End of training

README.md

@@ -1,17 +1,20 @@
 ---
 base_model: google/gemma-7b
+datasets:
+- silviasapora/dpo_7k_noisy_10
 library_name: transformers
-model_name: gemma-7b-borpo-noisy-5e-5-norm
+model_name: google/gemma-7b
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - orpo
 licence: license
 ---
 
-# Model Card for gemma-7b-borpo-noisy-5e-5-norm
+# Model Card for google/gemma-7b
 
-This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b).
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the [['silviasapora/dpo_7k_noisy_10']](https://huggingface.co/datasets/['silviasapora/dpo_7k_noisy_10']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -10,7 +10,7 @@
   "eos_token_id": 1,
   "head_dim": 256,
   "hidden_act": "gelu",
-  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_activation": null,
   "hidden_size": 3072,
   "initializer_range": 0.02,
   "intermediate_size": 24576,
@@ -24,7 +24,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.1",
+  "transformers_version": "4.48.1",
   "use_cache": true,
   "vocab_size": 256000
 }