Commit
•
226ebe1
1
Parent(s):
da435b9
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 +548 -0
README.md
CHANGED
|
@@ -3,6 +3,8 @@ license: mit
|
|
| 3 |
base_model: unicamp-dl/ptt5-base-t5-vocab
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: t5_base-qg-aap-nopeft
|
| 8 |
results: []
|
|
@@ -13,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# t5_base-qg-aap-nopeft
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 1.
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 3 |
base_model: unicamp-dl/ptt5-base-t5-vocab
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- tiagoblima/qg_squad_v1_pt
|
| 8 |
model-index:
|
| 9 |
- name: t5_base-qg-aap-nopeft
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# t5_base-qg-aap-nopeft
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [unicamp-dl/ptt5-base-t5-vocab](https://huggingface.co/unicamp-dl/ptt5-base-t5-vocab) on the tiagoblima/qg_squad_v1_pt dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.0926
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 1.0926330089569092,
|
| 4 |
+
"eval_runtime": 202.1767,
|
| 5 |
+
"eval_samples": 7223,
|
| 6 |
+
"eval_samples_per_second": 35.726,
|
| 7 |
+
"eval_steps_per_second": 8.933,
|
| 8 |
+
"train_loss": 0.9537819692403964,
|
| 9 |
+
"train_runtime": 26727.1522,
|
| 10 |
+
"train_samples": 51704,
|
| 11 |
+
"train_samples_per_second": 9.673,
|
| 12 |
+
"train_steps_per_second": 0.302
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_loss": 1.0926330089569092,
|
| 4 |
+
"eval_runtime": 202.1767,
|
| 5 |
+
"eval_samples": 7223,
|
| 6 |
+
"eval_samples_per_second": 35.726,
|
| 7 |
+
"eval_steps_per_second": 8.933
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.9537819692403964,
|
| 4 |
+
"train_runtime": 26727.1522,
|
| 5 |
+
"train_samples": 51704,
|
| 6 |
+
"train_samples_per_second": 9.673,
|
| 7 |
+
"train_steps_per_second": 0.302
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,548 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0926330089569092,
|
| 3 |
+
"best_model_checkpoint": "/temp/t5_base-qg-aap-nopeft/checkpoint-6464",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8080,
|
| 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": 9.876237623762377e-05,
|
| 14 |
+
"loss": 1.9841,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 9.752475247524753e-05,
|
| 20 |
+
"loss": 1.2569,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.19,
|
| 25 |
+
"learning_rate": 9.628712871287129e-05,
|
| 26 |
+
"loss": 1.2054,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.25,
|
| 31 |
+
"learning_rate": 9.504950495049505e-05,
|
| 32 |
+
"loss": 1.1704,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.31,
|
| 37 |
+
"learning_rate": 9.381188118811881e-05,
|
| 38 |
+
"loss": 1.1504,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.37,
|
| 43 |
+
"learning_rate": 9.257425742574259e-05,
|
| 44 |
+
"loss": 1.14,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.43,
|
| 49 |
+
"learning_rate": 9.133663366336635e-05,
|
| 50 |
+
"loss": 1.1303,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.5,
|
| 55 |
+
"learning_rate": 9.009900990099011e-05,
|
| 56 |
+
"loss": 1.1022,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.56,
|
| 61 |
+
"learning_rate": 8.886138613861387e-05,
|
| 62 |
+
"loss": 1.0985,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.62,
|
| 67 |
+
"learning_rate": 8.762376237623763e-05,
|
| 68 |
+
"loss": 1.0944,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.68,
|
| 73 |
+
"learning_rate": 8.638613861386139e-05,
|
| 74 |
+
"loss": 1.0762,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.74,
|
| 79 |
+
"learning_rate": 8.514851485148515e-05,
|
| 80 |
+
"loss": 1.0784,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.8,
|
| 85 |
+
"learning_rate": 8.391089108910891e-05,
|
| 86 |
+
"loss": 1.076,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.87,
|
| 91 |
+
"learning_rate": 8.267326732673268e-05,
|
| 92 |
+
"loss": 1.0672,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.93,
|
| 97 |
+
"learning_rate": 8.143564356435644e-05,
|
| 98 |
+
