End of training

README.md

@@ -0,0 +1,95 @@
+---
+license: other
+base_model: yahma/llama-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: V0305P2
+  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. -->
+
+# V0305P2
+
+This model is a fine-tuned version of [yahma/llama-7b-hf](https://huggingface.co/yahma/llama-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0602
+
+## 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: 0.0003
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.3061        | 0.09  | 10   | 0.1617          |
+| 0.1712        | 0.17  | 20   | 0.1558          |
+| 0.1564        | 0.26  | 30   | 0.1535          |
+| 0.1526        | 0.34  | 40   | 0.1479          |
+| 0.1503        | 0.43  | 50   | 0.1506          |
+| 0.1563        | 0.51  | 60   | 0.1505          |
+| 0.1517        | 0.6   | 70   | 0.1507          |
+| 0.1533        | 0.68  | 80   | 0.1489          |
+| 0.1491        | 0.77  | 90   | 0.1488          |
+| 0.1523        | 0.85  | 100  | 0.1471          |
+| 0.1522        | 0.94  | 110  | 0.1433          |
+| 0.1381        | 1.02  | 120  | 0.1229          |
+| 0.1303        | 1.11  | 130  | 0.1206          |
+| 0.1155        | 1.19  | 140  | 0.1018          |
+| 0.1095        | 1.28  | 150  | 0.0933          |
+| 0.103         | 1.37  | 160  | 0.0906          |
+| 0.1007        | 1.45  | 170  | 0.0904          |
+| 0.0895        | 1.54  | 180  | 0.0887          |
+| 0.0914        | 1.62  | 190  | 0.0840          |
+| 0.0943        | 1.71  | 200  | 0.0808          |
+| 0.0938        | 1.79  | 210  | 0.0757          |
+| 0.0884        | 1.88  | 220  | 0.0666          |
+| 0.0862        | 1.96  | 230  | 0.0733          |
+| 0.0709        | 2.05  | 240  | 0.0748          |
+| 0.0601        | 2.13  | 250  | 0.0730          |
+| 0.0593        | 2.22  | 260  | 0.0632          |
+| 0.059         | 2.3   | 270  | 0.0757          |
+| 0.06          | 2.39  | 280  | 0.0620          |
+| 0.0647        | 2.47  | 290  | 0.0605          |
+| 0.0619        | 2.56  | 300  | 0.0624          |
+| 0.0651        | 2.65  | 310  | 0.0605          |
+| 0.0578        | 2.73  | 320  | 0.0597          |
+| 0.0585        | 2.82  | 330  | 0.0598          |
+| 0.0575        | 2.9   | 340  | 0.0601          |
+| 0.0566        | 2.99  | 350  | 0.0602          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "adaptive_ratio": 1.0,
+  "adaptive_ratio_decay": 1.0,
+  "auto_mapping": null,
+  "base_model_name_or_path": "yahma/llama-7b-hf",
+  "bias": "none",
+  "dynamic_adapter_pool": false,
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "input_based_adapter_selection": false,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "merge_weights": false,
+  "modules_to_save": null,
+  "number_of_adapter_pre_layer": 8,
+  "ot_diversified_dispatcher": false,
+  "peft_type": "MA_LORA",
+  "pool_selective_inference": true,
+  "pool_selective_training": true,
+  "r": 16,
+  "selective_num": 8,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40266e19ad036f461bfded16a903e2337247523d146f2c4e568ee8befb716132
+size 277233383

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57b0a06ab34f3c7828922543a9d2fdbfc7268c4b573eb509c945fc01deb5d8ac
+size 13753862632

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": "<unk>",
+  "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 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "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 sha256:1da2ee100aeae847919eb215c0836c136d6d75de6e06bec27572543f44c0dd05
+size 5240