Upload folder using huggingface_hub

README.md

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+base_model: EleutherAI/pythia-1.4b
+tags:
+- generated_from_trainer
+- sft
+- ultrafeedback
+datasets:
+- trl-lib/tldr
+language:
+- en
+library_name: transformers
+---
+
+# pythia-1.4b Fine-tuned on tldr
+
+This model is a fine-tuned version of [EleutherAI/pythia-1.4b](https://huggingface.co/EleutherAI/pythia-1.4b) on the [trl-lib/tldr](https://huggingface.co/datasets/trl-lib/tldr) dataset.
+
+## Training Results
+
+![Training Loss](loss_plot.png)
+
+### Training Statistics
+
+| Metric | Value |
+|--------|-------|
+| Total Steps | 1356 |
+| Final Training Loss | 147.1650 |
+| Min Training Loss | 2.8189 |
+| Training Runtime | 347.80 seconds |
+| Samples/Second | 249.34 |
+
+## Training Configuration
+
+| Parameter | Value |
+|-----------|-------|
+| Base Model | EleutherAI/pythia-1.4b |
+| Dataset | trl-lib/tldr |
+| Number of Epochs | 1.0 |
+| Per Device Batch Size | 16 |
+| Gradient Accumulation Steps | 1 |
+| Total Batch Size | 64 (4 GPUs) |
+| Learning Rate | 2e-05 |
+| LR Scheduler | cosine |
+| Warmup Ratio | 0.1 |
+| Max Sequence Length | 512 |
+| Optimizer | adamw_torch_fused |
+| Mixed Precision | BF16 |
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "activeDap/pythia-1.4b_tldr"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Format input with prompt template
+prompt = "What is machine learning?\nAssistant:"
+inputs = tokenizer(prompt, return_tensors="pt")
+
+# Generate response
+outputs = model.generate(**inputs, max_new_tokens=100)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
+
+## Training Framework
+
+- **Library:** Transformers + TRL
+- **Training Type:** Supervised Fine-Tuning (SFT)
+- **Format:** Prompt-completion with Assistant-only loss
+
+## Citation
+
+If you use this model, please cite the original base model and dataset:
+
+```bibtex
+@misc{ultrafeedback2023,
+      title={UltraFeedback: Boosting Language Models with High-quality Feedback},
+      author={Ganqu Cui and Lifan Yuan and Ning Ding and others},
+      year={2023},
+      eprint={2310.01377},
+      archivePrefix={arXiv}
+}
+```

all_results.json

@@ -0,0 +1,7 @@
+{
+    "total_flos": 3.496798701936968e+17,
+    "train_loss": 186.48060493412973,
+    "train_runtime": 347.8047,
+    "train_samples_per_second": 249.341,
+    "train_steps_per_second": 3.899
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "dtype": "float16",
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": [
+    0
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062110a55acfb6333ab20a1ae8bafaf655eea5d80363d5160129ade61f15501e
+size 2829329920

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "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|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "total_flos": 3.496798701936968e+17,
+    "train_loss": 186.48060493412973,
+    "train_runtime": 347.8047,
+    "train_samples_per_second": 249.341,
+    "train_steps_per_second": 3.899
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55462d9bc61925ac53f655c795c8e879cc3e0b9dce7da501e176b6322fac6e2f
+size 6161