towhid2000bd/amplifier_design_Llama_2-7B-Instruct

README.md

@@ -0,0 +1,96 @@
+---
+library_name: peft
+license: llama2
+base_model: meta-llama/Llama-2-7b-chat-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama2-Instruct-7B
+  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. -->
+
+# Llama2-Instruct-7B
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2191
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.063         | 0.1144 | 50   | 1.8637          |
+| 1.3888        | 0.2288 | 100  | 0.8130          |
+| 0.4576        | 0.3432 | 150  | 0.3154          |
+| 0.3002        | 0.4577 | 200  | 0.2924          |
+| 0.285         | 0.5721 | 250  | 0.2795          |
+| 0.2711        | 0.6865 | 300  | 0.2652          |
+| 0.2598        | 0.8009 | 350  | 0.2550          |
+| 0.2469        | 0.9153 | 400  | 0.2471          |
+| 0.2427        | 1.0297 | 450  | 0.2420          |
+| 0.239         | 1.1442 | 500  | 0.2386          |
+| 0.2361        | 1.2586 | 550  | 0.2361          |
+| 0.2332        | 1.3730 | 600  | 0.2345          |
+| 0.2308        | 1.4874 | 650  | 0.2324          |
+| 0.2301        | 1.6018 | 700  | 0.2307          |
+| 0.228         | 1.7162 | 750  | 0.2295          |
+| 0.228         | 1.8307 | 800  | 0.2285          |
+| 0.2277        | 1.9451 | 850  | 0.2276          |
+| 0.2257        | 2.0595 | 900  | 0.2269          |
+| 0.2251        | 2.1739 | 950  | 0.2259          |
+| 0.223         | 2.2883 | 1000 | 0.2248          |
+| 0.2236        | 2.4027 | 1050 | 0.2241          |
+| 0.221         | 2.5172 | 1100 | 0.2234          |
+| 0.2211        | 2.6316 | 1150 | 0.2234          |
+| 0.2214        | 2.7460 | 1200 | 0.2224          |
+| 0.2205        | 2.8604 | 1250 | 0.2219          |
+| 0.2199        | 2.9748 | 1300 | 0.2214          |
+| 0.2193        | 3.0892 | 1350 | 0.2210          |
+| 0.219         | 3.2037 | 1400 | 0.2206          |
+| 0.2191        | 3.3181 | 1450 | 0.2203          |
+| 0.2185        | 3.4325 | 1500 | 0.2198          |
+| 0.2169        | 3.5469 | 1550 | 0.2197          |
+| 0.2176        | 3.6613 | 1600 | 0.2194          |
+| 0.2171        | 3.7757 | 1650 | 0.2192          |
+| 0.2148        | 3.8902 | 1700 | 0.2191          |
+
+
+### 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": "meta-llama/Llama-2-7b-chat-hf",
+  "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:da892f5afa4bc3eca82e570b126a8c54772b83d832af2e840c5b483ea4f58a73
+size 16785792

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc098a972a17d9216420ccf7e64358badfa2c08e89b2de4ee1f55c9875a8d026
+size 5368