End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 16.04,
|
| 3 |
+
"eval_loss": 0.38816705346107483,
|
| 4 |
+
"eval_runtime": 129.5693,
|
| 5 |
+
"eval_samples_per_second": 2.115,
|
| 6 |
+
"eval_steps_per_second": 0.139,
|
| 7 |
+
"eval_wer": 6.624661667480143,
|
| 8 |
+
"train_loss": 0.5347552497046334,
|
| 9 |
+
"train_runtime": 7389.0047,
|
| 10 |
+
"train_samples_per_second": 1.516,
|
| 11 |
+
"train_steps_per_second": 0.047
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 16.04,
|
| 3 |
+
"eval_loss": 0.38816705346107483,
|
| 4 |
+
"eval_runtime": 129.5693,
|
| 5 |
+
"eval_samples_per_second": 2.115,
|
| 6 |
+
"eval_steps_per_second": 0.139,
|
| 7 |
+
"eval_wer": 6.624661667480143
|
| 8 |
+
}
|
runs/Feb21_23-27-40_f445b5317dd4/events.out.tfevents.1677029835.f445b5317dd4.1.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0273aa3c7ecbe316f28224d8e06ef38395f51b4261826c8c91bead79d14ef39
|
| 3 |
+
size 406
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 16.04,
|
| 3 |
+
"train_loss": 0.5347552497046334,
|
| 4 |
+
"train_runtime": 7389.0047,
|
| 5 |
+
"train_samples_per_second": 1.516,
|
| 6 |
+
"train_steps_per_second": 0.047
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 6.624661667480143,
|
| 3 |
+
"best_model_checkpoint": "whisper-stakwork-crypto/checkpoint-275",
|
| 4 |
+
"epoch": 16.04,
|
| 5 |
+
"global_step": 350,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 8e-09,
|
| 13 |
+
"loss": 0.8207,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 2.1333333333333332e-08,
|
| 19 |
+
"loss": 0.8163,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.01,
|
| 24 |
+
"eval_loss": 0.8355672955513,
|
| 25 |
+
"eval_runtime": 119.9965,
|
| 26 |
+
"eval_samples_per_second": 2.283,
|
| 27 |
+
"eval_steps_per_second": 0.15,
|
| 28 |
+
"eval_wer": 10.063451213559924,
|
| 29 |
+
"step": 25
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.03,
|
| 33 |
+
"learning_rate": 3.4666666666666666e-08,
|
| 34 |
+
"loss": 0.8041,
|
| 35 |
+
"step": 30
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 1.05,
|
| 39 |
+
"learning_rate": 4.799999999999999e-08,
|
| 40 |
+
"loss": 0.8138,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.02,
|
| 45 |
+
"learning_rate": 6.133333333333333e-08,
|
| 46 |
+
"loss": 0.7916,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.02,
|
| 51 |
+
"eval_loss": 0.8102102875709534,
|
| 52 |
+
"eval_runtime": 128.996,
|
| 53 |
+
"eval_samples_per_second": 2.124,
|
| 54 |
+
"eval_steps_per_second": 0.14,
|
| 55 |
+
"eval_wer": 9.735102276256823,
|
| 56 |
+
"step": 50
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.05,
|
| 60 |
+
"learning_rate": 7.466666666666666e-08,
|
| 61 |
+
"loss": 0.7937,
|
| 62 |
+
"step": 60
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 3.02,
|
| 66 |
+
"learning_rate": 8.8e-08,
|
| 67 |
+
"loss": 0.7563,
|
| 68 |
+
"step": 70
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.03,
|
| 72 |
+
"eval_loss": 0.7621258497238159,
|
| 73 |
+
"eval_runtime": 118.1768,
|
| 74 |
+
"eval_samples_per_second": 2.319,
|
| 75 |
+
"eval_steps_per_second": 0.152,
|
| 76 |
+
"eval_wer": 9.508807738385766,
|
| 77 |
+
"step": 75
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 3.05,
|
| 81 |
+
"learning_rate": 1.0133333333333334e-07,
|
| 82 |
+
"loss": 0.7477,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.02,
|
| 87 |
+
"learning_rate": 1.1466666666666666e-07,
|
| 88 |
+
"loss": 0.7275,
|
| 89 |
+
"step": 90
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 4.05,
|
| 93 |
+
"learning_rate": 1.28e-07,
|
| 94 |
+
"loss": 0.7154,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 4.05,
|
| 99 |
+
"eval_loss": 0.7107397317886353,
|
| 100 |
+
"eval_runtime": 132.2935,
|
| 101 |
+
"eval_samples_per_second": 2.071,
|
| 102 |
+
"eval_steps_per_second": 0.136,
