End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.6599
+- Loss: 2.8945
 
 ## Model description
 
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 200
+- training_steps: 400
 
 ### Training results
 
@@ -58,6 +58,14 @@ The following hyperparameters were used during training:
 | 4.1435        | 0.05  | 150  | 4.2747          |
 | 3.7831        | 0.06  | 175  | 3.9269          |
 | 3.6802        | 0.06  | 200  | 3.6937          |
+| 3.5049        | 0.07  | 225  | 3.5292          |
+| 3.3127        | 0.08  | 250  | 3.4086          |
+| 3.1939        | 0.09  | 275  | 3.3188          |
+| 3.149         | 0.1   | 300  | 3.2472          |
+| 3.0679        | 0.1   | 325  | 3.1902          |
+| 3.0111        | 0.11  | 350  | 3.1422          |
+| 2.9573        | 0.12  | 375  | 3.1011          |
+| 3.0001        | 0.13  | 400  | 3.0645          |
 
 
 ### Framework versions

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10fd2b593cd1821a8db68be91062253754dbce283413637a29f7f39e235aa9a4
+oid sha256:b73162e13a5e2c2386aa25b3543102189603f743cf99982616d6d970a19f7e51
 size 4938985352

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378c8d2022837d954dd7d1380de6c18ff221fcff22bf0703586dfe2866d1a538
+oid sha256:41db403d325851edb5854dcec94dfd3bdb4029ec248e6069a5fda5232dc15558
 size 4947390880

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b05500e7a0210a4974188d571854f63f492175549f8a37fddcf284bf160b77
+oid sha256:f6598cd112b175203ce0ef341271e819da23cf75eca4fb975d967b36601313d9
 size 3590488816