End of training
Browse files- README.md +213 -0
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/Mar01_09-30-17_3022972a886d/events.out.tfevents.1709285965.3022972a886d.34.0 +3 -0
- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
ADDED
|
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: google/gemma-2b
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Gemma-2b-chat
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Gemma-2b-chat
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 2.3272
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 3
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 53 |
+
| 2.974 | 0.02 | 100 | 2.9419 |
|
| 54 |
+
| 3.1998 | 0.04 | 200 | 2.9117 |
|
| 55 |
+
| 2.9839 | 0.06 | 300 | 2.8745 |
|
| 56 |
+
| 2.9379 | 0.08 | 400 | 2.8328 |
|
| 57 |
+
| 2.9392 | 0.1 | 500 | 2.7909 |
|
| 58 |
+
| 2.7735 | 0.12 | 600 | 2.7461 |
|
| 59 |
+
| 2.7835 | 0.14 | 700 | 2.7075 |
|
| 60 |
+
| 2.7794 | 0.16 | 800 | 2.6695 |
|
| 61 |
+
| 2.7355 | 0.18 | 900 | 2.6363 |
|
| 62 |
+
| 2.7805 | 0.2 | 1000 | 2.6104 |
|
| 63 |
+
| 2.556 | 0.22 | 1100 | 2.5871 |
|
| 64 |
+
| 2.596 | 0.24 | 1200 | 2.5652 |
|
| 65 |
+
| 2.5838 | 0.26 | 1300 | 2.5432 |
|
| 66 |
+
| 2.6598 | 0.28 | 1400 | 2.5247 |
|
| 67 |
+
| 2.5475 | 0.3 | 1500 | 2.5100 |
|
| 68 |
+
| 2.4459 | 0.31 | 1600 | 2.4954 |
|
| 69 |
+
| 2.502 | 0.33 | 1700 | 2.4829 |
|
| 70 |
+
| 2.557 | 0.35 | 1800 | 2.4702 |
|
| 71 |
+
| 2.4944 | 0.37 | 1900 | 2.4604 |
|
| 72 |
+
| 2.4774 | 0.39 | 2000 | 2.4528 |
|
| 73 |
+
| 2.4287 | 0.41 | 2100 | 2.4453 |
|
| 74 |
+
| 2.5386 | 0.43 | 2200 | 2.4381 |
|
| 75 |
+
| 2.363 | 0.45 | 2300 | 2.4322 |
|
| 76 |
+
| 2.514 | 0.47 | 2400 | 2.4272 |
|
| 77 |
+
| 2.413 | 0.49 | 2500 | 2.4225 |
|
| 78 |
+
| 2.4667 | 0.51 | 2600 | 2.4176 |
|
| 79 |
+
| 2.4724 | 0.53 | 2700 | 2.4128 |
|
| 80 |
+
| 2.3949 | 0.55 | 2800 | 2.4084 |
|
| 81 |
+
| 2.4822 | 0.57 | 2900 | 2.4044 |
|
| 82 |
+
| 2.4556 | 0.59 | 3000 | 2.4009 |
|
| 83 |
+
| 2.4067 | 0.61 | 3100 | 2.3977 |
|
| 84 |
+
| 2.3911 | 0.63 | 3200 | 2.3947 |
|
| 85 |
+
| 2.3446 | 0.65 | 3300 | 2.3923 |
|
| 86 |
+
| 2.3358 | 0.67 | 3400 | 2.3891 |
|
| 87 |
+
| 2.3213 | 0.69 | 3500 | 2.3867 |
|
| 88 |
+
| 2.4041 | 0.71 | 3600 | 2.3840 |
|
| 89 |
+
| 2.4759 | 0.73 | 3700 | 2.3818 |
|
| 90 |
+
| 2.4622 | 0.75 | 3800 | 2.3801 |
|
| 91 |
+
| 2.3512 | 0.77 | 3900 | 2.3778 |
|
| 92 |
+
| 2.3653 | 0.79 | 4000 | 2.3760 |
|
| 93 |
+
| 2.3455 | 0.81 | 4100 | 2.3744 |
|
| 94 |
