Commit
·
2d1bb30
1
Parent(s):
9ebbbb3
Updated model
Browse files- README.md +52 -0
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +448 -0
README.md
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: BizConsultant
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# BizConsultant
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
| 16 |
+
|
| 17 |
+
## Model description
|
| 18 |
+
|
| 19 |
+
More information needed
|
| 20 |
+
|
| 21 |
+
## Intended uses & limitations
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Training and evaluation data
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
### Training hyperparameters
|
| 32 |
+
|
| 33 |
+
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 0.002
|
| 35 |
+
- train_batch_size: 1
|
| 36 |
+
- eval_batch_size: 8
|
| 37 |
+
- seed: 42
|
| 38 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
+
- lr_scheduler_type: linear
|
| 40 |
+
- lr_scheduler_warmup_steps: 20
|
| 41 |
+
- training_steps: 14000
|
| 42 |
+
|
| 43 |
+
### Training results
|
| 44 |
+
|
| 45 |
+
|
| 46 |
+
|
| 47 |
+
### Framework versions
|
| 48 |
+
|
| 49 |
+
- Transformers 4.33.0.dev0
|
| 50 |
+
- Pytorch 2.0.0
|
| 51 |
+
- Datasets 2.14.4
|
| 52 |
+
- Tokenizers 0.13.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.8,
|
| 3 |
+
"total_flos": 2.507370567185203e+16,
|
| 4 |
+
"train_loss": 0.05401366751534598,
|
| 5 |
+
"train_runtime": 24335.8249,
|
| 6 |
+
"train_samples_per_second": 0.575,
|
| 7 |
+
"train_steps_per_second": 0.575
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.8,
|
| 3 |
+
"total_flos": 2.507370567185203e+16,
|
| 4 |
+
"train_loss": 0.05401366751534598,
|
| 5 |
+
"train_runtime": 24335.8249,
|
| 6 |
+
"train_samples_per_second": 0.575,
|
| 7 |
+
"train_steps_per_second": 0.575
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,448 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8009153318077803,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 14000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.0019979971387696707,
|
| 14 |
+
"loss": 3.781,
|
| 15 |
+
"step": 200
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 0.001969384835479256,
|
| 20 |
+
"loss": 0.0,
|
| 21 |
+
"step": 400
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 0.0019407725321888413,
|
| 26 |
+
"loss": 0.0,
|
| 27 |
+
"step": 600
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.05,
|
| 31 |
+
"learning_rate": 0.0019121602288984262,
|
| 32 |
+
"loss": 0.0,
|
| 33 |
+
"step": 800
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.06,
|
| 37 |
+
"learning_rate": 0.0018835479256080114,
|
| 38 |
+
"loss": 0.0,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.07,
|
| 43 |
+
"learning_rate": 0.0018549356223175966,
|
| 44 |
+
"loss": 0.0,
|
| 45 |
+
"step": 1200
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08,
|
| 49 |
+
"learning_rate": 0.0018263233190271818,
|
| 50 |
+
"loss": 0.0,
|
| 51 |
+
"step": 1400
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09,
|
| 55 |
+
"learning_rate": 0.001797711015736767,
|
| 56 |
+
"loss": 0.0,
|
| 57 |
+
"step": 1600
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.1,
|
| 61 |
+
"learning_rate": 0.0017690987124463521,
|
| 62 |
+
"loss": 0.0,
|
| 63 |
+
"step": 1800
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.11,
|
| 67 |
+
"learning_rate": 0.001740486409155937,
|
| 68 |
+
"loss": 0.0,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.13,
|
| 73 |
+
"learning_rate": 0.0017118741058655222,
|
| 74 |
+
"loss": 0.0,
|
| 75 |
+
"step": 2200
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.14,
|
| 79 |
+
"learning_rate": 0.0016832618025751074,
|
| 80 |
+
"loss": 0.0,
|
| 81 |
+
"step": 2400
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.15,
|
| 85 |
+
"learning_rate": 0.0016546494992846926,
|
| 86 |
+
"loss": 0.0,
|
| 87 |
+
"step": 2600
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16,
|
| 91 |
+
"learning_rate": 0.0016260371959942775,
|
| 92 |
+
"loss": 0.0,
|
| 93 |
+
"step": 2800
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17,
|
| 97 |
+
"learning_rate": 0.0015974248927038625,
|
| 98 |
+
"loss": 0.0,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.18,
|
| 103 |
+
"learning_rate": 0.0015688125894134477,
|
| 104 |
+
"loss": 0.0,
|
| 105 |
+
"step": 3200
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.19,
|
| 109 |
+
"learning_rate": 0.0015402002861230329,
|
| 110 |
