End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +628 -0
README.md
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
---
|
|
|
|
| 2 |
tags:
|
| 3 |
- generated_from_trainer
|
| 4 |
model-index:
|
|
@@ -11,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# hibial-bert-i3-mlm
|
| 13 |
|
| 14 |
-
This model
|
| 15 |
|
| 16 |
## Model description
|
| 17 |
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model: /content/hier-bert-pytorch/data/hibial-model
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
model-index:
|
|
|
|
| 12 |
|
| 13 |
# hibial-bert-i3-mlm
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [/content/hier-bert-pytorch/data/hibial-model](https://huggingface.co//content/hier-bert-pytorch/data/hibial-model) on an unknown dataset.
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.31,
|
| 3 |
+
"train_loss": 3.758148254394531,
|
| 4 |
+
"train_runtime": 13724.031,
|
| 5 |
+
"train_samples": 4129855,
|
| 6 |
+
"train_samples_per_second": 93.267,
|
| 7 |
+
"train_steps_per_second": 0.364
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.31,
|
| 3 |
+
"train_loss": 3.758148254394531,
|
| 4 |
+
"train_runtime": 13724.031,
|
| 5 |
+
"train_samples": 4129855,
|
| 6 |
+
"train_samples_per_second": 93.267,
|
| 7 |
+
"train_steps_per_second": 0.364
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,628 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3099381673356165,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 9.7906,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 4e-05,
|
| 20 |
+
"loss": 7.9188,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 6e-05,
|
| 26 |
+
"loss": 6.8487,
|
| 27 |
+
"step": 150
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 8e-05,
|
| 32 |
+
"loss": 6.0994,
|
| 33 |
+
"step": 200
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 5.7442,
|
| 39 |
+
"step": 250
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 0.00012,
|
| 44 |
+
"loss": 5.5492,
|
| 45 |
+
"step": 300
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 0.00014000000000000001,
|
| 50 |
+
"loss": 5.4021,
|
| 51 |
+
"step": 350
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 0.00016,
|
| 56 |
+
"loss": 5.2486,
|
| 57 |
+
"step": 400
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00017999999999999998,
|
| 62 |
+
"loss": 5.128,
|
| 63 |
+
"step": 450
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.0002,
|
| 68 |
+
"loss": 5.0186,
|
| 69 |
+
"step": 500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 0.00022,
|
| 74 |
+
"loss": 4.9228,
|
| 75 |
+
"step": 550
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 0.00024,
|
| 80 |
+
"loss": 4.8538,
|
| 81 |
+
"step": 600
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.00026000000000000003,
|
| 86 |
+
"loss": 4.7268,
|
| 87 |
+
"step": 650
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 0.00028000000000000003,
|
| 92 |
+
"loss": 4.6724,
|
| 93 |
+
"step": 700
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 0.0003,
|
| 98 |
+
"loss": 4.5713,
|
| 99 |
+
"step": 750
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00032,
|
| 104 |
+
"loss": 4.488,
|
| 105 |
+
"step": 800
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 0.00034,
|
| 110 |
+
"loss": 4.4322,
|
| 111 |
+
"step": 850
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 0.00035999999999999997,
|
| 116 |
+
"loss": 4.3735,
|
| 117 |
+
"step": 900
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.06,
|
| 121 |
+
"learning_rate": 0.00038,
|
| 122 |
+
"loss": 4.3239,
|
| 123 |
+
"step": 950
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06,
|
| 127 |
+
"learning_rate": 0.0004,
|
| 128 |
+
"loss": 4.254,
|
| 129 |
+
"step": 1000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07,
|
| 133 |
+
"learning_rate": 0.00042,
|
| 134 |
+
"loss": 4.2093,
|
| 135 |
+
"step": 1050
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 0.00044,
|
| 140 |
+
"loss": 4.1751,
|
| 141 |
+
"step": 1100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"learning_rate": 0.00046,
|
| 146 |
+
"loss": 4.11,
