Hugging Face's logo

tuanna08go
/
87e605dc-7855-4690-84e6-8164f5e9f81e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
954c4fa
·
verified ·
1 Parent(s): 723db23

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -3
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -65,7 +65,7 @@ lora_model_dir: null
65
  lora_r: 8
66
  lora_target_linear: true
67
  lr_scheduler: cosine
68
- max_steps: 1
69
  micro_batch_size: 8
70
  mlflow_experiment_name: /tmp/13fe2da19dfd2cc8_train_data.json
71
  model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: 87e605dc-7855-4690-84e6-8164f5e9f81e
90
  wandb_project: Gradients-On-Demand
91
  wandb_run: your_name
92
  wandb_runid: 87e605dc-7855-4690-84e6-8164f5e9f81e
93
- warmup_steps: 1
94
  weight_decay: 0.0
95
  xformers_attention: null
96
 
@@ -101,6 +101,8 @@ xformers_attention: null
101
  # 87e605dc-7855-4690-84e6-8164f5e9f81e
102
 
103
  This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama) on the None dataset.
 
 
104
 
105
  ## Model description
106
 
@@ -128,13 +130,18 @@ The following hyperparameters were used during training:
128
  - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
129
  - lr_scheduler_type: cosine
130
  - lr_scheduler_warmup_steps: 2
131
- - training_steps: 1
132
 
133
  ### Training results
134
 
135
  | Training Loss | Epoch | Step | Validation Loss |
136
  |:-------------:|:------:|:----:|:---------------:|
137
  | No log | 0.0028 | 1 | 4.3551 |
 
 
 
 
 
138
 
139
 
140
  ### Framework versions
 
65
  lora_r: 8
66
  lora_target_linear: true
67
  lr_scheduler: cosine
68
+ max_steps: 50
69
  micro_batch_size: 8
70
  mlflow_experiment_name: /tmp/13fe2da19dfd2cc8_train_data.json
71
  model_type: AutoModelForCausalLM
 
90
  wandb_project: Gradients-On-Demand
91
  wandb_run: your_name
92
  wandb_runid: 87e605dc-7855-4690-84e6-8164f5e9f81e
93
+ warmup_steps: 2
94
  weight_decay: 0.0
95
  xformers_attention: null
96
 
 
101
  # 87e605dc-7855-4690-84e6-8164f5e9f81e
102
 
103
  This model is a fine-tuned version of [unsloth/tinyllama](https://huggingface.co/unsloth/tinyllama) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: 2.2608
106
 
107
  ## Model description
108
 
 
130
  - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
131
  - lr_scheduler_type: cosine
132
  - lr_scheduler_warmup_steps: 2
133
+ - training_steps: 50
134
 
135
  ### Training results
136
 
137
  | Training Loss | Epoch | Step | Validation Loss |
138
  |:-------------:|:------:|:----:|:---------------:|
139
  | No log | 0.0028 | 1 | 4.3551 |
140
+ | 3.6053 | 0.0277 | 10 | 3.0411 |
141
+ | 2.8277 | 0.0554 | 20 | 2.6206 |
142
+ | 2.4681 | 0.0831 | 30 | 2.3795 |
143
+ | 2.3263 | 0.1108 | 40 | 2.2777 |
144
+ | 2.2721 | 0.1386 | 50 | 2.2608 |
145
 
146
 
147
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a4688a6278d0aff93a0532613f6edc0f4bd7798549c1518a5cdaab28e35e7aa
3
  size 25342042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:beb3258ac9ab5e0dbc42d269acd32ee84190b71245057bd46901aaf4e898eda8
3
  size 25342042