+
| 2.4364 | 0.83 | 4200 | 2.3724 |
|
| 95 |
+
| 2.2805 | 0.85 | 4300 | 2.3706 |
|
| 96 |
+
| 2.5448 | 0.87 | 4400 | 2.3681 |
|
| 97 |
+
| 2.3061 | 0.89 | 4500 | 2.3674 |
|
| 98 |
+
| 2.2572 | 0.9 | 4600 | 2.3657 |
|
| 99 |
+
| 2.3259 | 0.92 | 4700 | 2.3645 |
|
| 100 |
+
| 2.4078 | 0.94 | 4800 | 2.3633 |
|
| 101 |
+
| 2.3841 | 0.96 | 4900 | 2.3618 |
|
| 102 |
+
| 2.5439 | 0.98 | 5000 | 2.3604 |
|
| 103 |
+
| 2.4556 | 1.0 | 5100 | 2.3593 |
|
| 104 |
+
| 2.3752 | 1.02 | 5200 | 2.3582 |
|
| 105 |
+
| 2.3415 | 1.04 | 5300 | 2.3567 |
|
| 106 |
+
| 2.2824 | 1.06 | 5400 | 2.3555 |
|
| 107 |
+
| 2.3748 | 1.08 | 5500 | 2.3541 |
|
| 108 |
+
| 2.2535 | 1.1 | 5600 | 2.3534 |
|
| 109 |
+
| 2.3277 | 1.12 | 5700 | 2.3530 |
|
| 110 |
+
| 2.394 | 1.14 | 5800 | 2.3518 |
|
| 111 |
+
| 2.4876 | 1.16 | 5900 | 2.3511 |
|
| 112 |
+
| 2.4705 | 1.18 | 6000 | 2.3503 |
|
| 113 |
+
| 2.4394 | 1.2 | 6100 | 2.3499 |
|
| 114 |
+
| 2.3898 | 1.22 | 6200 | 2.3488 |
|
| 115 |
+
| 2.3789 | 1.24 | 6300 | 2.3483 |
|
| 116 |
+
| 2.4315 | 1.26 | 6400 | 2.3472 |
|
| 117 |
+
| 2.4065 | 1.28 | 6500 | 2.3463 |
|
| 118 |
+
| 2.3331 | 1.3 | 6600 | 2.3456 |
|
| 119 |
+
| 2.3415 | 1.32 | 6700 | 2.3452 |
|
| 120 |
+
| 2.3433 | 1.34 | 6800 | 2.3448 |
|
| 121 |
+
| 2.337 | 1.36 | 6900 | 2.3434 |
|
| 122 |
+
| 2.4492 | 1.38 | 7000 | 2.3425 |
|
| 123 |
+
| 2.3757 | 1.4 | 7100 | 2.3419 |
|
| 124 |
+
| 2.4124 | 1.42 | 7200 | 2.3412 |
|
| 125 |
+
| 2.2778 | 1.44 | 7300 | 2.3408 |
|
| 126 |
+
| 2.3127 | 1.46 | 7400 | 2.3401 |
|
| 127 |
+
| 2.2558 | 1.48 | 7500 | 2.3398 |
|
| 128 |
+
| 2.4419 | 1.49 | 7600 | 2.3394 |
|
| 129 |
+
| 2.3052 | 1.51 | 7700 | 2.3388 |
|
| 130 |
+
| 2.3212 | 1.53 | 7800 | 2.3387 |
|
| 131 |
+
| 2.3989 | 1.55 | 7900 | 2.3376 |
|
| 132 |
+
| 2.3201 | 1.57 | 8000 | 2.3372 |
|
| 133 |
+
| 2.4111 | 1.59 | 8100 | 2.3364 |
|
| 134 |
+
| 2.3243 | 1.61 | 8200 | 2.3361 |
|
| 135 |
+
| 2.3158 | 1.63 | 8300 | 2.3360 |
|
| 136 |
+
| 2.3065 | 1.65 | 8400 | 2.3357 |
|
| 137 |
+
| 2.3627 | 1.67 | 8500 | 2.3353 |
|
| 138 |
+
| 2.4604 | 1.69 | 8600 | 2.3348 |
|
| 139 |
+
| 2.2451 | 1.71 | 8700 | 2.3346 |
|
| 140 |
+
| 2.3559 | 1.73 | 8800 | 2.3342 |
|
| 141 |
+
| 2.4832 | 1.75 | 8900 | 2.3338 |
|
| 142 |
+
| 2.5064 | 1.77 | 9000 | 2.3335 |
|
| 143 |
+
| 2.2961 | 1.79 | 9100 | 2.3336 |
|
| 144 |
+
| 2.4394 | 1.81 | 9200 | 2.3334 |
|
| 145 |
+
| 2.4337 | 1.83 | 9300 | 2.3332 |
|
| 146 |
+
| 2.2984 | 1.85 | 9400 | 2.3328 |
|
| 147 |
+
| 2.2544 | 1.87 | 9500 | 2.3325 |
