mistral-0.2

README.md

@@ -5,9 +5,9 @@ tags:
 - trl
 - sft
 - generated_from_trainer
+base_model: mistralai/Mistral-7B-Instruct-v0.2
 datasets:
 - generator
-base_model: mistralai/Mistral-7B-Instruct-v0.1
 model-index:
 - name: mistral_instruct_generation
   results: []
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_instruct_generation
 
-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.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8406
+- Loss: 0.8049
 
 ## Model description
 
@@ -52,17 +52,17 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.1329        | 0.87  | 20   | 0.9397          |
-| 0.8968        | 1.74  | 40   | 0.8661          |
-| 0.785         | 2.61  | 60   | 0.8353          |
-| 0.7084        | 3.48  | 80   | 0.8334          |
-| 0.7159        | 4.35  | 100  | 0.8406          |
+| 1.0509        | 0.87  | 20   | 0.8995          |
+| 0.8839        | 1.74  | 40   | 0.8167          |
+| 0.8105        | 2.61  | 60   | 0.7898          |
+| 0.7148        | 3.48  | 80   | 0.7915          |
+| 0.6221        | 4.35  | 100  | 0.8049          |
 
 
 ### Framework versions
 
-- PEFT 0.9.0
-- Transformers 4.37.0
+- PEFT 0.10.0
+- Transformers 4.38.2
 - Pytorch 2.1.2
-- Datasets 2.18.0
-- Tokenizers 0.15.1
+- Datasets 2.16.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,11 +1,12 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
@@ -19,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6be6d28f42622ffd140312d4bbf881d02e27a44dec67354618cf299780c0efb
+oid sha256:bff8112d95bc932ce88e61a9b6fb54a3b33ddc96ca50e1ead366158968c8cfbd
 size 109069176

runs/Apr02_04-12-42_4265b017aa0a/events.out.tfevents.1712031221.4265b017aa0a.91.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f8646adb97a3c48117f55978a0245837a81485ef99f9cb26aae383d60d5fc86
+size 8813

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25031e362f4c4ea2c5b84c8e056420a5fc1bbce7d56582e363312b0dff30b9be
-size 4728
+oid sha256:f59623b10aaf9dc82e1c5c843c17496f95721a4649edec88c7620ffaeadbe4b9
+size 4920