Upload folder using huggingface_hub

README.md

@@ -0,0 +1,97 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: kykim0/pythia-1b-tulu-v2-mix-nos
+tags:
+- trl
+- reward-trainer
+- generated_from_trainer
+datasets:
+- allenai/ultrafeedback_binarized_cleaned
+metrics:
+- accuracy
+model-index:
+- name: pythia-1b-tulu-v2-mix-nos-rm
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: allenai/ultrafeedback_binarized_cleaned
+      type: allenai/ultrafeedback_binarized_cleaned
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.7457800511508952
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pythia-1b-tulu-v2-mix-nos-rm
+
+This model is a fine-tuned version of [kykim0/pythia-1b-tulu-v2-mix-nos](https://huggingface.co/kykim0/pythia-1b-tulu-v2-mix-nos) on the allenai/ultrafeedback_binarized_cleaned dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5227
+- Accuracy: 0.7458
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.41e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.5749        | 0.0527 | 100  | 0.5849          | 0.6900   |
+| 0.5873        | 0.1055 | 200  | 0.5581          | 0.7100   |
+| 0.5599        | 0.1582 | 300  | 0.5470          | 0.7212   |
+| 0.5456        | 0.2109 | 400  | 0.5379          | 0.7258   |
+| 0.521         | 0.2637 | 500  | 0.5358          | 0.7294   |
+| 0.5361        | 0.3164 | 600  | 0.5363          | 0.7376   |
+| 0.5662        | 0.3691 | 700  | 0.5270          | 0.7412   |
+| 0.5301        | 0.4219 | 800  | 0.5268          | 0.7427   |
+| 0.5661        | 0.4746 | 900  | 0.5301          | 0.7381   |
+| 0.5608        | 0.5274 | 1000 | 0.5242          | 0.7437   |
+| 0.5223        | 0.5801 | 1100 | 0.5242          | 0.7422   |
+| 0.5322        | 0.6328 | 1200 | 0.5249          | 0.7448   |
+| 0.4891        | 0.6856 | 1300 | 0.5241          | 0.7427   |
+| 0.5111        | 0.7383 | 1400 | 0.5234          | 0.7437   |
+| 0.5145        | 0.7910 | 1500 | 0.5225          | 0.7422   |
+| 0.4746        | 0.8438 | 1600 | 0.5226          | 0.7458   |
+| 0.5551        | 0.8965 | 1700 | 0.5223          | 0.7448   |
+| 0.563         | 0.9492 | 1800 | 0.5222          | 0.7453   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9998681608437706,
+    "eval_accuracy": 0.7457800511508952,
+    "eval_loss": 0.5226647853851318,
+    "eval_runtime": 31.3969,
+    "eval_samples": 1955,
+    "eval_samples_per_second": 62.267,
+    "eval_steps_per_second": 1.975
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "kykim0/pythia-1b-tulu-v2-mix-nos",
+  "architectures": [
+    "GPTNeoXForSequenceClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 1,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9998681608437706,
+    "eval_accuracy": 0.7457800511508952,
+    "eval_loss": 0.5226647853851318,
+    "eval_runtime": 31.3969,
+    "eval_samples": 1955,
+    "eval_samples_per_second": 62.267,
+    "eval_steps_per_second": 1.975
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ed12c65666845df6fd342ad7254f0c80f4f9f57ca2689216b284fceca2f775
+size 1817545248

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,215 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|padding|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15040cc810e36ec4a77b6e90c92be590d64bf948b8146f648c7c82098c4fad95
+size 5496