Commit
•
fdc942b
1
Parent(s):
7afe171
Training complete
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +197 -0
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 719017869312000.0,
|
| 4 |
+
"train_loss": 0.19799817996554905,
|
| 5 |
+
"train_runtime": 356.7954,
|
| 6 |
+
"train_samples_per_second": 50.449,
|
| 7 |
+
"train_steps_per_second": 6.306
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 719017869312000.0,
|
| 4 |
+
"train_loss": 0.19799817996554905,
|
| 5 |
+
"train_runtime": 356.7954,
|
| 6 |
+
"train_samples_per_second": 50.449,
|
| 7 |
+
"train_steps_per_second": 6.306
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 2250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 0.0009555555555555556,
|
| 13 |
+
"loss": 0.2956,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.18,
|
| 18 |
+
"learning_rate": 0.0009111111111111111,
|
| 19 |
+
"loss": 0.2635,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.27,
|
| 24 |
+
"learning_rate": 0.0008666666666666667,
|
| 25 |
+
"loss": 0.2384,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.36,
|
| 30 |
+
"learning_rate": 0.0008222222222222222,
|
| 31 |
+
"loss": 0.2234,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.44,
|
| 36 |
+
"learning_rate": 0.0007777777777777778,
|
| 37 |
+
"loss": 0.2152,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.44,
|
| 42 |
+
"eval_loss": 0.3215401768684387,
|
| 43 |
+
"eval_macro-f1": 0.36252944248976143,
|
| 44 |
+
"eval_micro-f1": 0.5540940480105229,
|
| 45 |
+
"eval_runtime": 14.835,
|
| 46 |
+
"eval_samples_per_second": 67.408,
|
| 47 |
+
"eval_steps_per_second": 8.426,
|
| 48 |
+
"step": 500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.53,
|
| 52 |
+
"learning_rate": 0.0007333333333333333,
|
| 53 |
+
"loss": 0.2043,
|
| 54 |
+
"step": 600
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.62,
|
| 58 |
+
"learning_rate": 0.000688888888888889,
|
| 59 |
+
"loss": 0.2019,
|
| 60 |
+
"step": 700
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.71,
|
| 64 |
+
"learning_rate": 0.0006444444444444444,
|
| 65 |
+
"loss": 0.2058,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.8,
|
| 70 |
+
"learning_rate": 0.0006,
|
| 71 |
+
"loss": 0.2043,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.89,
|
| 76 |
+
"learning_rate": 0.0005555555555555556,
|
| 77 |
+
"loss": 0.1826,
|
| 78 |
+
"step": 1000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.89,
|
| 82 |
+
"eval_loss": 0.3090105652809143,
|
| 83 |
+
"eval_macro-f1": 0.40861377528604365,
|
| 84 |
+
"eval_micro-f1": 0.5695569729357007,
|
| 85 |
+
"eval_runtime": 14.9867,
|
| 86 |
+
"eval_samples_per_second": 66.726,
|
| 87 |
+
"eval_steps_per_second": 8.341,
|
| 88 |
+
"step": 1000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.98,
|
| 92 |
+
"learning_rate": 0.0005111111111111111,
|
| 93 |
+
"loss": 0.1933,
|
| 94 |
+
"step": 1100
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.07,
|
| 98 |
+
"learning_rate": 0.00046666666666666666,
|
| 99 |
+
"loss": 0.1791,
|
| 100 |
+
"step": 1200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.16,
|
| 104 |
+
"learning_rate": 0.0004222222222222222,
|
| 105 |
+
"loss": 0.1879,
|
| 106 |
+
"step": 1300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.24,
|
| 110 |
+
"learning_rate": 0.00037777777777777777,
|
| 111 |
+
"loss": 0.1739,
|
| 112 |
+
"step": 1400
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.33,
|
| 116 |
+
"learning_rate": 0.0003333333333333333,
|
| 117 |
+
"loss": 0.18,
|
| 118 |
+
"step": 1500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.33,
|
| 122 |
+
"eval_loss": 0.2883451581001282,
|
| 123 |
+
"eval_macro-f1": 0.4507416671361624,
|
| 124 |
+
"eval_micro-f1": 0.5963412549153702,
|
| 125 |
+
"eval_runtime": 15.127,
|
| 126 |
+
"eval_samples_per_second": 66.107,
|
| 127 |
+
"eval_steps_per_second": 8.263,
|
| 128 |
+
"step": 1500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.42,
|
| 132 |
+
"learning_rate": 0.0002888888888888889,
|
| 133 |
+
"loss": 0.179,
|
| 134 |
+
"step": 1600
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.51,
|
| 138 |
+
"learning_rate": 0.00024444444444444443,
|
| 139 |
+
"loss": 0.1729,
|
| 140 |
+
"step": 1700
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.6,
|
| 144 |
+
"learning_rate": 0.0002,
|
| 145 |
+
"loss": 0.1754,
|
| 146 |
+
"step": 1800
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.69,
|
| 150 |
+
"learning_rate": 0.00015555555555555556,
|
| 151 |
+
"loss": 0.1724,
|
| 152 |
+
"step": 1900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.78,
|
| 156 |
+
"learning_rate": 0.0001111111111111111,
|
| 157 |
+
"loss": 0.1669,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.78,
|
| 162 |
+
"eval_loss": 0.27745190262794495,
|
| 163 |
+
"eval_macro-f1": 0.4739843869881502,
|
| 164 |
+
"eval_micro-f1": 0.6247038917089679,
|
| 165 |
+
"eval_runtime": 15.1069,
|
| 166 |
+
"eval_samples_per_second": 66.195,
|
| 167 |
+
"eval_steps_per_second": 8.274,
|
| 168 |
+
"step": 2000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.87,
|
| 172 |
+
"learning_rate": 6.666666666666667e-05,
|
| 173 |
+
"loss": 0.1794,
|
| 174 |
+
"step": 2100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.96,
|
| 178 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 179 |
+
"loss": 0.1755,
|
| 180 |
+
"step": 2200
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.0,
|
| 184 |
+
"step": 2250,
|
| 185 |
+
"total_flos": 719017869312000.0,
|
| 186 |
+
"train_loss": 0.19799817996554905,
|
| 187 |
+
"train_runtime": 356.7954,
|
| 188 |
+
"train_samples_per_second": 50.449,
|
| 189 |
+
"train_steps_per_second": 6.306
|
| 190 |
+
}
|
| 191 |
+
],
|
| 192 |
+
"max_steps": 2250,
|
| 193 |
+
"num_train_epochs": 2,
|
| 194 |
+
"total_flos": 719017869312000.0,
|
| 195 |
+
"trial_name": null,
|
| 196 |
+
"trial_params": null
|
| 197 |
+
}
|