Model save
Browse files
README.md
CHANGED
|
@@ -1,26 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
datasets:
|
| 7 |
-
- tyzhu/lmind_nq_train6000_eval6489_v1_qa
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
model-index:
|
| 11 |
- name: lmind_nq_train6000_eval6489_v1_qa_5e-4_lora2
|
| 12 |
-
results:
|
| 13 |
-
- task:
|
| 14 |
-
name: Causal Language Modeling
|
| 15 |
-
type: text-generation
|
| 16 |
-
dataset:
|
| 17 |
-
name: tyzhu/lmind_nq_train6000_eval6489_v1_qa
|
| 18 |
-
type: tyzhu/lmind_nq_train6000_eval6489_v1_qa
|
| 19 |
-
metrics:
|
| 20 |
-
- name: Accuracy
|
| 21 |
-
type: accuracy
|
| 22 |
-
value: 0.5299487179487179
|
| 23 |
-
library_name: peft
|
| 24 |
---
|
| 25 |
|
| 26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -28,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 28 |
|
| 29 |
# lmind_nq_train6000_eval6489_v1_qa_5e-4_lora2
|
| 30 |
|
| 31 |
-
This model is a fine-tuned version of [
|
| 32 |
It achieves the following results on the evaluation set:
|
| 33 |
-
- Loss:
|
| 34 |
-
- Accuracy: 0.
|
| 35 |
|
| 36 |
## Model description
|
| 37 |
|
|
@@ -51,12 +38,12 @@ More information needed
|
|
| 51 |
|
| 52 |
The following hyperparameters were used during training:
|
| 53 |
- learning_rate: 0.0005
|
| 54 |
-
- train_batch_size:
|
| 55 |
- eval_batch_size: 2
|
| 56 |
- seed: 42
|
| 57 |
- distributed_type: multi-GPU
|
| 58 |
- num_devices: 4
|
| 59 |
-
- gradient_accumulation_steps:
|
| 60 |
- total_train_batch_size: 32
|
| 61 |
- total_eval_batch_size: 8
|
| 62 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
@@ -66,64 +53,63 @@ The following hyperparameters were used during training:
|
|
| 66 |
|
| 67 |
### Training results
|
| 68 |
|
| 69 |
-
| Training Loss | Epoch
|
| 70 |
-
|
| 71 |
-
| 1.
|
| 72 |
-
| 1.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
|
|
| 118 |
-
|
|
| 119 |
-
|
|
| 120 |
-
|
|
| 121 |
|
| 122 |
|
| 123 |
### Framework versions
|
| 124 |
|
| 125 |
-
-
|
| 126 |
-
- Transformers 4.41.1
|
| 127 |
- Pytorch 2.1.0+cu121
|
| 128 |
-
- Datasets 2.
|
| 129 |
-
- Tokenizers 0.
|
|
|
|
| 1 |
---
|
| 2 |
+
license: llama2
|
| 3 |
+
base_model: meta-llama/Llama-2-7b-hf
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: lmind_nq_train6000_eval6489_v1_qa_5e-4_lora2
|
| 10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
# lmind_nq_train6000_eval6489_v1_qa_5e-4_lora2
|
| 17 |
|
| 18 |
+
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.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 5.5751
|
| 21 |
+
- Accuracy: 0.3655
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 0.0005
|
| 41 |
+
- train_batch_size: 2
|
| 42 |
- eval_batch_size: 2
|
| 43 |
- seed: 42
|
| 44 |
- distributed_type: multi-GPU
|
| 45 |
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
- total_train_batch_size: 32
|
| 48 |
- total_eval_batch_size: 8
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 58 |