"loss": 1.0673,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.99,
|
| 103 |
+
"learning_rate": 8.019801980198021e-05,
|
| 104 |
+
"loss": 1.0561,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.0,
|
| 109 |
+
"eval_loss": 1.129577875137329,
|
| 110 |
+
"eval_runtime": 203.5144,
|
| 111 |
+
"eval_samples_per_second": 35.491,
|
| 112 |
+
"eval_steps_per_second": 8.874,
|
| 113 |
+
"step": 1616
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.05,
|
| 117 |
+
"learning_rate": 7.896039603960397e-05,
|
| 118 |
+
"loss": 0.989,
|
| 119 |
+
"step": 1700
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.11,
|
| 123 |
+
"learning_rate": 7.772277227722773e-05,
|
| 124 |
+
"loss": 0.9881,
|
| 125 |
+
"step": 1800
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.18,
|
| 129 |
+
"learning_rate": 7.64851485148515e-05,
|
| 130 |
+
"loss": 0.987,
|
| 131 |
+
"step": 1900
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.24,
|
| 135 |
+
"learning_rate": 7.524752475247526e-05,
|
| 136 |
+
"loss": 0.9849,
|
| 137 |
+
"step": 2000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.3,
|
| 141 |
+
"learning_rate": 7.400990099009902e-05,
|
| 142 |
+
"loss": 0.9807,
|
| 143 |
+
"step": 2100
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.36,
|
| 147 |
+
"learning_rate": 7.277227722772278e-05,
|
| 148 |
+
"loss": 0.9784,
|
| 149 |
+
"step": 2200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.42,
|
| 153 |
+
"learning_rate": 7.153465346534654e-05,
|
| 154 |
+
"loss": 0.9868,
|
| 155 |
+
"step": 2300
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.49,
|
| 159 |
+
"learning_rate": 7.02970297029703e-05,
|
| 160 |
+
"loss": 0.9792,
|
| 161 |
+
"step": 2400
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.55,
|
| 165 |
+
"learning_rate": 6.905940594059406e-05,
|
| 166 |
+
"loss": 0.988,
|
| 167 |
+
"step": 2500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.61,
|
| 171 |
+
"learning_rate": 6.782178217821783e-05,
|
| 172 |
+
"loss": 0.9806,
|
| 173 |
+
"step": 2600
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.67,
|
| 177 |
+
"learning_rate": 6.658415841584159e-05,
|
| 178 |
+
"loss": 0.9612,
|
| 179 |
+
"step": 2700
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.73,
|
| 183 |
+
"learning_rate": 6.534653465346535e-05,
|
| 184 |
+
"loss": 0.9632,
|
| 185 |
+
"step": 2800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.79,
|
| 189 |
+
"learning_rate": 6.410891089108911e-05,
|
| 190 |
+
"loss": 0.9861,
|
| 191 |
+
"step": 2900
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.86,
|
| 195 |
+
"learning_rate": 6.287128712871287e-05,
|
| 196 |
+
"loss": 0.968,
|
| 197 |
+
"step": 3000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.92,
|
| 201 |
+
"learning_rate": 6.163366336633663e-05,
|
| 202 |
+
"loss": 0.9727,
|
| 203 |
+
"step": 3100
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.98,
|
| 207 |
+
"learning_rate": 6.03960396039604e-05,
|
| 208 |
+
"loss": 0.9695,
|
| 209 |
+
"step": 3200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.0,
|
| 213 |
+
"eval_loss": 1.1012357473373413,
|
| 214 |
+
"eval_runtime": 203.1507,
|
| 215 |
+
"eval_samples_per_second": 35.555,
|
| 216 |
+
"eval_steps_per_second": 8.89,
|
| 217 |
+
"step": 3232
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.04,
|
| 221 |
+
"learning_rate": 5.915841584158416e-05,
|
| 222 |
+
"loss": 0.9333,
|
| 223 |
+
"step": 3300
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 2.1,
|
| 227 |
+
"learning_rate": 5.792079207920792e-05,
|
| 228 |
+
"loss": 0.9114,
|
| 229 |
+
"step": 3400
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.17,
|
| 233 |
+
"learning_rate": 5.668316831683168e-05,
|
| 234 |
+
"loss": 0.9173,
|
| 235 |
+
"step": 3500
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.23,
|
| 239 |
+
"learning_rate": 5.544554455445545e-05,
|
| 240 |
+
"loss": 0.9131,
|
| 241 |
+
"step": 3600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.29,
|
| 245 |
+
"learning_rate": 5.420792079207921e-05,
|
| 246 |
+
"loss": 0.9064,
|
| 247 |
+
"step": 3700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.35,
|
| 251 |
+
"learning_rate": 5.2970297029702974e-05,
