Commit
•
ceb8df2
1
Parent(s):
d793b19
End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +400 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.8888481855392456,
|
| 4 |
+
"eval_runtime": 12.7255,
|
| 5 |
+
"eval_samples": 341,
|
| 6 |
+
"eval_samples_per_second": 26.797,
|
| 7 |
+
"eval_steps_per_second": 3.379,
|
| 8 |
+
"eval_wer": 0.6642066420664207,
|
| 9 |
+
"train_loss": 2.1006999116785385,
|
| 10 |
+
"train_runtime": 2771.7539,
|
| 11 |
+
"train_samples": 810,
|
| 12 |
+
"train_samples_per_second": 14.612,
|
| 13 |
+
"train_steps_per_second": 0.92
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.8888481855392456,
|
| 4 |
+
"eval_runtime": 12.7255,
|
| 5 |
+
"eval_samples": 341,
|
| 6 |
+
"eval_samples_per_second": 26.797,
|
| 7 |
+
"eval_steps_per_second": 3.379,
|
| 8 |
+
"eval_wer": 0.6642066420664207
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 2.1006999116785385,
|
| 4 |
+
"train_runtime": 2771.7539,
|
| 5 |
+
"train_samples": 810,
|
| 6 |
+
"train_samples_per_second": 14.612,
|
| 7 |
+
"train_steps_per_second": 0.92
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,400 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 2550,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.96,
|
| 12 |
+
"learning_rate": 7.361999999999999e-05,
|
| 13 |
+
"loss": 10.1224,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.96,
|
| 18 |
+
"eval_loss": 3.5429043769836426,
|
| 19 |
+
"eval_runtime": 12.8681,
|
| 20 |
+
"eval_samples_per_second": 26.5,
|
| 21 |
+
"eval_steps_per_second": 3.342,
|
| 22 |
+
"eval_wer": 1.0,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 3.92,
|
| 27 |
+
"learning_rate": 7.062e-05,
|
| 28 |
+
"loss": 3.2411,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 3.92,
|
| 33 |
+
"eval_loss": 3.1785788536071777,
|
| 34 |
+
"eval_runtime": 12.8876,
|
| 35 |
+
"eval_samples_per_second": 26.46,
|
| 36 |
+
"eval_steps_per_second": 3.337,
|
| 37 |
+
"eval_wer": 1.0,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 5.88,
|
| 42 |
+
"learning_rate": 6.761999999999999e-05,
|
| 43 |
+
"loss": 3.1283,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.88,
|
| 48 |
+
"eval_loss": 3.057115316390991,
|
| 49 |
+
"eval_runtime": 12.9515,
|
| 50 |
+
"eval_samples_per_second": 26.329,
|
| 51 |
+
"eval_steps_per_second": 3.32,
|
| 52 |
+
"eval_wer": 1.0,
|
| 53 |
+
"step": 300
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 7.84,
|
| 57 |
+
"learning_rate": 6.462e-05,
|
| 58 |
+
"loss": 3.0044,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 7.84,
|
| 63 |
+
"eval_loss": 2.956029176712036,
|
| 64 |
+
"eval_runtime": 13.0792,
|
| 65 |
+
"eval_samples_per_second": 26.072,
|
| 66 |
+
"eval_steps_per_second": 3.288,
|
| 67 |
+
"eval_wer": 0.9996309963099631,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 9.8,
|
| 72 |
+
"learning_rate": 6.162e-05,
|
| 73 |
+
"loss": 2.9388,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 9.8,
|
| 78 |
+
"eval_loss": 2.897726535797119,
|
| 79 |
+
"eval_runtime": 13.249,
|
| 80 |
+
"eval_samples_per_second": 25.738,
|
| 81 |
+
"eval_steps_per_second": 3.246,
|
| 82 |
+
"eval_wer": 1.0011070110701108,
|
| 83 |
+
"step": 500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 11.76,
|
| 87 |
+
"learning_rate": 5.861999999999999e-05,
|
| 88 |
+
"loss": 2.86,
|
| 89 |
+
"step": 600
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 11.76,
|
| 93 |
+
"eval_loss": 2.694431781768799,
|
| 94 |
+
"eval_runtime": 12.8219,
|
| 95 |
+
"eval_samples_per_second": 26.595,
|
| 96 |
+
"eval_steps_per_second": 3.354,
|
| 97 |
+
"eval_wer": 0.9952029520295202,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 13.73,
|
| 102 |
+
"learning_rate": 5.562e-05,
|
| 103 |
+
"loss": 2.5538,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 13.73,
|
| 108 |
+
"eval_loss": 2.0967445373535156,
|
| 109 |
+
"eval_runtime": 12.8896,
|
| 110 |
+
"eval_samples_per_second": 26.456,
|
| 111 |
+
"eval_steps_per_second": 3.336,
|
| 112 |
+
"eval_wer": 0.9435424354243542,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 15.69,
|
| 117 |
+
"learning_rate": 5.2619999999999994e-05,
