annay3294/llm-course-hw2-reward-model

README.md

@@ -2,15 +2,13 @@
 base_model: HuggingFaceTB/SmolLM-135M-Instruct
 datasets: HumanLLMs/Human-Like-DPO-Dataset
 library_name: transformers
-model_name: annay3294/llm-course-hw2-reward-model
+model_name: trainer_output
 tags:
 - generated_from_trainer
-- trl
-- reward-trainer
 licence: license
 ---
 
-# Model Card for annay3294/llm-course-hw2-reward-model
+# Model Card for trainer_output
 
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM-135M-Instruct) on the [HumanLLMs/Human-Like-DPO-Dataset](https://huggingface.co/datasets/HumanLLMs/Human-Like-DPO-Dataset) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -31,7 +29,7 @@ print(output["generated_text"])
  
 
 
-This model was trained with Reward.
+This model was trained with PPO, a method introduced in [Fine-Tuning Language Models from Human Preferences](https://huggingface.co/papers/1909.08593).
 
 ### Framework versions
 
@@ -43,7 +41,16 @@ This model was trained with Reward.
 
 ## Citations
 
+Cite PPO as:
 
+```bibtex
+@article{mziegler2019fine-tuning,
+    title        = {{Fine-Tuning Language Models from Human Preferences}},
+    author       = {Daniel M. Ziegler and Nisan Stiennon and Jeffrey Wu and Tom B. Brown and Alec Radford and Dario Amodei and Paul F. Christiano and Geoffrey Irving},
+    year         = 2019,
+    eprint       = {arXiv:1909.08593}
+}
+```
 
 Cite TRL as:
     

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 49152
+}

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "LlamaForSequenceClassification"
+    "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
@@ -9,14 +9,8 @@
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
   "intermediate_size": 1536,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "max_new_tokens": 40,
+  "pad_token_id": 2,
+  "transformers_version": "4.50.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65533307bfe7df64c014f52a265af4e616bacff0fc092ec1d58b095ff6148c7e
-size 538092792
+oid sha256:bc5f0f95f81a5d84f7e1b024f23fd5cc4e994ba5ceef9d5fb7c14a00a6da1a7c
+size 538090408

runs/Mar30_13-05-30_b018ffff2fe4/events.out.tfevents.1743339932.b018ffff2fe4.1160.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b1ae5c36689ff0b9c2e9d13012ae8938272c094952aac3a9aadf4a01992827a
+size 662995

runs/Mar30_13-43-25_b018ffff2fe4/events.out.tfevents.1743342208.b018ffff2fe4.1160.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e6ddbcc7110de8aaac3486803c691c961d3e03c20e967e7db945ee85267987
+size 4184

runs/Mar30_13-45-16_b018ffff2fe4/events.out.tfevents.1743342317.b018ffff2fe4.12110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102c2b510b23bb699afd8ba968156d4f7ad9085383d6439f1273e5ad17968ced
+size 59102

special_tokens_map.json

@@ -17,7 +17,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|im_end|>",
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -155,6 +155,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 49152,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -136,6 +136,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "49152": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -148,7 +156,8 @@
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 2048,
-  "pad_token": "<|im_end|>",
+  "pad_token": "[PAD]",
+  "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea79283a2116ad3a2e77acd224a666ac52ded02dacf45e2c68f140f8a100355
-size 5432
+oid sha256:b23dcc5d19af379e6d711c48a1eb61cecbac5215bfe019cb5ec865fe7b89ebc7
+size 6136