greatakela/mistral_instruct_classifyFPB10k_adapters

README.md

@@ -2,11 +2,9 @@
 license: apache-2.0
 library_name: peft
 tags:
-- trl
-- sft
 - generated_from_trainer
-datasets:
-- generator
+metrics:
+- accuracy
 base_model: mistralai/Mistral-7B-Instruct-v0.1
 model-index:
 - name: mistral_instruct_classify10k
@@ -18,9 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral_instruct_classify10k
 
-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-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6021
+- Loss: 0.4669
+- F1 Micro: 0.5541
+- F1 Macro: 0.4757
+- Accuracy: 0.8606
 
 ## Model description
 
@@ -46,17 +47,18 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 0.03
-- num_epochs: 5
+- num_epochs: 6
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.7548        | 1.0   | 49   | 0.7252          |
-| 0.6684        | 2.0   | 98   | 0.6725          |
-| 0.5849        | 3.0   | 147  | 0.6398          |
-| 0.5236        | 4.0   | 196  | 0.6159          |
-| 0.4733        | 5.0   | 245  | 0.6021          |
+| Training Loss | Epoch | Step | Validation Loss | F1 Micro | F1 Macro | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|
+| 0.5713        | 1.0   | 1345 | 0.5121          | 0.5518   | 0.4780   | 0.8361   |
+| 2.1107        | 2.0   | 2690 | 1.0088          | 0.5039   | 0.4158   | 0.7536   |
+| 0.7897        | 3.0   | 4035 | 0.8093          | 0.4448   | 0.3756   | 0.6377   |
+| 0.2022        | 4.0   | 5380 | 0.3706          | 0.5619   | 0.4837   | 0.8751   |
+| 0.4403        | 5.0   | 6725 | 0.4996          | 0.5552   | 0.4811   | 0.8406   |
+| 0.3214        | 6.0   | 8070 | 0.4669          | 0.5541   | 0.4757   | 0.8606   |
 
 
 ### Framework versions

adapter_config.json

@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "q_proj",
+    "v_proj",
     "o_proj",
     "k_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170fe642770cdfddeb9c5b302a20e1706ac5e4b2d6ff86f8bdb1eac6d989e862
+oid sha256:6abaa99d9830b54f8fc0656b755e4cd0f239baa4f80809f9f4b01e46b780e4a7
 size 218138576

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 2,
+    "pad_type_id": 0,
+    "pad_token": "</s>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2647418726458fe8c42ad91926ebc4d538d170a90a91458aab481d6c4c5a44f8
+oid sha256:9dc7ab69676bf5d0eefaa1846aba79a78486b1ebffa88ca544111696c7da46c3
 size 4728