|
| 147 |
+
"step": 1150
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.07,
|
| 151 |
+
"learning_rate": 0.00048,
|
| 152 |
+
"loss": 4.0559,
|
| 153 |
+
"step": 1200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.08,
|
| 157 |
+
"learning_rate": 0.0005,
|
| 158 |
+
"loss": 4.0179,
|
| 159 |
+
"step": 1250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.08,
|
| 163 |
+
"learning_rate": 0.0005200000000000001,
|
| 164 |
+
"loss": 3.9553,
|
| 165 |
+
"step": 1300
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.08,
|
| 169 |
+
"learning_rate": 0.00054,
|
| 170 |
+
"loss": 3.8982,
|
| 171 |
+
"step": 1350
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09,
|
| 175 |
+
"learning_rate": 0.0005600000000000001,
|
| 176 |
+
"loss": 3.8803,
|
| 177 |
+
"step": 1400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09,
|
| 181 |
+
"learning_rate": 0.00058,
|
| 182 |
+
"loss": 3.865,
|
| 183 |
+
"step": 1450
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.09,
|
| 187 |
+
"learning_rate": 0.0006,
|
| 188 |
+
"loss": 3.8174,
|
| 189 |
+
"step": 1500
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1,
|
| 193 |
+
"learning_rate": 0.00062,
|
| 194 |
+
"loss": 3.8031,
|
| 195 |
+
"step": 1550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.1,
|
| 199 |
+
"learning_rate": 0.00064,
|
| 200 |
+
"loss": 3.7598,
|
| 201 |
+
"step": 1600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.1,
|
| 205 |
+
"learning_rate": 0.00066,
|
| 206 |
+
"loss": 3.7252,
|
| 207 |
+
"step": 1650
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.11,
|
| 211 |
+
"learning_rate": 0.00068,
|
| 212 |
+
"loss": 3.715,
|
| 213 |
+
"step": 1700
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11,
|
| 217 |
+
"learning_rate": 0.0007,
|
| 218 |
+
"loss": 3.6863,
|
| 219 |
+
"step": 1750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.11,
|
| 223 |
+
"learning_rate": 0.0007199999999999999,
|
| 224 |
+
"loss": 3.6786,
|
| 225 |
+
"step": 1800
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.11,
|
| 229 |
+
"learning_rate": 0.00074,
|
| 230 |
+
"loss": 3.6639,
|
| 231 |
+
"step": 1850
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.12,
|
| 235 |
+
"learning_rate": 0.00076,
|
| 236 |
+
"loss": 3.647,
|
| 237 |
+
"step": 1900
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.12,
|
| 241 |
+
"learning_rate": 0.0007800000000000001,
|
| 242 |
+
"loss": 3.6227,
|
| 243 |
+
"step": 1950
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.12,
|
| 247 |
+
"learning_rate": 0.0008,
|
| 248 |
+
"loss": 3.6005,
|
| 249 |
+
"step": 2000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.13,
|
| 253 |
+
"learning_rate": 0.00082,
|
| 254 |
+
"loss": 3.5824,
|
| 255 |
+
"step": 2050
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13,
|
| 259 |
+
"learning_rate": 0.00084,
|
| 260 |
+
"loss": 3.5806,
|
| 261 |
+
"step": 2100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.13,
|
| 265 |
+
"learning_rate": 0.00086,
|
| 266 |
+
"loss": 3.5605,
|
| 267 |
+
"step": 2150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.14,
|
| 271 |
+
"learning_rate": 0.00088,
|
| 272 |
+
"loss": 3.5325,
|
| 273 |
+
"step": 2200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.14,
|
| 277 |
+
"learning_rate": 0.0009000000000000001,
|
| 278 |
+
"loss": 3.5417,
|
| 279 |
+
"step": 2250
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.14,
|
| 283 |
+
"learning_rate": 0.00092,
|
| 284 |
+
"loss": 3.4979,
|
| 285 |
+
"step": 2300
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.15,
|
| 289 |
+
"learning_rate": 0.00094,
|
| 290 |
+
"loss": 3.5149,
|
| 291 |
+
"step": 2350
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.15,
|
| 295 |
+
"learning_rate": 0.00096,
|
| 296 |
+
"loss": 3.4793,
|
| 297 |
+
"step": 2400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.15,
|
| 301 |
+
"learning_rate": 0.00098,
|
| 302 |
+
"loss": 3.5049,
|
| 303 |
+
"step": 2450
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.15,
|
| 307 |
+
"learning_rate": 0.001,
|
| 308 |
+
"loss": 3.4843,
|
| 309 |
