Training completed for 6@lr:0.0001!

README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: ml6team/gpt2-small-german-finetune-oscar
+model-index:
+- name: ml6team-gpt2-small-german-finetune-oscar-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. -->
+
+# ml6team-gpt2-small-german-finetune-oscar-peft
+
+This model is a fine-tuned version of [ml6team/gpt2-small-german-finetune-oscar](https://huggingface.co/ml6team/gpt2-small-german-finetune-oscar) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.5772
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 5.173         | 1.0   | 210  | 4.7734          |
+| 4.6792        | 2.0   | 420  | 4.6458          |
+| 4.5685        | 3.0   | 630  | 4.6042          |
+| 4.2199        | 4.0   | 840  | 4.5872          |
+| 4.7324        | 5.0   | 1050 | 4.5797          |
+| 5.4576        | 6.0   | 1260 | 4.5772          |
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ml6team/gpt2-small-german-finetune-oscar",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "wte",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f182bf972d3367cbbc2aace42fcfd8b084d8b9f891b9a9f62a28859c4e437c
+size 312045352

runs/Feb22_18-31-07_4c120a416583/events.out.tfevents.1708626679.4c120a416583.404.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057efa8efbc4187cd6e48a8c4b31526ce95796b7e9e7cddb365c2188012dc163
+size 4184

runs/Feb22_18-32-08_4c120a416583/events.out.tfevents.1708626732.4c120a416583.404.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60251c13b7e31ae09f6e634edd0ab3ffdf3717183562766d1769948ff1f9441a
+size 8280

runs/Feb22_18-34-36_4c120a416583/events.out.tfevents.1708626891.4c120a416583.11440.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e1f95c7dec4f7e5a2c87c17f28c1d3b7aaf9936b9075824d90a8f665456d63c
+size 4184

runs/Feb22_18-36-23_4c120a416583/events.out.tfevents.1708626993.4c120a416583.12271.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c2229cab7787d8bd18ca80d2c8ae18ba28e4b39f489501e46aab86018a0765
+size 272287

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "full_tokenizer_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "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 sha256:34127852ac8b24422d117536f1a380d99ab27090671f13848a95908730a00c6c
+size 4920