Commit
•
4994ec2
1
Parent(s):
de47da5
End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,308 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: apple/OpenELM-1_1B
|
| 9 |
+
model-index:
|
| 10 |
+
- name: OpenELM
|
| 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 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/thaisonatk/huggingface/runs/g59y71tt)
|
| 18 |
+
# OpenELM
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [apple/OpenELM-1_1B](https://huggingface.co/apple/OpenELM-1_1B) on the None dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.8217
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0002
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 3407
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- lr_scheduler_warmup_steps: 5
|
| 50 |
+
- num_epochs: 1
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 1.4857 | 0.0041 | 10 | 1.3911 |
|
| 58 |
+
| 1.3665 | 0.0082 | 20 | 1.2476 |
|
| 59 |
+
| 1.2776 | 0.0123 | 30 | 1.1732 |
|
| 60 |
+
| 1.1933 | 0.0164 | 40 | 1.1347 |
|
| 61 |
+
| 1.1747 | 0.0205 | 50 | 1.1082 |
|
| 62 |
+
| 1.1433 | 0.0246 | 60 | 1.0864 |
|
| 63 |
+
| 1.1225 | 0.0288 | 70 | 1.0698 |
|
| 64 |
+
| 1.0967 | 0.0329 | 80 | 1.0541 |
|
| 65 |
+
| 1.075 | 0.0370 | 90 | 1.0411 |
|
| 66 |
+
| 1.0551 | 0.0411 | 100 | 1.0316 |
|
| 67 |
+
| 1.0587 | 0.0452 | 110 | 1.0231 |
|
| 68 |
+
| 1.0432 | 0.0493 | 120 | 1.0160 |
|
| 69 |
+
| 1.0512 | 0.0534 | 130 | 1.0095 |
|
| 70 |
+
| 1.0527 | 0.0575 | 140 | 1.0042 |
|
| 71 |
+
| 1.032 | 0.0616 | 150 | 0.9989 |
|
| 72 |
+
| 1.0277 | 0.0657 | 160 | 0.9936 |
|
| 73 |
+
| 1.0316 | 0.0698 | 170 | 0.9890 |
|
| 74 |
+
| 1.0225 | 0.0739 | 180 | 0.9848 |
|
| 75 |
+
| 1.007 | 0.0780 | 190 | 0.9804 |
|
| 76 |
+
| 0.9918 | 0.0822 | 200 | 0.9769 |
|
| 77 |
+
| 1.0152 | 0.0863 | 210 | 0.9734 |
|
| 78 |
+
| 0.9872 | 0.0904 | 220 | 0.9703 |
|
| 79 |
+
| 0.9972 | 0.0945 | 230 | 0.9670 |
|
| 80 |
+
| 1.0098 | 0.0986 | 240 | 0.9639 |
|
| 81 |
+
| 0.9869 | 0.1027 | 250 | 0.9607 |
|
| 82 |
+
| 0.9829 | 0.1068 | 260 | 0.9581 |
|
| 83 |
+
| 0.9983 | 0.1109 | 270 | 0.9556 |
|
| 84 |
+
| 0.9973 | 0.1150 | 280 | 0.9527 |
|
