Iker commited on
Commit
161aecb
1 Parent(s): ef9c263

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +442 -196
README.md CHANGED
@@ -1,201 +1,447 @@
1
  ---
2
  library_name: transformers
3
- tags: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
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
-
201
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  library_name: transformers
3
+ tags:
4
+ - synthetic
5
+ license: llama3
6
+ datasets:
7
+ - pinzhenchen/alpaca-cleaned-es
8
+ - Danielbrdz/Barcenas-Economia
9
+ - HiTZ/casimedicos-exp
10
+ - somosnlp/coser_resumenes
11
+ - csebuetnlp/CrossSum
12
+ - Iker/Document-Translation-en-es
13
+ - somosnlp/es-inclusive-language-it
14
+ - FreedomIntelligence/evol-instruct-spanish
15
+ - glaiveai/glaive-code-assistant-v3
16
+ - glaiveai/glaive-function-calling-v2
17
+ - Iker/InstructTranslation-EN-ES
18
+ - somosnlp/lenguaje-claro-dataset
19
+ - somosnlp/LingComp_QA
20
+ - bltlab/lr-sum
21
+ - Iker/NoticIA
22
+ - xaviviro/oasst2_es_gpt
23
+ - teknium/OpenHermes-2.5
24
+ - Iker/OpenHermes-2.5-Spanish
25
+ - Helsinki-NLP/opus-100
26
+ - projecte-aina/RAG_Multilingual
27
+ - sem_eval_2018_task_1
28
+ - davidstap/ted_talks
29
+ - HiTZ/This-is-not-a-dataset
30
+ - wikipedia
31
+ language:
32
+ - es
33
+ - en
34
+ pipeline_tag: text-generation
35
+ base_model: meta-llama/Meta-Llama-3-8B
36
  ---
37
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
 
39
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/614a1ebb8f82f1df64d55126/2i_CasoeJTgQPNoBIfA8E.jpeg)
40
+
41
+
42
+ # Neurona 8B Beta: Un Modelo de Lenguage en Español
43
+
44
+ > Esta es una versión preliminar del dataset card. El modelo está en desarrollo y no es la versión final. Si quieres saber más sobre este modelo, escribe a [email protected]
45
+
46
+
47
+ Neurona 8B es un modelo de lenguaje en Español. Esta es la primera iteración y un experimento para poner a punto los scripts y la infraestructura.
48
+
49
+ Neurona 8B ha sido entrenado con los siguiente datasets. No en todos los casos se ha usado el dataset completo
50
+
51
+ - [pinzhenchen/alpaca-cleaned-es](https://huggingface.co/datasets/pinzhenchen/alpaca-cleaned-es)
52
+ - [Danielbrdz/Barcenas-Economia](https://huggingface.co/datasets/Danielbrdz/Barcenas-Economia)
53
+ - [HiTZ/casimedicos-exp](https://huggingface.co/datasets/HiTZ/casimedicos-exp)
54
+ - [somosnlp/coser_resumenes](https://huggingface.co/datasets/somosnlp/coser_resumenes)
55
+ - [csebuetnlp/CrossSum en + es](https://huggingface.co/datasets/csebuetnlp/CrossSum)
56
+ - [Iker/Document-Translation-en-es](https://huggingface.co/datasets/Iker/Document-Translation-en-es)
57
+ - [somosnlp/es-inclusive-language-it](https://huggingface.co/datasets/somosnlp/es-inclusive-language-it)
58
+ - [FreedomIntelligence/evol-instruct-spanish](https://huggingface.co/datasets/FreedomIntelligence/evol-instruct-spanish)
59
+ - [glaiveai/glaive-code-assistant-v3](https://huggingface.co/datasets/glaiveai/glaive-code-assistant-v3)
60
+ - [glaiveai/glaive-function-calling-v2](https://huggingface.co/datasets/glaiveai/glaive-function-calling-v2)
61
+ - [Iker/InstructTranslation-EN-ES](https://huggingface.co/datasets/Iker/InstructTranslation-EN-ES)
62
+ - [somosnlp/lenguaje-claro-dataset](https://huggingface.co/datasets/somosnlp/lenguaje-claro-dataset)
