Training in progress, epoch 0
Browse files- all_results.json +8 -0
- model.safetensors +1 -1
- runs/Jul09_08-01-59_5c5ab1345193/events.out.tfevents.1720512129.5c5ab1345193.34.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +288 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 2.427840666897408e+17,
|
| 4 |
+
"train_loss": 0.08263867741210561,
|
| 5 |
+
"train_runtime": 466.1075,
|
| 6 |
+
"train_samples_per_second": 6.597,
|
| 7 |
+
"train_steps_per_second": 0.107
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 349854120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:651f9126da7fd4ed3d7d5f529f62bd2b3f27f176f9b2abc316f6ef8c408751b8
|
| 3 |
size 349854120
|
runs/Jul09_08-01-59_5c5ab1345193/events.out.tfevents.1720512129.5c5ab1345193.34.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:faec50ea3533814d1d2c34db46ec817c4d5a35b284556ba38faced59981fe21e
|
| 3 |
+
size 5037
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 25.0,
|
| 3 |
+
"total_flos": 2.427840666897408e+17,
|
| 4 |
+
"train_loss": 0.08263867741210561,
|
| 5 |
+
"train_runtime": 466.1075,
|
| 6 |
+
"train_samples_per_second": 6.597,
|
| 7 |
+
"train_steps_per_second": 0.107
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9010989010989011,
|
| 3 |
+
"best_model_checkpoint": "ktp-kk-crop/checkpoint-10",
|
| 4 |
+
"epoch": 25.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6153846153846154,
|
| 14 |
+
"eval_loss": 0.6706601977348328,
|
| 15 |
+
"eval_runtime": 4.349,
|
| 16 |
+
"eval_samples_per_second": 20.924,
|
| 17 |
+
"eval_steps_per_second": 1.38,
|
| 18 |
+
"step": 2
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.6153846153846154,
|
| 23 |
+
"eval_loss": 0.6923023462295532,
|
| 24 |
+
"eval_runtime": 3.6322,
|
| 25 |
+
"eval_samples_per_second": 25.053,
|
| 26 |
+
"eval_steps_per_second": 1.652,
|
| 27 |
+
"step": 4
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.0,
|
| 31 |
+
"eval_accuracy": 0.7032967032967034,
|
| 32 |
+
"eval_loss": 0.7208701372146606,
|
| 33 |
+
"eval_runtime": 3.5659,
|
| 34 |
+
"eval_samples_per_second": 25.52,
|
| 35 |
+
"eval_steps_per_second": 1.683,
|
| 36 |
+
"step": 6
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 4.0,
|
| 40 |
+
"eval_accuracy": 0.8021978021978022,
|
| 41 |
+
"eval_loss": 0.4788942337036133,
|
| 42 |
+
"eval_runtime": 3.617,
|
| 43 |
+
"eval_samples_per_second": 25.159,
|
| 44 |
+
"eval_steps_per_second": 1.659,
|
| 45 |
+
"step": 8
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.0,
|
| 49 |
+
"eval_accuracy": 0.9010989010989011,
|
| 50 |
+
"eval_loss": 0.3554236590862274,
|
| 51 |
+
"eval_runtime": 3.6003,
|
| 52 |
+
"eval_samples_per_second": 25.275,
|
| 53 |
+
"eval_steps_per_second": 1.667,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.0,
|
| 58 |
+
"eval_accuracy": 0.8241758241758241,
|
| 59 |
+
"eval_loss": 0.8337829113006592,
|
| 60 |
+
"eval_runtime": 3.6007,
|
| 61 |
+
"eval_samples_per_second": 25.273,
|
| 62 |
+
"eval_steps_per_second": 1.666,
|
| 63 |
+
"step": 12
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.0,
|
| 67 |
+
"eval_accuracy": 0.7912087912087912,
|
| 68 |
+
"eval_loss": 1.073412537574768,
|
| 69 |
+
"eval_runtime": 3.6715,
|
| 70 |
+
"eval_samples_per_second": 24.786,
|
| 71 |
+
"eval_steps_per_second": 1.634,
|
| 72 |
+
"step": 14
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 7.5,
|
| 76 |
+
"grad_norm": 38.24232864379883,
|
| 77 |
+
"learning_rate": 3.888888888888889e-05,
|
| 78 |
+
"loss": 0.2476,
|
| 79 |
+
"step": 15
