Commit
•
f0bd9da
1
Parent(s):
80d2383
End of training
Browse files- README.md +3 -1
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +548 -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-aap-nopeft
|
| 8 |
results: []
|
|
@@ -13,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# mt5_base-qg-aap-nopeft
|
| 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: 1.3944
|
| 19 |
|
|
|
|
| 3 |
base_model: google/mt5-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- tiagoblima/qg_squad_v1_pt
|
| 8 |
model-index:
|
| 9 |
- name: mt5_base-qg-aap-nopeft
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# mt5_base-qg-aap-nopeft
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the tiagoblima/qg_squad_v1_pt dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 1.3944
|
| 21 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 1.3943793773651123,
|
| 4 |
+
"eval_runtime": 114.1558,
|
| 5 |
+
"eval_samples": 3267,
|
| 6 |
+
"eval_samples_per_second": 28.619,
|
| 7 |
+
"eval_steps_per_second": 7.157,
|
| 8 |
+
"train_loss": 1.6016051414655088,
|
| 9 |
+
"train_runtime": 36995.0307,
|
| 10 |
+
"train_samples": 51704,
|
| 11 |
+
"train_samples_per_second": 6.988,
|
| 12 |
+
"train_steps_per_second": 0.218
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 1.3943793773651123,
|
| 4 |
+
"eval_runtime": 114.1558,
|
| 5 |
+
"eval_samples": 3267,
|
| 6 |
+
"eval_samples_per_second": 28.619,
|
| 7 |
+
"eval_steps_per_second": 7.157
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 1.6016051414655088,
|
| 4 |
+
"train_runtime": 36995.0307,
|
| 5 |
+
"train_samples": 51704,
|
| 6 |
+
"train_samples_per_second": 6.988,
|
| 7 |
+
"train_steps_per_second": 0.218
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,548 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3943793773651123,
|
| 3 |
+
"best_model_checkpoint": "/temp/mt5_base-qg-aap-nopeft/checkpoint-8075",
|
| 4 |
+
"epoch": 4.997679096394863,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8075,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 9.876160990712075e-05,
|
| 14 |
+
"loss": 9.0929,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 9.75232198142415e-05,
|
| 20 |
+
"loss": 2.5798,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.19,
|
| 25 |
+
"learning_rate": 9.628482972136223e-05,
|
| 26 |
+
"loss": 2.1619,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.25,
|
| 31 |
+
"learning_rate": 9.504643962848298e-05,
|
| 32 |
+
"loss": 2.0397,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.31,
|
| 37 |
+
"learning_rate": 9.380804953560372e-05,
|
| 38 |
+
"loss": 1.979,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.37,
|
| 43 |
+
"learning_rate": 9.256965944272447e-05,
|
| 44 |
+
"loss": 1.9337,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.43,
|
| 49 |
+
"learning_rate": 9.13312693498452e-05,
|
| 50 |
+
"loss": 1.8767,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5,
|
| 55 |
+
"learning_rate": 9.009287925696595e-05,
|
| 56 |
+
"loss": 1.8497,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.56,
|
| 61 |
+
"learning_rate": 8.885448916408669e-05,
|
| 62 |
+
"loss": 1.7893,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.62,
|
| 67 |
+
"learning_rate": 8.761609907120744e-05,
|
| 68 |
+
"loss": 1.802,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.68,
|
| 73 |
+
"learning_rate": 8.637770897832817e-05,
|
| 74 |
+
"loss": 1.7475,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.74,
|
| 79 |
+
"learning_rate": 8.513931888544892e-05,
|
| 80 |
+
"loss": 1.7353,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.8,
|
| 85 |
+
"learning_rate": 8.390092879256966e-05,
|
| 86 |
+
"loss": 1.7565,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.87,
|
| 91 |
+
"learning_rate": 8.266253869969041e-05,
|
| 92 |
+
"loss": 1.7261,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.93,
|
| 97 |
+
"learning_rate": 8.142414860681114e-05,
|
| 98 |
+
"loss": 1.7092,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.99,
|
| 103 |
+
"learning_rate": 8.01857585139319e-05,
|
| 104 |
+
