Model save
Browse files- README.md +175 -0
- final/config.json +32 -0
- final/merges.txt +0 -0
- final/model.safetensors +3 -0
- final/special_tokens_map.json +45 -0
- final/tokenizer.json +0 -0
- final/tokenizer_config.json +186 -0
- final/training_args.bin +3 -0
- final/vocab.json +0 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starencoder
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: classifier-llama3-python-500k
|
| 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 |
+
# classifier-llama3-python-500k
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co/bigcode/starencoder) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4216
|
| 22 |
+
- Precision: 0.5822
|
| 23 |
+
- Recall: 0.4400
|
| 24 |
+
- F1 Macro: 0.4652
|
| 25 |
+
- Accuracy: 0.5749
|
| 26 |
+
- F1 Binary Minimum3: 0.8018
|
| 27 |
+
- F1 Binary Minimum2: 0.9438
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 0.0001
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 256
|
| 49 |
+
- seed: 0
|
| 50 |
+
- distributed_type: multi-GPU
|
| 51 |
+
- num_devices: 8
|
| 52 |
+
- total_train_batch_size: 128
|
| 53 |
+
- total_eval_batch_size: 2048
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- lr_scheduler_warmup_steps: 200
|
| 57 |
+
- num_epochs: 30
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy | F1 Binary Minimum3 | F1 Binary Minimum2 |
|
| 62 |
+
|:-------------:|:-------:|:------:|:---------------:|:---------:|:------:|:--------:|:--------:|:------------------:|:------------------:|
|
| 63 |
+
| No log | 0 | 0 | 7.4938 | 0.0265 | 0.2 | 0.0468 | 0.1326 | 0 | 0 |
|
| 64 |
+
| 0.4898 | 0.2880 | 1000 | 0.4759 | 0.5180 | 0.3927 | 0.4073 | 0.5474 | 0.7902 | 0.9395 |
|
| 65 |
+
| 0.4733 | 0.5760 | 2000 | 0.4696 | 0.5338 | 0.3984 | 0.4131 | 0.5493 | 0.7767 | 0.9400 |
|
| 66 |
+
| 0.4761 | 0.8641 | 3000 | 0.4571 | 0.5266 | 0.4080 | 0.4235 | 0.5573 | 0.7893 | 0.9410 |
|
| 67 |
+
| 0.4473 | 1.1521 | 4000 | 0.4589 | 0.5171 | 0.4061 | 0.4202 | 0.5522 | 0.7806 | 0.9389 |
|
| 68 |
+
| 0.4472 | 1.4401 | 5000 | 0.4686 | 0.5557 | 0.4135 | 0.4280 | 0.5503 | 0.7991 | 0.9416 |
|
| 69 |
+
| 0.4399 | 1.7281 | 6000 | 0.4508 | 0.5605 | 0.4184 | 0.4359 | 0.5599 | 0.7988 | 0.9421 |
|
| 70 |
+
| 0.4511 | 2.0161 | 7000 | 0.4467 | 0.5597 | 0.4183 | 0.4357 | 0.5615 | 0.7927 | 0.9402 |
|
| 71 |
+
