"total_flos": 7437909605990400.0,
|
| 371 |
+
"train_batch_size": 1,
|
| 372 |
+
"trial_name": null,
|
| 373 |
+
"trial_params": null
|
| 374 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|