Upload folder using huggingface_hub

.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

@@ -0,0 +1,88 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen1.5-1.8B
+tags:
+- generated_from_trainer
+- sft
+- ultrafeedback
+datasets:
+- activeDap/ultrafeedback_chosen
+language:
+- en
+library_name: transformers
+---
+
+# Qwen1.5-1.8B Fine-tuned on ultrafeedback_chosen
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the [activeDap/ultrafeedback_chosen](https://huggingface.co/datasets/activeDap/ultrafeedback_chosen) dataset.
+
+## Training Results
+
+![Training Loss](loss_plot.png)
+
+### Training Statistics
+
+| Metric | Value |
+|--------|-------|
+| Total Steps | 816 |
+| Final Training Loss | 1.5145 |
+| Min Training Loss | 1.5145 |
+| Training Runtime | 263.04 seconds |
+| Samples/Second | 198.53 |
+
+## Training Configuration
+
+| Parameter | Value |
+|-----------|-------|
+| Base Model | Qwen/Qwen1.5-1.8B |
+| Dataset | activeDap/ultrafeedback_chosen |
+| 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/Qwen1.5-1.8B_ultrafeedback_chosen"
+
+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}
+}
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "total_flos": 2.4476548106236723e+17,
+    "train_loss": 1.5669958942076738,
+    "train_runtime": 263.0433,
+    "train_samples_per_second": 198.534,
+    "train_steps_per_second": 3.102
+}

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful assistant<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,54 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df788e0a1a2ae8b307c17eca0c6af9c6643176f12a1d83e47d1ba9bc805a07da
+size 3673690696

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "total_flos": 2.4476548106236723e+17,
+    "train_loss": 1.5669958942076738,
+    "train_runtime": 263.0433,
+    "train_samples_per_second": 198.534,
+    "train_steps_per_second": 3.102
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ef4ad72a24e0171b988c023a5219ba0c5684700e887af4f29b26b433501164
+size 6161