End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +501 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.99,
|
| 3 |
+
"eval_loss": 1.887495756149292,
|
| 4 |
+
"eval_runtime": 5.9465,
|
| 5 |
+
"eval_samples": 444,
|
| 6 |
+
"eval_samples_per_second": 74.666,
|
| 7 |
+
"eval_steps_per_second": 18.666,
|
| 8 |
+
"perplexity": 6.602812906228741,
|
| 9 |
+
"train_loss": 2.230022551796653,
|
| 10 |
+
"train_runtime": 1073.0912,
|
| 11 |
+
"train_samples": 8516,
|
| 12 |
+
"train_samples_per_second": 79.36,
|
| 13 |
+
"train_steps_per_second": 0.308
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.99,
|
| 3 |
+
"eval_loss": 1.887495756149292,
|
| 4 |
+
"eval_runtime": 5.9465,
|
| 5 |
+
"eval_samples": 444,
|
| 6 |
+
"eval_samples_per_second": 74.666,
|
| 7 |
+
"eval_steps_per_second": 18.666,
|
| 8 |
+
"perplexity": 6.602812906228741
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.99,
|
| 3 |
+
"train_loss": 2.230022551796653,
|
| 4 |
+
"train_runtime": 1073.0912,
|
| 5 |
+
"train_samples": 8516,
|
| 6 |
+
"train_samples_per_second": 79.36,
|
| 7 |
+
"train_steps_per_second": 0.308
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.992481203007518,
|
| 5 |
+
"global_step": 330,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 13 |
+
"loss": 4.7948,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.3,
|
| 18 |
+
"learning_rate": 5.882352941176471e-05,
|
| 19 |
+
"loss": 4.6565,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.45,
|
| 24 |
+
"learning_rate": 8.823529411764706e-05,
|
| 25 |
+
"loss": 4.2672,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.6,
|
| 30 |
+
"learning_rate": 9.997733473639876e-05,
|
| 31 |
+
"loss": 3.8103,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.75,
|
| 36 |
+
"learning_rate": 9.983889919973586e-05,
|
| 37 |
+
"loss": 3.4219,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.9,
|
| 42 |
+
"learning_rate": 9.957496810072027e-05,
|
| 43 |
+
"loss": 3.2189,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.99,
|
| 48 |
+
"eval_loss": 3.00506591796875,
|
| 49 |
+
"eval_runtime": 5.8168,
|
| 50 |
+
"eval_samples_per_second": 76.331,
|
| 51 |
+
"eval_steps_per_second": 19.083,
|
| 52 |
+
"step": 33
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.06,
|
| 56 |
+
"learning_rate": 9.918620602428915e-05,
|
| 57 |
+
"loss": 3.1568,
|
| 58 |
+
"step": 35
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.21,
|
| 62 |
+
"learning_rate": 9.867359188282192e-05,
|
| 63 |
+
"loss": 2.8976,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.36,
|
| 68 |
+
"learning_rate": 9.803841645121504e-05,
|
| 69 |
+
"loss": 2.8159,
|
| 70 |
+
"step": 45
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.51,
|
| 74 |
+
"learning_rate": 9.728227911667934e-05,
|
| 75 |
+
"loss": 2.7279,
|
| 76 |
+
"step": 50
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.66,
|
| 80 |
+
"learning_rate": 9.640708385144403e-05,
|
| 81 |
+
"loss": 2.6442,
|
| 82 |
+
"step": 55
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.81,
|
| 86 |
+
"learning_rate": 9.541503441850843e-05,
|
| 87 |
+
"loss": 2.5975,
|
| 88 |
+
"step": 60
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.96,
|
| 92 |
+
"learning_rate": 9.430862882251278e-05,
|
| 93 |
+
"loss": 2.5466,
|
| 94 |
+
"step": 65
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.99,
|
| 98 |
+
"eval_loss": 2.5214502811431885,
|
| 99 |
+
"eval_runtime": 5.9909,
|
| 100 |
+
"eval_samples_per_second": 74.113,
|
| 101 |
+
"eval_steps_per_second": 18.528,
|
| 102 |
+
"step": 66
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.12,
|
| 106 |
+