|
| 118 |
+
"loss": 2.1214,
|
| 119 |
+
"step": 800
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 15.69,
|
| 123 |
+
"eval_loss": 1.4815592765808105,
|
| 124 |
+
"eval_runtime": 12.9225,
|
| 125 |
+
"eval_samples_per_second": 26.388,
|
| 126 |
+
"eval_steps_per_second": 3.328,
|
| 127 |
+
"eval_wer": 0.8428044280442805,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 17.65,
|
| 132 |
+
"learning_rate": 4.9619999999999996e-05,
|
| 133 |
+
"loss": 1.8136,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 17.65,
|
| 138 |
+
"eval_loss": 1.245869517326355,
|
| 139 |
+
"eval_runtime": 12.7527,
|
| 140 |
+
"eval_samples_per_second": 26.739,
|
| 141 |
+
"eval_steps_per_second": 3.372,
|
| 142 |
+
"eval_wer": 0.8047970479704797,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 19.61,
|
| 147 |
+
"learning_rate": 4.662e-05,
|
| 148 |
+
"loss": 1.6795,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 19.61,
|
| 153 |
+
"eval_loss": 1.1232149600982666,
|
| 154 |
+
"eval_runtime": 12.9316,
|
| 155 |
+
"eval_samples_per_second": 26.37,
|
| 156 |
+
"eval_steps_per_second": 3.325,
|
| 157 |
+
"eval_wer": 0.7649446494464944,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 21.57,
|
| 162 |
+
"learning_rate": 4.362e-05,
|
| 163 |
+
"loss": 1.5571,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 21.57,
|
| 168 |
+
"eval_loss": 1.0510376691818237,
|
| 169 |
+
"eval_runtime": 12.7516,
|
| 170 |
+
"eval_samples_per_second": 26.742,
|
| 171 |
+
"eval_steps_per_second": 3.372,
|
| 172 |
+
"eval_wer": 0.7431734317343174,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 23.53,
|
| 177 |
+
"learning_rate": 4.0619999999999994e-05,
|
| 178 |
+
"loss": 1.4975,
|
| 179 |
+
"step": 1200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 23.53,
|
| 183 |
+
"eval_loss": 1.0297844409942627,
|
| 184 |
+
"eval_runtime": 12.7119,
|
| 185 |
+
"eval_samples_per_second": 26.825,
|
| 186 |
+
"eval_steps_per_second": 3.383,
|
| 187 |
+
"eval_wer": 0.696309963099631,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 25.49,
|
| 192 |
+
"learning_rate": 3.762e-05,
|
| 193 |
+
"loss": 1.4485,
|
| 194 |
+
"step": 1300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 25.49,
|
| 198 |
+
"eval_loss": 0.9775241017341614,
|
| 199 |
+
"eval_runtime": 12.651,
|
| 200 |
+
"eval_samples_per_second": 26.954,
|
| 201 |
+
"eval_steps_per_second": 3.399,
|
| 202 |
+
"eval_wer": 0.707380073800738,
|
| 203 |
+
"step": 1300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 27.45,
|
| 207 |
+
"learning_rate": 3.462e-05,
|
| 208 |
+
"loss": 1.3924,
|
| 209 |
+
"step": 1400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 27.45,
|
| 213 |
+
"eval_loss": 0.9797706007957458,
|
| 214 |
+
"eval_runtime": 12.6253,
|
| 215 |
+
"eval_samples_per_second": 27.009,
|
| 216 |
+
"eval_steps_per_second": 3.406,
|
| 217 |
+
"eval_wer": 0.6955719557195572,
|
| 218 |
+
"step": 1400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 29.41,
|
| 222 |
+
"learning_rate": 3.161999999999999e-05,
|
| 223 |
+
"loss": 1.3604,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 29.41,
|
| 228 |
+
"eval_loss": 0.9344653487205505,
|
| 229 |
+
"eval_runtime": 12.7334,
|
| 230 |
+
"eval_samples_per_second": 26.78,
|
| 231 |
+
"eval_steps_per_second": 3.377,
|
| 232 |
+
"eval_wer": 0.7092250922509226,
|
| 233 |
+
"step": 1500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 31.37,
|
| 237 |
+
"learning_rate": 2.8619999999999997e-05,
|
| 238 |
+
"loss": 1.3224,
|
| 239 |
+
"step": 1600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 31.37,
|
| 243 |
+
"eval_loss": 0.9535229802131653,
|
| 244 |
+
"eval_runtime": 12.7291,
|
| 245 |
+
"eval_samples_per_second": 26.789,
|
| 246 |
+
"eval_steps_per_second": 3.378,
|
| 247 |
+
"eval_wer": 0.6830258302583025,
|
| 248 |
+
"step": 1600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 33.33,
|
| 252 |
+
"learning_rate": 2.562e-05,
|
| 253 |
+
"loss": 1.2816,
|
| 254 |
+
"step": 1700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 33.33,
|
| 258 |
+
"eval_loss": 0.9177776575088501,
|
| 259 |
+
"eval_runtime": 12.8107,
|
| 260 |
+