| 0.445 | 2.3041 | 8000 | 0.4441 | 0.5395 | 0.4167 | 0.4326 | 0.5618 | 0.7913 | 0.9412 |
|
| 72 |
+
| 0.4554 | 2.5922 | 9000 | 0.4486 | 0.5640 | 0.4197 | 0.4372 | 0.5609 | 0.7999 | 0.9415 |
|
| 73 |
+
| 0.4499 | 2.8802 | 10000 | 0.4428 | 0.5702 | 0.4225 | 0.4405 | 0.5633 | 0.7990 | 0.9419 |
|
| 74 |
+
| 0.4492 | 3.1682 | 11000 | 0.4651 | 0.5714 | 0.4279 | 0.4459 | 0.5549 | 0.8015 | 0.9420 |
|
| 75 |
+
| 0.4459 | 3.4562 | 12000 | 0.4401 | 0.5690 | 0.4190 | 0.4368 | 0.5646 | 0.7986 | 0.9418 |
|
| 76 |
+
| 0.4469 | 3.7442 | 13000 | 0.4428 | 0.5753 | 0.4189 | 0.4378 | 0.5625 | 0.7976 | 0.9405 |
|
| 77 |
+
| 0.459 | 4.0323 | 14000 | 0.4385 | 0.5729 | 0.4229 | 0.4415 | 0.5661 | 0.7955 | 0.9421 |
|
| 78 |
+
| 0.4543 | 4.3203 | 15000 | 0.4418 | 0.5721 | 0.4220 | 0.4404 | 0.5629 | 0.8009 | 0.9408 |
|
| 79 |
+
| 0.442 | 4.6083 | 16000 | 0.4488 | 0.5803 | 0.4207 | 0.4388 | 0.5595 | 0.8028 | 0.9412 |
|
| 80 |
+
| 0.4525 | 4.8963 | 17000 | 0.4469 | 0.5712 | 0.4174 | 0.4338 | 0.5597 | 0.8005 | 0.9399 |
|
| 81 |
+
| 0.4539 | 5.1843 | 18000 | 0.4371 | 0.5867 | 0.4183 | 0.4372 | 0.5659 | 0.7996 | 0.9421 |
|
| 82 |
+
| 0.4527 | 5.4724 | 19000 | 0.4371 | 0.5707 | 0.4269 | 0.4450 | 0.5653 | 0.7920 | 0.9413 |
|
| 83 |
+
| 0.455 | 5.7604 | 20000 | 0.4364 | 0.5712 | 0.4288 | 0.4494 | 0.5664 | 0.7982 | 0.9416 |
|
| 84 |
+
| 0.4519 | 6.0484 | 21000 | 0.4371 | 0.5805 | 0.4274 | 0.4479 | 0.5667 | 0.8012 | 0.9421 |
|
| 85 |
+
| 0.4293 | 6.3364 | 22000 | 0.4351 | 0.5841 | 0.4214 | 0.4412 | 0.5669 | 0.7989 | 0.9424 |
|
| 86 |
+
| 0.4441 | 6.6244 | 23000 | 0.4360 | 0.5707 | 0.4272 | 0.4456 | 0.5667 | 0.7933 | 0.9413 |
|
| 87 |
+
| 0.4376 | 6.9124 | 24000 | 0.4360 | 0.5652 | 0.4262 | 0.4450 | 0.5652 | 0.7933 | 0.9412 |
|
| 88 |
+
| 0.4357 | 7.2005 | 25000 | 0.4382 | 0.5716 | 0.4244 | 0.4441 | 0.5647 | 0.8009 | 0.9411 |
|
| 89 |
+
| 0.4513 | 7.4885 | 26000 | 0.4382 | 0.5764 | 0.4245 | 0.4425 | 0.5629 | 0.7857 | 0.9410 |
|
| 90 |
+
| 0.422 | 7.7765 | 27000 | 0.4344 | 0.5736 | 0.4256 | 0.4456 | 0.5670 | 0.7967 | 0.9418 |
|
| 91 |
+
| 0.4317 | 8.0645 | 28000 | 0.4343 | 0.5799 | 0.4209 | 0.4406 | 0.5658 | 0.7995 | 0.9413 |
|
| 92 |
+
| 0.4458 | 8.3525 | 29000 | 0.4339 | 0.5793 | 0.4307 | 0.4521 | 0.5686 | 0.8015 | 0.9431 |
|
| 93 |
+
| 0.4591 | 8.6406 | 30000 | 0.4382 | 0.5869 | 0.4260 | 0.4470 | 0.5655 | 0.8031 | 0.9420 |
|
| 94 |
+