"learning_rate": 9.309065301970193e-05,
|
| 107 |
+
"loss": 2.6158,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 2.27,
|
| 112 |
+
"learning_rate": 9.176417390281944e-05,
|
| 113 |
+
"loss": 2.4248,
|
| 114 |
+
"step": 75
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.42,
|
| 118 |
+
"learning_rate": 9.033253157859714e-05,
|
| 119 |
+
"loss": 2.3915,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.57,
|
| 124 |
+
"learning_rate": 8.879933095728485e-05,
|
| 125 |
+
"loss": 2.3519,
|
| 126 |
+
"step": 85
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.72,
|
| 130 |
+
"learning_rate": 8.716843267539869e-05,
|
| 131 |
+
"loss": 2.3216,
|
| 132 |
+
"step": 90
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.87,
|
| 136 |
+
"learning_rate": 8.544394337454409e-05,
|
| 137 |
+
"loss": 2.2791,
|
| 138 |
+
"step": 95
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.99,
|
| 142 |
+
"eval_loss": 2.2881205081939697,
|
| 143 |
+
"eval_runtime": 6.1549,
|
| 144 |
+
"eval_samples_per_second": 72.138,
|
| 145 |
+
"eval_steps_per_second": 18.034,
|
| 146 |
+
"step": 99
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 3.03,
|
| 150 |
+
"learning_rate": 8.363020536079239e-05,
|
| 151 |
+
"loss": 2.3846,
|
| 152 |
+
"step": 100
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.18,
|
| 156 |
+
"learning_rate": 8.17317856706482e-05,
|
| 157 |
+
"loss": 2.2154,
|
| 158 |
+
"step": 105
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 3.33,
|
| 162 |
+
"learning_rate": 7.975346457114034e-05,
|
| 163 |
+
"loss": 2.1769,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 3.48,
|
| 168 |
+
"learning_rate": 7.770022352299293e-05,
|
| 169 |
+
"loss": 2.1613,
|
| 170 |
+
"step": 115
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.63,
|
| 174 |
+
"learning_rate": 7.557723263718596e-05,
|
| 175 |
+
"loss": 2.1198,
|
| 176 |
+
"step": 120
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.78,
|
| 180 |
+
"learning_rate": 7.338983765648985e-05,
|
| 181 |
+
"loss": 2.1125,
|
| 182 |
+
"step": 125
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.93,
|
| 186 |
+
"learning_rate": 7.114354649475499e-05,
|
| 187 |
+
"loss": 2.107,
|
| 188 |
+
"step": 130
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.99,
|
| 192 |
+
"eval_loss": 2.1322436332702637,
|
| 193 |
+
"eval_runtime": 5.9353,
|
| 194 |
+
"eval_samples_per_second": 74.807,
|
| 195 |
+
"eval_steps_per_second": 18.702,
|
| 196 |
+
"step": 132
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 4.09,
|
| 200 |
+
"learning_rate": 6.884401536785045e-05,
|
| 201 |
+
"loss": 2.1638,
|
| 202 |
+
"step": 135
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.24,
|
| 206 |
+
"learning_rate": 6.649703455117458e-05,
|
| 207 |
+
"loss": 2.0297,
|
| 208 |
+
"step": 140
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 4.39,
|
| 212 |
+
"learning_rate": 6.41085137996006e-05,
|
| 213 |
+
"loss": 1.9982,
|
| 214 |
+
"step": 145
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 4.54,
|
| 218 |
+
"learning_rate": 6.168446746656973e-05,
|
| 219 |
+
"loss": 1.9981,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.69,
|
| 224 |
+
"learning_rate": 5.9230999359802784e-05,
|
| 225 |
+
"loss": 1.9916,
|
| 226 |
+
"step": 155
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 4.84,
|
| 230 |
+
"learning_rate": 5.675428737176367e-05,
|
| 231 |
+
"loss": 1.9654,
|
| 232 |
+
"step": 160
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.99,
|
| 236 |
+
"learning_rate": 5.426056792357551e-05,
|
| 237 |
+
"loss": 1.9458,
|
| 238 |
+
"step": 165
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.99,
