duyphu commited on
Commit
5fb1700
·
verified ·
1 Parent(s): a069fbe

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/60ec1eaa4acb1cf5_train_data.json
71
  model_type: AutoModelForCausalLM
@@ -92,7 +92,7 @@ wandb_name: 9ac43e03-044d-46f3-9303-8c7e590e0d06
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
  wandb_runid: 9ac43e03-044d-46f3-9303-8c7e590e0d06
95
- warmup_steps: 1
96
  weight_decay: 0.0
97
  xformers_attention: null
98
 
@@ -103,6 +103,8 @@ xformers_attention: null
103
  # 45991bd4-764f-5c72-03d7-21d5edcf6067
104
 
105
  This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) 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 | 0.0004 | 1 | 2.6600 |
 
 
 
 
 
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/60ec1eaa4acb1cf5_train_data.json
71
  model_type: AutoModelForCausalLM
 
92
  wandb_project: Gradients-On-Demand
93
  wandb_run: your_name
94
  wandb_runid: 9ac43e03-044d-46f3-9303-8c7e590e0d06
95
+ warmup_steps: 10
96
  weight_decay: 0.0
97
  xformers_attention: null
98
 
 
103
  # 45991bd4-764f-5c72-03d7-21d5edcf6067
104
 
105
  This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset.
106
+ It achieves the following results on the evaluation set:
107
+ - Loss: 1.6824
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 | 0.0004 | 1 | 2.6600 |
142
+ | 2.2713 | 0.0043 | 10 | 2.1321 |
143
+ | 2.0763 | 0.0085 | 20 | 1.8722 |
144
+ | 1.6768 | 0.0128 | 30 | 1.7495 |
145
+ | 1.7516 | 0.0170 | 40 | 1.6913 |
146
+ | 1.623 | 0.0213 | 50 | 1.6824 |
147
 
148
 
149
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10be2eb39cad58ff40480def397d75d744e3fabb927305ae901c1dbaf17ae3f1
3
  size 25342042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41255d5cf0a7a178df7a5f727dbec9bc6099e299f782f2f0e3ed42226a235c4e
3
  size 25342042