Qwen1-1-4B-UDA-rules

README.md

@@ -0,0 +1,82 @@
+---
+license: other
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-4B-Chat
+model-index:
+- name: temps
+  results: []
+---
+
+<!-- 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. -->
+
+# temps
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2647
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 2
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.4933        | 0.95  | 9    | 1.3903          |
+| 1.1607        | 2.0   | 19   | 0.9786          |
+| 0.9208        | 2.95  | 28   | 0.6901          |
+| 0.5404        | 4.0   | 38   | 0.4664          |
+| 0.3362        | 4.95  | 47   | 0.3509          |
+| 0.1628        | 6.0   | 57   | 0.2848          |
+| 0.117         | 6.95  | 66   | 0.2630          |
+| 0.074         | 8.0   | 76   | 0.2563          |
+| 0.0727        | 8.95  | 85   | 0.2402          |
+| 0.0613        | 10.0  | 95   | 0.2536          |
+| 0.0597        | 10.95 | 104  | 0.2642          |
+| 0.0508        | 12.0  | 114  | 0.2567          |
+| 0.0558        | 12.95 | 123  | 0.2476          |
+| 0.0477        | 14.0  | 133  | 0.2648          |
+| 0.0537        | 14.95 | 142  | 0.2691          |
+| 0.0447        | 16.0  | 152  | 0.2629          |
+| 0.0473        | 16.95 | 161  | 0.2812          |
+| 0.0421        | 18.0  | 171  | 0.2566          |
+| 0.0428        | 18.95 | 180  | 0.2647          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.39.3
+- Pytorch 2.2.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca5810ea36123a2bddacb466e51efe430ff1a407da308a62ec5d802f1da6329
+size 31367672

added_tokens.json

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

special_tokens_map.json

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

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,
+  "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": 2048,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af00cc325d7c3e6cf327a8fd28c1265ecd77659d056f6ebe17f39e7f28b2dab
+size 4920