|
| 242 |
+
"eval_loss": 2.02701735496521,
|
| 243 |
+
"eval_runtime": 6.09,
|
| 244 |
+
"eval_samples_per_second": 72.906,
|
| 245 |
+
"eval_steps_per_second": 18.227,
|
| 246 |
+
"step": 165
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 5.15,
|
| 250 |
+
"learning_rate": 5.1756120261560446e-05,
|
| 251 |
+
"loss": 2.0128,
|
| 252 |
+
"step": 170
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.3,
|
| 256 |
+
"learning_rate": 4.924725064594447e-05,
|
| 257 |
+
"loss": 1.9078,
|
| 258 |
+
"step": 175
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 5.45,
|
| 262 |
+
"learning_rate": 4.674027647154037e-05,
|
| 263 |
+
"loss": 1.8843,
|
| 264 |
+
"step": 180
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 5.6,
|
| 268 |
+
"learning_rate": 4.4241510360393804e-05,
|
| 269 |
+
"loss": 1.8944,
|
| 270 |
+
"step": 185
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.75,
|
| 274 |
+
"learning_rate": 4.1757244266447245e-05,
|
| 275 |
+
"loss": 1.8812,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.9,
|
| 280 |
+
"learning_rate": 3.9293733632246544e-05,
|
| 281 |
+
"loss": 1.8664,
|
| 282 |
+
"step": 195
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 5.99,
|
| 286 |
+
"eval_loss": 1.9580020904541016,
|
| 287 |
+
"eval_runtime": 5.9675,
|
| 288 |
+
"eval_samples_per_second": 74.403,
|
| 289 |
+
"eval_steps_per_second": 18.601,
|
| 290 |
+
"step": 198
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 6.06,
|
| 294 |
+
"learning_rate": 3.685718163758427e-05,
|
| 295 |
+
"loss": 1.9469,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.21,
|
| 300 |
+
"learning_rate": 3.445372357974194e-05,
|
| 301 |
+
"loss": 1.8484,
|
| 302 |
+
"step": 205
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.36,
|
| 306 |
+
"learning_rate": 3.208941142466187e-05,
|
| 307 |
+
"loss": 1.8128,
|
| 308 |
+
"step": 210
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.51,
|
| 312 |
+
"learning_rate": 2.9770198567949546e-05,
|
| 313 |
+
"loss": 1.8096,
|
| 314 |
+
"step": 215
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 6.66,
|
| 318 |
+
"learning_rate": 2.7501924844078534e-05,
|
| 319 |
+
"loss": 1.8189,
|
| 320 |
+
"step": 220
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 6.81,
|
| 324 |
+
"learning_rate": 2.5290301821544825e-05,
|
| 325 |
+
"loss": 1.8172,
|
| 326 |
+
"step": 225
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 6.96,
|
| 330 |
+
"learning_rate": 2.3140898420998426e-05,
|
| 331 |
+
"loss": 1.8083,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.99,
|
| 336 |
+
"eval_loss": 1.9176976680755615,
|
| 337 |
+
"eval_runtime": 6.163,
|
| 338 |
+
"eval_samples_per_second": 72.043,
|
| 339 |
+
"eval_steps_per_second": 18.011,
|
| 340 |
+
"step": 231
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 7.12,
|
| 344 |
+
"learning_rate": 2.105912689256533e-05,
|
| 345 |
+
"loss": 1.8905,
|
| 346 |
+
"step": 235
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 7.27,
|
| 350 |
+
"learning_rate": 1.905022918766995e-05,
|
| 351 |
+
"loss": 1.7894,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.42,
|
| 356 |
+
"learning_rate": 1.7119263759673675e-05,
|
| 357 |
+
"loss": 1.7816,
|
| 358 |
+
"step": 245
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 7.57,
|
| 362 |
+
"learning_rate": 1.527109282656611e-05,
|
| 363 |
+
"loss": 1.7818,
|
| 364 |
+
"step": 250
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 7.72,
|
| 368 |
+
"learning_rate": 1.3510370127781635e-05,
|
| 369 |
+
"loss": 1.7792,
|
| 370 |
+
"step": 255
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 7.87,
|
