MHGanainy/gpt2-xl-lora-multi

README.md

@@ -0,0 +1,60 @@
+---
+base_model: openai-community/gpt2-xl
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: gpt2-xl-lora-multi
+  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-xl-lora-multi
+
+This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.7722
+- eval_model_preparation_time: 0.0288
+- eval_runtime: 144.7768
+- eval_samples_per_second: 6.272
+- eval_steps_per_second: 3.136
+- step: 0
+
+## 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: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- PEFT 0.13.0
+- Transformers 4.45.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "openai-community/gpt2-xl",
+  "bias": "none",
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn",
+    "c_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 sha256:02933dc3002a814b29a52f22e674b9070ee5bffe1bb37303bf05d353917a9ffa
+size 216306688

all_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_loss": 2.772221088409424,
+    "eval_model_preparation_time": 0.0288,
+    "eval_runtime": 144.7768,
+    "eval_samples_per_second": 6.272,
+    "eval_steps_per_second": 3.136,
+    "perplexity": 15.99411893981886
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_loss": 2.772221088409424,
+    "eval_model_preparation_time": 0.0288,
+    "eval_runtime": 144.7768,
+    "eval_samples_per_second": 6.272,
+    "eval_steps_per_second": 3.136,
+    "perplexity": 15.99411893981886
+}

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": false,
+  "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 sha256:0653b3662f825fa46d72ebb7de7a7b3129d2bb2decbfe89527e0a765fa72c9c0
+size 5240