End of training

README.md

@@ -0,0 +1,55 @@
+---
+license: mit
+base_model: gpt2-medium
+tags:
+- generated_from_trainer
+datasets:
+- piqa
+model-index:
+- name: platistil
+  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. -->
+
+# platistil
+
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the piqa 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: 0.001
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.25
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.4
+- Tokenizers 0.13.3

adapter_config.json

@@ -0,0 +1,43 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "gpt2-medium",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "transformer.h.0.attn.c_attn",
+    "transformer.h.1.attn.c_attn",
+    "transformer.h.2.attn.c_attn",
+    "transformer.h.3.attn.c_attn",
+    "transformer.h.4.attn.c_attn",
+    "transformer.h.5.attn.c_attn",
+    "transformer.h.6.attn.c_attn",
+    "transformer.h.7.attn.c_attn",
+    "transformer.h.8.attn.c_attn",
+    "transformer.h.9.attn.c_attn",
+    "transformer.h.10.attn.c_attn",
+    "transformer.h.11.attn.c_attn",
+    "transformer.h.12.attn.c_attn",
+    "transformer.h.13.attn.c_attn",
+    "transformer.h.14.attn.c_attn",
+    "transformer.h.15.attn.c_attn",
+    "transformer.h.16.attn.c_attn",
+    "transformer.h.17.attn.c_attn",
+    "transformer.h.18.attn.c_attn",
+    "transformer.h.19.attn.c_attn",
+    "transformer.h.20.attn.c_attn",
+    "transformer.h.21.attn.c_attn",
+    "transformer.h.22.attn.c_attn",
+    "transformer.h.23.attn.c_attn"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb9562ebb4eca660bc4028c9fca124a187c84c301e9bbb5bd16ccfef098325f8
+size 3151856

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<pad>": 50257
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_to_multiple_of": 8,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2d6cdb35b79718ff6544b529b6090c2cadb53d585bed5e0c767865bfe4601e
+size 4091