End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8911205073995772,
|
| 4 |
+
"eval_loss": 0.3048795163631439,
|
| 5 |
+
"eval_runtime": 3.7453,
|
| 6 |
+
"eval_samples": 946,
|
| 7 |
+
"eval_samples_per_second": 252.581,
|
| 8 |
+
"eval_steps_per_second": 16.02,
|
| 9 |
+
"train_loss": 0.16311937355604328,
|
| 10 |
+
"train_runtime": 870.9833,
|
| 11 |
+
"train_samples": 7801,
|
| 12 |
+
"train_samples_per_second": 89.565,
|
| 13 |
+
"train_steps_per_second": 2.801
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.8911205073995772,
|
| 4 |
+
"eval_loss": 0.3048795163631439,
|
| 5 |
+
"eval_runtime": 3.7453,
|
| 6 |
+
"eval_samples": 946,
|
| 7 |
+
"eval_samples_per_second": 252.581,
|
| 8 |
+
"eval_steps_per_second": 16.02
|
| 9 |
+
}
|
runs/Jul31_14-37-40_monica.sm.unibocconi.it/events.out.tfevents.1690807992.monica.sm.unibocconi.it.2295249.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eba58f83d32a809f72c12b23f84d1be1fe74c3eaba34e6ac4a1cebce964b650e
|
| 3 |
+
size 363
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 0.16311937355604328,
|
| 4 |
+
"train_runtime": 870.9833,
|
| 5 |
+
"train_samples": 7801,
|
| 6 |
+
"train_samples_per_second": 89.565,
|
| 7 |
+
"train_steps_per_second": 2.801
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,385 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.3048795163631439,
|
| 3 |
+
"best_model_checkpoint": "./models/bert-italian-xxl-cased-ItaCoLA/checkpoint-700",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 2440,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.41,
|
| 12 |
+
"learning_rate": 1e-05,
|
| 13 |
+
"loss": 0.4243,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.41,
|
| 18 |
+
"eval_accuracy": 0.854122621564482,
|
| 19 |
+
"eval_loss": 0.38053709268569946,
|
| 20 |
+
"eval_runtime": 3.6758,
|
| 21 |
+
"eval_samples_per_second": 257.362,
|
| 22 |
+
"eval_steps_per_second": 16.323,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.82,
|
| 27 |
+
"learning_rate": 1e-05,
|
| 28 |
+
"loss": 0.3806,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.82,
|
| 33 |
+
"eval_accuracy": 0.857293868921776,
|
| 34 |
+
"eval_loss": 0.3861564099788666,
|
| 35 |
+
"eval_runtime": 3.5095,
|
| 36 |
+
"eval_samples_per_second": 269.553,
|
| 37 |
+
"eval_steps_per_second": 17.096,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.23,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 0.3289,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.23,
|
| 48 |
+
"eval_accuracy": 0.8678646934460887,
|
| 49 |
+
"eval_loss": 0.35367050766944885,
|
| 50 |
+
"eval_runtime": 3.7169,
|
| 51 |
+
"eval_samples_per_second": 254.517,
|
| 52 |
+
"eval_steps_per_second": 16.143,
|
| 53 |
+
"step": 300
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.64,
|
| 57 |
+
"learning_rate": 1e-05,
|
| 58 |
+
"loss": 0.2967,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.64,
|
| 63 |
+
"eval_accuracy": 0.8826638477801269,
|
| 64 |
+
"eval_loss": 0.3165006935596466,
|
| 65 |
+
"eval_runtime": 3.5485,
|
| 66 |
+
"eval_samples_per_second": 266.59,
|
| 67 |
+
"eval_steps_per_second": 16.908,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.05,
|
| 72 |
+
"learning_rate": 1e-05,
|
| 73 |
+
"loss": 0.2992,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.05,
|
| 78 |
+
"eval_accuracy": 0.8784355179704016,
|
| 79 |
+
"eval_loss": 0.33816611766815186,
|
| 80 |
+
"eval_runtime": 3.7064,
|
| 81 |
+
"eval_samples_per_second": 255.231,
|
| 82 |
+
"eval_steps_per_second": 16.188,
|
| 83 |
+
"step": 500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.46,
|
| 87 |
+
"learning_rate": 1e-05,
|
| 88 |
+
"loss": 0.2273,
|
| 89 |
+
"step": 600
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.46,
|
| 93 |
+
"eval_accuracy": 0.8816067653276956,
|
| 94 |
+
"eval_loss": 0.329441100358963,
|
| 95 |
+
"eval_runtime": 3.7539,
|
| 96 |
+
"eval_samples_per_second": 252.003,
|
| 97 |
+
"eval_steps_per_second": 15.983,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.87,
|
| 102 |
+
"learning_rate": 1e-05,
|
