jonathanjordan21/Qwen2-0.5-Instruct-lora-resume-parser

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: facebook/opt-125m
+base_model: Qwen/Qwen2-0.5B-Instruct
 library_name: peft
-license: other
+license: apache-2.0
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tests
 
-This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on an unknown dataset.
 
 ## Model description
 
@@ -34,8 +34,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
@@ -51,4 +51,4 @@ The following hyperparameters were used during training:
 - Transformers 4.46.0
 - Pytorch 2.4.0
 - Datasets 3.0.2
-- Tokenizers 0.20.1
+- Tokenizers 0.20.0

adapter_config.json

@@ -1,27 +1,27 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "facebook/opt-125m",
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
   "bias": "none",
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": true,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 128,
+  "lora_alpha": 64,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 128,
+  "r": 64,
   "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:d7d14a636d5e7c132ea188310f59edb150e8b1a8b7e4d0f408a4bb9a223e3ab8
-size 18881176
+oid sha256:e4bce6cf735c6214f8abd9151d0384cf663cbb1f417a8369780eb6fc473055fd
+size 17314248

added_tokens.json

@@ -1,4 +1,5 @@
 {
-  "<|im_end|>": 50266,
-  "<|im_start|>": 50265
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
 }

runs/Oct29_02-11-40_0963431b98ff/events.out.tfevents.1730167902.0963431b98ff.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d254757a29ba836899abac1a85faa453c4239caef211d40b6497fc5abc48c1
+size 28890

runs/Oct29_02-33-01_0963431b98ff/events.out.tfevents.1730169189.0963431b98ff.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e781be0ead8af6c1facf562f2522c569ff901feeac6a64aa3df52780a23cc7e
+size 18790

runs/Oct29_02-41-52_0963431b98ff/events.out.tfevents.1730169720.0963431b98ff.30.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d4538be8741a9a9a7a3832df73b7b1f4bad4a3201e8bf40b38749689f992c0
+size 33070

special_tokens_map.json

@@ -1,23 +1,19 @@
 {
-  "bos_token": {
-    "content": "</s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "eos_token": "<|im_end|>",
   "pad_token": {
-    "content": "<pad>",
+    "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,24 +1,15 @@
 {
-  "add_bos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "1": {
-      "content": "<pad>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50265": {
+    "151644": {
       "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
@@ -26,7 +17,7 @@
       "single_word": false,
       "special": true
     },
-    "50266": {
+    "151645": {
       "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
@@ -35,12 +26,18 @@
       "special": true
     }
   },
-  "bos_token": "</s>",
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "</s>"
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc1961b8a04313ec34aa7e4cdc585407c47e21b6f5800453213bee4ec9a9910
+oid sha256:a82dd9a2b1953cb5dc477104b27370197c5c4b9af6a4643d9844b820cffa05f4
 size 5240