| 0.4313 | 8.9286 | 31000 | 0.4364 | 0.5717 | 0.4352 | 0.4577 | 0.5681 | 0.8022 | 0.9426 |
|
| 95 |
+
| 0.4201 | 9.2166 | 32000 | 0.4328 | 0.5686 | 0.4326 | 0.4540 | 0.5691 | 0.7958 | 0.9420 |
|
| 96 |
+
| 0.4433 | 9.5046 | 33000 | 0.4378 | 0.5778 | 0.4339 | 0.4554 | 0.5674 | 0.8036 | 0.9428 |
|
| 97 |
+
| 0.4404 | 9.7926 | 34000 | 0.4339 | 0.5855 | 0.4292 | 0.4516 | 0.5692 | 0.8021 | 0.9434 |
|
| 98 |
+
| 0.4324 | 10.0806 | 35000 | 0.4318 | 0.5695 | 0.4316 | 0.4533 | 0.5685 | 0.7985 | 0.9424 |
|
| 99 |
+
| 0.4393 | 10.3687 | 36000 | 0.4365 | 0.5804 | 0.4307 | 0.4529 | 0.5672 | 0.8040 | 0.9425 |
|
| 100 |
+
| 0.4334 | 10.6567 | 37000 | 0.4304 | 0.5780 | 0.4308 | 0.4525 | 0.5700 | 0.7996 | 0.9424 |
|
| 101 |
+
| 0.4396 | 10.9447 | 38000 | 0.4311 | 0.5691 | 0.4329 | 0.4547 | 0.5708 | 0.8001 | 0.9427 |
|
| 102 |
+
| 0.4398 | 11.2327 | 39000 | 0.4362 | 0.5732 | 0.4356 | 0.4579 | 0.5681 | 0.8040 | 0.9426 |
|
| 103 |
+
| 0.4568 | 11.5207 | 40000 | 0.4305 | 0.5814 | 0.4299 | 0.4516 | 0.5700 | 0.7998 | 0.9424 |
|
| 104 |
+
| 0.4459 | 11.8088 | 41000 | 0.4307 | 0.5793 | 0.4339 | 0.4562 | 0.5705 | 0.8017 | 0.9427 |
|
| 105 |
+
| 0.4326 | 12.0968 | 42000 | 0.4326 | 0.5821 | 0.4331 | 0.4559 | 0.5693 | 0.8026 | 0.9431 |
|
| 106 |
+
| 0.4343 | 12.3848 | 43000 | 0.4320 | 0.5751 | 0.4347 | 0.4578 | 0.5702 | 0.8026 | 0.9430 |
|
| 107 |
+
| 0.4247 | 12.6728 | 44000 | 0.4292 | 0.5768 | 0.4360 | 0.4592 | 0.5713 | 0.8011 | 0.9429 |
|
| 108 |
+
| 0.4285 | 12.9608 | 45000 | 0.4414 | 0.5789 | 0.4342 | 0.4566 | 0.5652 | 0.8054 | 0.9425 |
|
| 109 |
+
| 0.4304 | 13.2488 | 46000 | 0.4305 | 0.5767 | 0.4354 | 0.4584 | 0.5709 | 0.8028 | 0.9432 |
|
| 110 |
+
| 0.4211 | 13.5369 | 47000 | 0.4279 | 0.5759 | 0.4323 | 0.4542 | 0.5712 | 0.7996 | 0.9425 |
|
| 111 |
+
| 0.4451 | 13.8249 | 48000 | 0.4280 | 0.5906 | 0.4282 | 0.4507 | 0.5723 | 0.8002 | 0.9437 |
|
| 112 |
+
| 0.4298 | 14.1129 | 49000 | 0.4295 | 0.5799 | 0.4278 | 0.4488 | 0.5680 | 0.7921 | 0.9424 |
|
| 113 |
+
| 0.4328 | 14.4009 | 50000 | 0.4283 | 0.5804 | 0.4349 | 0.4587 | 0.5717 | 0.8014 | 0.9431 |
|
| 114 |
+
| 0.4366 | 14.6889 | 51000 | 0.4276 | 0.5777 | 0.4367 | 0.4606 | 0.5718 | 0.8007 | 0.9433 |
|
| 115 |
+
| 0.4225 | 14.9770 | 52000 | 0.4333 | 0.5690 | 0.4382 | 0.4614 | 0.5693 | 0.8039 | 0.9421 |
|
| 116 |
+
| 0.4411 | 15.2650 | 53000 | 0.4280 | 0.5738 | 0.4327 | 0.4559 | 0.5711 | 0.8013 | 0.9428 |