+
"loss": 0.0,
|
| 111 |
+
"step": 3400
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.21,
|
| 115 |
+
"learning_rate": 0.001511587982832618,
|
| 116 |
+
"loss": 0.0,
|
| 117 |
+
"step": 3600
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.22,
|
| 121 |
+
"learning_rate": 0.0014829756795422032,
|
| 122 |
+
"loss": 0.0,
|
| 123 |
+
"step": 3800
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.23,
|
| 127 |
+
"learning_rate": 0.0014543633762517884,
|
| 128 |
+
"loss": 0.0,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24,
|
| 133 |
+
"learning_rate": 0.0014257510729613733,
|
| 134 |
+
"loss": 0.0,
|
| 135 |
+
"step": 4200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.25,
|
| 139 |
+
"learning_rate": 0.0013971387696709585,
|
| 140 |
+
"loss": 0.0,
|
| 141 |
+
"step": 4400
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.26,
|
| 145 |
+
"learning_rate": 0.0013685264663805437,
|
| 146 |
+
"loss": 0.0,
|
| 147 |
+
"step": 4600
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.27,
|
| 151 |
+
"learning_rate": 0.0013399141630901289,
|
| 152 |
+
"loss": 0.0,
|
| 153 |
+
"step": 4800
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.29,
|
| 157 |
+
"learning_rate": 0.001311301859799714,
|
| 158 |
+
"loss": 0.0,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.3,
|
| 163 |
+
"learning_rate": 0.001282689556509299,
|
| 164 |
+
"loss": 0.0,
|
| 165 |
+
"step": 5200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.31,
|
| 169 |
+
"learning_rate": 0.0012540772532188842,
|
| 170 |
+
"loss": 0.0,
|
| 171 |
+
"step": 5400
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.32,
|
| 175 |
+
"learning_rate": 0.0012254649499284693,
|
| 176 |
+
"loss": 0.0,
|
| 177 |
+
"step": 5600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.33,
|
| 181 |
+
"learning_rate": 0.0011968526466380545,
|
| 182 |
+
"loss": 0.0,
|
| 183 |
+
"step": 5800
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.34,
|
| 187 |
+
"learning_rate": 0.0011682403433476395,
|
| 188 |
+
"loss": 0.0,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.35,
|
| 193 |
+
"learning_rate": 0.0011396280400572246,
|
| 194 |
+
"loss": 0.0,
|
| 195 |
+
"step": 6200
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.37,
|
| 199 |
+
"learning_rate": 0.0011110157367668096,
|
| 200 |
+
"loss": 0.0,
|
| 201 |
+
"step": 6400
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.38,
|
| 205 |
+
"learning_rate": 0.0010824034334763948,
|
| 206 |
+
"loss": 0.0,
|
| 207 |
+
"step": 6600
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.39,
|
| 211 |
+
"learning_rate": 0.00105379113018598,
|
| 212 |
+
"loss": 0.0,
|
| 213 |
+
"step": 6800
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.4,
|
| 217 |
+
"learning_rate": 0.0010251788268955651,
|
| 218 |
+
"loss": 0.0,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.41,
|
| 223 |
+
"learning_rate": 0.0009965665236051503,
|
| 224 |
+
"loss": 0.0,
|
| 225 |
+
"step": 7200
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.42,
|
| 229 |
+
"learning_rate": 0.0009679542203147354,
|
| 230 |
+
"loss": 0.0,
|
| 231 |
+
"step": 7400
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.43,
|
| 235 |
+
"learning_rate": 0.0009393419170243205,
|
| 236 |
+
"loss": 0.0,
|
| 237 |
+
"step": 7600
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.45,
|
| 241 |
+
"learning_rate": 0.0009107296137339056,
|
| 242 |
+
"loss": 0.0,
|
| 243 |
+
"step": 7800
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.46,
|
| 247 |
+
"learning_rate": 0.0008821173104434908,
|
| 248 |
+
"loss": 0.0,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.47,
|
| 253 |
+
"learning_rate": 0.0008535050071530759,
|
| 254 |
+
"loss": 0.0,
|
| 255 |
+
"step": 8200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.48,
|
| 259 |
+
"learning_rate": 0.0008248927038626609,
|
| 260 |
+
"loss": 0.0,
|
| 261 |
+
"step": 8400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.49,
|
| 265 |
+
"learning_rate": 0.0007962804005722461,
|
| 266 |
+
"loss": 0.0,
|
| 267 |
+
"step": 8600
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.5,
|
| 271 |
+
"learning_rate": 0.0007676680972818311,
|
| 272 |
+
"loss": 0.0,
|
| 273 |
+
"step": 8800
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.51,
|
| 277 |
+
"learning_rate": 0.0007390557939914163,
|
| 278 |
+
"loss": 0.0,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.53,
|
| 283 |
