End of training

README.md

@@ -0,0 +1,71 @@
+---
+base_model: gpt2
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-lora
+  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-lora
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2244
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.352         | 0.4737 | 200  | 2.2613          |
+| 2.363         | 0.9473 | 400  | 2.2484          |
+| 2.3263        | 1.4210 | 600  | 2.2433          |
+| 2.3454        | 1.8946 | 800  | 2.2371          |
+| 2.3287        | 2.3683 | 1000 | 2.2321          |
+| 2.3003        | 2.8419 | 1200 | 2.2296          |
+| 2.2973        | 3.3156 | 1400 | 2.2266          |
+| 2.296         | 3.7892 | 1600 | 2.2257          |
+| 2.2924        | 4.2629 | 1800 | 2.2253          |
+| 2.2923        | 4.7365 | 2000 | 2.2244          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -3,7 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "gpt2",
   "bias": "none",
-  "fan_in_fan_out": true,
+  "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layer_replication": null,

runs/Aug28_14-05-32_86d6d300df19/events.out.tfevents.1724853945.86d6d300df19.215.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a9ef01f8e0fb7c8bcc1cc84d391424ad7bf57b82cab4a9f8bf9b9cf645ede8
-size 12197
+oid sha256:6fa42912ed4957c68a35aa22fb005c26d225dd54efb19d8ffe176490864e1fae
+size 12551

runs/Aug28_14-47-01_86d6d300df19/events.out.tfevents.1724856426.86d6d300df19.215.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096980cc5bbb1603d08160e992b72ad01a87d088f60795877a6e57588b65d2c5
+size 5414

special_tokens_map.json

@@ -1,6 +1,30 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -13,8 +13,12 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 1024,
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04b0c39548a29e17c455cbaafbcca092bc4a1f63a91871685da502262e44ee7b
+oid sha256:ac808cdaefd151e141733b3dceead8564a92a5eebeaabd181fc0e6eec1269385
 size 5112