huiwonLee/function_calling_v1

README.md

@@ -15,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # function_call_12_v1
 
 This model is a fine-tuned version of [hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode](https://huggingface.co/hiieu/Meta-Llama-3-8B-Instruct-function-calling-json-mode) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3571
 
 ## Model description
 
@@ -35,20 +33,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 1
+- learning_rate: 1e-05
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 15   | 2.3917          |
-| No log        | 2.0   | 30   | 0.3571          |
+| No log        | 1.0   | 8    | 0.2566          |
 
 
 ### Framework versions

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16915d581e5e0c8d2200fcc558849962b0a9b77d47f9d7c0d8b71994ec3e5de7
+oid sha256:ed9782f599f14873295a9eeaea37f305feed3ae404cc614bf840a24f4175d5da
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e29a46595db61806bbde4799f69adb0f2c895637d1d0314d622be51fd618b1
+oid sha256:366349262a4f5eb6a6cc5955261c5f534040ba5deba36cc93ab340541fda0ab3
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86c0816508b85249660180b7715076e83b0749768899fd89f1cf8a8b3cc6060
+oid sha256:65fe49f2fc10643fbfd39c929c6fcffb1fd5117332727c321126078e3796f931
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d59b15aea4e60271fb44a4fdca9a872dcbdc91b9c6f4a1c5ca29595caa2ccb7
+oid sha256:7a4bf276cf50e3292d9aa3440a5eee2c6783781801917fb83e02c6a99309e00d
 size 1168138808

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {