Update README.md
Browse files
README.md
CHANGED
@@ -5,6 +5,9 @@ tags:
|
|
5 |
model-index:
|
6 |
- name: checkpoint-41_9k-lr5em5-bs15n5_r64LA128dt01_2811
|
7 |
results: []
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -26,7 +29,7 @@ More information needed
|
|
26 |
|
27 |
## Training and evaluation data
|
28 |
|
29 |
-
|
30 |
|
31 |
## Training procedure
|
32 |
|
@@ -43,6 +46,13 @@ The following hyperparameters were used during training:
|
|
43 |
- lr_scheduler_type: cosine
|
44 |
- lr_scheduler_warmup_steps: 300
|
45 |
- num_epochs: 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
### Training results
|
48 |
|
@@ -72,5 +82,12 @@ The following hyperparameters were used during training:
|
|
72 |
|
73 |
- Transformers 4.35.2
|
74 |
- Pytorch 2.1.1+cu121
|
75 |
-
- Datasets 2.
|
76 |
- Tokenizers 0.15.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
model-index:
|
6 |
- name: checkpoint-41_9k-lr5em5-bs15n5_r64LA128dt01_2811
|
7 |
results: []
|
8 |
+
license: mit
|
9 |
+
language:
|
10 |
+
- es
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
29 |
|
30 |
## Training and evaluation data
|
31 |
|
32 |
+
The used Dataset is "BrunoGR/HEAR-Hispanic_Emotional_Accompaniment_Responses".
|
33 |
|
34 |
## Training procedure
|
35 |
|
|
|
46 |
- lr_scheduler_type: cosine
|
47 |
- lr_scheduler_warmup_steps: 300
|
48 |
- num_epochs: 3
|
49 |
+
Lora Parameters:
|
50 |
+
- r: 64
|
51 |
+
- Alpha: 128
|
52 |
+
- LoRA_DROPOUT: 0.1
|
53 |
+
- bias: "none"
|
54 |
+
- task_type: "CAUSAL_LM"
|
55 |
+
- LoRA_TARGET_MODULES = \[ "q_proj", "v_proj" \]
|
56 |
|
57 |
### Training results
|
58 |
|
|
|
82 |
|
83 |
- Transformers 4.35.2
|
84 |
- Pytorch 2.1.1+cu121
|
85 |
+
- Datasets 2.16.0
|
86 |
- Tokenizers 0.15.0
|
87 |
+
- torch: 2.1.1
|
88 |
+
- trl: 0.7.5
|
89 |
+
- tokenizers: 0.15.0
|
90 |
+
- peft: 0.7.0
|
91 |
+
- evaluate: 0.4.1
|
92 |
+
- accelerate: 0.25.0
|
93 |
+
- seaborn: 0.13.0
|