tuanna08go commited on
Commit
76028ec
·
verified ·
1 Parent(s): e98c035

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/a85a691963f19b85_train_data.json
71
  model_type: AutoModelForCausalLM
@@ -90,7 +90,7 @@ wandb_name: a7c81892-f441-469e-9e5c-36ef5a1e8f7f
90
  wandb_project: Gradients-On-Demand
91
  wandb_run: your_name
92
  wandb_runid: a7c81892-f441-469e-9e5c-36ef5a1e8f7f
93
- warmup_steps: 1
94
  weight_decay: 0.0
95
  xformers_attention: null
96
 
@@ -101,6 +101,8 @@ xformers_attention: null
101
  # a7c81892-f441-469e-9e5c-36ef5a1e8f7f
102
 
103
  This model is a fine-tuned version of [unsloth/Phi-3.5-mini-instruct](https://huggingface.co/unsloth/Phi-3.5-mini-instruct) 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 | 0.0088 | 1 | nan |
 
 
 
 
 
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/a85a691963f19b85_train_data.json
71
  model_type: AutoModelForCausalLM
 
90
  wandb_project: Gradients-On-Demand
91
  wandb_run: your_name
92
  wandb_runid: a7c81892-f441-469e-9e5c-36ef5a1e8f7f
93
+ warmup_steps: 2
94
  weight_decay: 0.0
95
  xformers_attention: null
96
 
 
101
  # a7c81892-f441-469e-9e5c-36ef5a1e8f7f
102
 
103
  This model is a fine-tuned version of [unsloth/Phi-3.5-mini-instruct](https://huggingface.co/unsloth/Phi-3.5-mini-instruct) on the None dataset.
104
+ It achieves the following results on the evaluation set:
105
+ - Loss: nan
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 | 0.0088 | 1 | nan |
140
+ | 0.0 | 0.0878 | 10 | nan |
141
+ | 0.0 | 0.1755 | 20 | nan |
142
+ | 0.0 | 0.2633 | 30 | nan |
143
+ | 0.0 | 0.3511 | 40 | nan |
144
+ | 0.0 | 0.4388 | 50 | nan |
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:ace33721d58986b52359a3ac34f1001b55b517ea304ad358952196eff4dae804
3
  size 59930122
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d9f7e96ea34cf47c8a70d26ee7969338a6598c82afe98ce71ebe80c9b03b4e
3
  size 59930122