Commit
•
7c92b20
1
Parent(s):
876fbfe
End of training
Browse files- README.md +4 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +482 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: apache-2.0
|
|
| 3 |
base_model: google/mt5-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: mt5_base-qg-af-oficial
|
| 8 |
results: []
|
|
@@ -13,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# mt5_base-qg-af-oficial
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 3 |
base_model: google/mt5-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- tiagoblima/preprocessed-du-qg-squadv1_pt
|
| 8 |
model-index:
|
| 9 |
- name: mt5_base-qg-af-oficial
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# mt5_base-qg-af-oficial
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the tiagoblima/preprocessed-du-qg-squadv1_pt dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.5155
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 1.5155326128005981,
|
| 4 |
+
"eval_runtime": 33.1897,
|
| 5 |
+
"eval_samples": 6511,
|
| 6 |
+
"eval_samples_per_second": 196.175,
|
| 7 |
+
"eval_steps_per_second": 3.073,
|
| 8 |
+
"train_loss": 1.7969476851205977,
|
| 9 |
+
"train_runtime": 4653.9626,
|
| 10 |
+
"train_samples": 44334,
|
| 11 |
+
"train_samples_per_second": 47.63,
|
| 12 |
+
"train_steps_per_second": 1.489
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 1.5155326128005981,
|
| 4 |
+
"eval_runtime": 33.1897,
|
| 5 |
+
"eval_samples": 6511,
|
| 6 |
+
"eval_samples_per_second": 196.175,
|
| 7 |
+
"eval_steps_per_second": 3.073
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 1.7969476851205977,
|
| 4 |
+
"train_runtime": 4653.9626,
|
| 5 |
+
"train_samples": 44334,
|
| 6 |
+
"train_samples_per_second": 47.63,
|
| 7 |
+
"train_steps_per_second": 1.489
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,482 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.5155326128005981,
|
| 3 |
+
"best_model_checkpoint": "/temp/mt5_base-qg-af-oficial/checkpoint-5544",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6930,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07,
|
| 13 |
+
"learning_rate": 9.855699855699856e-05,
|
| 14 |
+
"loss": 12.1403,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.14,
|
| 19 |
+
"learning_rate": 9.711399711399713e-05,
|
| 20 |
+
"loss": 3.3838,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.22,
|
| 25 |
+
"learning_rate": 9.567099567099568e-05,
|
| 26 |
+
"loss": 2.2366,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.29,
|
| 31 |
+
"learning_rate": 9.422799422799424e-05,
|
| 32 |
+
"loss": 2.1106,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.36,
|
| 37 |
+
"learning_rate": 9.278499278499279e-05,
|
| 38 |
+
"loss": 2.0552,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.43,
|
| 43 |
+
"learning_rate": 9.134199134199136e-05,
|
| 44 |
+
"loss": 2.0231,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.51,
|
| 49 |
+
"learning_rate": 8.98989898989899e-05,
|
| 50 |
+
"loss": 1.974,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.58,
|
| 55 |
+
"learning_rate": 8.845598845598845e-05,
|
| 56 |
+
"loss": 1.9583,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.65,
|
| 61 |
+
"learning_rate": 8.701298701298701e-05,
|
| 62 |
+
"loss": 1.8944,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.72,
|
| 67 |
+
"learning_rate": 8.556998556998557e-05,
|
| 68 |
+
"loss": 1.8719,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.79,
|
| 73 |
+
"learning_rate": 8.412698412698413e-05,
|
| 74 |
+
"loss": 1.8895,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.87,
|
| 79 |
+
"learning_rate": 8.268398268398268e-05,
|
| 80 |
+