63
+ - [somosnlp/LingComp_QA](https://huggingface.co/datasets/somosnlp/LingComp_QA)
64
+ - [bltlab/lr-sum](https://huggingface.co/datasets/bltlab/lr-sum)
65
+ - [Iker/NoticIA](https://huggingface.co/datasets/Iker/NoticIA)
66
+ - [xaviviro/oasst2_es_gpt](https://huggingface.co/datasets/xaviviro/oasst2_es_gpt)
67
+ - [teknium/OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5)
68
+ - [Iker/OpenHermes-2.5-Spanish](https://huggingface.co/datasets/Iker/OpenHermes-2.5-Spanish)
69
+ - [Helsinki-NLP/opus-100 en es](https://huggingface.co/datasets/Helsinki-NLP/opus-100)
70
+ - [projecte-aina/RAG_Multilingual](https://huggingface.co/datasets/projecte-aina/RAG_Multilingual)
71
+ - [sem_eval_2018_task_1](https://huggingface.co/datasets/sem_eval_2018_task_1)
72
+ - [davidstap/ted_talks](https://huggingface.co/datasets/davidstap/ted_talks)
73
+ - [HiTZ/This-is-not-a-dataset](https://huggingface.co/datasets/HiTZ/This-is-not-a-dataset)
74
+ - [wikipedia es](https://huggingface.co/datasets/wikipedia)
75
+
76
+
77
+
78
+
79
+ Esta mezcla de datasets en Inglés y Español, permite al modelo adquirir diferentes capacidades, como RAG, function calling, code assistant, question answering, summarization... tanto en Inglés como en Español.
80
+
81
+ # Entrenamiento
82
+
83
+ Este modelo se ha entrado usando 4xNvidia A100 80Gb y axolotl
84
+ [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
85
+
86
+ Esta es la configuración usada
87
+
88
+ ```yaml
89
+ base_model: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Spanish/base_model
90
+ model_type: AutoModelForCausalLM
91
+ tokenizer_type: AutoTokenizer
92
+ is_falcon_derived_model:
93
+ is_llama_derived_model:
94
+ is_qwen_derived_model:
95
+ is_mistral_derived_model:
96
+
97
+ load_in_8bit: false
98
+ load_in_4bit: false
99
+ strict: false
100
+
101
+ device_map: null
102
+
103
+ datasets:
104
+ - path: /ikerlariak/igarcia945/InstructDatasets/alpaca-cleaned-es.jsonl
105
+ type: sharegpt
106
+ conversation: llama3
107
+ field: conversations
108
+ roles:
109
+ input:
110
+ - system
111
+ - gpt
112
+ output:
113
+ - human
114
+ - path: /ikerlariak/igarcia945/InstructDatasets/Barcenas-Economia.jsonl
115
+ type: sharegpt
116
+ conversation: llama3
117
+ field: conversations
118
+ roles:
119
+ input:
120
+ - system
121
+ - gpt
122
+ output:
123
+ - human
124
+ - path: /ikerlariak/igarcia945/InstructDatasets/casimedicos.jsonl
125
+ type: sharegpt
126
+ conversation: llama3
127
+ field: conversations
128
+ roles:
129
+ input:
130
+ - system
131
+ - gpt
132
+ output:
133
+ - human
134
+ - path: /ikerlariak/igarcia945/InstructDatasets/coser_resumene.jsonl
135
+ type: sharegpt
136
+ conversation: llama3
137
+ field: conversations
138
+ roles:
139
+ input:
140
+ - system
141
+ - gpt
142
+ output:
143
+ - human
144
+ - path: /ikerlariak/igarcia945/InstructDatasets/CrossSum_en.jsonl
145
+ type: sharegpt
146
+ conversation: llama3
147
+ field: conversations
148
+ roles:
149
+ input:
150
+ - system
151
+ - gpt
152
+ output:
153
+ - human
154
+ - path: /ikerlariak/igarcia945/InstructDatasets/CrossSum_es.jsonl
155
+ type: sharegpt
156
+ conversation: llama3
157
+ field: conversations
158
+ roles:
159
+ input:
160
+ - system
161
+ - gpt
162
+ output:
163
+ - human
164