| 103 |
+
"loss": 0.2215,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.87,
|
| 108 |
+
"eval_accuracy": 0.8911205073995772,
|
| 109 |
+
"eval_loss": 0.3048795163631439,
|
| 110 |
+
"eval_runtime": 3.5485,
|
| 111 |
+
"eval_samples_per_second": 266.591,
|
| 112 |
+
"eval_steps_per_second": 16.909,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.28,
|
| 117 |
+
"learning_rate": 1e-05,
|
| 118 |
+
"loss": 0.1718,
|
| 119 |
+
"step": 800
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.28,
|
| 123 |
+
"eval_accuracy": 0.8911205073995772,
|
| 124 |
+
"eval_loss": 0.35308167338371277,
|
| 125 |
+
"eval_runtime": 3.56,
|
| 126 |
+
"eval_samples_per_second": 265.727,
|
| 127 |
+
"eval_steps_per_second": 16.854,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.69,
|
| 132 |
+
"learning_rate": 1e-05,
|
| 133 |
+
"loss": 0.1757,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.69,
|
| 138 |
+
"eval_accuracy": 0.8921775898520085,
|
| 139 |
+
"eval_loss": 0.39034464955329895,
|
| 140 |
+
"eval_runtime": 3.7329,
|
| 141 |
+
"eval_samples_per_second": 253.42,
|
| 142 |
+
"eval_steps_per_second": 16.073,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.1,
|
| 147 |
+
"learning_rate": 1e-05,
|
| 148 |
+
"loss": 0.1698,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.1,
|
| 153 |
+
"eval_accuracy": 0.8953488372093024,
|
| 154 |
+
"eval_loss": 0.3871164321899414,
|
| 155 |
+
"eval_runtime": 3.5471,
|
| 156 |
+
"eval_samples_per_second": 266.695,
|
| 157 |
+
"eval_steps_per_second": 16.915,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.51,
|
| 162 |
+
"learning_rate": 1e-05,
|
| 163 |
+
"loss": 0.1307,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 4.51,
|
| 168 |
+
"eval_accuracy": 0.8953488372093024,
|
| 169 |
+
"eval_loss": 0.42552220821380615,
|
| 170 |
+
"eval_runtime": 3.5867,
|
| 171 |
+
"eval_samples_per_second": 263.752,
|
| 172 |
+
"eval_steps_per_second": 16.728,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 4.92,
|
| 177 |
+
"learning_rate": 1e-05,
|
| 178 |
+
"loss": 0.1426,
|
| 179 |
+
"step": 1200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 4.92,
|
| 183 |
+
"eval_accuracy": 0.8985200845665962,
|
| 184 |
+
"eval_loss": 0.37290310859680176,
|
| 185 |
+
"eval_runtime": 3.5578,
|
| 186 |
+
"eval_samples_per_second": 265.898,
|
| 187 |
+
"eval_steps_per_second": 16.865,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.33,
|
| 192 |
+
"learning_rate": 1e-05,
|
| 193 |
+
"loss": 0.1136,
|
| 194 |
+
"step": 1300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 5.33,
|
| 198 |
+
"eval_accuracy": 0.8964059196617337,
|
| 199 |
+
"eval_loss": 0.49388667941093445,
|
| 200 |
+
"eval_runtime": 3.5671,
|
| 201 |
+
"eval_samples_per_second": 265.203,
|
| 202 |
+
"eval_steps_per_second": 16.82,
|
| 203 |
+
"step": 1300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 5.74,
|
| 207 |
+
"learning_rate": 1e-05,
|
| 208 |
+
"loss": 0.1163,
|
| 209 |
+
"step": 1400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.74,
|
| 213 |
+
"eval_accuracy": 0.8964059196617337,
|
| 214 |
+
"eval_loss": 0.4004368782043457,
|
| 215 |
+
"eval_runtime": 3.7365,
|
| 216 |
+
"eval_samples_per_second": 253.18,
|
| 217 |
+
"eval_steps_per_second": 16.058,
|
| 218 |
+
"step": 1400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.15,
|
| 222 |
+
"learning_rate": 1e-05,
|
| 223 |
+
"loss": 0.0936,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.15,
|
| 228 |
+
"eval_accuracy": 0.8964059196617337,
|
| 229 |
+
"eval_loss": 0.5116058588027954,
|
| 230 |
+
"eval_runtime": 3.5814,
|
| 231 |
+
"eval_samples_per_second": 264.146,
|
| 232 |
+
"eval_steps_per_second": 16.753,
|
| 233 |
+
"step": 1500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.56,
|
| 237 |
+
"learning_rate": 1e-05,
|
| 238 |
+
"loss": 0.0973,
|
| 239 |
+
"step": 1600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.56,
|
| 243 |
+
"eval_accuracy": 0.8921775898520085,
|
| 244 |
+
"eval_loss": 0.4807981848716736,
|
| 245 |
+
"eval_runtime": 3.7354,
|
| 246 |
+
