dyang415 commited on
Commit
8976098
1 Parent(s): 68e880f

End of training

Browse files
Files changed (2) hide show
  1. README.md +16 -1
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -2,6 +2,7 @@
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
 
5
  - generated_from_trainer
6
  base_model: mistralai/Mistral-7B-Instruct-v0.2
7
  model-index:
@@ -92,7 +93,9 @@ fsdp_config:
92
 
93
  # nohto-v0-10e
94
 
95
- This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
 
 
96
 
97
  ## Model description
98
 
@@ -125,6 +128,18 @@ The following hyperparameters were used during training:
125
  - lr_scheduler_warmup_steps: 10
126
  - num_epochs: 10
127
 
 
 
 
 
 
 
 
 
 
 
 
 
128
  ### Framework versions
129
 
130
  - PEFT 0.7.0
 
2
  license: apache-2.0
3
  library_name: peft
4
  tags:
5
+ - axolotl
6
  - generated_from_trainer
7
  base_model: mistralai/Mistral-7B-Instruct-v0.2
8
  model-index:
 
93
 
94
  # nohto-v0-10e
95
 
96
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
97
+ It achieves the following results on the evaluation set:
98
+ - Loss: 0.8229
99
 
100
  ## Model description
101
 
 
128
  - lr_scheduler_warmup_steps: 10
129
  - num_epochs: 10
130
 
131
+ ### Training results
132
+
133
+ | Training Loss | Epoch | Step | Validation Loss |
134
+ |:-------------:|:-----:|:----:|:---------------:|
135
+ | 1.7166 | 0.18 | 1 | 3.7658 |
136
+ | 0.5158 | 1.64 | 10 | 0.5278 |
137
+ | 0.2492 | 3.09 | 20 | 0.5739 |
138
+ | 0.0338 | 4.73 | 30 | 0.7476 |
139
+ | 0.0083 | 6.36 | 40 | 0.8089 |
140
+ | 0.0078 | 8.0 | 50 | 0.8229 |
141
+
142
+
143
  ### Framework versions
144
 
145
  - PEFT 0.7.0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1ec92a030bd697af62f93b548c19393127732d0f9484efdca1c7492604a28b91
3
  size 102921869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fc33f68289f96c24371f82dd9bb596089c6f2a56650f02452a2eb0367967039
3
  size 102921869