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 8.0,
|
| 83 |
+
"eval_accuracy": 0.8241758241758241,
|
| 84 |
+
"eval_loss": 1.0161423683166504,
|
| 85 |
+
"eval_runtime": 3.6667,
|
| 86 |
+
"eval_samples_per_second": 24.818,
|
| 87 |
+
"eval_steps_per_second": 1.636,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 9.0,
|
| 92 |
+
"eval_accuracy": 0.8571428571428571,
|
| 93 |
+
"eval_loss": 0.8966610431671143,
|
| 94 |
+
"eval_runtime": 3.6608,
|
| 95 |
+
"eval_samples_per_second": 24.858,
|
| 96 |
+
"eval_steps_per_second": 1.639,
|
| 97 |
+
"step": 18
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 10.0,
|
| 101 |
+
"eval_accuracy": 0.8681318681318682,
|
| 102 |
+
"eval_loss": 0.8477412462234497,
|
| 103 |
+
"eval_runtime": 3.4998,
|
| 104 |
+
"eval_samples_per_second": 26.001,
|
| 105 |
+
"eval_steps_per_second": 1.714,
|
| 106 |
+
"step": 20
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 11.0,
|
| 110 |
+
"eval_accuracy": 0.8351648351648352,
|
| 111 |
+
"eval_loss": 1.3332176208496094,
|
| 112 |
+
"eval_runtime": 3.6008,
|
| 113 |
+
"eval_samples_per_second": 25.272,
|
| 114 |
+
"eval_steps_per_second": 1.666,
|
| 115 |
+
"step": 22
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 12.0,
|
| 119 |
+
"eval_accuracy": 0.7252747252747253,
|
| 120 |
+
"eval_loss": 3.477609395980835,
|
| 121 |
+
"eval_runtime": 3.6298,
|
| 122 |
+
"eval_samples_per_second": 25.071,
|
| 123 |
+
"eval_steps_per_second": 1.653,
|
| 124 |
+
"step": 24
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 13.0,
|
| 128 |
+
"eval_accuracy": 0.6373626373626373,
|
| 129 |
+
"eval_loss": 6.0097527503967285,
|
| 130 |
+
"eval_runtime": 3.6304,
|
| 131 |
+
"eval_samples_per_second": 25.066,
|
| 132 |
+
"eval_steps_per_second": 1.653,
|
| 133 |
+
"step": 26
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 14.0,
|
| 137 |
+
"eval_accuracy": 0.7252747252747253,
|
| 138 |
+
"eval_loss": 3.8649513721466064,
|
| 139 |
+
"eval_runtime": 3.5214,
|
| 140 |
+
"eval_samples_per_second": 25.842,
|
| 141 |
+
"eval_steps_per_second": 1.704,
|
| 142 |
+
"step": 28
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 15.0,
|
| 146 |
+
"grad_norm": 0.0022278681863099337,
|
| 147 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 148 |
+
"loss": 0.0277,
|
| 149 |
+
"step": 30
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 15.0,
|
| 153 |
+
"eval_accuracy": 0.8131868131868132,
|
| 154 |
+
"eval_loss": 2.2409703731536865,
|
| 155 |
+
"eval_runtime": 3.6708,
|
| 156 |
+
"eval_samples_per_second": 24.79,
|
| 157 |
+
"eval_steps_per_second": 1.635,
|
| 158 |
+
"step": 30
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 16.0,
|
| 162 |
+
"eval_accuracy": 0.8131868131868132,
|
| 163 |
+
"eval_loss": 1.45852792263031,
|
| 164 |
+
"eval_runtime": 3.7348,
|
| 165 |
+
"eval_samples_per_second": 24.365,
|
| 166 |
+
"eval_steps_per_second": 1.607,
|
| 167 |
+
"step": 32
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 17.0,
|
| 171 |
+
"eval_accuracy": 0.8021978021978022,
|
| 172 |
+
"eval_loss": 1.4789769649505615,
|
| 173 |
+
"eval_runtime": 3.7258,
|
| 174 |
+
"eval_samples_per_second": 24.424,
|
| 175 |
+
"eval_steps_per_second": 1.61,
|
| 176 |
+
"step": 34
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 18.0,
|
| 180 |
+
"eval_accuracy": 0.8241758241758241,
|
| 181 |
+
"eval_loss": 1.8427152633666992,
|
| 182 |
+
"eval_runtime": 3.6118,
|
| 183 |
+
"eval_samples_per_second": 25.195,
|
| 184 |
+
"eval_steps_per_second": 1.661,
|
| 185 |
+
