Hugging Face's logo

jnjj
/
Vvbvv

Text Generation
Transformers
Safetensors
llama
sequential-fine-tuning
lora
text-generation-inference
Model card Files
xet
 Community
jnjj commited on
Commit
4ac214e
·
verified ·
1 Parent(s): e71e731

Periodic upload

Browse files
Files changed (3) hide show
  1. README.md +4 -4
  2. model.safetensors +1 -1
  3. training.log +12 -0
README.md CHANGED
@@ -9,7 +9,7 @@ library_name: transformers
9
 
10
  ## Progreso de Entrenamiento
11
 
12
- - **Datasets procesados:** 17.0
13
- - **Ejemplos de texto procesados:** 51.0
14
- - **Tokens procesados:** 18371.0
15
- - **Última subida:** 2025-05-06 14:36:29 UTC
 
9
 
10
  ## Progreso de Entrenamiento
11
 
12
+ - **Datasets procesados:** 20.0
13
+ - **Ejemplos de texto procesados:** 60.0
14
+ - **Tokens procesados:** 21374.0
15
+ - **Última subida:** 2025-05-06 14:37:31 UTC
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd92ed573e0edca1dc1a578f107033549a7b268be7e8d8d12eaf039b8c95aac9
3
  size 51957256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bd64b67192364049541fd8275db53968ea518659a8bf7c13b59b75058cd2eb
3
  size 51957256
training.log CHANGED
@@ -168,3 +168,15 @@ ValueError: Compression type zstd not supported
168
  2025-05-06 16:35:43,130 INFO: Finished training and saved model/tokenizer for Mxode/Chinese-Instruct config stem_zh
169
  2025-05-06 16:35:43,130 INFO: Starting model update for syCen/CameraBench, config: default
170
  2025-05-06 16:35:44,612 INFO: Finished training and saved model/tokenizer for syCen/CameraBench config default
 
 
 
 
 
 
 
 
 
 
 
 
 
168
  2025-05-06 16:35:43,130 INFO: Finished training and saved model/tokenizer for Mxode/Chinese-Instruct config stem_zh
169
  2025-05-06 16:35:43,130 INFO: Starting model update for syCen/CameraBench, config: default
170
  2025-05-06 16:35:44,612 INFO: Finished training and saved model/tokenizer for syCen/CameraBench config default
171
+ 2025-05-06 16:36:31,841 INFO: Upload successful.
172
+ 2025-05-06 16:36:36,228 INFO: Preparing data for open-r1/OpenR1-Math-220k, config: all
173
+ 2025-05-06 16:36:36,551 INFO: Preparing data for quotientai/HalluMix, config: default
174
+ 2025-05-06 16:36:40,037 INFO: Starting model update for quotientai/HalluMix, config: default
175
+ 2025-05-06 16:36:43,175 INFO: Finished training and saved model/tokenizer for quotientai/HalluMix config default
176
+ 2025-05-06 16:36:43,176 ERROR: Error in background_training_loop task scheduling: local variable 'merged_model' referenced before assignment
177
+ 2025-05-06 16:36:43,349 INFO: Starting model update for open-r1/OpenR1-Math-220k, config: all
178
+ 2025-05-06 16:36:43,350 ERROR: Failed to get configs for LLM360/MegaMath: Dataset 'LLM360/MegaMath' is a gated dataset on the Hub. Visit the dataset page at https://huggingface.co/datasets/LLM360/MegaMath to ask for access.
179
+ 2025-05-06 16:36:45,068 INFO: Preparing data for Aleph-Alpha/Aleph-Alpha-GermanWeb, config: fineweb2
180
+ 2025-05-06 16:36:47,376 INFO: Finished training and saved model/tokenizer for open-r1/OpenR1-Math-220k config all
181
+ 2025-05-06 16:36:52,446 INFO: Starting model update for Aleph-Alpha/Aleph-Alpha-GermanWeb, config: fineweb2
182
+ 2025-05-06 16:36:57,163 INFO: Finished training and saved model/tokenizer for Aleph-Alpha/Aleph-Alpha-GermanWeb config fineweb2