|
| 148 |
+
| 2.4421 | 1.89 | 9600 | 2.3321 |
|
| 149 |
+
| 2.2737 | 1.91 | 9700 | 2.3322 |
|
| 150 |
+
| 2.4483 | 1.93 | 9800 | 2.3319 |
|
| 151 |
+
| 2.4371 | 1.95 | 9900 | 2.3314 |
|
| 152 |
+
| 2.3184 | 1.97 | 10000 | 2.3312 |
|
| 153 |
+
| 2.2936 | 1.99 | 10100 | 2.3308 |
|
| 154 |
+
| 2.432 | 2.01 | 10200 | 2.3304 |
|
| 155 |
+
| 2.3306 | 2.03 | 10300 | 2.3301 |
|
| 156 |
+
| 2.3926 | 2.05 | 10400 | 2.3301 |
|
| 157 |
+
| 2.358 | 2.07 | 10500 | 2.3300 |
|
| 158 |
+
| 2.341 | 2.08 | 10600 | 2.3298 |
|
| 159 |
+
| 2.3886 | 2.1 | 10700 | 2.3297 |
|
| 160 |
+
| 2.2559 | 2.12 | 10800 | 2.3296 |
|
| 161 |
+
| 2.4121 | 2.14 | 10900 | 2.3294 |
|
| 162 |
+
| 2.3301 | 2.16 | 11000 | 2.3292 |
|
| 163 |
+
| 2.2807 | 2.18 | 11100 | 2.3290 |
|
| 164 |
+
| 2.3028 | 2.2 | 11200 | 2.3288 |
|
| 165 |
+
| 2.2957 | 2.22 | 11300 | 2.3289 |
|
| 166 |
+
| 2.296 | 2.24 | 11400 | 2.3289 |
|
| 167 |
+
| 2.248 | 2.26 | 11500 | 2.3288 |
|
| 168 |
+
| 2.3639 | 2.28 | 11600 | 2.3286 |
|
| 169 |
+
| 2.4383 | 2.3 | 11700 | 2.3284 |
|
| 170 |
+
| 2.2921 | 2.32 | 11800 | 2.3282 |
|
| 171 |
+
| 2.4594 | 2.34 | 11900 | 2.3282 |
|
| 172 |
+
| 2.4243 | 2.36 | 12000 | 2.3280 |
|
| 173 |
+
| 2.344 | 2.38 | 12100 | 2.3280 |
|
| 174 |
+
| 2.3063 | 2.4 | 12200 | 2.3279 |
|
| 175 |
+
| 2.3875 | 2.42 | 12300 | 2.3280 |
|
| 176 |
+
| 2.3502 | 2.44 | 12400 | 2.3278 |
|
| 177 |
+
| 2.3034 | 2.46 | 12500 | 2.3278 |
|
| 178 |
+
| 2.4234 | 2.48 | 12600 | 2.3277 |
|
| 179 |
+
| 2.2829 | 2.5 | 12700 | 2.3277 |
|
| 180 |
+
| 2.3965 | 2.52 | 12800 | 2.3277 |
|
| 181 |
+
| 2.4046 | 2.54 | 12900 | 2.3274 |
|
| 182 |
+
| 2.3374 | 2.56 | 13000 | 2.3274 |
|
| 183 |
+
| 2.1988 | 2.58 | 13100 | 2.3274 |
|
| 184 |
+
| 2.3893 | 2.6 | 13200 | 2.3274 |
|
| 185 |
+
| 2.3621 | 2.62 | 13300 | 2.3273 |
|
| 186 |
+
| 2.2888 | 2.64 | 13400 | 2.3273 |
|
| 187 |
+
| 2.3928 | 2.66 | 13500 | 2.3273 |
|
| 188 |
+
| 2.3523 | 2.68 | 13600 | 2.3272 |
|
| 189 |
+
| 2.3158 | 2.69 | 13700 | 2.3273 |
|
| 190 |
+
| 2.3453 | 2.71 | 13800 | 2.3273 |
|
| 191 |
+
| 2.3113 | 2.73 | 13900 | 2.3272 |
|
| 192 |
+
| 2.3878 | 2.75 | 14000 | 2.3272 |
|
| 193 |
+
| 2.3361 | 2.77 | 14100 | 2.3273 |
|
| 194 |
+
| 2.2343 | 2.79 | 14200 | 2.3273 |
|
| 195 |
+
| 2.2963 | 2.81 | 14300 | 2.3271 |
|
| 196 |
+
| 2.252 | 2.83 | 14400 | 2.3272 |
|
| 197 |
+
| 2.4307 | 2.85 | 14500 | 2.3272 |
|
| 198 |
+
| 2.2778 | 2.87 | 14600 | 2.3272 |
|
| 199 |
+
| 2.3832 | 2.89 | 14700 | 2.3272 |
|
| 200 |
+
