End of training

README.md

@@ -1,14 +1,13 @@
 ---
 library_name: peft
-license: apache-2.0
-base_model: EleutherAI/pythia-410m-deduped
+base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_f5aaf6b6-8b8a-4d62-a003-0a4288146cc5
+- Aivesa/dataset_8fc4a6ef-bd04-43fb-917a-b960b40d439b
 model-index:
-- name: a5f1d39f-30d4-4ab2-93d1-269d93a6989b
+- name: 275e3437-81b9-4dba-a295-d95efe1f1668
   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: EleutherAI/pythia-410m-deduped
+base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_f5aaf6b6-8b8a-4d62-a003-0a4288146cc5
+  path: Aivesa/dataset_8fc4a6ef-bd04-43fb-917a-b960b40d439b
   type:
-    field_input: title
+    field_input: wiki
     field_instruction: query
-    field_output: positive
+    field_output: atom
     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/a5f1d39f-30d4-4ab2-93d1-269d93a6989b
+hub_model_id: Aivesa/275e3437-81b9-4dba-a295-d95efe1f1668
 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: <|endoftext|>
 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: f5aaf6b6-8b8a-4d62-a003-0a4288146cc5
+wandb_name: 8fc4a6ef-bd04-43fb-917a-b960b40d439b
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: f5aaf6b6-8b8a-4d62-a003-0a4288146cc5
+wandb_runid: 8fc4a6ef-bd04-43fb-917a-b960b40d439b
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -102,11 +99,11 @@ xformers_attention: null
 
 </details><br>
 
-# a5f1d39f-30d4-4ab2-93d1-269d93a6989b
+# 275e3437-81b9-4dba-a295-d95efe1f1668
 
-This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on the Aivesa/dataset_f5aaf6b6-8b8a-4d62-a003-0a4288146cc5 dataset.
+This model is a fine-tuned version of [trl-internal-testing/tiny-random-LlamaForCausalLM](https://huggingface.co/trl-internal-testing/tiny-random-LlamaForCausalLM) on the Aivesa/dataset_8fc4a6ef-bd04-43fb-917a-b960b40d439b dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4159
+- Loss: 10.3830
 
 ## Model description
 
@@ -140,9 +137,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 13.5865       | 0.0003 | 3    | 3.4376          |
-| 13.3023       | 0.0006 | 6    | 3.4332          |
-| 13.8277       | 0.0008 | 9    | 3.4159          |
+| 10.3899       | 0.0014 | 3    | 10.3832         |
+| 10.3768       | 0.0028 | 6    | 10.3831         |
+| 10.3806       | 0.0042 | 9    | 10.3830         |
 
 
 ### Framework versions