"loss": 1.6835,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.0,
|
| 109 |
+
"eval_loss": 1.4690113067626953,
|
| 110 |
+
"eval_runtime": 114.1107,
|
| 111 |
+
"eval_samples_per_second": 28.63,
|
| 112 |
+
"eval_steps_per_second": 7.16,
|
| 113 |
+
"step": 1615
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.05,
|
| 117 |
+
"learning_rate": 7.894736842105263e-05,
|
| 118 |
+
"loss": 1.5934,
|
| 119 |
+
"step": 1700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.11,
|
| 123 |
+
"learning_rate": 7.770897832817338e-05,
|
| 124 |
+
"loss": 1.6005,
|
| 125 |
+
"step": 1800
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.18,
|
| 129 |
+
"learning_rate": 7.647058823529411e-05,
|
| 130 |
+
"loss": 1.5843,
|
| 131 |
+
"step": 1900
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.24,
|
| 135 |
+
"learning_rate": 7.523219814241487e-05,
|
| 136 |
+
"loss": 1.5981,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.3,
|
| 141 |
+
"learning_rate": 7.39938080495356e-05,
|
| 142 |
+
"loss": 1.5642,
|
| 143 |
+
"step": 2100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.36,
|
| 147 |
+
"learning_rate": 7.275541795665635e-05,
|
| 148 |
+
"loss": 1.5595,
|
| 149 |
+
"step": 2200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.42,
|
| 153 |
+
"learning_rate": 7.15170278637771e-05,
|
| 154 |
+
"loss": 1.5664,
|
| 155 |
+
"step": 2300
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.49,
|
| 159 |
+
"learning_rate": 7.027863777089784e-05,
|
| 160 |
+
"loss": 1.5509,
|
| 161 |
+
"step": 2400
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.55,
|
| 165 |
+
"learning_rate": 6.904024767801857e-05,
|
| 166 |
+
"loss": 1.5532,
|
| 167 |
+
"step": 2500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.61,
|
| 171 |
+
"learning_rate": 6.780185758513932e-05,
|
| 172 |
+
"loss": 1.5457,
|
| 173 |
+
"step": 2600
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.67,
|
| 177 |
+
"learning_rate": 6.656346749226007e-05,
|
| 178 |
+
"loss": 1.5318,
|
| 179 |
+
"step": 2700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.73,
|
| 183 |
+
"learning_rate": 6.532507739938081e-05,
|
| 184 |
+
"loss": 1.5343,
|
| 185 |
+
"step": 2800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.79,
|
| 189 |
+
"learning_rate": 6.408668730650154e-05,
|
| 190 |
+
"loss": 1.5509,
|
| 191 |
+
"step": 2900
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.86,
|
| 195 |
+
"learning_rate": 6.28482972136223e-05,
|
| 196 |
+
"loss": 1.5316,
|
| 197 |
+
"step": 3000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.92,
|
| 201 |
+
"learning_rate": 6.160990712074304e-05,
|
| 202 |
+
"loss": 1.527,
|
| 203 |
+
"step": 3100
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.98,
|
| 207 |
+
"learning_rate": 6.0371517027863775e-05,
|
| 208 |
+
"loss": 1.5342,
|
| 209 |
+
"step": 3200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.0,
|
| 213 |
+
"eval_loss": 1.4252674579620361,
|
| 214 |
+
"eval_runtime": 113.4293,
|
| 215 |
+
"eval_samples_per_second": 28.802,
|
| 216 |
+
"eval_steps_per_second": 7.203,
|
| 217 |
+
"step": 3231
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.04,
|
| 221 |
+
"learning_rate": 5.913312693498453e-05,
|
| 222 |
+
"loss": 1.4687,
|
| 223 |
+
"step": 3300
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.1,
|
| 227 |
+
"learning_rate": 5.789473684210527e-05,
|
| 228 |
+
"loss": 1.4445,
|
| 229 |
+
"step": 3400
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.17,
|
| 233 |
+
"learning_rate": 5.6656346749226006e-05,
|
| 234 |
+
"loss": 1.4528,
|
| 235 |
+
"step": 3500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.23,
|
| 239 |
+
"learning_rate": 5.5417956656346745e-05,
|
| 240 |
+
"loss": 1.4412,
|
| 241 |
+
"step": 3600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.29,
|
| 245 |
+
"learning_rate": 5.41795665634675e-05,
|
| 246 |
+
"loss": 1.434,
|
| 247 |
+
"step": 3700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.35,
|
| 251 |
+
"learning_rate": 5.294117647058824e-05,
|
| 252 |
+
"loss": 1.4412,
|
| 253 |
+
"step": 3800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.41,