| 85 |
+
| 0.9848 | 0.1191 | 290 | 0.9505 |
|
| 86 |
+
| 0.9734 | 0.1232 | 300 | 0.9478 |
|
| 87 |
+
| 0.9677 | 0.1273 | 310 | 0.9451 |
|
| 88 |
+
| 0.9638 | 0.1314 | 320 | 0.9434 |
|
| 89 |
+
| 0.9654 | 0.1356 | 330 | 0.9411 |
|
| 90 |
+
| 0.9653 | 0.1397 | 340 | 0.9389 |
|
| 91 |
+
| 0.976 | 0.1438 | 350 | 0.9370 |
|
| 92 |
+
| 0.9627 | 0.1479 | 360 | 0.9355 |
|
| 93 |
+
| 0.9533 | 0.1520 | 370 | 0.9331 |
|
| 94 |
+
| 0.9441 | 0.1561 | 380 | 0.9309 |
|
| 95 |
+
| 0.958 | 0.1602 | 390 | 0.9294 |
|
| 96 |
+
| 0.9467 | 0.1643 | 400 | 0.9273 |
|
| 97 |
+
| 0.9412 | 0.1684 | 410 | 0.9254 |
|
| 98 |
+
| 0.9632 | 0.1725 | 420 | 0.9237 |
|
| 99 |
+
| 0.9248 | 0.1766 | 430 | 0.9218 |
|
| 100 |
+
| 0.9384 | 0.1807 | 440 | 0.9204 |
|
| 101 |
+
| 0.9407 | 0.1848 | 450 | 0.9187 |
|
| 102 |
+
| 0.9439 | 0.1890 | 460 | 0.9170 |
|
| 103 |
+
| 0.9353 | 0.1931 | 470 | 0.9154 |
|
| 104 |
+
| 0.9346 | 0.1972 | 480 | 0.9139 |
|
| 105 |
+
| 0.9373 | 0.2013 | 490 | 0.9121 |
|
| 106 |
+
| 0.936 | 0.2054 | 500 | 0.9107 |
|
| 107 |
+
| 0.9375 | 0.2095 | 510 | 0.9096 |
|
| 108 |
+
| 0.9456 | 0.2136 | 520 | 0.9076 |
|
| 109 |
+
| 0.9354 | 0.2177 | 530 | 0.9065 |
|
| 110 |
+
| 0.9173 | 0.2218 | 540 | 0.9052 |
|
| 111 |
+
| 0.921 | 0.2259 | 550 | 0.9042 |
|
| 112 |
+
| 0.9233 | 0.2300 | 560 | 0.9025 |
|
| 113 |
+
| 0.9338 | 0.2341 | 570 | 0.9012 |
|
| 114 |
+
| 0.918 | 0.2382 | 580 | 0.8996 |
|
| 115 |
+
| 0.9221 | 0.2424 | 590 | 0.8985 |
|
| 116 |
+
| 0.903 | 0.2465 | 600 | 0.8973 |
|
| 117 |
+
| 0.9094 | 0.2506 | 610 | 0.8965 |
|
| 118 |
+
| 0.9077 | 0.2547 | 620 | 0.8953 |
|
| 119 |
+
| 0.9076 | 0.2588 | 630 | 0.8944 |
|
| 120 |
+
| 0.9304 | 0.2629 | 640 | 0.8931 |
|
| 121 |
+
| 0.9118 | 0.2670 | 650 | 0.8917 |
|
| 122 |
+
| 0.9131 | 0.2711 | 660 | 0.8910 |
|
| 123 |
+
| 0.9213 | 0.2752 | 670 | 0.8901 |
|
| 124 |
+
| 0.901 | 0.2793 | 680 | 0.8891 |
|
| 125 |
+
| 0.9089 | 0.2834 | 690 | 0.8882 |
|
| 126 |
+
| 0.9152 | 0.2875 | 700 | 0.8871 |
|
| 127 |
+
| 0.9138 | 0.2916 | 710 | 0.8863 |
|
| 128 |
+
| 0.8988 | 0.2958 | 720 | 0.8849 |
|
| 129 |
+
| 0.8945 | 0.2999 | 730 | 0.8843 |
|
| 130 |
+
| 0.9104 | 0.3040 | 740 | 0.8836 |
