desarrolloasesoreslocales commited on
Commit
320256f
·
1 Parent(s): ddacf84

desarrolloasesoreslocales/legal-mistral-v2

Browse files
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.1
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: legal-mistral-v2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # legal-mistral-v2
15
+
16
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.9807
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 80
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 1
44
+
45
+ ### Training results
46
+
47
+ | Training Loss | Epoch | Step | Validation Loss |
48
+ |:-------------:|:-----:|:----:|:---------------:|
49
+ | 2.9084 | 0.09 | 100 | 2.5259 |
50
+ | 2.5097 | 0.17 | 200 | 2.3141 |
51
+ | 2.377 | 0.26 | 300 | 2.1949 |
52
+ | 2.2432 | 0.34 | 400 | 2.1256 |
53
+ | 2.215 | 0.43 | 500 | 2.0810 |
54
+ | 2.1517 | 0.52 | 600 | 2.0496 |
55
+ | 2.0899 | 0.6 | 700 | 2.0256 |
56
+ | 2.0947 | 0.69 | 800 | 2.0088 |
57
+ | 2.0748 | 0.77 | 900 | 1.9961 |
58
+ | 2.0845 | 0.86 | 1000 | 1.9865 |
59
+ | 2.0586 | 0.95 | 1100 | 1.9807 |
60
+
61
+
62
+ ### Framework versions
63
+
64
+ - Transformers 4.35.2
65
+ - Pytorch 2.1.0+cu118
66
+ - Datasets 2.15.0
67
+ - Tokenizers 0.15.0
runs/Dec04_13-04-25_978396801cfc/events.out.tfevents.1701695072.978396801cfc.12148.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d0fe11c3d9c2a6c198bfa07e66db2fbf80dade77a6b3a55bd40d852cc09072b
3
- size 9356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4db340c039b17dfc66f84eeb8d602c00f2edb03d0efff15b7dd9608379b37c
3
+ size 9710
runs/Dec04_13-04-25_978396801cfc/events.out.tfevents.1701734568.978396801cfc.12148.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29402a75c48f5106a8ca3674768a247d4a265a6cc20d7c109e186cd647c9f466
3
+ size 359