"eval_samples_per_second": 253.253,
|
| 247 |
+
"eval_steps_per_second": 16.063,
|
| 248 |
+
"step": 1600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 6.97,
|
| 252 |
+
"learning_rate": 1e-05,
|
| 253 |
+
"loss": 0.0899,
|
| 254 |
+
"step": 1700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 6.97,
|
| 258 |
+
"eval_accuracy": 0.8868921775898521,
|
| 259 |
+
"eval_loss": 0.48126643896102905,
|
| 260 |
+
"eval_runtime": 3.5551,
|
| 261 |
+
"eval_samples_per_second": 266.094,
|
| 262 |
+
"eval_steps_per_second": 16.877,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 7.38,
|
| 267 |
+
"learning_rate": 1e-05,
|
| 268 |
+
"loss": 0.0687,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 7.38,
|
| 273 |
+
"eval_accuracy": 0.8847780126849895,
|
| 274 |
+
"eval_loss": 0.6045676469802856,
|
| 275 |
+
"eval_runtime": 3.7224,
|
| 276 |
+
"eval_samples_per_second": 254.138,
|
| 277 |
+
"eval_steps_per_second": 16.119,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 7.79,
|
| 282 |
+
"learning_rate": 1e-05,
|
| 283 |
+
"loss": 0.0709,
|
| 284 |
+
"step": 1900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 7.79,
|
| 288 |
+
"eval_accuracy": 0.8964059196617337,
|
| 289 |
+
"eval_loss": 0.5939581394195557,
|
| 290 |
+
"eval_runtime": 3.7591,
|
| 291 |
+
"eval_samples_per_second": 251.655,
|
| 292 |
+
"eval_steps_per_second": 15.961,
|
| 293 |
+
"step": 1900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 8.2,
|
| 297 |
+
"learning_rate": 1e-05,
|
| 298 |
+
"loss": 0.0694,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 8.2,
|
| 303 |
+
"eval_accuracy": 0.8911205073995772,
|
| 304 |
+
"eval_loss": 0.5791226029396057,
|
| 305 |
+
"eval_runtime": 3.5526,
|
| 306 |
+
"eval_samples_per_second": 266.284,
|
| 307 |
+
"eval_steps_per_second": 16.889,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 8.61,
|
| 312 |
+
"learning_rate": 1e-05,
|
| 313 |
+
"loss": 0.0732,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 8.61,
|
| 318 |
+
"eval_accuracy": 0.8921775898520085,
|
| 319 |
+
"eval_loss": 0.5576857924461365,
|
| 320 |
+
"eval_runtime": 3.5693,
|
| 321 |
+
"eval_samples_per_second": 265.038,
|
| 322 |
+
"eval_steps_per_second": 16.81,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 9.02,
|
| 327 |
+
"learning_rate": 1e-05,
|
| 328 |
+
"loss": 0.0714,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 9.02,
|
| 333 |
+
"eval_accuracy": 0.8995771670190275,
|
| 334 |
+
"eval_loss": 0.5248907804489136,
|
| 335 |
+
"eval_runtime": 3.7426,
|
| 336 |
+
"eval_samples_per_second": 252.768,
|
| 337 |
+
"eval_steps_per_second": 16.032,
|
| 338 |
+
"step": 2200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 9.43,
|
| 342 |
+
"learning_rate": 1e-05,
|
| 343 |
+
"loss": 0.0531,
|
| 344 |
+
"step": 2300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 9.43,
|
| 348 |
+
"eval_accuracy": 0.8932346723044398,
|
| 349 |
+
"eval_loss": 0.6098359227180481,
|
| 350 |
+
"eval_runtime": 3.5458,
|
| 351 |
+
"eval_samples_per_second": 266.794,
|
| 352 |
+
"eval_steps_per_second": 16.921,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 9.84,
|
| 357 |
+
"learning_rate": 1e-05,
|
| 358 |
+
"loss": 0.0713,
|
| 359 |
+
"step": 2400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 9.84,
|
| 363 |
+
"eval_accuracy": 0.8942917547568711,
|
| 364 |
+
"eval_loss": 0.5609742403030396,
|
| 365 |
+
"eval_runtime": 3.5561,
|
| 366 |
+
"eval_samples_per_second": 266.022,
|
| 367 |
+
"eval_steps_per_second": 16.872,
|
| 368 |
+
"step": 2400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 10.0,
|
| 372 |
+
"step": 2440,
|
| 373 |
+
"total_flos": 5131323357158400.0,
|
| 374 |
+
"train_loss": 0.16311937355604328,
|
| 375 |
+
"train_runtime": 870.9833,
|
| 376 |
+
"train_samples_per_second": 89.565,
|
| 377 |
+
"train_steps_per_second": 2.801
|
| 378 |
+
}
|
| 379 |
+
],
|
| 380 |
+
"max_steps": 2440,
|
| 381 |
+
"num_train_epochs": 10,
|
| 382 |
+
"total_flos": 5131323357158400.0,
|
| 383 |
+
"trial_name": null,
|
| 384 |
+
"trial_params": null
|
| 385 |
+
}
|