|
| 131 |
+
| 0.919 | 0.3081 | 750 | 0.8826 |
|
| 132 |
+
| 0.9049 | 0.3122 | 760 | 0.8815 |
|
| 133 |
+
| 0.8834 | 0.3163 | 770 | 0.8806 |
|
| 134 |
+
| 0.9053 | 0.3204 | 780 | 0.8795 |
|
| 135 |
+
| 0.9039 | 0.3245 | 790 | 0.8789 |
|
| 136 |
+
| 0.9018 | 0.3286 | 800 | 0.8781 |
|
| 137 |
+
| 0.8847 | 0.3327 | 810 | 0.8775 |
|
| 138 |
+
| 0.8884 | 0.3368 | 820 | 0.8760 |
|
| 139 |
+
| 0.8867 | 0.3409 | 830 | 0.8756 |
|
| 140 |
+
| 0.8782 | 0.3450 | 840 | 0.8747 |
|
| 141 |
+
| 0.8765 | 0.3492 | 850 | 0.8737 |
|
| 142 |
+
| 0.8862 | 0.3533 | 860 | 0.8733 |
|
| 143 |
+
| 0.889 | 0.3574 | 870 | 0.8722 |
|
| 144 |
+
| 0.8997 | 0.3615 | 880 | 0.8716 |
|
| 145 |
+
| 0.8706 | 0.3656 | 890 | 0.8708 |
|
| 146 |
+
| 0.8982 | 0.3697 | 900 | 0.8701 |
|
| 147 |
+
| 0.8792 | 0.3738 | 910 | 0.8693 |
|
| 148 |
+
| 0.8869 | 0.3779 | 920 | 0.8686 |
|
| 149 |
+
| 0.8704 | 0.3820 | 930 | 0.8678 |
|
| 150 |
+
| 0.8902 | 0.3861 | 940 | 0.8676 |
|
| 151 |
+
| 0.8827 | 0.3902 | 950 | 0.8667 |
|
| 152 |
+
| 0.8832 | 0.3943 | 960 | 0.8662 |
|
| 153 |
+
| 0.883 | 0.3984 | 970 | 0.8650 |
|
| 154 |
+
| 0.8803 | 0.4026 | 980 | 0.8642 |
|
| 155 |
+
| 0.8605 | 0.4067 | 990 | 0.8634 |
|
| 156 |
+
| 0.8838 | 0.4108 | 1000 | 0.8627 |
|
| 157 |
+
| 0.8878 | 0.4149 | 1010 | 0.8623 |
|
| 158 |
+
| 0.8835 | 0.4190 | 1020 | 0.8614 |
|
| 159 |
+
| 0.8597 | 0.4231 | 1030 | 0.8609 |
|
| 160 |
+
| 0.8648 | 0.4272 | 1040 | 0.8603 |
|
| 161 |
+
| 0.8847 | 0.4313 | 1050 | 0.8598 |
|
| 162 |
+
| 0.8921 | 0.4354 | 1060 | 0.8592 |
|
| 163 |
+
| 0.8718 | 0.4395 | 1070 | 0.8590 |
|
| 164 |
+
| 0.8829 | 0.4436 | 1080 | 0.8583 |
|
| 165 |
+
| 0.8715 | 0.4477 | 1090 | 0.8576 |
|
| 166 |
+
| 0.8736 | 0.4518 | 1100 | 0.8570 |
|
| 167 |
+
| 0.8611 | 0.4560 | 1110 | 0.8563 |
|
| 168 |
+
| 0.872 | 0.4601 | 1120 | 0.8558 |
|
| 169 |
+
| 0.8756 | 0.4642 | 1130 | 0.8554 |
|
| 170 |
+
| 0.8793 | 0.4683 | 1140 | 0.8548 |
|
| 171 |
+
| 0.8872 | 0.4724 | 1150 | 0.8545 |
|
| 172 |
+
| 0.8719 | 0.4765 | 1160 | 0.8539 |
|
| 173 |
+
| 0.8699 | 0.4806 | 1170 | 0.8536 |
|
| 174 |
+
| 0.8779 | 0.4847 | 1180 | 0.8527 |
|
| 175 |
+
| 0.876 | 0.4888 | 1190 | 0.8526 |