"step": 36
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 19.0,
|
| 189 |
+
"eval_accuracy": 0.8241758241758241,
|
| 190 |
+
"eval_loss": 2.0873501300811768,
|
| 191 |
+
"eval_runtime": 3.6114,
|
| 192 |
+
"eval_samples_per_second": 25.198,
|
| 193 |
+
"eval_steps_per_second": 1.661,
|
| 194 |
+
"step": 38
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.0,
|
| 198 |
+
"eval_accuracy": 0.8131868131868132,
|
| 199 |
+
"eval_loss": 2.245572090148926,
|
| 200 |
+
"eval_runtime": 3.651,
|
| 201 |
+
"eval_samples_per_second": 24.924,
|
| 202 |
+
"eval_steps_per_second": 1.643,
|
| 203 |
+
"step": 40
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 21.0,
|
| 207 |
+
"eval_accuracy": 0.8021978021978022,
|
| 208 |
+
"eval_loss": 2.366342782974243,
|
| 209 |
+
"eval_runtime": 3.6311,
|
| 210 |
+
"eval_samples_per_second": 25.061,
|
| 211 |
+
"eval_steps_per_second": 1.652,
|
| 212 |
+
"step": 42
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 22.0,
|
| 216 |
+
"eval_accuracy": 0.8021978021978022,
|
| 217 |
+
"eval_loss": 2.4484336376190186,
|
| 218 |
+
"eval_runtime": 3.6882,
|
| 219 |
+
"eval_samples_per_second": 24.673,
|
| 220 |
+
"eval_steps_per_second": 1.627,
|
| 221 |
+
"step": 44
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 22.5,
|
| 225 |
+
"grad_norm": 0.0005057471571490169,
|
| 226 |
+
"learning_rate": 5.555555555555556e-06,
|
| 227 |
+
"loss": 0.0001,
|
| 228 |
+
"step": 45
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 23.0,
|
| 232 |
+
"eval_accuracy": 0.8021978021978022,
|
| 233 |
+
"eval_loss": 2.4973790645599365,
|
| 234 |
+
"eval_runtime": 3.6432,
|
| 235 |
+
"eval_samples_per_second": 24.978,
|
| 236 |
+
"eval_steps_per_second": 1.647,
|
| 237 |
+
"step": 46
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 24.0,
|
| 241 |
+
"eval_accuracy": 0.8021978021978022,
|
| 242 |
+
"eval_loss": 2.5220789909362793,
|
| 243 |
+
"eval_runtime": 3.6924,
|
| 244 |
+
"eval_samples_per_second": 24.645,
|
| 245 |
+
"eval_steps_per_second": 1.625,
|
| 246 |
+
"step": 48
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 25.0,
|
| 250 |
+
"eval_accuracy": 0.8021978021978022,
|
| 251 |
+
"eval_loss": 2.530649185180664,
|
| 252 |
+
"eval_runtime": 3.7584,
|
| 253 |
+
"eval_samples_per_second": 24.212,
|
| 254 |
+
"eval_steps_per_second": 1.596,
|
| 255 |
+
"step": 50
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 25.0,
|
| 259 |
+
"step": 50,
|
| 260 |
+
"total_flos": 2.427840666897408e+17,
|
| 261 |
+
"train_loss": 0.08263867741210561,
|
| 262 |
+
"train_runtime": 466.1075,
|
| 263 |
+
"train_samples_per_second": 6.597,
|
| 264 |
+
"train_steps_per_second": 0.107
|
| 265 |
+
}
|
| 266 |
+
],
|
| 267 |
+
"logging_steps": 15,
|
| 268 |
+
"max_steps": 50,
|
| 269 |
+
"num_input_tokens_seen": 0,
|
| 270 |
+
"num_train_epochs": 25,
|
| 271 |
+
"save_steps": 500,
|
| 272 |
+
"stateful_callbacks": {
|
| 273 |
+
"TrainerControl": {
|
| 274 |
+
"args": {
|
| 275 |
+
"should_epoch_stop": false,
|
| 276 |
+
"should_evaluate": false,
|
| 277 |
+
"should_log": false,
|
| 278 |
+
"should_save": true,
|
| 279 |
+
"should_training_stop": true
|
| 280 |
+
},
|
| 281 |
+
"attributes": {}
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
+
"total_flos": 2.427840666897408e+17,
|
| 285 |
+
"train_batch_size": 16,
|
| 286 |
+
"trial_name": null,
|
| 287 |
+
"trial_params": null
|
| 288 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d572861d8129f250c09a3ab035f94a52aa443e764dd9e02338244d7d2b1f3e3a
|
| 3 |
size 5112
|