End of training

README.md

@@ -5,18 +5,18 @@ tags:
 - sft
 - generated_from_trainer
 model-index:
-- name: Llama2_7B_chat_arithmetic_2
+- name: Llama2_7B_chat_arithmetic_nocarry
   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. -->
 
-# Llama2_7B_chat_arithmetic_2
+# Llama2_7B_chat_arithmetic_nocarry
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6614
+- Loss: 1.1935
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.622         | 0.2   | 94   | 2.4674          |
-| 0.9407        | 0.4   | 188  | 2.9233          |
-| 1.0502        | 0.6   | 282  | 2.0151          |
-| 1.2152        | 0.8   | 376  | 1.6614          |
+| 0.5437        | 0.2   | 94   | 1.6203          |
+| 0.499         | 0.4   | 188  | 2.2858          |
+| 0.6523        | 0.6   | 282  | 1.6741          |
+| 0.7247        | 0.8   | 376  | 1.1935          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbaddaf841c9ca6370f3b64612347f83c1661117a7dadf6f8c2744692eb8dd12
+oid sha256:f29d20dd264553490541fec24f996334baa932e59a329412d30937489a91a7e1
 size 16794200

runs/Jan02_11-16-36_1c9f3f1f0a74/events.out.tfevents.1704194211.1c9f3f1f0a74.2290.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fca1af064f1a9d909a4e10018d278246e156b0ef010027620155d3d6b76f2e0
-size 77569
+oid sha256:a286fb65a808c964d5e28a412d78798b85edc60d5d80ff43a607c8f9206e81c0
+size 79179