|
| 176 |
+
| 0.8777 | 0.4929 | 1200 | 0.8519 |
|
| 177 |
+
| 0.8552 | 0.4970 | 1210 | 0.8514 |
|
| 178 |
+
| 0.8717 | 0.5011 | 1220 | 0.8508 |
|
| 179 |
+
| 0.879 | 0.5053 | 1230 | 0.8502 |
|
| 180 |
+
| 0.8606 | 0.5094 | 1240 | 0.8499 |
|
| 181 |
+
| 0.865 | 0.5135 | 1250 | 0.8492 |
|
| 182 |
+
| 0.8723 | 0.5176 | 1260 | 0.8489 |
|
| 183 |
+
| 0.8685 | 0.5217 | 1270 | 0.8485 |
|
| 184 |
+
| 0.8521 | 0.5258 | 1280 | 0.8480 |
|
| 185 |
+
| 0.8666 | 0.5299 | 1290 | 0.8475 |
|
| 186 |
+
| 0.8621 | 0.5340 | 1300 | 0.8473 |
|
| 187 |
+
| 0.8509 | 0.5381 | 1310 | 0.8469 |
|
| 188 |
+
| 0.8604 | 0.5422 | 1320 | 0.8462 |
|
| 189 |
+
| 0.8692 | 0.5463 | 1330 | 0.8459 |
|
| 190 |
+
| 0.8684 | 0.5504 | 1340 | 0.8454 |
|
| 191 |
+
| 0.8701 | 0.5545 | 1350 | 0.8451 |
|
| 192 |
+
| 0.856 | 0.5587 | 1360 | 0.8445 |
|
| 193 |
+
| 0.8578 | 0.5628 | 1370 | 0.8439 |
|
| 194 |
+
| 0.862 | 0.5669 | 1380 | 0.8435 |
|
| 195 |
+
| 0.8563 | 0.5710 | 1390 | 0.8431 |
|
| 196 |
+
| 0.8503 | 0.5751 | 1400 | 0.8428 |
|
| 197 |
+
| 0.857 | 0.5792 | 1410 | 0.8425 |
|
| 198 |
+
| 0.8468 | 0.5833 | 1420 | 0.8419 |
|
| 199 |
+
| 0.8555 | 0.5874 | 1430 | 0.8415 |
|
| 200 |
+
| 0.8398 | 0.5915 | 1440 | 0.8412 |
|
| 201 |
+
| 0.8649 | 0.5956 | 1450 | 0.8407 |
|
| 202 |
+
| 0.8495 | 0.5997 | 1460 | 0.8404 |
|
| 203 |
+
| 0.855 | 0.6038 | 1470 | 0.8401 |
|
| 204 |
+
| 0.8531 | 0.6079 | 1480 | 0.8397 |
|
| 205 |
+
| 0.8614 | 0.6121 | 1490 | 0.8391 |
|
| 206 |
+
| 0.8481 | 0.6162 | 1500 | 0.8389 |
|
| 207 |
+
| 0.861 | 0.6203 | 1510 | 0.8385 |
|
| 208 |
+
| 0.8426 | 0.6244 | 1520 | 0.8384 |
|
| 209 |
+
| 0.8494 | 0.6285 | 1530 | 0.8380 |
|
| 210 |
+
| 0.8475 | 0.6326 | 1540 | 0.8375 |
|
| 211 |
+
| 0.8563 | 0.6367 | 1550 | 0.8372 |
|
| 212 |
+
| 0.8372 | 0.6408 | 1560 | 0.8369 |
|
| 213 |
+
| 0.8567 | 0.6449 | 1570 | 0.8366 |
|
| 214 |
+
| 0.8555 | 0.6490 | 1580 | 0.8365 |
|
| 215 |
+
| 0.8435 | 0.6531 | 1590 | 0.8361 |
|
| 216 |
+
| 0.8533 | 0.6572 | 1600 | 0.8356 |
|
| 217 |
+
| 0.8431 | 0.6613 | 1610 | 0.8353 |
|
| 218 |
+
| 0.8577 | 0.6655 | 1620 | 0.8352 |
|
| 219 |
+
| 0.854 | 0.6696 | 1630 | 0.8347 |
|
| 220 |
+
