mnoukhov/pythia410m-test-tldr

README.md

@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mnoukhov/pythia410m-sft-tldr](https://huggingface.co/mnoukhov/pythia410m-sft-tldr) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6867
-- Rewards/chosen: 0.0544
-- Rewards/rejected: 0.0391
-- Rewards/accuracies: 0.4922
-- Rewards/margins: 0.0154
-- Logps/rejected: -103.2449
-- Logps/chosen: -103.2449
+- Loss: 0.6766
+- Rewards/chosen: 0.0321
+- Rewards/rejected: -0.0032
+- Rewards/accuracies: 0.7656
+- Rewards/margins: 0.0353
+- Logps/rejected: -103.6910
+- Logps/chosen: -103.6910
 - Logps/ref Rejected: -82.9119
 - Logps/ref Chosen: -104.3332
 
@@ -56,14 +56,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logps/ref Rejected | Logps/ref Chosen |
 |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:------------------:|:----------------:|
-| No log        | 0.5   | 4    | 0.6956          | 0.0594         | 0.0634           | 0.3828             | -0.0040         | -103.1458      | -103.1458    | -82.9119           | -104.3332        |
-| No log        | 1.0   | 8    | 0.6867          | 0.0544         | 0.0391           | 0.4922             | 0.0154          | -103.2449      | -103.2449    | -82.9119           | -104.3332        |
+| No log        | 0.5   | 4    | 0.6336          | 0.1889         | 0.0621           | 0.7656             | 0.1268          | -100.5552      | -100.5552    | -82.9119           | -104.3332        |
+| No log        | 1.0   | 8    | 0.6766          | 0.0321         | -0.0032          | 0.7656             | 0.0353          | -103.6910      | -103.6910    | -82.9119           | -104.3332        |
 
 
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.38.2
-- Pytorch 2.1.2+cu121
-- Datasets 2.17.0
-- Tokenizers 0.15.2
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
     "dense",
     "dense_h_to_4h",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "query_key_value"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675ab8d15657e56da216f0b2e7cce6e21affa5ec77d9229f6f2a0dbb8f7f985c
+oid sha256:bbe98ae4175ae9261c28a9e4b4495a94aa90c0878dcf4b6b27826d857287445b
 size 25192592

tokenizer.json

@@ -239,10 +239,30 @@
     "use_regex": true
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": false,
-    "trim_offsets": true,
-    "use_regex": true
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
   },
   "decoder": {
     "type": "ByteLevel",
@@ -258,6 +278,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<|endoftext|>": 0,
       "<|padding|>": 1,

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": false,
+  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf786461ba419274a353d2957dc06029f0eca66d77c6e6b9067a0f19f08adf4
-size 5176
+oid sha256:1053542ee39d77231244ed0f658cfb77d2771b4cfbf5216e8004482fed975a2b
+size 5240