End of training

README.md

@@ -2,9 +2,10 @@
 library_name: peft
 base_model: NousResearch/CodeLlama-7b-hf
 tags:
+- axolotl
 - generated_from_trainer
 model-index:
-- name: miner_id_24
+- name: 4463fa2d-bcef-4d53-8443-d3c7f10564d8
   results: []
 ---
 
@@ -39,10 +40,10 @@ datasets:
     system_prompt: ''
 debug: null
 deepspeed: null
-early_stopping_patience: 
+early_stopping_patience: 3
 early_stopping_threshold: 0.0001
 eval_max_new_tokens: 128
-eval_steps: 
+eval_steps: 96
 eval_strategy: null
 flash_attention: false
 fp16: null
@@ -51,7 +52,7 @@ fsdp_config: null
 gradient_accumulation_steps: 2
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: 
+hub_model_id: mrferr3t/4463fa2d-bcef-4d53-8443-d3c7f10564d8
 hub_repo: null
 hub_strategy: checkpoint
 hub_token: null
@@ -59,7 +60,7 @@ learning_rate: 0.0004
 load_in_4bit: false
 load_in_8bit: false
 local_rank: null
-logging_steps: 
+logging_steps: 96
 lora_alpha: 16
 lora_dropout: 0.05
 lora_fan_in_fan_out: null
@@ -67,7 +68,7 @@ lora_model_dir: null
 lora_r: 8
 lora_target_linear: true
 lr_scheduler: cosine
-max_steps: 20
+max_steps: 
 micro_batch_size: 32
 mlflow_experiment_name: /tmp/b64954fcc6e77b0d_train_data.json
 model_type: AutoModelForCausalLM
@@ -75,10 +76,10 @@ num_epochs: 100
 optimizer: adamw_bnb_8bit
 output_dir: miner_id_24
 pad_to_sequence_len: true
-resume_from_checkpoint: null
+resume_from_checkpoint: 
 s2_attention: null
 sample_packing: false
-save_steps: 
+save_steps: 96
 saves_per_epoch: 0
 sequence_len: 512
 special_tokens:
@@ -88,9 +89,9 @@ tf32: false
 tokenizer_type: AutoTokenizer
 train_on_inputs: false
 trust_remote_code: true
-val_set_size: 0.0
+val_set_size: 0.05
 wandb_entity: null
-wandb_mode: disabled
+wandb_mode: 
 wandb_name: bbdc12a3-1333-4e46-9918-0d4631f90551
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
@@ -103,9 +104,11 @@ xformers_attention: true
 
 </details><br>
 
-# miner_id_24
+# 4463fa2d-bcef-4d53-8443-d3c7f10564d8
 
 This model is a fine-tuned version of [NousResearch/CodeLlama-7b-hf](https://huggingface.co/NousResearch/CodeLlama-7b-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9914
 
 ## Model description
 
@@ -133,10 +136,19 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- training_steps: 20
+- num_epochs: 100
 
 ### Training results
 
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0054 | 1    | 2.6265          |
+| 2.8198        | 0.5161 | 96   | 1.0719          |
+| 1.8322        | 1.0323 | 192  | 0.9115          |
+| 1.4055        | 1.5484 | 288  | 0.8627          |
+| 1.2677        | 2.0645 | 384  | 0.8888          |
+| 0.9139        | 2.5806 | 480  | 0.8767          |
+| 0.9038        | 3.0968 | 576  | 0.9914          |
 
 
 ### Framework versions

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66b2e14c638f9f094fa398b8d430e784eabb75804a3ae79c8707b87b2640b80
+oid sha256:b253f744cf4ad6d9093ec55c68436873df9b935d7a24507781d26a91a215b836
 size 80115210

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a1b50f8d312b81c347ed7c53d7de332439d8a753541e36a84f19f46937dd2fa
+oid sha256:bdcad25513543b0946baa7fda4b46ba9229d1a8f96220cd051d69e996c75e749
 size 80013120