|
| 257 |
+
"learning_rate": 5.170278637770898e-05,
|
| 258 |
+
"loss": 1.4254,
|
| 259 |
+
"step": 3900
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.48,
|
| 263 |
+
"learning_rate": 5.046439628482973e-05,
|
| 264 |
+
"loss": 1.4442,
|
| 265 |
+
"step": 4000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.54,
|
| 269 |
+
"learning_rate": 4.922600619195047e-05,
|
| 270 |
+
"loss": 1.4194,
|
| 271 |
+
"step": 4100
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.6,
|
| 275 |
+
"learning_rate": 4.798761609907121e-05,
|
| 276 |
+
"loss": 1.447,
|
| 277 |
+
"step": 4200
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.66,
|
| 281 |
+
"learning_rate": 4.6749226006191954e-05,
|
| 282 |
+
"loss": 1.4215,
|
| 283 |
+
"step": 4300
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.72,
|
| 287 |
+
"learning_rate": 4.551083591331269e-05,
|
| 288 |
+
"loss": 1.4179,
|
| 289 |
+
"step": 4400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.79,
|
| 293 |
+
"learning_rate": 4.427244582043344e-05,
|
| 294 |
+
"loss": 1.4311,
|
| 295 |
+
"step": 4500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.85,
|
| 299 |
+
"learning_rate": 4.303405572755418e-05,
|
| 300 |
+
"loss": 1.4638,
|
| 301 |
+
"step": 4600
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.91,
|
| 305 |
+
"learning_rate": 4.1795665634674924e-05,
|
| 306 |
+
"loss": 1.4279,
|
| 307 |
+
"step": 4700
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.97,
|
| 311 |
+
"learning_rate": 4.055727554179567e-05,
|
| 312 |
+
"loss": 1.4247,
|
| 313 |
+
"step": 4800
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.0,
|
| 317 |
+
"eval_loss": 1.404792308807373,
|
| 318 |
+
"eval_runtime": 113.7341,
|
| 319 |
+
"eval_samples_per_second": 28.725,
|
| 320 |
+
"eval_steps_per_second": 7.183,
|
| 321 |
+
"step": 4847
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.03,
|
| 325 |
+
"learning_rate": 3.931888544891641e-05,
|
| 326 |
+
"loss": 1.3985,
|
| 327 |
+
"step": 4900
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.09,
|
| 331 |
+
"learning_rate": 3.8080495356037155e-05,
|
| 332 |
+
"loss": 1.3469,
|
| 333 |
+
"step": 5000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.16,
|
| 337 |
+
"learning_rate": 3.6842105263157895e-05,
|
| 338 |
+
"loss": 1.3738,
|
| 339 |
+
"step": 5100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.22,
|
| 343 |
+
"learning_rate": 3.560371517027864e-05,
|
| 344 |
+
"loss": 1.3448,
|
| 345 |
+
"step": 5200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.28,
|
| 349 |
+
"learning_rate": 3.436532507739939e-05,
|
| 350 |
+
"loss": 1.3751,
|
| 351 |
+
"step": 5300
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.34,
|
| 355 |
+
"learning_rate": 3.3126934984520126e-05,
|
| 356 |
+
"loss": 1.3738,
|
| 357 |
+
"step": 5400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.4,
|
| 361 |
+
"learning_rate": 3.188854489164087e-05,
|
| 362 |
+
"loss": 1.3731,
|
| 363 |
+
"step": 5500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.47,
|
| 367 |
+
"learning_rate": 3.065015479876161e-05,
|
| 368 |
+
"loss": 1.3676,
|
| 369 |
+
"step": 5600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.53,
|
| 373 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 374 |
+
"loss": 1.3766,
|
| 375 |
+
"step": 5700
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.59,
|
| 379 |
+
"learning_rate": 2.8173374613003096e-05,
|
| 380 |
+
"loss": 1.3597,
|
| 381 |
+
"step": 5800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.65,
|
| 385 |
+
"learning_rate": 2.693498452012384e-05,
|
| 386 |
+
"loss": 1.3505,
|
| 387 |
+
"step": 5900
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.71,
|
| 391 |
+
"learning_rate": 2.5696594427244585e-05,
|
| 392 |
+
"loss": 1.3309,
|
| 393 |
+
"step": 6000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.78,
|
| 397 |
+
"learning_rate": 2.4458204334365324e-05,
|
| 398 |
+
"loss": 1.3837,
|
| 399 |
+
"step": 6100
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.84,
|
| 403 |
+
"learning_rate": 2.3219814241486067e-05,
|