| 0.8376 | 0.6737 | 1640 | 0.8347 |
|
| 221 |
+
| 0.8403 | 0.6778 | 1650 | 0.8343 |
|
| 222 |
+
| 0.8629 | 0.6819 | 1660 | 0.8340 |
|
| 223 |
+
| 0.841 | 0.6860 | 1670 | 0.8337 |
|
| 224 |
+
| 0.8339 | 0.6901 | 1680 | 0.8334 |
|
| 225 |
+
| 0.855 | 0.6942 | 1690 | 0.8331 |
|
| 226 |
+
| 0.8391 | 0.6983 | 1700 | 0.8327 |
|
| 227 |
+
| 0.8488 | 0.7024 | 1710 | 0.8324 |
|
| 228 |
+
| 0.8458 | 0.7065 | 1720 | 0.8322 |
|
| 229 |
+
| 0.8495 | 0.7106 | 1730 | 0.8319 |
|
| 230 |
+
| 0.8543 | 0.7147 | 1740 | 0.8317 |
|
| 231 |
+
| 0.8453 | 0.7189 | 1750 | 0.8317 |
|
| 232 |
+
| 0.8378 | 0.7230 | 1760 | 0.8313 |
|
| 233 |
+
| 0.8447 | 0.7271 | 1770 | 0.8309 |
|
| 234 |
+
| 0.8505 | 0.7312 | 1780 | 0.8306 |
|
| 235 |
+
| 0.8384 | 0.7353 | 1790 | 0.8303 |
|
| 236 |
+
| 0.824 | 0.7394 | 1800 | 0.8302 |
|
| 237 |
+
| 0.8574 | 0.7435 | 1810 | 0.8298 |
|
| 238 |
+
| 0.8365 | 0.7476 | 1820 | 0.8296 |
|
| 239 |
+
| 0.853 | 0.7517 | 1830 | 0.8294 |
|
| 240 |
+
| 0.8409 | 0.7558 | 1840 | 0.8292 |
|
| 241 |
+
| 0.8417 | 0.7599 | 1850 | 0.8290 |
|
| 242 |
+
| 0.8413 | 0.7640 | 1860 | 0.8288 |
|
| 243 |
+
| 0.8294 | 0.7681 | 1870 | 0.8286 |
|
| 244 |
+
| 0.8535 | 0.7723 | 1880 | 0.8283 |
|
| 245 |
+
| 0.8352 | 0.7764 | 1890 | 0.8281 |
|
| 246 |
+
| 0.8411 | 0.7805 | 1900 | 0.8281 |
|
| 247 |
+
| 0.8498 | 0.7846 | 1910 | 0.8279 |
|
| 248 |
+
| 0.8322 | 0.7887 | 1920 | 0.8276 |
|
| 249 |
+
| 0.8504 | 0.7928 | 1930 | 0.8273 |
|
| 250 |
+
| 0.8274 | 0.7969 | 1940 | 0.8272 |
|
| 251 |
+
| 0.8378 | 0.8010 | 1950 | 0.8269 |
|
| 252 |
+
| 0.8364 | 0.8051 | 1960 | 0.8268 |
|
| 253 |
+
| 0.8395 | 0.8092 | 1970 | 0.8267 |
|
| 254 |
+
| 0.8472 | 0.8133 | 1980 | 0.8264 |
|
| 255 |
+
| 0.8577 | 0.8174 | 1990 | 0.8262 |
|
| 256 |
+
| 0.8277 | 0.8215 | 2000 | 0.8259 |
|
| 257 |
+
| 0.8371 | 0.8257 | 2010 | 0.8258 |
|
| 258 |
+
| 0.8477 | 0.8298 | 2020 | 0.8256 |
|
| 259 |
+
| 0.8282 | 0.8339 | 2030 | 0.8256 |
|
| 260 |
+
| 0.8335 | 0.8380 | 2040 | 0.8255 |
|
| 261 |
+
| 0.8323 | 0.8421 | 2050 | 0.8253 |
|
| 262 |
+
| 0.8319 | 0.8462 | 2060 | 0.8251 |
|
| 263 |
+
| 0.8126 | 0.8503 | 2070 | 0.8250 |
|
| 264 |
+
| 0.8436 | 0.8544 | 2080 | 0.8249 |