|
| 103 |
+
"eval_wer": 9.233704574699383,
|
| 104 |
+
"step": 100
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 5.01,
|
| 108 |
+
"learning_rate": 1.4133333333333333e-07,
|
| 109 |
+
"loss": 0.6774,
|
| 110 |
+
"step": 110
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.04,
|
| 114 |
+
"learning_rate": 1.5466666666666665e-07,
|
| 115 |
+
"loss": 0.6548,
|
| 116 |
+
"step": 120
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 5.06,
|
| 120 |
+
"eval_loss": 0.6588723659515381,
|
| 121 |
+
"eval_runtime": 118.5646,
|
| 122 |
+
"eval_samples_per_second": 2.311,
|
| 123 |
+
"eval_steps_per_second": 0.152,
|
| 124 |
+
"eval_wer": 9.38013045214536,
|
| 125 |
+
"step": 125
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 6.01,
|
| 129 |
+
"learning_rate": 1.68e-07,
|
| 130 |
+
"loss": 0.6362,
|
| 131 |
+
"step": 130
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 6.04,
|
| 135 |
+
"learning_rate": 1.8133333333333332e-07,
|
| 136 |
+
"loss": 0.6105,
|
| 137 |
+
"step": 140
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 7.01,
|
| 141 |
+
"learning_rate": 1.9466666666666666e-07,
|
| 142 |
+
"loss": 0.6017,
|
| 143 |
+
"step": 150
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 7.01,
|
| 147 |
+
"eval_loss": 0.6061531901359558,
|
| 148 |
+
"eval_runtime": 125.9398,
|
| 149 |
+
"eval_samples_per_second": 2.176,
|
| 150 |
+
"eval_steps_per_second": 0.143,
|
| 151 |
+
"eval_wer": 9.007410036828327,
|
| 152 |
+
"step": 150
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 7.04,
|
| 156 |
+
"learning_rate": 2.08e-07,
|
| 157 |
+
"loss": 0.5569,
|
| 158 |
+
"step": 160
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 8.01,
|
| 162 |
+
"learning_rate": 2.2133333333333333e-07,
|
| 163 |
+
"loss": 0.5333,
|
| 164 |
+
"step": 170
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.02,
|
| 168 |
+
"eval_loss": 0.5347172617912292,
|
| 169 |
+
"eval_runtime": 129.1421,
|
| 170 |
+
"eval_samples_per_second": 2.122,
|
| 171 |
+
"eval_steps_per_second": 0.139,
|
| 172 |
+
"eval_wer": 8.621378178107113,
|
| 173 |
+
"step": 175
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 8.03,
|
| 177 |
+
"learning_rate": 2.3466666666666665e-07,
|
| 178 |
+
"loss": 0.4959,
|
| 179 |
+
"step": 180
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.0,
|
| 183 |
+
"learning_rate": 2.48e-07,
|
| 184 |
+
"loss": 0.4715,
|
| 185 |
+
"step": 190
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 9.03,
|
| 189 |
+
"learning_rate": 2.613333333333333e-07,
|
| 190 |
+
"loss": 0.4493,
|
| 191 |
+
"step": 200
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 9.03,
|
| 195 |
+
"eval_loss": 0.47380271553993225,
|
| 196 |
+
"eval_runtime": 131.2715,
|
| 197 |
+
"eval_samples_per_second": 2.087,
|
| 198 |
+
"eval_steps_per_second": 0.137,
|
| 199 |
+
"eval_wer": 8.284154945201225,
|
| 200 |
+
"step": 200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 9.06,
|
| 204 |
+
"learning_rate": 2.7466666666666664e-07,
|
| 205 |
+
"loss": 0.4248,
|
| 206 |
+
"step": 210
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 10.03,
|
| 210 |
+
"learning_rate": 2.88e-07,
|
| 211 |
+
"loss": 0.4016,
|
| 212 |
+
"step": 220
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 10.04,
|
| 216 |
+
"eval_loss": 0.43325528502464294,
|
| 217 |
+
"eval_runtime": 126.954,
|
| 218 |
+
"eval_samples_per_second": 2.158,
|
| 219 |
+
"eval_steps_per_second": 0.142,
|
| 220 |
+
"eval_wer": 7.117185073434797,
|
| 221 |
+
"step": 225
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 10.06,
|
| 225 |
+
"learning_rate": 3.0133333333333333e-07,
|
| 226 |
+
"loss": 0.4003,
|
| 227 |
+
"step": 230
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 11.03,
|
| 231 |
+
"learning_rate": 3.146666666666666e-07,
|
| 232 |
+
"loss": 0.374,
|
| 233 |
+
"step": 240
