End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+base_model: gpt2-medium
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-medium-custom-peft
+ 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. -->
+
+# gpt2-medium-custom-peft
+
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
+
+## 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- 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: 1000
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu118
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,20 @@
+{
+ "auto_mapping": null,
+ "base_model_name_or_path": "gpt2-medium",
+ "bias": "none",
+ "fan_in_fan_out": true,
+ "inference_mode": true,
+ "init_lora_weights": true,
+ "layers_pattern": null,
+ "layers_to_transform": null,
+ "lora_alpha": 32,
+ "lora_dropout": 0.05,
+ "modules_to_save": null,
+ "peft_type": "LORA",
+ "r": 16,
+ "revision": null,
+ "target_modules": [
+ "c_attn"
+ ],
+ "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8038a9ba40134351fdca1161288a717ffbf1b4f0bd63c48afbd5d8304ca7814
+size 6297648

runs/Nov03_05-34-24_bd7c3efb7b35/events.out.tfevents.1698989677.bd7c3efb7b35.4651.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d8d05c0ee4aa3b62bfc20e05a730efb58332b9807613fc29c86a28846d87dd
+size 4184

runs/Nov03_05-36-04_bd7c3efb7b35/events.out.tfevents.1698989777.bd7c3efb7b35.5212.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c14f386fb5dd313a2260d125468fd4ecb95c454909e215e1d56f858b4afbc5
+size 4184

runs/Nov03_05-37-23_bd7c3efb7b35/events.out.tfevents.1698989860.bd7c3efb7b35.5631.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4574e0d3bb85afc11a10349783562f8c21a9f2d58313130a80c1995773c34060
+size 4533

runs/Nov03_05-42-36_bd7c3efb7b35/events.out.tfevents.1698990165.bd7c3efb7b35.6992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960e1e249c2d7ffc653b1013f661162491e15e960afce1c439afbb88e661890f
+size 4184

runs/Nov03_05-43-52_bd7c3efb7b35/events.out.tfevents.1698990244.bd7c3efb7b35.7478.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f828693a14a73b00ca99e9dff3203be3f6f89b1b8d97ec2d2f9bacd607e485c
+size 4885

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+ "bos_token": "<|endoftext|>",
+ "eos_token": "<|endoftext|>",
+ "pad_token": "<|endoftext|>",
+ "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+ "add_prefix_space": false,
+ "added_tokens_decoder": {
+ "50256": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": true,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "bos_token": "<|endoftext|>",
+ "clean_up_tokenization_spaces": true,
+ "eos_token": "<|endoftext|>",
+ "model_max_length": 1024,
+ "pad_token": "<|endoftext|>",
+ "tokenizer_class": "GPT2Tokenizer",
+ "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9396a0fe92e6b53bce4e8c1f7135abf203ca0fb4f25ab47c64fcad17d5681bb5
+size 4600