| 404 |
+
"loss": 1.3533,
|
| 405 |
+
"step": 6200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.9,
|
| 409 |
+
"learning_rate": 2.1981424148606813e-05,
|
| 410 |
+
"loss": 1.3464,
|
| 411 |
+
"step": 6300
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.96,
|
| 415 |
+
"learning_rate": 2.0743034055727555e-05,
|
| 416 |
+
"loss": 1.3656,
|
| 417 |
+
"step": 6400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.0,
|
| 421 |
+
"eval_loss": 1.395339846611023,
|
| 422 |
+
"eval_runtime": 113.8926,
|
| 423 |
+
"eval_samples_per_second": 28.685,
|
| 424 |
+
"eval_steps_per_second": 7.173,
|
| 425 |
+
"step": 6463
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.02,
|
| 429 |
+
"learning_rate": 1.9504643962848298e-05,
|
| 430 |
+
"loss": 1.3372,
|
| 431 |
+
"step": 6500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.08,
|
| 435 |
+
"learning_rate": 1.826625386996904e-05,
|
| 436 |
+
"loss": 1.3373,
|
| 437 |
+
"step": 6600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.15,
|
| 441 |
+
"learning_rate": 1.7027863777089783e-05,
|
| 442 |
+
"loss": 1.3204,
|
| 443 |
+
"step": 6700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.21,
|
| 447 |
+
"learning_rate": 1.5789473684210526e-05,
|
| 448 |
+
"loss": 1.3226,
|
| 449 |
+
"step": 6800
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.27,
|
| 453 |
+
"learning_rate": 1.4551083591331268e-05,
|
| 454 |
+
"loss": 1.3357,
|
| 455 |
+
"step": 6900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.33,
|
| 459 |
+
"learning_rate": 1.3312693498452014e-05,
|
| 460 |
+
"loss": 1.3274,
|
| 461 |
+
"step": 7000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.39,
|
| 465 |
+
"learning_rate": 1.2074303405572757e-05,
|
| 466 |
+
"loss": 1.3031,
|
| 467 |
+
"step": 7100
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.46,
|
| 471 |
+
"learning_rate": 1.08359133126935e-05,
|
| 472 |
+
"loss": 1.3148,
|
| 473 |
+
"step": 7200
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.52,
|
| 477 |
+
"learning_rate": 9.597523219814242e-06,
|
| 478 |
+
"loss": 1.3216,
|
| 479 |
+
"step": 7300
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.58,
|
| 483 |
+
"learning_rate": 8.359133126934985e-06,
|
| 484 |
+
"loss": 1.312,
|
| 485 |
+
"step": 7400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.64,
|
| 489 |
+
"learning_rate": 7.120743034055728e-06,
|
| 490 |
+
"loss": 1.2973,
|
| 491 |
+
"step": 7500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.7,
|
| 495 |
+
"learning_rate": 5.882352941176471e-06,
|
| 496 |
+
"loss": 1.3029,
|
| 497 |
+
"step": 7600
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.77,
|
| 501 |
+
"learning_rate": 4.643962848297214e-06,
|
| 502 |
+
"loss": 1.3188,
|
| 503 |
+
"step": 7700
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.83,
|
| 507 |
+
"learning_rate": 3.4055727554179566e-06,
|
| 508 |
+
"loss": 1.3382,
|
| 509 |
+
"step": 7800
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.89,
|
| 513 |
+
"learning_rate": 2.1671826625387e-06,
|
| 514 |
+
"loss": 1.3042,
|
| 515 |
+
"step": 7900
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.95,
|
| 519 |
+
"learning_rate": 9.287925696594427e-07,
|
| 520 |
+
"loss": 1.3288,
|
| 521 |
+
"step": 8000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 5.0,
|
| 525 |
+
"eval_loss": 1.3943793773651123,
|
| 526 |
+
"eval_runtime": 114.1254,
|
| 527 |
+
"eval_samples_per_second": 28.626,
|
| 528 |
+
"eval_steps_per_second": 7.159,
|
| 529 |
+
"step": 8075
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 5.0,
|
| 533 |
+
"step": 8075,
|
| 534 |
+
"total_flos": 3.098335204343808e+17,
|
| 535 |
+
"train_loss": 1.6016051414655088,
|
| 536 |
+
"train_runtime": 36995.0307,
|
| 537 |
+
"train_samples_per_second": 6.988,
|
| 538 |
+
"train_steps_per_second": 0.218
|
| 539 |
+
}
|
| 540 |
+
],
|
| 541 |
+
"logging_steps": 100,
|
| 542 |
+
"max_steps": 8075,
|
| 543 |
+
"num_train_epochs": 5,
|
| 544 |
+
"save_steps": 500,
|
| 545 |
+
"total_flos": 3.098335204343808e+17,
|
| 546 |
+
"trial_name": null,
|
| 547 |
+
"trial_params": null
|
| 548 |
+
}
|