Hugging Face's logo

raulgdp
/
Mistral-7B-Instruct-v0.3-JEP

PEFT
Safetensors
Spanish
Generated from Trainer
Model card Files
xet
 Community
raulgdp commited on
Commit
b2ed097
·
verified ·
1 Parent(s): eb4f69d

End of training

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. adapter_model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: mistralai/Mistral-7B-Instruct-v0.3
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Mistral-7B-Instruct-v0.3-JEP
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Mistral-7B-Instruct-v0.3-JEP
16
+
17
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.9339
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 4
44
+ - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - num_epochs: 10
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:------:|:----:|:---------------:|
53
+ | 1.1764 | 0.1535 | 100 | 1.1504 |
54
+ | 1.0487 | 0.3070 | 200 | 1.0548 |
55
+ | 0.9853 | 0.4605 | 300 | 1.0175 |
56
+ | 0.9844 | 0.6140 | 400 | 0.9919 |
57
+ | 1.011 | 0.7675 | 500 | 0.9780 |
58
+ | 0.9396 | 0.9210 | 600 | 0.9663 |
59
+ | 0.9259 | 1.0737 | 700 | 0.9569 |
60
+ | 0.9444 | 1.2272 | 800 | 0.9483 |
61
+ | 0.8928 | 1.3807 | 900 | 0.9415 |
62
+ | 0.9195 | 1.5342 | 1000 | 0.9364 |
63
+ | 0.8967 | 1.6876 | 1100 | 0.9338 |
64
+ | 0.927 | 1.8411 | 1200 | 0.9300 |
65
+ | 0.9417 | 1.9946 | 1300 | 0.9263 |
66
+ | 0.9198 | 2.1474 | 1400 | 0.9276 |
67
+ | 0.9108 | 2.3008 | 1500 | 0.9237 |
68
+ | 0.8971 | 2.4543 | 1600 | 0.9223 |
69
+ | 0.8758 | 2.6078 | 1700 | 0.9199 |
70
+ | 0.8681 | 2.7613 | 1800 | 0.9169 |
71
+ | 0.8557 | 2.9148 | 1900 | 0.9153 |
72
+ | 0.82 | 3.0675 | 2000 | 0.9161 |
73
+ | 0.8379 | 3.2210 | 2100 | 0.9170 |
74
+ | 0.8414 | 3.3745 | 2200 | 0.9161 |
75
+ | 0.9164 | 3.5280 | 2300 | 0.9141 |
76
+ | 0.8764 | 3.6815 | 2400 | 0.9101 |
77
+ | 0.8449 | 3.8350 | 2500 | 0.9094 |
78
+ | 0.8708 | 3.9885 | 2600 | 0.9088 |
79
+ | 0.83 | 4.1412 | 2700 | 0.9132 |
80
+ | 0.7793 | 4.2947 | 2800 | 0.9148 |
81
+ | 0.8527 | 4.4482 | 2900 | 0.9120 |
82
+ | 0.7941 | 4.6017 | 3000 | 0.9102 |
83
+ | 0.8103 | 4.7552 | 3100 | 0.9111 |
84
+ | 0.7991 | 4.9087 | 3200 | 0.9083 |
85
+ | 0.7791 | 5.0614 | 3300 | 0.9126 |
86
+ | 0.8297 | 5.2149 | 3400 | 0.9154 |
87
+ | 0.739 | 5.3684 | 3500 | 0.9181 |
88
+ | 0.8456 | 5.5219 | 3600 | 0.9105 |
89
+ | 0.826 | 5.6754 | 3700 | 0.9135 |
90
+ | 0.8336 | 5.8289 | 3800 | 0.9127 |
91
+ | 0.7995 | 5.9823 | 3900 | 0.9134 |
92
+ | 0.7782 | 6.1351 | 4000 | 0.9207 |
93
+ | 0.7822 | 6.2886 | 4100 | 0.9170 |
94
+ | 0.7556 | 6.4421 | 4200 | 0.9182 |
95
+ | 0.7522 | 6.5955 | 4300 | 0.9213 |
96
+ | 0.7669 | 6.7490 | 4400 | 0.9168 |
97
+ | 0.7503 | 6.9025 | 4500 | 0.9173 |
98
+ | 0.7739 | 7.0553 | 4600 | 0.9217 |
99
+ | 0.7699 | 7.2087 | 4700 | 0.9293 |
100
+ | 0.761 | 7.3622 | 4800 | 0.9234 |
101
+ | 0.7257 | 7.5157 | 4900 | 0.9269 |
102
+ | 0.7394 | 7.6692 | 5000 | 0.9233 |
103
+ | 0.7354 | 7.8227 | 5100 | 0.9218 |
104
+ | 0.8162 | 7.9762 | 5200 | 0.9209 |
105
+ | 0.7276 | 8.1289 | 5300 | 0.9294 |
106
+ | 0.7477 | 8.2824 | 5400 | 0.9299 |
107
+ | 0.7278 | 8.4359 | 5500 | 0.9282 |
108
+ | 0.6571 | 8.5894 | 5600 | 0.9297 |
109
+ | 0.7494 | 8.7429 | 5700 | 0.9286 |
110
+ | 0.767 | 8.8964 | 5800 | 0.9267 |
111
+ | 0.6792 | 9.0491 | 5900 | 0.9338 |
112
+ | 0.7053 | 9.2026 | 6000 | 0.9350 |
113
+ | 0.706 | 9.3561 | 6100 | 0.9351 |
114
+ | 0.7232 | 9.5096 | 6200 | 0.9334 |
115
+ | 0.7301 | 9.6631 | 6300 | 0.9332 |
116
+ | 0.7424 | 9.8166 | 6400 | 0.9344 |
117
+ | 0.6775 | 9.9701 | 6500 | 0.9339 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.15.2
123
+ - Transformers 4.51.3
124
+ - Pytorch 2.6.0+cu126
125
+ - Datasets 3.5.0
126
+ - Tokenizers 0.21.1
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91102fb0b26efeda8eba936986d347dadc8778c65588727138678c354d1d78e8
3
  size 27297032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d7851a042f87dcac1e0a874ba5a91a5856f2c999516bbd84d9af79497714a0
3
  size 27297032