Upload folder using huggingface_hub
Browse files- README.md +181 -42
- checkpoint-3/adapter_config.json +2 -2
- checkpoint-3/adapter_model.safetensors +1 -1
- checkpoint-3/optimizer.pt +1 -1
- checkpoint-3/rng_state.pth +1 -1
- checkpoint-3/trainer_state.json +4 -4
- checkpoint-3/training_args.bin +2 -2
- checkpoint-6/adapter_config.json +2 -2
- checkpoint-6/adapter_model.safetensors +1 -1
- checkpoint-6/optimizer.pt +1 -1
- checkpoint-6/rng_state.pth +1 -1
- checkpoint-6/trainer_state.json +8 -8
- checkpoint-6/training_args.bin +2 -2
README.md
CHANGED
@@ -1,63 +1,202 @@
|
|
1 |
---
|
2 |
-
library_name: peft
|
3 |
-
license: llama2
|
4 |
base_model: meta-llama/Llama-2-7b-chat-hf
|
5 |
-
|
6 |
-
- generated_from_trainer
|
7 |
-
model-index:
|
8 |
-
- name: llama2-violencia_genero
|
9 |
-
results: []
|
10 |
---
|
11 |
|
12 |
-
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
-
|
16 |
|
17 |
-
|
18 |
-
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 14.9933
|
20 |
|
21 |
-
|
22 |
|
23 |
-
More
|
24 |
|
25 |
-
|
26 |
|
27 |
-
More
|
28 |
|
29 |
-
##
|
30 |
|
31 |
-
|
32 |
|
33 |
-
|
34 |
|
35 |
-
|
36 |
|
37 |
-
|
38 |
-
- learning_rate: 2e-05
|
39 |
-
- train_batch_size: 1
|
40 |
-
- eval_batch_size: 1
|
41 |
-
- seed: 42
|
42 |
-
- gradient_accumulation_steps: 32
|
43 |
-
- total_train_batch_size: 32
|
44 |
-
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 3
|
47 |
-
- mixed_precision_training: Native AMP
|
48 |
|
49 |
-
|
50 |
|
51 |
-
|
52 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| No log | 1.0 | 3 | 15.2179 |
|
54 |
-
| No log | 2.0 | 6 | 14.9933 |
|
55 |
|
|
|
56 |
|
|
|
57 |
### Framework versions
|
58 |
|
59 |
-
- PEFT 0.14.0
|
60 |
-
- Transformers 4.48.3
|
61 |
-
- Pytorch 2.5.1+cu124
|
62 |
-
- Datasets 3.3.2
|
63 |
-
- Tokenizers 0.21.0
|
|
|
1 |
---
|
|
|
|
|
2 |
base_model: meta-llama/Llama-2-7b-chat-hf
|
3 |
+
library_name: peft
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
|
171 |
+
## Citation [optional]
|
172 |
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
|
|
|
|
174 |
|
175 |
+
**BibTeX:**
|
176 |
|
177 |
+
[More Information Needed]
|
178 |
|
179 |
+
**APA:**
|
180 |
|
181 |
+
[More Information Needed]
|
182 |
|
183 |
+
## Glossary [optional]
|
184 |
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
|
187 |
+
[More Information Needed]
|
188 |
|
189 |
+
## More Information [optional]
|
190 |
|
191 |
+
[More Information Needed]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
|
193 |
+
## Model Card Authors [optional]
|
194 |
|
195 |
+
[More Information Needed]
|
|
|
|
|
|
|
196 |
|
197 |
+
## Model Card Contact
|
198 |
|
199 |
+
[More Information Needed]
|
200 |
### Framework versions
|
201 |
|
202 |
+
- PEFT 0.14.0
|
|
|
|
|
|
|
|
checkpoint-3/adapter_config.json
CHANGED
@@ -23,8 +23,8 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
checkpoint-3/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16794200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:755d2054f62b96028ae4a458eb1fa4abf0b9e40584d5603830a703636c4314de
|
3 |
size 16794200
|
checkpoint-3/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33662074
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:341d4a041c5ac066f8f5e990cf8b60bfe9c37e8cfdb8647b20bfb5b514e4d6be
|
3 |
size 33662074
|
checkpoint-3/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6de5fa485a7b8105a0ef41a51f89cf4c3c295f6e820d54ce0ccfd204b7ab938f
|
3 |
size 14244
|
checkpoint-3/trainer_state.json
CHANGED
@@ -10,10 +10,10 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_runtime": 3.
|
15 |
-
"eval_samples_per_second": 2.
|
16 |
-
"eval_steps_per_second": 2.
|
17 |
"step": 3
|
18 |
}
|
19 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 12.453683853149414,
|
14 |
+
"eval_runtime": 3.2768,
|
15 |
+
"eval_samples_per_second": 2.747,
|
16 |
+
"eval_steps_per_second": 2.747,
|
17 |
"step": 3
|
18 |
}
|
19 |
],
|
checkpoint-3/training_args.bin
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 sha256:1e0ed3a648cd8a54f73665296e6710e9919bcb759a54f7ca1cb36559d879a694
|
3 |
+
size 5304
|
checkpoint-6/adapter_config.json
CHANGED
@@ -23,8 +23,8 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
27 |
-
"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"v_proj",
|
27 |
+
"q_proj"
|
28 |
],
|
29 |
"task_type": "CAUSAL_LM",
|
30 |
"use_dora": false,
|
checkpoint-6/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16794200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a04314cc3785486ed9cdd9cfda90a122e36e2e3fbaa593fe9e816a486ee9c6f0
|
3 |
size 16794200
|
checkpoint-6/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33662074
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bac5178077958843c5e3c3147ff25f0ce98bdc3ee96fa104d9edf28b7eb4bc55
|
3 |
size 33662074
|
checkpoint-6/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a42e76873585df4b01608448a5f83221108e7c5f78ee8675d490003b6029f80
|
3 |
size 14244
|
checkpoint-6/trainer_state.json
CHANGED
@@ -10,18 +10,18 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_runtime": 3.
|
15 |
-
"eval_samples_per_second": 2.
|
16 |
-
"eval_steps_per_second": 2.
|
17 |
"step": 3
|
18 |
},
|
19 |
{
|
20 |
"epoch": 2.0,
|
21 |
-
"eval_loss":
|
22 |
-
"eval_runtime": 3.
|
23 |
-
"eval_samples_per_second": 2.
|
24 |
-
"eval_steps_per_second": 2.
|
25 |
"step": 6
|
26 |
}
|
27 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 12.453683853149414,
|
14 |
+
"eval_runtime": 3.2768,
|
15 |
+
"eval_samples_per_second": 2.747,
|
16 |
+
"eval_steps_per_second": 2.747,
|
17 |
"step": 3
|
18 |
},
|
19 |
{
|
20 |
"epoch": 2.0,
|
21 |
+
"eval_loss": 12.341687202453613,
|
22 |
+
"eval_runtime": 3.2387,
|
23 |
+
"eval_samples_per_second": 2.779,
|
24 |
+
"eval_steps_per_second": 2.779,
|
25 |
"step": 6
|
26 |
}
|
27 |
],
|
checkpoint-6/training_args.bin
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 sha256:1e0ed3a648cd8a54f73665296e6710e9919bcb759a54f7ca1cb36559d879a694
|
3 |
+
size 5304
|