+
"learning_rate": 0.0007104434907010015,
|
| 284 |
+
"loss": 0.0,
|
| 285 |
+
"step": 9200
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.54,
|
| 289 |
+
"learning_rate": 0.0006818311874105865,
|
| 290 |
+
"loss": 0.0,
|
| 291 |
+
"step": 9400
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.55,
|
| 295 |
+
"learning_rate": 0.0006532188841201717,
|
| 296 |
+
"loss": 0.0,
|
| 297 |
+
"step": 9600
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.56,
|
| 301 |
+
"learning_rate": 0.0006246065808297569,
|
| 302 |
+
"loss": 0.0,
|
| 303 |
+
"step": 9800
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.57,
|
| 307 |
+
"learning_rate": 0.0005959942775393419,
|
| 308 |
+
"loss": 0.0,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.58,
|
| 313 |
+
"learning_rate": 0.000567381974248927,
|
| 314 |
+
"loss": 0.0,
|
| 315 |
+
"step": 10200
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.59,
|
| 319 |
+
"learning_rate": 0.0005387696709585122,
|
| 320 |
+
"loss": 0.0,
|
| 321 |
+
"step": 10400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.61,
|
| 325 |
+
"learning_rate": 0.0005101573676680973,
|
| 326 |
+
"loss": 0.0,
|
| 327 |
+
"step": 10600
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.62,
|
| 331 |
+
"learning_rate": 0.00048154506437768244,
|
| 332 |
+
"loss": 0.0,
|
| 333 |
+
"step": 10800
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.63,
|
| 337 |
+
"learning_rate": 0.00045293276108726756,
|
| 338 |
+
"loss": 0.0,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.64,
|
| 343 |
+
"learning_rate": 0.0004243204577968526,
|
| 344 |
+
"loss": 0.0,
|
| 345 |
+
"step": 11200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.65,
|
| 349 |
+
"learning_rate": 0.00039570815450643774,
|
| 350 |
+
"loss": 0.0,
|
| 351 |
+
"step": 11400
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.66,
|
| 355 |
+
"learning_rate": 0.0003670958512160229,
|
| 356 |
+
"loss": 0.0,
|
| 357 |
+
"step": 11600
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.68,
|
| 361 |
+
"learning_rate": 0.00033848354792560803,
|
| 362 |
+
"loss": 0.0,
|
| 363 |
+
"step": 11800
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.69,
|
| 367 |
+
"learning_rate": 0.0003098712446351931,
|
| 368 |
+
"loss": 0.0,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.7,
|
| 373 |
+
"learning_rate": 0.0002812589413447783,
|
| 374 |
+
"loss": 0.0,
|
| 375 |
+
"step": 12200
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.71,
|
| 379 |
+
"learning_rate": 0.0002526466380543634,
|
| 380 |
+
"loss": 0.0,
|
| 381 |
+
"step": 12400
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.72,
|
| 385 |
+
"learning_rate": 0.00022403433476394849,
|
| 386 |
+
"loss": 0.0,
|
| 387 |
+
"step": 12600
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.73,
|
| 391 |
+
"learning_rate": 0.00019542203147353363,
|
| 392 |
+
"loss": 0.0,
|
| 393 |
+
"step": 12800
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.74,
|
| 397 |
+
"learning_rate": 0.00016680972818311872,
|
| 398 |
+
"loss": 0.0,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.76,
|
| 403 |
+
"learning_rate": 0.00013819742489270387,
|
| 404 |
+
"loss": 0.0,
|
| 405 |
+
"step": 13200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.77,
|
| 409 |
+
"learning_rate": 0.00010958512160228899,
|
| 410 |
+
"loss": 0.0,
|
| 411 |
+
"step": 13400
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.78,
|
| 415 |
+
"learning_rate": 8.097281831187411e-05,
|
| 416 |
+
"loss": 0.0,
|
| 417 |
+
"step": 13600
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.79,
|
| 421 |
+
"learning_rate": 5.236051502145923e-05,
|
| 422 |
+
"loss": 0.0,
|
| 423 |
+
"step": 13800
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8,
|
| 427 |
+
"learning_rate": 2.374821173104435e-05,
|
| 428 |
+
"loss": 0.0,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8,
|
| 433 |
+
"step": 14000,
|
| 434 |
+
"total_flos": 2.507370567185203e+16,
|
| 435 |
+
"train_loss": 0.05401366751534598,
|
| 436 |
+
"train_runtime": 24335.8249,
|
| 437 |
+
"train_samples_per_second": 0.575,
|
| 438 |
+
"train_steps_per_second": 0.575
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 200,
|
| 442 |
+
"max_steps": 14000,
|
| 443 |
+
"num_train_epochs": 1,
|
| 444 |
+
"save_steps": 500,
|
| 445 |
+
"total_flos": 2.507370567185203e+16,
|
| 446 |
+
"trial_name": null,
|
| 447 |
+
"trial_params": null
|
| 448 |
+
}
|