+ - path: /ikerlariak/igarcia945/InstructDatasets/Document-Translation-en-es.jsonl
165
+ type: sharegpt
166
+ conversation: llama3
167
+ field: conversations
168
+ roles:
169
+ input:
170
+ - system
171
+ - gpt
172
+ output:
173
+ - human
174
+ - path: /ikerlariak/igarcia945/InstructDatasets/es-inclusive-language.jsonl
175
+ type: sharegpt
176
+ conversation: llama3
177
+ field: conversations
178
+ roles:
179
+ input:
180
+ - system
181
+ - gpt
182
+ output:
183
+ - human
184
+ - path: /ikerlariak/igarcia945/InstructDatasets/evol-instruct-spanish.jsonl
185
+ type: sharegpt
186
+ conversation: llama3
187
+ field: conversations
188
+ roles:
189
+ input:
190
+ - system
191
+ - gpt
192
+ output:
193
+ - human
194
+ - path: /ikerlariak/igarcia945/InstructDatasets/glaive-code-assistant-v3-small.jsonl
195
+ type: sharegpt
196
+ conversation: llama3
197
+ field: conversations
198
+ roles:
199
+ input:
200
+ - system
201
+ - gpt
202
+ output:
203
+ - human
204
+ - path: /ikerlariak/igarcia945/InstructDatasets/glaive-function-calling-v2.jsonl
205
+ type: sharegpt
206
+ conversation: llama3
207
+ field: conversations
208
+ roles:
209
+ input:
210
+ - system
211
+ - gpt
212
+ - tool
213
+ output:
214
+ - human
215
+ - path: /ikerlariak/igarcia945/InstructDatasets/InstructTranslation-EN-ES.jsonl
216
+ type: sharegpt
217
+ conversation: llama3
218
+ field: conversations
219
+ roles:
220
+ input:
221
+ - system
222
+ - gpt
223
+ output:
224
+ - human
225
+ - path: /ikerlariak/igarcia945/InstructDatasets/lenguaje-claro-dataset.jsonl
226
+ type: sharegpt
227
+ conversation: llama3
228
+ field: conversations
229
+ roles:
230
+ input:
231
+ - system
232
+ - gpt
233
+ output:
234
+ - human
235
+ - path: /ikerlariak/igarcia945/InstructDatasets/LingComp_QA.jsonl
236
+ type: sharegpt
237
+ conversation: llama3
238
+ field: conversations
239
+ roles:
240
+ input:
241
+ - system
242
+ - gpt
243
+ output:
244
+ - human
245
+ - path: /ikerlariak/igarcia945/InstructDatasets/lr-sum-es.jsonl
246
+ type: sharegpt
247
+ conversation: llama3
248
+ field: conversations
249
+ roles:
250
+ input:
251
+ - system
252
+ - gpt
253
+ output:
254
+ - human
255
+ - path: /ikerlariak/igarcia945/InstructDatasets/NoticIA.jsonl
256
+ type: sharegpt
257
+ conversation: llama3
258
+ field: conversations
259
+ roles:
260
+ input:
261
+ - system
262
+ - gpt
263
+ output:
264
+ - human
265
+ - path: /ikerlariak/igarcia945/InstructDatasets/NoticIA-large.jsonl
266
+ type: sharegpt
267
+ conversation: llama3
268
+ field: conversations
269
+ roles:
270
+ input:
271
+ - system
272
+ - gpt
273
+ output:
274
+ - human
275
+ - path: /ikerlariak/igarcia945/InstructDatasets/NoticIA-summary.jsonl
276
+ type: sharegpt
277
+ conversation: llama3
278
+ field: conversations
279
+ roles:
280
+ input:
281
+ - system
282
+ - gpt
283
+ output:
284
+ - human
285
+ - path: /ikerlariak/igarcia945/InstructDatasets/oasst2_es_gpt.jsonl
286
+ type: sharegpt
287
+ conversation: llama3
288
+ field: conversations
289
+ roles:
290
+ input:
291
+ - system
292
+ - gpt
293
+ output:
294
+ - human
295
+ - path: /ikerlariak/igarcia945/InstructDatasets/OpenHermes-2.5-English.jsonl
296
+ type: sharegpt
297
+ conversation: llama3
298
+ field: conversations
299
+ roles:
300
+ input:
301
+ - system
302
+ - gpt
303
+ output:
304
+ - human
305