+
"step": 2500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.16,
|
| 313 |
+
"learning_rate": 0.00098,
|
| 314 |
+
"loss": 3.464,
|
| 315 |
+
"step": 2550
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.16,
|
| 319 |
+
"learning_rate": 0.00096,
|
| 320 |
+
"loss": 3.4651,
|
| 321 |
+
"step": 2600
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.16,
|
| 325 |
+
"learning_rate": 0.00094,
|
| 326 |
+
"loss": 3.4353,
|
| 327 |
+
"step": 2650
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.17,
|
| 331 |
+
"learning_rate": 0.00092,
|
| 332 |
+
"loss": 3.4139,
|
| 333 |
+
"step": 2700
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.17,
|
| 337 |
+
"learning_rate": 0.0009000000000000001,
|
| 338 |
+
"loss": 3.4013,
|
| 339 |
+
"step": 2750
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.17,
|
| 343 |
+
"learning_rate": 0.00088,
|
| 344 |
+
"loss": 3.3647,
|
| 345 |
+
"step": 2800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.18,
|
| 349 |
+
"learning_rate": 0.00086,
|
| 350 |
+
"loss": 3.3461,
|
| 351 |
+
"step": 2850
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.18,
|
| 355 |
+
"learning_rate": 0.00084,
|
| 356 |
+
"loss": 3.3339,
|
| 357 |
+
"step": 2900
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.18,
|
| 361 |
+
"learning_rate": 0.00082,
|
| 362 |
+
"loss": 3.3228,
|
| 363 |
+
"step": 2950
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.19,
|
| 367 |
+
"learning_rate": 0.0008,
|
| 368 |
+
"loss": 3.3239,
|
| 369 |
+
"step": 3000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.19,
|
| 373 |
+
"learning_rate": 0.0007800000000000001,
|
| 374 |
+
"loss": 3.2763,
|
| 375 |
+
"step": 3050
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.19,
|
| 379 |
+
"learning_rate": 0.00076,
|
| 380 |
+
"loss": 3.2408,
|
| 381 |
+
"step": 3100
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.2,
|
| 385 |
+
"learning_rate": 0.00074,
|
| 386 |
+
"loss": 3.231,
|
| 387 |
+
"step": 3150
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2,
|
| 391 |
+
"learning_rate": 0.0007199999999999999,
|
| 392 |
+
"loss": 3.2317,
|
| 393 |
+
"step": 3200
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.2,
|
| 397 |
+
"learning_rate": 0.0007,
|
| 398 |
+
"loss": 3.2208,
|
| 399 |
+
"step": 3250
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.2,
|
| 403 |
+
"learning_rate": 0.00068,
|
| 404 |
+
"loss": 3.1952,
|
| 405 |
+
"step": 3300
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.21,
|
| 409 |
+
"learning_rate": 0.00066,
|
| 410 |
+
"loss": 3.1825,
|
| 411 |
+
"step": 3350
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.21,
|
| 415 |
+
"learning_rate": 0.00064,
|
| 416 |
+
"loss": 3.184,
|
| 417 |
+
"step": 3400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.21,
|
| 421 |
+
"learning_rate": 0.00062,
|
| 422 |
+
"loss": 3.1452,
|
| 423 |
+
"step": 3450
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.22,
|
| 427 |
+
"learning_rate": 0.0006,
|
| 428 |
+
"loss": 3.1298,
|
| 429 |
+
"step": 3500
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.22,
|
| 433 |
+
"learning_rate": 0.00058,
|
| 434 |
+
"loss": 3.1244,
|
| 435 |
+
"step": 3550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.22,
|
| 439 |
+
"learning_rate": 0.0005600000000000001,
|
| 440 |
+
"loss": 3.114,
|
| 441 |
+
"step": 3600
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.23,
|
| 445 |
+
"learning_rate": 0.00054,
|
| 446 |
+
"loss": 3.1101,
|
| 447 |
+
"step": 3650
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.23,
|
| 451 |
+
"learning_rate": 0.0005200000000000001,
|
| 452 |
+
"loss": 3.0911,
|
| 453 |
+
"step": 3700
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.23,
|
| 457 |
+
"learning_rate": 0.0005,
|
| 458 |
+
"loss": 3.0805,
|
| 459 |
+
"step": 3750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.24,
|
| 463 |
+
"learning_rate": 0.00048,
|
| 464 |
+
"loss": 3.0669,
|
| 465 |
+
"step": 3800
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.24,
|
| 469 |
+
"learning_rate": 0.00046,
|
| 470 |
+
"loss": 3.0597,
|
| 471 |
+