| 374 |
+
"learning_rate": 1.184152920597028e-05,
|
| 375 |
+
"loss": 1.7631,
|
| 376 |
+
"step": 260
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 7.99,
|
| 380 |
+
"eval_loss": 1.896404504776001,
|
| 381 |
+
"eval_runtime": 6.0238,
|
| 382 |
+
"eval_samples_per_second": 73.708,
|
| 383 |
+
"eval_steps_per_second": 18.427,
|
| 384 |
+
"step": 264
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.03,
|
| 388 |
+
"learning_rate": 1.026877224322923e-05,
|
| 389 |
+
"loss": 1.8595,
|
| 390 |
+
"step": 265
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 8.18,
|
| 394 |
+
"learning_rate": 8.7960594799059e-06,
|
| 395 |
+
"loss": 1.7476,
|
| 396 |
+
"step": 270
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 8.33,
|
| 400 |
+
"learning_rate": 7.427099242616348e-06,
|
| 401 |
+
"loss": 1.7775,
|
| 402 |
+
"step": 275
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.48,
|
| 406 |
+
"learning_rate": 6.1653386065885165e-06,
|
| 407 |
+
"loss": 1.7544,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 8.63,
|
| 412 |
+
"learning_rate": 5.0139547158427e-06,
|
| 413 |
+
"loss": 1.7617,
|
| 414 |
+
"step": 285
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 8.78,
|
| 418 |
+
"learning_rate": 3.975846783065662e-06,
|
| 419 |
+
"loss": 1.7706,
|
| 420 |
+
"step": 290
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 8.93,
|
| 424 |
+
"learning_rate": 3.0536287893223604e-06,
|
| 425 |
+
"loss": 1.7369,
|
| 426 |
+
"step": 295
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 8.99,
|
| 430 |
+
"eval_loss": 1.8884940147399902,
|
| 431 |
+
"eval_runtime": 5.932,
|
| 432 |
+
"eval_samples_per_second": 74.849,
|
| 433 |
+
"eval_steps_per_second": 18.712,
|
| 434 |
+
"step": 297
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 9.09,
|
| 438 |
+
"learning_rate": 2.249622901987963e-06,
|
| 439 |
+
"loss": 1.8462,
|
| 440 |
+
"step": 300
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 9.24,
|
| 444 |
+
"learning_rate": 1.5658536274738621e-06,
|
| 445 |
+
"loss": 1.7371,
|
| 446 |
+
"step": 305
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 9.39,
|
| 450 |
+
"learning_rate": 1.004042713471165e-06,
|
| 451 |
+
"loss": 1.7526,
|
| 452 |
+
"step": 310
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 9.54,
|
| 456 |
+
"learning_rate": 5.656048135480763e-07,
|
| 457 |
+
"loss": 1.7684,
|
| 458 |
+
"step": 315
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 9.69,
|
| 462 |
+
"learning_rate": 2.5164392501777487e-07,
|
| 463 |
+
"loss": 1.7508,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 9.84,
|
| 468 |
+
"learning_rate": 6.295060904623617e-08,
|
| 469 |
+
"loss": 1.7465,
|
| 470 |
+
"step": 325
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 9.99,
|
| 474 |
+
"learning_rate": 0.0,
|
| 475 |
+
"loss": 1.766,
|
| 476 |
+
"step": 330
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 9.99,
|
| 480 |
+
"eval_loss": 1.887495756149292,
|
| 481 |
+
"eval_runtime": 6.0398,
|
| 482 |
+
"eval_samples_per_second": 73.513,
|
| 483 |
+
"eval_steps_per_second": 18.378,
|
| 484 |
+
"step": 330
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 9.99,
|
| 488 |
+
"step": 330,
|
| 489 |
+
"total_flos": 2.2217230871691264e+16,
|
| 490 |
+
"train_loss": 2.230022551796653,
|
| 491 |
+
"train_runtime": 1073.0912,
|
| 492 |
+
"train_samples_per_second": 79.36,
|
| 493 |
+
"train_steps_per_second": 0.308
|
| 494 |
+
}
|
| 495 |
+
],
|
| 496 |
+
"max_steps": 330,
|
| 497 |
+
"num_train_epochs": 10,
|
| 498 |
+
"total_flos": 2.2217230871691264e+16,
|
| 499 |
+
"trial_name": null,
|
| 500 |
+
"trial_params": null
|
| 501 |
+
}
|