|
| 252 |
+
"loss": 0.9113,
|
| 253 |
+
"step": 3800
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.41,
|
| 257 |
+
"learning_rate": 5.1732673267326735e-05,
|
| 258 |
+
"loss": 0.8984,
|
| 259 |
+
"step": 3900
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.48,
|
| 263 |
+
"learning_rate": 5.0495049504950497e-05,
|
| 264 |
+
"loss": 0.9149,
|
| 265 |
+
"step": 4000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.54,
|
| 269 |
+
"learning_rate": 4.925742574257426e-05,
|
| 270 |
+
"loss": 0.9041,
|
| 271 |
+
"step": 4100
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.6,
|
| 275 |
+
"learning_rate": 4.801980198019802e-05,
|
| 276 |
+
"loss": 0.9137,
|
| 277 |
+
"step": 4200
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.66,
|
| 281 |
+
"learning_rate": 4.678217821782179e-05,
|
| 282 |
+
"loss": 0.9117,
|
| 283 |
+
"step": 4300
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 2.72,
|
| 287 |
+
"learning_rate": 4.554455445544555e-05,
|
| 288 |
+
"loss": 0.9024,
|
| 289 |
+
"step": 4400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.78,
|
| 293 |
+
"learning_rate": 4.430693069306931e-05,
|
| 294 |
+
"loss": 0.914,
|
| 295 |
+
"step": 4500
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.85,
|
| 299 |
+
"learning_rate": 4.306930693069307e-05,
|
| 300 |
+
"loss": 0.9295,
|
| 301 |
+
"step": 4600
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 2.91,
|
| 305 |
+
"learning_rate": 4.183168316831683e-05,
|
| 306 |
+
"loss": 0.9088,
|
| 307 |
+
"step": 4700
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 2.97,
|
| 311 |
+
"learning_rate": 4.05940594059406e-05,
|
| 312 |
+
"loss": 0.9111,
|
| 313 |
+
"step": 4800
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 3.0,
|
| 317 |
+
"eval_loss": 1.0933234691619873,
|
| 318 |
+
"eval_runtime": 203.1992,
|
| 319 |
+
"eval_samples_per_second": 35.546,
|
| 320 |
+
"eval_steps_per_second": 8.888,
|
| 321 |
+
"step": 4848
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.03,
|
| 325 |
+
"learning_rate": 3.935643564356436e-05,
|
| 326 |
+
"loss": 0.8905,
|
| 327 |
+
"step": 4900
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.09,
|
| 331 |
+
"learning_rate": 3.811881188118812e-05,
|
| 332 |
+
"loss": 0.8628,
|
| 333 |
+
"step": 5000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.16,
|
| 337 |
+
"learning_rate": 3.6881188118811884e-05,
|
| 338 |
+
"loss": 0.8712,
|
| 339 |
+
"step": 5100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.22,
|
| 343 |
+
"learning_rate": 3.5643564356435645e-05,
|
| 344 |
+
"loss": 0.8545,
|
| 345 |
+
"step": 5200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.28,
|
| 349 |
+
"learning_rate": 3.440594059405941e-05,
|
| 350 |
+
"loss": 0.8793,
|
| 351 |
+
"step": 5300
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.34,
|
| 355 |
+
"learning_rate": 3.3168316831683175e-05,
|
| 356 |
+
"loss": 0.8677,
|
| 357 |
+
"step": 5400
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.4,
|
| 361 |
+
"learning_rate": 3.1930693069306936e-05,
|
| 362 |
+
"loss": 0.8716,
|
| 363 |
+
"step": 5500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.47,
|
| 367 |
+
"learning_rate": 3.06930693069307e-05,
|
| 368 |
+
"loss": 0.8708,
|
| 369 |
+
"step": 5600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.53,
|
| 373 |
+
"learning_rate": 2.9455445544554455e-05,
|
| 374 |
+
"loss": 0.8782,
|
| 375 |
+
"step": 5700
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.59,
|
| 379 |
+
"learning_rate": 2.8217821782178216e-05,
|
| 380 |
+
"loss": 0.8651,
|
| 381 |
+
"step": 5800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.65,
|
| 385 |
+
"learning_rate": 2.6980198019801985e-05,
|
| 386 |
+
"loss": 0.8597,
|
| 387 |
+
"step": 5900
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.71,
|
| 391 |
+
"learning_rate": 2.5742574257425746e-05,
|
| 392 |
+
"loss": 0.8516,
|
| 393 |
+
"step": 6000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.77,
|
| 397 |
+
"learning_rate": 2.4504950495049507e-05,
|
| 398 |
+
"loss": 0.8759,
|
| 399 |
+
"step": 6100
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 3.84,
|
| 403 |
+