"eval_samples_per_second": 26.618,
|
| 261 |
+
"eval_steps_per_second": 3.357,
|
| 262 |
+
"eval_wer": 0.6678966789667896,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 35.29,
|
| 267 |
+
"learning_rate": 2.2619999999999997e-05,
|
| 268 |
+
"loss": 1.2623,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 35.29,
|
| 273 |
+
"eval_loss": 0.924865186214447,
|
| 274 |
+
"eval_runtime": 12.5463,
|
| 275 |
+
"eval_samples_per_second": 27.179,
|
| 276 |
+
"eval_steps_per_second": 3.427,
|
| 277 |
+
"eval_wer": 0.6678966789667896,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 37.25,
|
| 282 |
+
"learning_rate": 1.962e-05,
|
| 283 |
+
"loss": 1.2421,
|
| 284 |
+
"step": 1900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 37.25,
|
| 288 |
+
"eval_loss": 0.9123861193656921,
|
| 289 |
+
"eval_runtime": 12.7025,
|
| 290 |
+
"eval_samples_per_second": 26.845,
|
| 291 |
+
"eval_steps_per_second": 3.385,
|
| 292 |
+
"eval_wer": 0.6734317343173432,
|
| 293 |
+
"step": 1900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 39.22,
|
| 297 |
+
"learning_rate": 1.6619999999999997e-05,
|
| 298 |
+
"loss": 1.2208,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 39.22,
|
| 303 |
+
"eval_loss": 0.8961586356163025,
|
| 304 |
+
"eval_runtime": 12.5233,
|
| 305 |
+
"eval_samples_per_second": 27.229,
|
| 306 |
+
"eval_steps_per_second": 3.434,
|
| 307 |
+
"eval_wer": 0.666420664206642,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 41.18,
|
| 312 |
+
"learning_rate": 1.362e-05,
|
| 313 |
+
"loss": 1.2145,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 41.18,
|
| 318 |
+
"eval_loss": 0.8903014063835144,
|
| 319 |
+
"eval_runtime": 12.6636,
|
| 320 |
+
"eval_samples_per_second": 26.928,
|
| 321 |
+
"eval_steps_per_second": 3.396,
|
| 322 |
+
"eval_wer": 0.6734317343173432,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 43.14,
|
| 327 |
+
"learning_rate": 1.062e-05,
|
| 328 |
+
"loss": 1.1888,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 43.14,
|
| 333 |
+
"eval_loss": 0.8883377313613892,
|
| 334 |
+
"eval_runtime": 12.7667,
|
| 335 |
+
"eval_samples_per_second": 26.71,
|
| 336 |
+
"eval_steps_per_second": 3.368,
|
| 337 |
+
"eval_wer": 0.6708487084870849,
|
| 338 |
+
"step": 2200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 45.1,
|
| 342 |
+
"learning_rate": 7.619999999999999e-06,
|
| 343 |
+
"loss": 1.1933,
|
| 344 |
+
"step": 2300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 45.1,
|
| 348 |
+
"eval_loss": 0.8928494453430176,
|
| 349 |
+
"eval_runtime": 12.6877,
|
| 350 |
+
"eval_samples_per_second": 26.876,
|
| 351 |
+
"eval_steps_per_second": 3.389,
|
| 352 |
+
"eval_wer": 0.6723247232472325,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 47.06,
|
| 357 |
+
"learning_rate": 4.62e-06,
|
| 358 |
+
"loss": 1.1838,
|
| 359 |
+
"step": 2400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 47.06,
|
| 363 |
+
"eval_loss": 0.8868067860603333,
|
| 364 |
+
"eval_runtime": 12.5901,
|
| 365 |
+
"eval_samples_per_second": 27.085,
|
| 366 |
+
"eval_steps_per_second": 3.415,
|
| 367 |
+
"eval_wer": 0.6678966789667896,
|
| 368 |
+
"step": 2400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 49.02,
|
| 372 |
+
"learning_rate": 1.62e-06,
|
| 373 |
+
"loss": 1.1634,
|
| 374 |
+
"step": 2500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 49.02,
|
| 378 |
+
"eval_loss": 0.888584554195404,
|
| 379 |
+
"eval_runtime": 12.7157,
|
| 380 |
+
"eval_samples_per_second": 26.817,
|
| 381 |
+
"eval_steps_per_second": 3.382,
|
| 382 |
+
"eval_wer": 0.6656826568265682,
|
| 383 |
+
"step": 2500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 50.0,
|
| 387 |
+
"step": 2550,
|
| 388 |
+
"total_flos": 4.920553620909019e+18,
|
| 389 |
+
"train_loss": 2.1006999116785385,
|
| 390 |
+
"train_runtime": 2771.7539,
|
| 391 |
+
"train_samples_per_second": 14.612,
|
| 392 |
+
"train_steps_per_second": 0.92
|
| 393 |
+
}
|
| 394 |
+
],
|
| 395 |
+
"max_steps": 2550,
|
| 396 |
+
"num_train_epochs": 50,
|
| 397 |
+
"total_flos": 4.920553620909019e+18,
|
| 398 |
+
"trial_name": null,
|
| 399 |
+
"trial_params": null
|
| 400 |
+
}
|