| 2.3611 | 2.91 | 14800 | 2.3272 |
|
| 201 |
+
| 2.3556 | 2.93 | 14900 | 2.3271 |
|
| 202 |
+
| 2.3712 | 2.95 | 15000 | 2.3272 |
|
| 203 |
+
| 2.3667 | 2.97 | 15100 | 2.3272 |
|
| 204 |
+
| 2.3816 | 2.99 | 15200 | 2.3272 |
|
| 205 |
+
|
| 206 |
+
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.9.0
|
| 210 |
+
- Transformers 4.38.2
|
| 211 |
+
- Pytorch 2.1.2
|
| 212 |
+
- Datasets 2.17.1
|
| 213 |
+
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
|
@@ -10,7 +10,7 @@
|
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"loftq_config": {},
|
| 12 |
"lora_alpha": 16,
|
| 13 |
-
"lora_dropout": 0.
|
| 14 |
"megatron_config": null,
|
| 15 |
"megatron_core": "megatron.core",
|
| 16 |
"modules_to_save": null,
|
|
@@ -19,8 +19,8 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM",
|
| 26 |
"use_dora": false,
|
|
|
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"loftq_config": {},
|
| 12 |
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.0,
|
| 14 |
"megatron_config": null,
|
| 15 |
"megatron_core": "megatron.core",
|
| 16 |
"modules_to_save": null,
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"q_proj",
|
| 23 |
+
"v_proj"
|
| 24 |
],
|
| 25 |
"task_type": "CAUSAL_LM",
|
| 26 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 930928
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e0515be8c6b5b90c1fd70a82868f5c3d5cf2c63dce4b3d538980f8eb08c0f39
|
| 3 |
size 930928
|
runs/Mar01_09-30-17_3022972a886d/events.out.tfevents.1709285965.3022972a886d.34.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caec59bdb2009755e4b34ee2c0b1b24b28a940774daaed65351e011b07622793
|
| 3 |
+
size 78614
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<pad>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -40,7 +40,7 @@
|
|
| 40 |
"eos_token": "<eos>",
|
| 41 |
"legacy": null,
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
-
"pad_token": "<
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
"spaces_between_special_tokens": false,
|
| 46 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
|
| 40 |
"eos_token": "<eos>",
|
| 41 |
"legacy": null,
|
| 42 |
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "<pad>",
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
"spaces_between_special_tokens": false,
|
| 46 |
"tokenizer_class": "GemmaTokenizer",
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a49f648bf5624cbde70baada009a54ecf02095fffd5872212e6eea929ec90c4
|
| 3 |
+
size 4856
|