"learning_rate": 2.326732673267327e-05,
|
| 404 |
+
"loss": 0.8631,
|
| 405 |
+
"step": 6200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 3.9,
|
| 409 |
+
"learning_rate": 2.202970297029703e-05,
|
| 410 |
+
"loss": 0.8636,
|
| 411 |
+
"step": 6300
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 3.96,
|
| 415 |
+
"learning_rate": 2.079207920792079e-05,
|
| 416 |
+
"loss": 0.8691,
|
| 417 |
+
"step": 6400
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.0,
|
| 421 |
+
"eval_loss": 1.0926330089569092,
|
| 422 |
+
"eval_runtime": 203.0632,
|
| 423 |
+
"eval_samples_per_second": 35.57,
|
| 424 |
+
"eval_steps_per_second": 8.894,
|
| 425 |
+
"step": 6464
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.02,
|
| 429 |
+
"learning_rate": 1.9554455445544556e-05,
|
| 430 |
+
"loss": 0.8573,
|
| 431 |
+
"step": 6500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.08,
|
| 435 |
+
"learning_rate": 1.8316831683168317e-05,
|
| 436 |
+
"loss": 0.8536,
|
| 437 |
+
"step": 6600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 4.15,
|
| 441 |
+
"learning_rate": 1.707920792079208e-05,
|
| 442 |
+
"loss": 0.8329,
|
| 443 |
+
"step": 6700
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.21,
|
| 447 |
+
"learning_rate": 1.5841584158415843e-05,
|
| 448 |
+
"loss": 0.8407,
|
| 449 |
+
"step": 6800
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.27,
|
| 453 |
+
"learning_rate": 1.4603960396039604e-05,
|
| 454 |
+
"loss": 0.8525,
|
| 455 |
+
"step": 6900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.33,
|
| 459 |
+
"learning_rate": 1.3366336633663367e-05,
|
| 460 |
+
"loss": 0.8473,
|
| 461 |
+
"step": 7000
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.39,
|
| 465 |
+
"learning_rate": 1.2128712871287128e-05,
|
| 466 |
+
"loss": 0.825,
|
| 467 |
+
"step": 7100
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.46,
|
| 471 |
+
"learning_rate": 1.0891089108910891e-05,
|
| 472 |
+
"loss": 0.834,
|
| 473 |
+
"step": 7200
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.52,
|
| 477 |
+
"learning_rate": 9.653465346534654e-06,
|
| 478 |
+
"loss": 0.8397,
|
| 479 |
+
"step": 7300
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.58,
|
| 483 |
+
"learning_rate": 8.415841584158417e-06,
|
| 484 |
+
"loss": 0.8436,
|
| 485 |
+
"step": 7400
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.64,
|
| 489 |
+
"learning_rate": 7.178217821782178e-06,
|
| 490 |
+
"loss": 0.8353,
|
| 491 |
+
"step": 7500
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.7,
|
| 495 |
+
"learning_rate": 5.940594059405941e-06,
|
| 496 |
+
"loss": 0.8332,
|
| 497 |
+
"step": 7600
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 4.76,
|
| 501 |
+
"learning_rate": 4.702970297029704e-06,
|
| 502 |
+
"loss": 0.8402,
|
| 503 |
+
"step": 7700
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.83,
|
| 507 |
+
"learning_rate": 3.4653465346534657e-06,
|
| 508 |
+
"loss": 0.8526,
|
| 509 |
+
"step": 7800
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 4.89,
|
| 513 |
+
"learning_rate": 2.227722772277228e-06,
|
| 514 |
+
"loss": 0.827,
|
| 515 |
+
"step": 7900
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.95,
|
| 519 |
+
"learning_rate": 9.900990099009902e-07,
|
| 520 |
+
"loss": 0.8543,
|
| 521 |
+
"step": 8000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 5.0,
|
| 525 |
+
"eval_loss": 1.0950443744659424,
|
| 526 |
+
"eval_runtime": 202.8265,
|
| 527 |
+
"eval_samples_per_second": 35.612,
|
| 528 |
+
"eval_steps_per_second": 8.904,
|
| 529 |
+
"step": 8080
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 5.0,
|
| 533 |
+
"step": 8080,
|
| 534 |
+
"total_flos": 1.574277938675712e+17,
|
| 535 |
+
"train_loss": 0.9537819692403964,
|
| 536 |
+
"train_runtime": 26727.1522,
|
| 537 |
+
"train_samples_per_second": 9.673,
|
| 538 |
+
"train_steps_per_second": 0.302
|
| 539 |
+
}
|
| 540 |
+
],
|
| 541 |
+
"logging_steps": 100,
|
| 542 |
+
"max_steps": 8080,
|
| 543 |
+
"num_train_epochs": 5,
|
| 544 |
+
"save_steps": 500,
|
| 545 |
+
"total_flos": 1.574277938675712e+17,
|
| 546 |
+
"trial_name": null,
|
| 547 |
+
"trial_params": null
|
| 548 |
+
}
|