+
| 1.43 | 1.0 | 187 | 1.2683 | 0.6162 |
|
| 59 |
+
| 1.0285 | 2.0 | 375 | 1.3220 | 0.6129 |
|
| 60 |
+
| 0.7318 | 3.0 | 562 | 1.4645 | 0.6076 |
|
| 61 |
+
| 0.5898 | 4.0 | 750 | 1.5454 | 0.6050 |
|
| 62 |
+
| 0.5309 | 5.0 | 937 | 1.6439 | 0.6026 |
|
| 63 |
+
| 0.4985 | 6.0 | 1125 | 1.7220 | 0.6034 |
|
| 64 |
+
| 0.5091 | 7.0 | 1312 | 1.8008 | 0.6008 |
|
| 65 |
+
| 0.4796 | 8.0 | 1500 | 1.7782 | 0.6001 |
|
| 66 |
+
| 0.4453 | 9.0 | 1687 | 1.8255 | 0.5985 |
|
| 67 |
+
| 0.448 | 10.0 | 1875 | 1.7979 | 0.5931 |
|
| 68 |
+
| 0.4522 | 11.0 | 2062 | 1.8272 | 0.5959 |
|
| 69 |
+
| 0.4552 | 12.0 | 2250 | 1.8670 | 0.5946 |
|
| 70 |
+
| 0.4551 | 13.0 | 2437 | 1.8706 | 0.5950 |
|
| 71 |
+
| 0.4559 | 14.0 | 2625 | 1.8731 | 0.5925 |
|
| 72 |
+
| 0.4581 | 15.0 | 2812 | 1.8531 | 0.5932 |
|
| 73 |
+
| 0.4535 | 16.0 | 3000 | 1.9492 | 0.5923 |
|
| 74 |
+
| 0.4308 | 17.0 | 3187 | 1.8944 | 0.5915 |
|
| 75 |
+
| 0.4312 | 18.0 | 3375 | 1.9315 | 0.5904 |
|
| 76 |
+
| 0.4372 | 19.0 | 3562 | 1.9201 | 0.5899 |
|
| 77 |
+
| 0.4359 | 20.0 | 3750 | 1.9753 | 0.5895 |
|
| 78 |
+
| 0.4363 | 21.0 | 3937 | 1.9932 | 0.5877 |
|
| 79 |
+
| 0.4404 | 22.0 | 4125 | 2.0326 | 0.5866 |
|
| 80 |
+
| 0.4436 | 23.0 | 4312 | 2.0008 | 0.5848 |
|
| 81 |
+
| 0.4438 | 24.0 | 4500 | 2.0186 | 0.5877 |
|
| 82 |
+
| 0.4233 | 25.0 | 4687 | 2.0452 | 0.5863 |
|
| 83 |
+
| 0.4237 | 26.0 | 4875 | 2.0520 | 0.5843 |
|
| 84 |
+
| 0.4289 | 27.0 | 5062 | 2.0817 | 0.5828 |
|
| 85 |
+
| 0.4325 | 28.0 | 5250 | 2.0512 | 0.5833 |
|
| 86 |
+
| 0.4329 | 29.0 | 5437 | 2.0906 | 0.5828 |
|
| 87 |
+
| 0.4314 | 30.0 | 5625 | 2.0403 | 0.5824 |
|
| 88 |
+
| 0.431 | 31.0 | 5812 | 2.1194 | 0.5824 |
|
| 89 |
+
| 0.4318 | 32.0 | 6000 | 2.0985 | 0.5829 |
|
| 90 |
+
| 0.414 | 33.0 | 6187 | 2.1533 | 0.5805 |
|
| 91 |
+
| 0.4214 | 34.0 | 6375 | 2.1918 | 0.5779 |
|
| 92 |
+
| 0.4264 | 35.0 | 6562 | 2.1835 | 0.5774 |
|
| 93 |
+
| 0.4361 | 36.0 | 6750 | 2.1864 | 0.5771 |
|
| 94 |
+
| 0.4369 | 37.0 | 6937 | 2.1546 | 0.5761 |
|
| 95 |
+
| 0.4362 | 38.0 | 7125 | 2.1423 | 0.5752 |
|
| 96 |
+
| 0.4322 | 39.0 | 7312 | 2.1938 | 0.5778 |
|
| 97 |
+
| 0.4359 | 40.0 | 7500 | 2.2000 | 0.5752 |
|
| 98 |
+
| 0.4153 | 41.0 | 7687 | 2.2344 | 0.5751 |
|
| 99 |
+
| 0.4195 | 42.0 | 7875 | 2.2526 | 0.5747 |
|
| 100 |
+
| 0.9164 | 43.0 | 8062 | 2.1985 | 0.5717 |
|
| 101 |
+
| 0.4295 | 44.0 | 8250 | 2.2145 | 0.5718 |
|
| 102 |
+
| 0.4298 | 45.0 | 8437 | 2.2211 | 0.5714 |
|
| 103 |
+
| 0.4446 | 46.0 | 8625 | 2.2656 | 0.5703 |
|
| 104 |
+
| 2.0935 | 47.0 | 8812 | 2.6962 | 0.5081 |
|
| 105 |
+
| 3.096 | 48.0 | 9000 | 3.2961 | 0.4494 |
|
| 106 |
+
| 2.9615 | 49.0 | 9187 | 4.3483 | 0.4241 |
|
| 107 |
+
| 4.5736 | 49.87 | 9350 | 5.5751 | 0.3655 |
|
| 108 |
|
| 109 |
|
| 110 |
### Framework versions
|
| 111 |
|
| 112 |
+
- Transformers 4.34.0
|
|
|
|
| 113 |
- Pytorch 2.1.0+cu121
|
| 114 |
+
- Datasets 2.18.0
|
| 115 |
+
- Tokenizers 0.14.1
|