|
| 265 |
+
| 0.8248 | 0.8585 | 2090 | 0.8248 |
|
| 266 |
+
| 0.8261 | 0.8626 | 2100 | 0.8245 |
|
| 267 |
+
| 0.8234 | 0.8667 | 2110 | 0.8244 |
|
| 268 |
+
| 0.8592 | 0.8708 | 2120 | 0.8243 |
|
| 269 |
+
| 0.8275 | 0.8749 | 2130 | 0.8242 |
|
| 270 |
+
| 0.8426 | 0.8791 | 2140 | 0.8240 |
|
| 271 |
+
| 0.8433 | 0.8832 | 2150 | 0.8240 |
|
| 272 |
+
| 0.8281 | 0.8873 | 2160 | 0.8239 |
|
| 273 |
+
| 0.8381 | 0.8914 | 2170 | 0.8237 |
|
| 274 |
+
| 0.8382 | 0.8955 | 2180 | 0.8235 |
|
| 275 |
+
| 0.8164 | 0.8996 | 2190 | 0.8234 |
|
| 276 |
+
| 0.8343 | 0.9037 | 2200 | 0.8233 |
|
| 277 |
+
| 0.8367 | 0.9078 | 2210 | 0.8231 |
|
| 278 |
+
| 0.837 | 0.9119 | 2220 | 0.8230 |
|
| 279 |
+
| 0.8245 | 0.9160 | 2230 | 0.8229 |
|
| 280 |
+
| 0.8489 | 0.9201 | 2240 | 0.8228 |
|
| 281 |
+
| 0.8391 | 0.9242 | 2250 | 0.8227 |
|
| 282 |
+
| 0.8341 | 0.9283 | 2260 | 0.8227 |
|
| 283 |
+
| 0.8442 | 0.9325 | 2270 | 0.8226 |
|
| 284 |
+
| 0.8302 | 0.9366 | 2280 | 0.8225 |
|
| 285 |
+
| 0.832 | 0.9407 | 2290 | 0.8224 |
|
| 286 |
+
| 0.833 | 0.9448 | 2300 | 0.8223 |
|
| 287 |
+
| 0.8313 | 0.9489 | 2310 | 0.8223 |
|
| 288 |
+
| 0.8444 | 0.9530 | 2320 | 0.8222 |
|
| 289 |
+
| 0.8405 | 0.9571 | 2330 | 0.8221 |
|
| 290 |
+
| 0.8433 | 0.9612 | 2340 | 0.8221 |
|
| 291 |
+
| 0.8348 | 0.9653 | 2350 | 0.8220 |
|
| 292 |
+
| 0.8355 | 0.9694 | 2360 | 0.8219 |
|
| 293 |
+
| 0.8361 | 0.9735 | 2370 | 0.8219 |
|
| 294 |
+
| 0.8254 | 0.9776 | 2380 | 0.8219 |
|
| 295 |
+
| 0.8371 | 0.9817 | 2390 | 0.8218 |
|
| 296 |
+
| 0.8304 | 0.9859 | 2400 | 0.8218 |
|
| 297 |
+
| 0.8169 | 0.9900 | 2410 | 0.8218 |
|
| 298 |
+
| 0.8219 | 0.9941 | 2420 | 0.8217 |
|
| 299 |
+
| 0.833 | 0.9982 | 2430 | 0.8217 |
|
| 300 |
+
|
| 301 |
+
|
| 302 |
+
### Framework versions
|
| 303 |
+
|
| 304 |
+
- PEFT 0.10.0
|
| 305 |
+
- Transformers 4.41.0.dev0
|
| 306 |
+
- Pytorch 2.3.1+cu121
|
| 307 |
+
- Datasets 2.19.0
|
| 308 |
+
- Tokenizers 0.19.1
|
runs/Jul02_00-15-06_gpuhpc06/events.out.tfevents.1719846910.gpuhpc06
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 sha256:7781b2c0700ab836e732a46de9f61551bb52aa974ff3545f3c095359a6a58ab7
|
| 3 |
+
size 123731
|