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 11.05,
|
| 237 |
+
"learning_rate": 3.2799999999999997e-07,
|
| 238 |
+
"loss": 0.3738,
|
| 239 |
+
"step": 250
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 11.05,
|
| 243 |
+
"eval_loss": 0.40573614835739136,
|
| 244 |
+
"eval_runtime": 120.1397,
|
| 245 |
+
"eval_samples_per_second": 2.281,
|
| 246 |
+
"eval_steps_per_second": 0.15,
|
| 247 |
+
"eval_wer": 6.7000931801038295,
|
| 248 |
+
"step": 250
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 12.02,
|
| 252 |
+
"learning_rate": 3.413333333333333e-07,
|
| 253 |
+
"loss": 0.346,
|
| 254 |
+
"step": 260
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 12.05,
|
| 258 |
+
"learning_rate": 3.5466666666666667e-07,
|
| 259 |
+
"loss": 0.3544,
|
| 260 |
+
"step": 270
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.01,
|
| 264 |
+
"eval_loss": 0.38816705346107483,
|
| 265 |
+
"eval_runtime": 121.943,
|
| 266 |
+
"eval_samples_per_second": 2.247,
|
| 267 |
+
"eval_steps_per_second": 0.148,
|
| 268 |
+
"eval_wer": 6.624661667480143,
|
| 269 |
+
"step": 275
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 13.02,
|
| 273 |
+
"learning_rate": 3.68e-07,
|
| 274 |
+
"loss": 0.3345,
|
| 275 |
+
"step": 280
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 13.05,
|
| 279 |
+
"learning_rate": 3.813333333333333e-07,
|
| 280 |
+
"loss": 0.3354,
|
| 281 |
+
"step": 290
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 14.02,
|
| 285 |
+
"learning_rate": 3.9466666666666665e-07,
|
| 286 |
+
"loss": 0.3294,
|
| 287 |
+
"step": 300
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 14.02,
|
| 291 |
+
"eval_loss": 0.37637442350387573,
|
| 292 |
+
"eval_runtime": 132.1904,
|
| 293 |
+
"eval_samples_per_second": 2.073,
|
| 294 |
+
"eval_steps_per_second": 0.136,
|
| 295 |
+
"eval_wer": 6.695656032302436,
|
| 296 |
+
"step": 300
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 14.05,
|
| 300 |
+
"learning_rate": 3.52e-07,
|
| 301 |
+
"loss": 0.321,
|
| 302 |
+
"step": 310
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 15.01,
|
| 306 |
+
"learning_rate": 2.72e-07,
|
| 307 |
+
"loss": 0.313,
|
| 308 |
+
"step": 320
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 15.03,
|
| 312 |
+
"eval_loss": 0.3692246973514557,
|
| 313 |
+
"eval_runtime": 129.104,
|
| 314 |
+
"eval_samples_per_second": 2.122,
|
| 315 |
+
"eval_steps_per_second": 0.139,
|
| 316 |
+
"eval_wer": 6.66015884989129,
|
| 317 |
+
"step": 325
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 15.04,
|
| 321 |
+
"learning_rate": 1.9199999999999997e-07,
|
| 322 |
+
"loss": 0.3141,
|
| 323 |
+
"step": 330
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 16.01,
|
| 327 |
+
"learning_rate": 1.1200000000000001e-07,
|
| 328 |
+
"loss": 0.3172,
|
| 329 |
+
"step": 340
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 16.04,
|
| 333 |
+
"learning_rate": 3.2e-08,
|
| 334 |
+
"loss": 0.3023,
|
| 335 |
+
"step": 350
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 16.04,
|
| 339 |
+
"eval_loss": 0.36682912707328796,
|
| 340 |
+
"eval_runtime": 127.3924,
|
| 341 |
+
"eval_samples_per_second": 2.151,
|
| 342 |
+
"eval_steps_per_second": 0.141,
|
| 343 |
+
"eval_wer": 6.646847406487109,
|
| 344 |
+
"step": 350
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 16.04,
|
| 348 |
+
"step": 350,
|
| 349 |
+
"total_flos": 1.125114850050048e+19,
|
| 350 |
+
"train_loss": 0.5347552497046334,
|
| 351 |
+
"train_runtime": 7389.0047,
|
| 352 |
+
"train_samples_per_second": 1.516,
|
| 353 |
+
"train_steps_per_second": 0.047
|
| 354 |
+
}
|
| 355 |
+
],
|
| 356 |
+
"max_steps": 350,
|
| 357 |
+
"num_train_epochs": 9223372036854775807,
|
| 358 |
+
"total_flos": 1.125114850050048e+19,
|
| 359 |
+
"trial_name": null,
|
| 360 |
+
"trial_params": null
|
| 361 |
+
}
|