|
| 117 |
+
| 0.4279 | 15.5530 | 54000 | 0.4273 | 0.5787 | 0.4349 | 0.4589 | 0.5720 | 0.8016 | 0.9433 |
|
| 118 |
+
| 0.418 | 15.8410 | 55000 | 0.4283 | 0.5747 | 0.4328 | 0.4542 | 0.5694 | 0.7920 | 0.9423 |
|
| 119 |
+
| 0.4472 | 16.1290 | 56000 | 0.4276 | 0.5761 | 0.4350 | 0.4560 | 0.5712 | 0.7953 | 0.9426 |
|
| 120 |
+
| 0.426 | 16.4171 | 57000 | 0.4260 | 0.5910 | 0.4283 | 0.4514 | 0.5725 | 0.7983 | 0.9438 |
|
| 121 |
+
| 0.437 | 16.7051 | 58000 | 0.4298 | 0.5777 | 0.4354 | 0.4589 | 0.5708 | 0.8040 | 0.9430 |
|
| 122 |
+
| 0.4289 | 16.9931 | 59000 | 0.4272 | 0.5741 | 0.4382 | 0.4619 | 0.5725 | 0.8019 | 0.9435 |
|
| 123 |
+
| 0.4454 | 17.2811 | 60000 | 0.4254 | 0.5921 | 0.4311 | 0.4542 | 0.5734 | 0.8013 | 0.9433 |
|
| 124 |
+
| 0.4367 | 17.5691 | 61000 | 0.4273 | 0.5792 | 0.4377 | 0.4625 | 0.5726 | 0.8021 | 0.9432 |
|
| 125 |
+
| 0.4555 | 17.8571 | 62000 | 0.4259 | 0.5746 | 0.4379 | 0.4616 | 0.5725 | 0.7998 | 0.9430 |
|
| 126 |
+
| 0.4351 | 18.1452 | 63000 | 0.4257 | 0.5776 | 0.4334 | 0.4566 | 0.5719 | 0.7972 | 0.9431 |
|
| 127 |
+
| 0.4334 | 18.4332 | 64000 | 0.4247 | 0.5813 | 0.4378 | 0.4622 | 0.5739 | 0.7988 | 0.9437 |
|
| 128 |
+
| 0.423 | 18.7212 | 65000 | 0.4261 | 0.5783 | 0.4343 | 0.4573 | 0.5713 | 0.7934 | 0.9426 |
|
| 129 |
+
| 0.4433 | 19.0092 | 66000 | 0.4248 | 0.5756 | 0.4352 | 0.4591 | 0.5730 | 0.7996 | 0.9433 |
|
| 130 |
+
| 0.4355 | 19.2972 | 67000 | 0.4241 | 0.5822 | 0.4378 | 0.4623 | 0.5738 | 0.8012 | 0.9436 |
|
| 131 |
+
| 0.4268 | 19.5853 | 68000 | 0.4308 | 0.5814 | 0.4356 | 0.4589 | 0.5706 | 0.8044 | 0.9426 |
|
| 132 |
+
| 0.4291 | 19.8733 | 69000 | 0.4297 | 0.5802 | 0.4351 | 0.4587 | 0.5696 | 0.8044 | 0.9427 |
|
| 133 |
+
| 0.4291 | 20.1613 | 70000 | 0.4247 | 0.5799 | 0.4361 | 0.4598 | 0.5738 | 0.8020 | 0.9433 |
|
| 134 |
+
| 0.419 | 20.4493 | 71000 | 0.4241 | 0.5820 | 0.4363 | 0.4606 | 0.5739 | 0.8012 | 0.9434 |
|
| 135 |
+
| 0.4264 | 20.7373 | 72000 | 0.4282 | 0.5817 | 0.4369 | 0.4613 | 0.5714 | 0.8042 | 0.9430 |
|
| 136 |
+
| 0.4259 | 21.0253 | 73000 | 0.4239 | 0.5794 | 0.4353 | 0.4588 | 0.5729 | 0.7969 | 0.9431 |
|
| 137 |
+
| 0.422 | 21.3134 | 74000 | 0.4230 | 0.5843 | 0.4376 | 0.4622 | 0.5744 | 0.7990 | 0.9437 |
|
| 138 |
+
| 0.4312 | 21.6014 | 75000 | 0.4247 | 0.5835 | 0.4340 | 0.4585 | 0.5725 | 0.8012 | 0.9430 |
|
| 139 |
+
