End of training

README.md

@@ -0,0 +1,100 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: daryl149/llama-2-13b-chat-hf
+model-index:
+- name: peft-claim-detection-training-1718016334
+ 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. -->
+
+# peft-claim-detection-training-1718016334
+
+This model is a fine-tuned version of [daryl149/llama-2-13b-chat-hf](https://huggingface.co/daryl149/llama-2-13b-chat-hf) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7537
+
+## 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: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- training_steps: 1000
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.6754 | 0.1953 | 25 | 1.5439 |
+| 1.5234 | 0.3906 | 50 | 1.5111 |
+| 1.4658 | 0.5859 | 75 | 1.4981 |
+| 1.4833 | 0.7812 | 100 | 1.4938 |
+| 1.5195 | 0.9766 | 125 | 1.4862 |
+| 1.4119 | 1.1719 | 150 | 1.4849 |
+| 1.3982 | 1.3672 | 175 | 1.4881 |
+| 1.4369 | 1.5625 | 200 | 1.4929 |
+| 1.427 | 1.7578 | 225 | 1.4900 |
+| 1.463 | 1.9531 | 250 | 1.4858 |
+| 1.3686 | 2.1484 | 275 | 1.4965 |
+| 1.2803 | 2.3438 | 300 | 1.5105 |
+| 1.3467 | 2.5391 | 325 | 1.5215 |
+| 1.3511 | 2.7344 | 350 | 1.5079 |
+| 1.3662 | 2.9297 | 375 | 1.5067 |
+| 1.2864 | 3.125 | 400 | 1.5295 |
+| 1.1724 | 3.3203 | 425 | 1.5497 |
+| 1.1846 | 3.5156 | 450 | 1.6101 |
+| 1.2683 | 3.7109 | 475 | 1.5444 |
+| 1.2701 | 3.9062 | 500 | 1.5333 |
+| 1.1946 | 4.1016 | 525 | 1.5805 |
+| 0.9993 | 4.2969 | 550 | 1.6382 |
+| 1.1423 | 4.4922 | 575 | 1.6158 |
+| 1.1734 | 4.6875 | 600 | 1.5982 |
+| 1.107 | 4.8828 | 625 | 1.5630 |
+| 1.0531 | 5.0781 | 650 | 1.6544 |
+| 0.9469 | 5.2734 | 675 | 1.7376 |
+| 1.0501 | 5.4688 | 700 | 1.6753 |
+| 1.0237 | 5.6641 | 725 | 1.6146 |
+| 0.9976 | 5.8594 | 750 | 1.6472 |
+| 0.8801 | 6.0547 | 775 | 1.7507 |
+| 0.8045 | 6.25 | 800 | 1.7875 |
+| 0.9957 | 6.4453 | 825 | 1.6558 |
+| 0.961 | 6.6406 | 850 | 1.7039 |
+| 0.8889 | 6.8359 | 875 | 1.7554 |
+| 0.8674 | 7.0312 | 900 | 1.6885 |
+| 0.8393 | 7.2266 | 925 | 1.7469 |
+| 0.8802 | 7.4219 | 950 | 1.7618 |
+| 0.8384 | 7.6172 | 975 | 1.7559 |
+| 0.8324 | 7.8125 | 1000 | 1.7537 |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+ "alpha_pattern": {},
+ "auto_mapping": null,
+ "base_model_name_or_path": "daryl149/llama-2-13b-chat-hf",
+ "bias": "none",
+ "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": 32,
+ "lora_dropout": 0.05,
+ "megatron_config": null,
+ "megatron_core": "megatron.core",
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 32,
+ "rank_pattern": {},
+ "revision": null,
+ "target_modules": [
+ "k_proj",
+ "q_proj",
+ "dense",
+ "v_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:d928fa341733a0998bf45fbf791fc7aa04e4fd905f9392df634f612dda1efc09
+size 157318920

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+ "bos_token": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": "</s>",
+ "unk_token": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "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 +1,43 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": true,
+ "add_prefix_space": true,
+ "added_tokens_decoder": {
+ "0": {
+ "content": "<unk>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "1": {
+ "content": "<s>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "2": {
+ "content": "</s>",
+ "lstrip": false,
+ "normalized": true,
+ "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": "</s>",
+ "padding_side": "left",
+ "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:a2a63471e7c3423b8c40afeaf4172f0f715eed0d6b224700d2392f830f67c957
+size 5048