Upload 7 files

README.md

@@ -0,0 +1,86 @@
+---
+library_name: peft
+license: llama2
+base_model: meta-llama/Llama-2-7b-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: Llama2-7B-lora-r-32-generic-step-1200-lr-1e-5-labels_40.0-3
+  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. -->
+
+# Llama2-7B-lora-r-32-generic-step-1200-lr-1e-5-labels_40.0-3
+
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.8089
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- training_steps: 1200
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 5.4776        | 0.9132  | 50   | 4.8849          |
+| 4.2584        | 1.8265  | 100  | 3.8766          |
+| 3.674         | 2.7397  | 150  | 3.5260          |
+| 3.3895        | 3.6530  | 200  | 3.3094          |
+| 3.2045        | 4.5662  | 250  | 3.1682          |
+| 3.0743        | 5.4795  | 300  | 3.0658          |
+| 2.944         | 6.3927  | 350  | 2.9913          |
+| 2.8487        | 7.3059  | 400  | 2.9373          |
+| 2.7773        | 8.2192  | 450  | 2.8989          |
+| 2.7123        | 9.1324  | 500  | 2.8699          |
+| 2.6538        | 10.0457 | 550  | 2.8497          |
+| 2.6145        | 10.9589 | 600  | 2.8358          |
+| 2.5768        | 11.8721 | 650  | 2.8264          |
+| 2.5979        | 12.7854 | 700  | 2.8210          |
+| 2.5595        | 13.6986 | 750  | 2.8141          |
+| 2.5285        | 14.6119 | 800  | 2.8104          |
+| 2.5112        | 15.5251 | 850  | 2.8109          |
+| 2.4877        | 16.4384 | 900  | 2.8095          |
+| 2.4536        | 17.3516 | 950  | 2.8070          |
+| 2.5073        | 18.2648 | 1000 | 2.8081          |
+| 2.4321        | 19.1781 | 1050 | 2.8069          |
+| 2.4284        | 20.0913 | 1100 | 2.8085          |
+| 2.4627        | 21.0046 | 1150 | 2.8088          |
+| 2.4636        | 21.9178 | 1200 | 2.8089          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.45.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d76dda35e60cb1c28c320e4f6a844daa8a929a31ecf5ac9fde8508cb6d8eb69
+size 5560

training_metrics.json

@@ -0,0 +1,158 @@
+{
+  "train_loss": [
+    5.4776,
+    4.2584,
+    3.674,
+    3.3895,
+    3.2045,
+    3.0743,
+    2.944,
+    2.8487,
+    2.7773,
+    2.7123,
+    2.6538,
+    2.6145,
+    2.5768,
+    2.5979,
+    2.5595,
+    2.5285,
+    2.5112,
+    2.4877,
+    2.4536,
+    2.5073,
+    2.4321,
+    2.4284,
+    2.4627,
+    2.4636
+  ],
+  "train_steps": [
+    50,
+    100,
+    150,
+    200,
+    250,
+    300,
+    350,
+    400,
+    450,
+    500,
+    550,
+    600,
+    650,
+    700,
+    750,
+    800,
+    850,
+    900,
+    950,
+    1000,
+    1050,
+    1100,
+    1150,
+    1200
+  ],
+  "train_epochs": [
+    0.91324200913242,
+    1.82648401826484,
+    2.73972602739726,
+    3.65296803652968,
+    4.566210045662101,
+    5.47945205479452,
+    6.392694063926941,
+    7.30593607305936,
+    8.219178082191782,
+    9.132420091324201,
+    10.045662100456621,
+    10.95890410958904,
+    11.872146118721462,
+    12.785388127853881,
+    13.698630136986301,
+    14.61187214611872,
+    15.525114155251142,
+    16.438356164383563,
+    17.35159817351598,
+    18.264840182648403,
+    19.17808219178082,
+    20.091324200913242,
+    21.004566210045663,
+    21.91780821917808
+  ],
+  "eval_loss": [
+    4.884899139404297,
+    3.8766419887542725,
+    3.5259857177734375,
+    3.3093771934509277,
+    3.168154239654541,
+    3.06583571434021,
+    2.991332769393921,
+    2.9372518062591553,
+    2.8988661766052246,
+    2.8699264526367188,
+    2.8496575355529785,
+    2.835752010345459,
+    2.826432466506958,
+    2.821038007736206,
+    2.814145565032959,
+    2.8103811740875244,
+    2.8109121322631836,
+    2.8094851970672607,
+    2.8070461750030518,
+    2.808090925216675,
+    2.806938886642456,
+    2.808488607406616,
+    2.808797597885132,
+    2.808856248855591
+  ],
+  "eval_steps": [
+    50,
+    100,
+    150,
+    200,
+    250,
+    300,
+    350,
+    400,
+    450,
+    500,
+    550,
+    600,
+    650,
+    700,
+    750,
+    800,
+    850,
+    900,
+    950,
+    1000,
+    1050,
+    1100,
+    1150,
+    1200
+  ],
+  "eval_epochs": [
+    0.91324200913242,
+    1.82648401826484,
+    2.73972602739726,
+    3.65296803652968,
+    4.566210045662101,
+    5.47945205479452,
+    6.392694063926941,
+    7.30593607305936,
+    8.219178082191782,
+    9.132420091324201,
+    10.045662100456621,
+    10.95890410958904,
+    11.872146118721462,
+    12.785388127853881,
+    13.698630136986301,
+    14.61187214611872,
+    15.525114155251142,
+    16.438356164383563,
+    17.35159817351598,
+    18.264840182648403,
+    19.17808219178082,
+    20.091324200913242,
+    21.004566210045663,
+    21.91780821917808
+  ]
+}