| 0.4103 | 21.8894 | 76000 | 0.4245 | 0.5804 | 0.4409 | 0.4664 | 0.5732 | 0.8026 | 0.9436 |
|
| 140 |
+
| 0.4473 | 22.1774 | 77000 | 0.4235 | 0.5831 | 0.4360 | 0.4603 | 0.5738 | 0.8008 | 0.9434 |
|
| 141 |
+
| 0.4205 | 22.4654 | 78000 | 0.4244 | 0.5807 | 0.4357 | 0.4600 | 0.5733 | 0.8021 | 0.9433 |
|
| 142 |
+
| 0.4294 | 22.7535 | 79000 | 0.4229 | 0.5862 | 0.4342 | 0.4584 | 0.5741 | 0.8011 | 0.9434 |
|
| 143 |
+
| 0.4467 | 23.0415 | 80000 | 0.4232 | 0.5749 | 0.4401 | 0.4649 | 0.5740 | 0.8009 | 0.9432 |
|
| 144 |
+
| 0.4296 | 23.3295 | 81000 | 0.4229 | 0.5812 | 0.4381 | 0.4629 | 0.5743 | 0.8006 | 0.9433 |
|
| 145 |
+
| 0.4308 | 23.6175 | 82000 | 0.4235 | 0.5758 | 0.4442 | 0.4698 | 0.5746 | 0.8022 | 0.9438 |
|
| 146 |
+
| 0.4251 | 23.9055 | 83000 | 0.4219 | 0.5862 | 0.4358 | 0.4602 | 0.5747 | 0.8003 | 0.9436 |
|
| 147 |
+
| 0.4383 | 24.1935 | 84000 | 0.4229 | 0.5784 | 0.4381 | 0.4626 | 0.5743 | 0.8015 | 0.9432 |
|
| 148 |
+
| 0.4309 | 24.4816 | 85000 | 0.4219 | 0.5837 | 0.4372 | 0.4618 | 0.5748 | 0.8001 | 0.9434 |
|
| 149 |
+
| 0.4245 | 24.7696 | 86000 | 0.4222 | 0.5810 | 0.4391 | 0.4633 | 0.5748 | 0.7982 | 0.9435 |
|
| 150 |
+
| 0.4227 | 25.0576 | 87000 | 0.4221 | 0.5836 | 0.4362 | 0.4606 | 0.5743 | 0.7991 | 0.9435 |
|
| 151 |
+
| 0.4224 | 25.3456 | 88000 | 0.4220 | 0.5775 | 0.4416 | 0.4664 | 0.5744 | 0.7998 | 0.9433 |
|
| 152 |
+
| 0.4247 | 25.6336 | 89000 | 0.4227 | 0.5854 | 0.4382 | 0.4632 | 0.5743 | 0.8028 | 0.9434 |
|
| 153 |
+
| 0.416 | 25.9217 | 90000 | 0.4230 | 0.5760 | 0.4427 | 0.4675 | 0.5746 | 0.8018 | 0.9434 |
|
| 154 |
+
| 0.4221 | 26.2097 | 91000 | 0.4215 | 0.5820 | 0.4390 | 0.4638 | 0.5752 | 0.8012 | 0.9439 |
|
| 155 |
+
| 0.4126 | 26.4977 | 92000 | 0.4263 | 0.5836 | 0.4391 | 0.4641 | 0.5723 | 0.8050 | 0.9431 |
|
| 156 |
+
| 0.424 | 26.7857 | 93000 | 0.4215 | 0.5828 | 0.4381 | 0.4627 | 0.5750 | 0.7986 | 0.9438 |
|
| 157 |
+
| 0.4272 | 27.0737 | 94000 | 0.4239 | 0.5853 | 0.4403 | 0.4660 | 0.5740 | 0.8040 | 0.9438 |
|
| 158 |
+
| 0.4306 | 27.3618 | 95000 | 0.4235 | 0.5801 | 0.4399 | 0.4651 | 0.5736 | 0.8029 | 0.9435 |
|
| 159 |
+
| 0.4164 | 27.6498 | 96000 | 0.4219 | 0.5801 | 0.4405 | 0.4656 | 0.5747 | 0.8015 | 0.9437 |
|
| 160 |
+
| 0.431 | 27.9378 | 97000 | 0.4213 | 0.5791 | 0.4393 | 0.4637 | 0.5748 | 0.7993 | 0.9434 |
|
| 161 |
+
| 0.4284 | 28.2258 | 98000 | 0.4227 | 0.5826 | 0.4402 | 0.4658 | 0.5744 | 0.8033 | 0.9435 |