"step": 3850
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.24,
|
| 475 |
+
"learning_rate": 0.00044,
|
| 476 |
+
"loss": 3.0388,
|
| 477 |
+
"step": 3900
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.24,
|
| 481 |
+
"learning_rate": 0.00042,
|
| 482 |
+
"loss": 3.0504,
|
| 483 |
+
"step": 3950
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.25,
|
| 487 |
+
"learning_rate": 0.0004,
|
| 488 |
+
"loss": 3.0222,
|
| 489 |
+
"step": 4000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.25,
|
| 493 |
+
"learning_rate": 0.00038,
|
| 494 |
+
"loss": 3.0142,
|
| 495 |
+
"step": 4050
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.25,
|
| 499 |
+
"learning_rate": 0.00035999999999999997,
|
| 500 |
+
"loss": 3.0106,
|
| 501 |
+
"step": 4100
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.26,
|
| 505 |
+
"learning_rate": 0.00034,
|
| 506 |
+
"loss": 3.0054,
|
| 507 |
+
"step": 4150
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.26,
|
| 511 |
+
"learning_rate": 0.00032,
|
| 512 |
+
"loss": 2.9846,
|
| 513 |
+
"step": 4200
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.26,
|
| 517 |
+
"learning_rate": 0.0003,
|
| 518 |
+
"loss": 2.967,
|
| 519 |
+
"step": 4250
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.27,
|
| 523 |
+
"learning_rate": 0.00028000000000000003,
|
| 524 |
+
"loss": 2.9749,
|
| 525 |
+
"step": 4300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.27,
|
| 529 |
+
"learning_rate": 0.00026000000000000003,
|
| 530 |
+
"loss": 2.9415,
|
| 531 |
+
"step": 4350
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.27,
|
| 535 |
+
"learning_rate": 0.00024,
|
| 536 |
+
"loss": 2.9486,
|
| 537 |
+
"step": 4400
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.28,
|
| 541 |
+
"learning_rate": 0.00022,
|
| 542 |
+
"loss": 2.9509,
|
| 543 |
+
"step": 4450
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.28,
|
| 547 |
+
"learning_rate": 0.0002,
|
| 548 |
+
"loss": 2.9261,
|
| 549 |
+
"step": 4500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.28,
|
| 553 |
+
"learning_rate": 0.00017999999999999998,
|
| 554 |
+
"loss": 2.9138,
|
| 555 |
+
"step": 4550
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.29,
|
| 559 |
+
"learning_rate": 0.00016,
|
| 560 |
+
"loss": 2.9356,
|
| 561 |
+
"step": 4600
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.29,
|
| 565 |
+
"learning_rate": 0.00014000000000000001,
|
| 566 |
+
"loss": 2.9036,
|
| 567 |
+
"step": 4650
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.29,
|
| 571 |
+
"learning_rate": 0.00012,
|
| 572 |
+
"loss": 2.8768,
|
| 573 |
+
"step": 4700
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.29,
|
| 577 |
+
"learning_rate": 0.0001,
|
| 578 |
+
"loss": 2.8875,
|
| 579 |
+
"step": 4750
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.3,
|
| 583 |
+
"learning_rate": 8e-05,
|
| 584 |
+
"loss": 2.8752,
|
| 585 |
+
"step": 4800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.3,
|
| 589 |
+
"learning_rate": 6e-05,
|
| 590 |
+
"loss": 2.8816,
|
| 591 |
+
"step": 4850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.3,
|
| 595 |
+
"learning_rate": 4e-05,
|
| 596 |
+
"loss": 2.8772,
|
| 597 |
+
"step": 4900
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.31,
|
| 601 |
+
"learning_rate": 2e-05,
|
| 602 |
+
"loss": 2.8658,
|
| 603 |
+
"step": 4950
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.31,
|
| 607 |
+
"learning_rate": 0.0,
|
| 608 |
+
"loss": 2.8755,
|
| 609 |
+
"step": 5000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.31,
|
| 613 |
+
"step": 5000,
|
| 614 |
+
"total_flos": 7.55408830464e+16,
|
| 615 |
+
"train_loss": 3.758148254394531,
|
| 616 |
+
"train_runtime": 13724.031,
|
| 617 |
+
"train_samples_per_second": 93.267,
|
| 618 |
+
"train_steps_per_second": 0.364
|
| 619 |
+
}
|
| 620 |
+
],
|
| 621 |
+
"logging_steps": 50,
|
| 622 |
+
"max_steps": 5000,
|
| 623 |
+
"num_train_epochs": 1,
|
| 624 |
+
"save_steps": 2000,
|
| 625 |
+
"total_flos": 7.55408830464e+16,
|
| 626 |
+
"trial_name": null,
|
| 627 |
+
"trial_params": null
|
| 628 |
+
}
|