qwen-nampdn-ai/tiny-textbooks

README.md

@@ -0,0 +1,107 @@
+---
+base_model: Qwen/Qwen-14B
+tags:
+- generated_from_trainer
+model-index:
+- name: nampdn-ai_tiny-textbooks
+  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. -->
+
+# nampdn-ai_tiny-textbooks
+
+This model is a fine-tuned version of [Qwen/Qwen-14B](https://huggingface.co/Qwen/Qwen-14B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4456
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.01
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.3995        | 0.02  | 63   | 2.4534          |
+| 2.4114        | 0.04  | 126  | 2.4578          |
+| 2.3929        | 0.06  | 189  | 2.4563          |
+| 2.4145        | 0.08  | 252  | 2.4551          |
+| 2.4145        | 0.1   | 315  | 2.4539          |
+| 2.3687        | 0.12  | 378  | 2.4537          |
+| 2.3899        | 0.14  | 441  | 2.4537          |
+| 2.3827        | 0.16  | 504  | 2.4513          |
+| 2.4124        | 0.18  | 567  | 2.4509          |
+| 2.3839        | 0.2   | 630  | 2.4502          |
+| 2.3962        | 0.22  | 693  | 2.4489          |
+| 2.4156        | 0.24  | 756  | 2.4498          |
+| 2.4085        | 0.26  | 819  | 2.4491          |
+| 2.4303        | 0.28  | 882  | 2.4480          |
+| 2.4038        | 0.3   | 945  | 2.4473          |
+| 2.397         | 0.32  | 1008 | 2.4474          |
+| 2.4259        | 0.34  | 1071 | 2.4484          |
+| 2.4248        | 0.36  | 1134 | 2.4481          |
+| 2.3889        | 0.38  | 1197 | 2.4480          |
+| 2.397         | 0.4   | 1260 | 2.4472          |
+| 2.3966        | 0.42  | 1323 | 2.4485          |
+| 2.3764        | 0.44  | 1386 | 2.4464          |
+| 2.389         | 0.46  | 1449 | 2.4477          |
+| 2.4051        | 0.48  | 1512 | 2.4477          |
+| 2.3919        | 0.5   | 1575 | 2.4483          |
+| 2.3874        | 0.52  | 1638 | 2.4475          |
+| 2.3575        | 0.54  | 1701 | 2.4457          |
+| 2.3941        | 0.56  | 1764 | 2.4468          |
+| 2.4167        | 0.58  | 1827 | 2.4467          |
+| 2.3787        | 0.6   | 1890 | 2.4466          |
+| 2.3838        | 0.62  | 1953 | 2.4472          |
+| 2.4292        | 0.65  | 2016 | 2.4465          |
+| 2.3788        | 0.67  | 2079 | 2.4459          |
+| 2.4314        | 0.69  | 2142 | 2.4466          |
+| 2.4071        | 0.71  | 2205 | 2.4462          |
+| 2.3655        | 0.73  | 2268 | 2.4462          |
+| 2.427         | 0.75  | 2331 | 2.4463          |
+| 2.3794        | 0.77  | 2394 | 2.4460          |
+| 2.3645        | 0.79  | 2457 | 2.4458          |
+| 2.393         | 0.81  | 2520 | 2.4458          |
+| 2.4032        | 0.83  | 2583 | 2.4457          |
+| 2.3818        | 0.85  | 2646 | 2.4456          |
+| 2.4262        | 0.87  | 2709 | 2.4457          |
+| 2.3719        | 0.89  | 2772 | 2.4457          |
+| 2.3935        | 0.91  | 2835 | 2.4457          |
+| 2.393         | 0.93  | 2898 | 2.4456          |
+| 2.3695        | 0.95  | 2961 | 2.4455          |
+| 2.3878        | 0.97  | 3024 | 2.4454          |
+| 2.3873        | 0.99  | 3087 | 2.4456          |
+
+
+### Framework versions
+
+- Transformers 4.35.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.5.2
+- Tokenizers 0.14.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen-14B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": [
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39
+  ],
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "c_attn",
+    "c_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e894f1a24c9f2b471fc9caba4b68dc158dab14bc6da9c973cd60fd2287c3ca56
+size 15873058

special_tokens_map.json

@@ -0,0 +1,4 @@
+{
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "added_tokens_decoder": {},
+  "additional_special_tokens": [],
+  "auto_map": {
+    "AutoTokenizer": [
+      "Qwen/Qwen-14B--tokenization_qwen.QWenTokenizer",
+      null
+    ]
+  },
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 8192,
+  "tokenizer_class": "QWenTokenizer",
+  "tokenizer_file": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d00f73287665ee4c68de8b4fd6279949df866bff0b5dd4e97822d2c755b516
+size 4600