|
| 162 |
+
| 0.4289 | 28.5138 | 99000 | 0.4216 | 0.5845 | 0.4384 | 0.4634 | 0.5749 | 0.8009 | 0.9438 |
|
| 163 |
+
| 0.4244 | 28.8018 | 100000 | 0.4221 | 0.5813 | 0.4377 | 0.4623 | 0.5746 | 0.8020 | 0.9436 |
|
| 164 |
+
| 0.4314 | 29.0899 | 101000 | 0.4216 | 0.5829 | 0.4402 | 0.4654 | 0.5751 | 0.8013 | 0.9437 |
|
| 165 |
+
| 0.4269 | 29.3779 | 102000 | 0.4212 | 0.5852 | 0.4405 | 0.4658 | 0.5754 | 0.8006 | 0.9438 |
|
| 166 |
+
| 0.4367 | 29.6659 | 103000 | 0.4215 | 0.5841 | 0.4400 | 0.4653 | 0.5749 | 0.8013 | 0.9437 |
|
| 167 |
+
| 0.4223 | 29.9539 | 104000 | 0.4216 | 0.5822 | 0.4400 | 0.4652 | 0.5749 | 0.8018 | 0.9438 |
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
### Framework versions
|
| 171 |
+
|
| 172 |
+
- Transformers 4.43.4
|
| 173 |
+
- Pytorch 2.4.0+cu121
|
| 174 |
+
- Datasets 2.21.0
|
| 175 |
+
- Tokenizers 0.19.1
|
final/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigcode/starencoder",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 1024,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 49152,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.43.4",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49156
|
| 32 |
+
}
|
final/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
final/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d0857699faea5493ed8b0062f3dd649034467fb89887a7c7c9ebb02f7e42646
|
| 3 |
+
size 496772092
|
final/special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": "<|endoftext|>",
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|
final/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
final/tokenizer_config.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"clean_up_tokenization_spaces": true,
|
| 180 |
+
"eos_token": "<|endoftext|>",
|
| 181 |
+
"model_max_length": 1024,
|
| 182 |
+
"pad_token": "<|endoftext|>",
|
| 183 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 184 |
+
"unk_token": "<|endoftext|>",
|
| 185 |
+
"vocab_size": 49152
|
| 186 |
+
}
|
final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34060b3a5294de798d75a53763f2ac6b3fed893f4c08ef3e2b2bf8c46f693749
|
| 3 |
+
size 5304
|
final/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 496772092
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d0857699faea5493ed8b0062f3dd649034467fb89887a7c7c9ebb02f7e42646
|
| 3 |
size 496772092
|