"loss": 1.8459,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.94,
|
| 85 |
+
"learning_rate": 8.124098124098124e-05,
|
| 86 |
+
"loss": 1.8203,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.0,
|
| 91 |
+
"eval_loss": 1.6114802360534668,
|
| 92 |
+
"eval_runtime": 33.1219,
|
| 93 |
+
"eval_samples_per_second": 196.577,
|
| 94 |
+
"eval_steps_per_second": 3.08,
|
| 95 |
+
"step": 1386
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.01,
|
| 99 |
+
"learning_rate": 7.97979797979798e-05,
|
| 100 |
+
"loss": 1.8007,
|
| 101 |
+
"step": 1400
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.08,
|
| 105 |
+
"learning_rate": 7.835497835497836e-05,
|
| 106 |
+
"loss": 1.7247,
|
| 107 |
+
"step": 1500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.15,
|
| 111 |
+
"learning_rate": 7.691197691197691e-05,
|
| 112 |
+
"loss": 1.7288,
|
| 113 |
+
"step": 1600
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.23,
|
| 117 |
+
"learning_rate": 7.546897546897548e-05,
|
| 118 |
+
"loss": 1.7174,
|
| 119 |
+
"step": 1700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.3,
|
| 123 |
+
"learning_rate": 7.402597402597404e-05,
|
| 124 |
+
"loss": 1.6836,
|
| 125 |
+
"step": 1800
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.37,
|
| 129 |
+
"learning_rate": 7.258297258297259e-05,
|
| 130 |
+
"loss": 1.7096,
|
| 131 |
+
"step": 1900
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.44,
|
| 135 |
+
"learning_rate": 7.113997113997114e-05,
|
| 136 |
+
"loss": 1.681,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.52,
|
| 141 |
+
"learning_rate": 6.96969696969697e-05,
|
| 142 |
+
"loss": 1.6965,
|
| 143 |
+
"step": 2100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.59,
|
| 147 |
+
"learning_rate": 6.825396825396825e-05,
|
| 148 |
+
"loss": 1.6696,
|
| 149 |
+
"step": 2200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.66,
|
| 153 |
+
"learning_rate": 6.681096681096681e-05,
|
| 154 |
+
"loss": 1.6779,
|
| 155 |
+
"step": 2300
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.73,
|
| 159 |
+
"learning_rate": 6.536796536796536e-05,
|
| 160 |
+
"loss": 1.6736,
|
| 161 |
+
"step": 2400
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.8,
|
| 165 |
+
"learning_rate": 6.392496392496393e-05,
|
| 166 |
+
"loss": 1.6729,
|
| 167 |
+
"step": 2500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.88,
|
| 171 |
+
"learning_rate": 6.248196248196248e-05,
|
| 172 |
+
"loss": 1.6795,
|
| 173 |
+
"step": 2600
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.95,
|
| 177 |
+
"learning_rate": 6.103896103896104e-05,
|
| 178 |
+
"loss": 1.6624,
|
| 179 |
+
"step": 2700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.0,
|
| 183 |
+
"eval_loss": 1.5542315244674683,
|
| 184 |
+
"eval_runtime": 33.2024,
|
| 185 |
+
"eval_samples_per_second": 196.101,
|
| 186 |
+
"eval_steps_per_second": 3.072,
|
| 187 |
+
"step": 2772
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.02,
|
| 191 |
+
"learning_rate": 5.959595959595959e-05,
|
| 192 |
+
"loss": 1.6222,
|
| 193 |
+
"step": 2800
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.09,
|
| 197 |
+
"learning_rate": 5.815295815295816e-05,
|
| 198 |
+
"loss": 1.5908,
|
| 199 |
+
"step": 2900
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.16,
|
| 203 |
+
"learning_rate": 5.6709956709956715e-05,
|
| 204 |
+
"loss": 1.5692,
|
| 205 |
+
"step": 3000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.24,
|
| 209 |
+
"learning_rate": 5.526695526695527e-05,
|
| 210 |
+
"loss": 1.5753,
|
| 211 |
+
"step": 3100
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.31,
|
| 215 |
+
"learning_rate": 5.382395382395382e-05,
|
| 216 |
+
"loss": 1.5802,
|
| 217 |
+
"step": 3200
