End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: llama2
-base_model: codellama/CodeLlama-7b-hf
+base_model: katuni4ka/tiny-random-olmo-hf
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_94f2e377-9724-4e56-8e70-b3ffcec65e76
+- Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2
 model-index:
-- name: cc9d165b-dd47-4489-b8bd-c39fa0314206
+- name: fd35b19c-d072-42cd-a87a-9b420f48b2cf
   results: []
 ---
 
@@ -21,18 +20,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: codellama/CodeLlama-7b-hf
+base_model: katuni4ka/tiny-random-olmo-hf
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_94f2e377-9724-4e56-8e70-b3ffcec65e76
+  path: Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2
   type:
-    field_input: dominio
-    field_instruction: tarea
-    field_output: question
+    field_input: input
+    field_instruction: instruction
+    field_output: output
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +47,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/cc9d165b-dd47-4489-b8bd-c39fa0314206
+hub_model_id: Aivesa/fd35b19c-d072-42cd-a87a-9b420f48b2cf
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -79,8 +78,6 @@ sample_packing: false
 save_safetensors: true
 saves_per_epoch: 4
 sequence_len: 512
-special_tokens:
-  pad_token: </s>
 strict: false
 tf32: false
 tokenizer_type: AutoTokenizer
@@ -90,10 +87,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 94f2e377-9724-4e56-8e70-b3ffcec65e76
+wandb_name: 6968a579-81bd-4958-a406-832f6d9ed6e2
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 94f2e377-9724-4e56-8e70-b3ffcec65e76
+wandb_runid: 6968a579-81bd-4958-a406-832f6d9ed6e2
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -102,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# cc9d165b-dd47-4489-b8bd-c39fa0314206
+# fd35b19c-d072-42cd-a87a-9b420f48b2cf
 
-This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the Aivesa/dataset_94f2e377-9724-4e56-8e70-b3ffcec65e76 dataset.
+This model is a fine-tuned version of [katuni4ka/tiny-random-olmo-hf](https://huggingface.co/katuni4ka/tiny-random-olmo-hf) on the Aivesa/dataset_6968a579-81bd-4958-a406-832f6d9ed6e2 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3245
+- Loss: 10.8337
 
 ## Model description
 
@@ -140,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 2.1445        | 0.0073 | 3    | 2.3860          |
-| 2.0854        | 0.0145 | 6    | 2.3669          |
-| 2.2885        | 0.0218 | 9    | 2.3245          |
+| 10.8479       | 0.0040 | 3    | 10.8399         |
+| 10.8437       | 0.0080 | 6    | 10.8375         |
+| 10.8212       | 0.0120 | 9    | 10.8337         |
 
 
 ### Framework versions