End of training

README.md

@@ -3,17 +3,28 @@ library_name: peft
 tags:
 - generated_from_trainer
 base_model: NousResearch/Llama-2-7b-hf
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
-- name: billm_conll2003_NousResearch-Llama-2-7b-hf_ckpt
+- name: llama-2-ner
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# billm_conll2003_NousResearch-Llama-2-7b-hf_ckpt
+# llama-2-ner
 
 This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1279
+- Precision: 0.5561
+- Recall: 0.5474
+- F1: 0.5517
+- Accuracy: 0.9787
 
 ## Model description
 
@@ -42,6 +53,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 39   | 0.1206          | 0.2340    | 0.1158 | 0.1549 | 0.9656   |
+| No log        | 2.0   | 78   | 0.1256          | 0.2173    | 0.4368 | 0.2902 | 0.9619   |
+| No log        | 3.0   | 117  | 0.0843          | 0.3937    | 0.2632 | 0.3155 | 0.9729   |
+| No log        | 4.0   | 156  | 0.0666          | 0.4774    | 0.5    | 0.4884 | 0.9767   |
+| No log        | 5.0   | 195  | 0.0930          | 0.5376    | 0.4895 | 0.5124 | 0.9774   |
+| No log        | 6.0   | 234  | 0.1014          | 0.5150    | 0.6316 | 0.5674 | 0.9781   |
+| No log        | 7.0   | 273  | 0.1238          | 0.5583    | 0.6053 | 0.5808 | 0.9795   |
+| No log        | 8.0   | 312  | 0.1279          | 0.5561    | 0.5474 | 0.5517 | 0.9787   |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0330ff092c5f932f6262f7dd50c23a97a36d1b66a29f87e8e856f03ca499b18b
+oid sha256:f342bba0b4ac42e09a47d5ba3d6ef8b1b6d4625108eba1bb2262752144896c15
 size 33596518