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.38,
|
| 221 |
+
"learning_rate": 5.2380952380952384e-05,
|
| 222 |
+
"loss": 1.5546,
|
| 223 |
+
"step": 3300
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.45,
|
| 227 |
+
"learning_rate": 5.093795093795094e-05,
|
| 228 |
+
"loss": 1.5665,
|
| 229 |
+
"step": 3400
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.53,
|
| 233 |
+
"learning_rate": 4.94949494949495e-05,
|
| 234 |
+
"loss": 1.5381,
|
| 235 |
+
"step": 3500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.6,
|
| 239 |
+
"learning_rate": 4.8051948051948054e-05,
|
| 240 |
+
"loss": 1.5634,
|
| 241 |
+
"step": 3600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.67,
|
| 245 |
+
"learning_rate": 4.6608946608946615e-05,
|
| 246 |
+
"loss": 1.5554,
|
| 247 |
+
"step": 3700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.74,
|
| 251 |
+
"learning_rate": 4.516594516594517e-05,
|
| 252 |
+
"loss": 1.5645,
|
| 253 |
+
"step": 3800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.81,
|
| 257 |
+
"learning_rate": 4.3722943722943724e-05,
|
| 258 |
+
"loss": 1.5652,
|
| 259 |
+
"step": 3900
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.89,
|
| 263 |
+
"learning_rate": 4.227994227994228e-05,
|
| 264 |
+
"loss": 1.5615,
|
| 265 |
+
"step": 4000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.96,
|
| 269 |
+
"learning_rate": 4.083694083694084e-05,
|
| 270 |
+
"loss": 1.5489,
|
| 271 |
+
"step": 4100
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 3.0,
|
| 275 |
+
"eval_loss": 1.5325491428375244,
|
| 276 |
+
"eval_runtime": 33.1544,
|
| 277 |
+
"eval_samples_per_second": 196.384,
|
| 278 |
+
"eval_steps_per_second": 3.077,
|
| 279 |
+
"step": 4158
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.03,
|
| 283 |
+
"learning_rate": 3.939393939393939e-05,
|
| 284 |
+
"loss": 1.5307,
|
| 285 |
+
"step": 4200
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 3.1,
|
| 289 |
+
"learning_rate": 3.7950937950937954e-05,
|
| 290 |
+
"loss": 1.4781,
|
| 291 |
+
"step": 4300
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 3.17,
|
| 295 |
+
"learning_rate": 3.650793650793651e-05,
|
| 296 |
+
"loss": 1.4875,
|
| 297 |
+
"step": 4400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.25,
|
| 301 |
+
"learning_rate": 3.506493506493507e-05,
|
| 302 |
+
"loss": 1.4927,
|
| 303 |
+
"step": 4500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.32,
|
| 307 |
+
"learning_rate": 3.3621933621933624e-05,
|
| 308 |
+
"loss": 1.4904,
|
| 309 |
+
"step": 4600
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.39,
|
| 313 |
+
"learning_rate": 3.217893217893218e-05,
|
| 314 |
+
"loss": 1.5048,
|
| 315 |
+
"step": 4700
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.46,
|
| 319 |
+
"learning_rate": 3.073593073593073e-05,
|
| 320 |
+
"loss": 1.4868,
|
| 321 |
+
"step": 4800
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.54,
|
| 325 |
+
"learning_rate": 2.9292929292929294e-05,
|
| 326 |
+
"loss": 1.4631,
|
| 327 |
+
"step": 4900
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.61,
|
| 331 |
+
"learning_rate": 2.7849927849927855e-05,
|
| 332 |
+
"loss": 1.4957,
|
| 333 |
+
"step": 5000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.68,
|
| 337 |
+
"learning_rate": 2.640692640692641e-05,
|
| 338 |
+
"loss": 1.488,
|
| 339 |
+
"step": 5100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.75,
|
| 343 |
+
"learning_rate": 2.4963924963924963e-05,
|
| 344 |
+
"loss": 1.4898,
|
| 345 |
+
"step": 5200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.82,
|
| 349 |
+
"learning_rate": 2.352092352092352e-05,
|
| 350 |
+
"loss": 1.4818,
|
| 351 |
+
"step": 5300
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.9,
