duyphu commited on
Commit
5c5b17e
·
verified ·
1 Parent(s): 1c60209

End of training

Browse files
Files changed (2) hide show
  1. README.md +11 -4
  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: 2
70
  mlflow_experiment_name: /tmp/43b97beb6cb95c3f_train_data.json
71
  model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: cc30fccd-d4cd-4973-81b5-20778b16cec3
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
  wandb_runid: cc30fccd-d4cd-4973-81b5-20778b16cec3
95
- warmup_steps: 1
96
  weight_decay: 0.0
97
  xformers_attention: null
98
 
@@ -103,6 +103,8 @@ xformers_attention: null
103
  # 86758f57-249e-432a-b11e-8e003113b4dc
104
 
105
  This model is a fine-tuned version of [OpenBuddy/openbuddy-llama2-13b-v8.1-fp16](https://huggingface.co/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16) on the None dataset.
 
 
106
 
107
  ## Model description
108
 
@@ -129,14 +131,19 @@ The following hyperparameters were used during training:
129
  - total_train_batch_size: 8
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: 1
134
 
135
  ### Training results
136
 
137
  | Training Loss | Epoch | Step | Validation Loss |
138
  |:-------------:|:------:|:----:|:---------------:|
139
  | No log | 0.0005 | 1 | 1.0615 |
 
 
 
 
 
140
 
141
 
142
  ### Framework versions
 
65
  lora_r: 8
66
  lora_target_linear: true
67
  lr_scheduler: cosine
68
+ max_steps: 50
69
  micro_batch_size: 2
70
  mlflow_experiment_name: /tmp/43b97beb6cb95c3f_train_data.json
71
  model_type: AutoModelForCausalLM
 
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
  wandb_runid: cc30fccd-d4cd-4973-81b5-20778b16cec3
95
+ warmup_steps: 10
96
  weight_decay: 0.0
97
  xformers_attention: null
98
 
 
103
  # 86758f57-249e-432a-b11e-8e003113b4dc
104
 
105
  This model is a fine-tuned version of [OpenBuddy/openbuddy-llama2-13b-v8.1-fp16](https://huggingface.co/OpenBuddy/openbuddy-llama2-13b-v8.1-fp16) on the None dataset.
106
+ It achieves the following results on the evaluation set:
107
+ - Loss: 0.0107
108
 
109
  ## Model description
110
 
 
131
  - total_train_batch_size: 8
132
  - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
133
  - lr_scheduler_type: cosine
134
+ - lr_scheduler_warmup_steps: 10
135
+ - training_steps: 50
136
 
137
  ### Training results
138
 
139
  | Training Loss | Epoch | Step | Validation Loss |
140
  |:-------------:|:------:|:----:|:---------------:|
141
  | No log | 0.0005 | 1 | 1.0615 |
142
+ | 0.727 | 0.0053 | 10 | 0.3960 |
143
+ | 0.093 | 0.0107 | 20 | 0.0437 |
144
+ | 0.0159 | 0.0160 | 30 | 0.0113 |
145
+ | 0.0064 | 0.0213 | 40 | 0.0113 |
146
+ | 0.0082 | 0.0267 | 50 | 0.0107 |
147
 
148
 
149
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cdd39d3b25911b34cac479c44eed5ac9a3a5001de4866921127b9f89c937365
3
  size 125375434
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c9a9966b8ad17948c25d896039ad79c567fab4d8ff4252b4649805490022b1
3
  size 125375434