towhid2000bd/amplifier_design_deepseek_7B-Instruct

README.md

@@ -0,0 +1,96 @@
+---
+library_name: peft
+license: other
+base_model: deepseek-ai/deepseek-llm-7b-base
+tags:
+- generated_from_trainer
+model-index:
+- name: deepseek-Instruct-8B
+  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. -->
+
+# deepseek-Instruct-8B
+
+This model is a fine-tuned version of [deepseek-ai/deepseek-llm-7b-base](https://huggingface.co/deepseek-ai/deepseek-llm-7b-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2329
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.9256        | 0.1144 | 50   | 1.8577          |
+| 1.4949        | 0.2288 | 100  | 0.9622          |
+| 0.5315        | 0.3432 | 150  | 0.3328          |
+| 0.3079        | 0.4577 | 200  | 0.3011          |
+| 0.2974        | 0.5721 | 250  | 0.2960          |
+| 0.2921        | 0.6865 | 300  | 0.2903          |
+| 0.2869        | 0.8009 | 350  | 0.2832          |
+| 0.2757        | 0.9153 | 400  | 0.2731          |
+| 0.2676        | 1.0297 | 450  | 0.2644          |
+| 0.2594        | 1.1442 | 500  | 0.2590          |
+| 0.2546        | 1.2586 | 550  | 0.2535          |
+| 0.2497        | 1.3730 | 600  | 0.2505          |
+| 0.2477        | 1.4874 | 650  | 0.2489          |
+| 0.2462        | 1.6018 | 700  | 0.2463          |
+| 0.2438        | 1.7162 | 750  | 0.2452          |
+| 0.2439        | 1.8307 | 800  | 0.2436          |
+| 0.2434        | 1.9451 | 850  | 0.2426          |
+| 0.2414        | 2.0595 | 900  | 0.2415          |
+| 0.2408        | 2.1739 | 950  | 0.2406          |
+| 0.2374        | 2.2883 | 1000 | 0.2396          |
+| 0.2388        | 2.4027 | 1050 | 0.2385          |
+| 0.2357        | 2.5172 | 1100 | 0.2378          |
+| 0.2358        | 2.6316 | 1150 | 0.2377          |
+| 0.236         | 2.7460 | 1200 | 0.2371          |
+| 0.2352        | 2.8604 | 1250 | 0.2361          |
+| 0.2342        | 2.9748 | 1300 | 0.2357          |
+| 0.2337        | 3.0892 | 1350 | 0.2352          |
+| 0.2337        | 3.2037 | 1400 | 0.2346          |
+| 0.2335        | 3.3181 | 1450 | 0.2343          |
+| 0.2327        | 3.4325 | 1500 | 0.2337          |
+| 0.2314        | 3.5469 | 1550 | 0.2337          |
+| 0.2322        | 3.6613 | 1600 | 0.2334          |
+| 0.2318        | 3.7757 | 1650 | 0.2330          |
+| 0.2292        | 3.8902 | 1700 | 0.2329          |
+
+
+### Framework versions
+
+- PEFT 0.14.0
+- Transformers 4.50.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.02,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b31b8ce13b220759022473cb823c5870cfa90fad3a120293f5cecd75c1f143
+size 15736672

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

tokenizer_config.json

@@ -0,0 +1,138 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7932b718b191ca67284b02c842c285f86ceac274a180266233c90f8db82b771
+size 5368