+ - path: /ikerlariak/igarcia945/InstructDatasets/OpenHermes-2.5-Spanish.jsonl
306
+ type: sharegpt
307
+ conversation: llama3
308
+ field: conversations
309
+ roles:
310
+ input:
311
+ - system
312
+ - gpt
313
+ output:
314
+ - human
315
+ - path: /ikerlariak/igarcia945/InstructDatasets/opus-100-en-es.jsonl
316
+ type: sharegpt
317
+ conversation: llama3
318
+ field: conversations
319
+ roles:
320
+ input:
321
+ - system
322
+ - gpt
323
+ output:
324
+ - human
325
+ - path: /ikerlariak/igarcia945/InstructDatasets/RAG_Multilingual-es.jsonl
326
+ type: sharegpt
327
+ conversation: llama3
328
+ field: conversations
329
+ roles:
330
+ input:
331
+ - system
332
+ - gpt
333
+ output:
334
+ - human
335
+ - path: /ikerlariak/igarcia945/InstructDatasets/sem_eval_2018_task_1.jsonl
336
+ type: sharegpt
337
+ conversation: llama3
338
+ field: conversations
339
+ roles:
340
+ input:
341
+ - system
342
+ - gpt
343
+ output:
344
+ - human
345
+ - path: /ikerlariak/igarcia945/InstructDatasets/ted_talks-es_en.jsonl
346
+ type: sharegpt
347
+ conversation: llama3
348
+ field: conversations
349
+ roles:
350
+ input:
351
+ - system
352
+ - gpt
353
+ output:
354
+ - human
355
+ - path: /ikerlariak/igarcia945/InstructDatasets/This-is-not-a-dataset.jsonl
356
+ type: sharegpt
357
+ conversation: llama3
358
+ field: conversations
359
+ roles:
360
+ input:
361
+ - system
362
+ - gpt
363
+ output:
364
+ - human
365
+ - path: /ikerlariak/igarcia945/InstructDatasets/wikipedia-es.jsonl
366
+ type: sharegpt
367
+ conversation: llama3
368
+ field: conversations
369
+ roles:
370
+ input:
371
+ - system
372
+ - gpt
373
+ output:
374
+ - human
375
+
376
+ chat_template: llama3
377
+
378
+ dataset_prepared_path: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Spanish/dataset
379
+
380
+ shuffle_merged_datasets: true
381
+
382
+ val_set_size: 0.005
383
+
384
+ output_dir: /ikerlariak/igarcia945/Mortadelo-Filemon/Meta-Llama-3-8B-Spanish
385
+
386
+ adapter:
387
+ lora_model_dir:
388
+
389
+ sequence_len: 8192
390
+ sample_packing: true
391
+ eval_sample_packing: false
392
+ pad_to_sequence_len: false
393
+
394
+ tokens:
395
+ - "<tool_call>"
396
+ - "<tool_response>"
397
+ - "<tools>"
398
+ - "</tool_call>"
399
+ - "</tool_response>"
400
+ - "</tools>"
401
+ - "<reserved1>"
402
+ - "<reserved2>"
403
+
404
+
405
+ neftune_noise_alpha: 5
406
+
407
+ wandb_project: Mortadelo&Filemon
408
+ wandb_entity: igarciaf
409
+ wandb_watch:
410
+ wandb_name: meta-llama-3-8B-spanish
411
+ wandb_log_model:
412
+
413
+ gradient_accumulation_steps: 32
414
+ micro_batch_size: 2
415
+ eval_batch_size: 2
416
+ num_epochs: 2
417
+ optimizer: adamw_torch_fused
418
+ lr_scheduler: cosine
419
+ learning_rate: 0.00007
420
+
421
+
422
+ train_on_inputs: false
423
+ group_by_length: false
424
+ bf16: true
425
+ fp16: false
426
+ tf32: false
427
+
428
+ gradient_checkpointing: true
429
+ early_stopping_patience:
430
+ resume_from_checkpoint:
431
+ local_rank:
432
+ logging_steps: 1
433
+ xformers_attention:
434
+ flash_attention: true
435
+
436
+ warmup_ratio: 0.03
437
+ evals_per_epoch: 4
438
+ eval_table_size:
439
+ save_strategy: "no"
440
+ debug:
441
+ deepspeed: /ikerlariak/igarcia945/Mortadelo-Filemon/train_configs/deepspeed_zero3.json
442
+ weight_decay: 0.0
443
+ fsdp:
444
+ fsdp_config:
445
+
446
+ seed: 33
447
+ ```