tuanna08go commited on
Commit
d702656
·
verified ·
1 Parent(s): 3e13018

End of training

Browse files
Files changed (2) hide show
  1. README.md +10 -3
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -66,7 +66,7 @@ lora_model_dir: null
66
  lora_r: 8
67
  lora_target_linear: true
68
  lr_scheduler: cosine
69
- max_steps: 1
70
  micro_batch_size: 8
71
  mlflow_experiment_name: /tmp/e45e7d07eb8d80a2_train_data.json
72
  model_type: AutoModelForCausalLM
@@ -91,7 +91,7 @@ wandb_name: 0fe9e498-43d5-45d7-9d6b-978ed929a507
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
  wandb_runid: 0fe9e498-43d5-45d7-9d6b-978ed929a507
94
- warmup_steps: 1
95
  weight_decay: 0.0
96
  xformers_attention: null
97
 
@@ -102,6 +102,8 @@ xformers_attention: null
102
  # 0fe9e498-43d5-45d7-9d6b-978ed929a507
103
 
104
  This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset.
 
 
105
 
106
  ## Model description
107
 
@@ -129,13 +131,18 @@ The following hyperparameters were used during training:
129
  - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
130
  - lr_scheduler_type: cosine
131
  - lr_scheduler_warmup_steps: 2
132
- - training_steps: 1
133
 
134
  ### Training results
135
 
136
  | Training Loss | Epoch | Step | Validation Loss |
137
  |:-------------:|:------:|:----:|:---------------:|
138
  | No log | 0.0033 | 1 | nan |
 
 
 
 
 
139
 
140
 
141
  ### Framework versions
 
66
  lora_r: 8
67
  lora_target_linear: true
68
  lr_scheduler: cosine
69
+ max_steps: 50
70
  micro_batch_size: 8
71
  mlflow_experiment_name: /tmp/e45e7d07eb8d80a2_train_data.json
72
  model_type: AutoModelForCausalLM
 
91
  wandb_project: Gradients-On-Demand
92
  wandb_run: your_name
93
  wandb_runid: 0fe9e498-43d5-45d7-9d6b-978ed929a507
94
+ warmup_steps: 2
95
  weight_decay: 0.0
96
  xformers_attention: null
97
 
 
102
  # 0fe9e498-43d5-45d7-9d6b-978ed929a507
103
 
104
  This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset.
105
+ It achieves the following results on the evaluation set:
106
+ - Loss: nan
107
 
108
  ## Model description
109
 
 
131
  - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
132
  - lr_scheduler_type: cosine
133
  - lr_scheduler_warmup_steps: 2
134
+ - training_steps: 50
135
 
136
  ### Training results
137
 
138
  | Training Loss | Epoch | Step | Validation Loss |
139
  |:-------------:|:------:|:----:|:---------------:|
140
  | No log | 0.0033 | 1 | nan |
141
+ | 0.9945 | 0.0334 | 10 | nan |
142
+ | 0.5268 | 0.0668 | 20 | nan |
143
+ | 0.374 | 0.1002 | 30 | nan |
144
+ | 0.3486 | 0.1336 | 40 | nan |
145
+ | 0.3219 | 0.1670 | 50 | nan |
146
 
147
 
148
  ### Framework versions
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adadfbf69c54ef2fce71664da386c1a3ac50771afed19a1a9663131c7a2cfc3f
3
  size 48768810
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e36d1db889989de53c736b564b44290044e6e07857c0a0d98a13ee5648443d
3
  size 48768810