ai-maker-space/mistral-finetuned

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3081
+- Loss: 1.3045
 
 ## Model description
 
@@ -47,22 +47,23 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 0.03
 - training_steps: 100
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.5637        | 0.16  | 20   | 1.3754          |
-| 1.4669        | 0.33  | 40   | 1.3321          |
-| 1.3976        | 0.49  | 60   | 1.3208          |
-| 1.4256        | 0.65  | 80   | 1.3133          |
-| 1.4387        | 0.81  | 100  | 1.3081          |
+| 1.5301        | 0.16  | 20   | 1.3666          |
+| 1.4395        | 0.33  | 40   | 1.3320          |
+| 1.4298        | 0.49  | 60   | 1.3190          |
+| 1.3994        | 0.65  | 80   | 1.3129          |
+| 1.4091        | 0.81  | 100  | 1.3045          |
 
 
 ### Framework versions
 
 - PEFT 0.8.2
-- Transformers 4.37.2
-- Pytorch 2.2.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Transformers 4.38.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bd351df7957b1198484332b89336cedbb8e6460c6ad124e066f022ffe8659d
+oid sha256:ebae88a744838eb8882f1123e4b8f2a77053dfb4744ed3bbaf82f2bb640c5a6e
 size 109069176

runs/Feb27_20-58-38_afae08281dd5/events.out.tfevents.1709067521.afae08281dd5.2345.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d62854dce1d1f44b7a2cacb1078e39f6bbe162b5b016f68bd0099dd6267ec26
+size 8797

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0604aafd584ba959a09667614b8ac9df47f0d04796bfbae32e12acc99d7220b6
-size 4728
+oid sha256:30042f05adfee86a41c945596e76a96863ef2f2ccb829e45d98970511ed4d16e
+size 4920