|
| 355 |
+
"learning_rate": 2.207792207792208e-05,
|
| 356 |
+
"loss": 1.4967,
|
| 357 |
+
"step": 5400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.97,
|
| 361 |
+
"learning_rate": 2.0634920634920636e-05,
|
| 362 |
+
"loss": 1.4926,
|
| 363 |
+
"step": 5500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.0,
|
| 367 |
+
"eval_loss": 1.5155326128005981,
|
| 368 |
+
"eval_runtime": 33.2094,
|
| 369 |
+
"eval_samples_per_second": 196.059,
|
| 370 |
+
"eval_steps_per_second": 3.071,
|
| 371 |
+
"step": 5544
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 4.04,
|
| 375 |
+
"learning_rate": 1.919191919191919e-05,
|
| 376 |
+
"loss": 1.4528,
|
| 377 |
+
"step": 5600
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 4.11,
|
| 381 |
+
"learning_rate": 1.7748917748917752e-05,
|
| 382 |
+
"loss": 1.4396,
|
| 383 |
+
"step": 5700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.18,
|
| 387 |
+
"learning_rate": 1.630591630591631e-05,
|
| 388 |
+
"loss": 1.4457,
|
| 389 |
+
"step": 5800
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 4.26,
|
| 393 |
+
"learning_rate": 1.4862914862914865e-05,
|
| 394 |
+
"loss": 1.4471,
|
| 395 |
+
"step": 5900
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.33,
|
| 399 |
+
"learning_rate": 1.3419913419913421e-05,
|
| 400 |
+
"loss": 1.4543,
|
| 401 |
+
"step": 6000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.4,
|
| 405 |
+
"learning_rate": 1.1976911976911977e-05,
|
| 406 |
+
"loss": 1.4612,
|
| 407 |
+
"step": 6100
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.47,
|
| 411 |
+
"learning_rate": 1.0533910533910535e-05,
|
| 412 |
+
"loss": 1.4536,
|
| 413 |
+
"step": 6200
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.55,
|
| 417 |
+
"learning_rate": 9.090909090909091e-06,
|
| 418 |
+
"loss": 1.4451,
|
| 419 |
+
"step": 6300
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 4.62,
|
| 423 |
+
"learning_rate": 7.647907647907649e-06,
|
| 424 |
+
"loss": 1.4491,
|
| 425 |
+
"step": 6400
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.69,
|
| 429 |
+
"learning_rate": 6.204906204906205e-06,
|
| 430 |
+
"loss": 1.4394,
|
| 431 |
+
"step": 6500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.76,
|
| 435 |
+
"learning_rate": 4.7619047619047615e-06,
|
| 436 |
+
"loss": 1.4367,
|
| 437 |
+
"step": 6600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.83,
|
| 441 |
+
"learning_rate": 3.318903318903319e-06,
|
| 442 |
+
"loss": 1.445,
|
| 443 |
+
"step": 6700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.91,
|
| 447 |
+
"learning_rate": 1.875901875901876e-06,
|
| 448 |
+
"loss": 1.4478,
|
| 449 |
+
"step": 6800
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.98,
|
| 453 |
+
"learning_rate": 4.329004329004329e-07,
|
| 454 |
+
"loss": 1.4687,
|
| 455 |
+
"step": 6900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.0,
|
| 459 |
+
"eval_loss": 1.5195423364639282,
|
| 460 |
+
"eval_runtime": 33.3056,
|
| 461 |
+
"eval_samples_per_second": 195.493,
|
| 462 |
+
"eval_steps_per_second": 3.063,
|
| 463 |
+
"step": 6930
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 5.0,
|
| 467 |
+
"step": 6930,
|
| 468 |
+
"total_flos": 2.6579255601659904e+17,
|
| 469 |
+
"train_loss": 1.7969476851205977,
|
| 470 |
+
"train_runtime": 4653.9626,
|
| 471 |
+
"train_samples_per_second": 47.63,
|
| 472 |
+
"train_steps_per_second": 1.489
|
| 473 |
+
}
|
| 474 |
+
],
|
| 475 |
+
"logging_steps": 100,
|
| 476 |
+
"max_steps": 6930,
|
| 477 |
+
"num_train_epochs": 5,
|
| 478 |
+
"save_steps": 500,
|
| 479 |
+
"total_flos": 2.6579255601659904e+17,
|
| 480 |
+
"trial_name": null,
|
| 481 |
+
"trial_params": null
|
| 482 |
+
}
|