End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+base_model: openai-community/gpt2
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- piqa
+model-index:
+- name: HW2-supervised
+  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. -->
+
+# HW2-supervised
+
+This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) 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: 5e-05
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.0
+- Pytorch 2.4.0+cu124
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "openai-community/gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.44.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b16bcc88121a24d0ac4bc25134ad5714acb18cd9a693a6fafdbe6ab4ccb020f
+size 497774208

runs/Aug31_15-30-21_katana17ubuntu/events.out.tfevents.1725114623.katana17ubuntu.80091.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71678c88d874f892784db9449fd5e11a4c36ee71981a009d6069fe7c1b7b2403
+size 5454

runs/Aug31_15-32-52_katana17ubuntu/events.out.tfevents.1725114774.katana17ubuntu.81362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d976a1f5da60a5f170de6cb36ee7ce4b8c76cd608f9ce58ae62798b0eec7f40
+size 5453

runs/Aug31_15-40-15_katana17ubuntu/events.out.tfevents.1725115217.katana17ubuntu.84534.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca017bf31f39468dfba7dacd72d74c830bc40e901d97791571ae777be11194c
+size 5454

runs/Aug31_15-42-43_katana17ubuntu/events.out.tfevents.1725115366.katana17ubuntu.85850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5604fa40e09927160af03e8bb279677d65296d1c69f26e782f856c55f8651d
+size 5454

runs/Aug31_15-44-13_katana17ubuntu/events.out.tfevents.1725115453.katana17ubuntu.86554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df1fc3a9a4d2c2739c166cbe78e0153eaea46e887fc96cb6689083892729453
+size 5454

runs/Aug31_15-46-55_katana17ubuntu/events.out.tfevents.1725115616.katana17ubuntu.88000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d432e0d6cef3e979ecbe5070498780cf15e1711875e09b5a7d4c0e7bdeb93695
+size 5665

runs/Aug31_15-54-18_katana17ubuntu/events.out.tfevents.1725116059.katana17ubuntu.91167.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c9acabe46bd4e5f51ff72a9395c2994d23ccbef8e1d64ed44adc36edbe4683
+size 5453

runs/Aug31_15-56-54_katana17ubuntu/events.out.tfevents.1725116215.katana17ubuntu.92474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b261202eec33801d85413f7317f69b07f3752d569d23f4aead6b881d9197c44
+size 6020

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 sha256:4bf8de2e61131289ae1f937f3410921dd144ce9f0ef68806103c7acbce8c6f6a
+size 5432