GPT-2

models/gpt2/README.md

@@ -0,0 +1,56 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: gpt2
+  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
+
+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: 0.2178
+- Accuracy: 0.9231
+
+## 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: 24
+- eval_batch_size: 24
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.9.0
+- Tokenizers 0.13.2

models/gpt2/all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9230769276618958,
+    "eval_loss": 0.2177695333957672,
+    "eval_runtime": 10.0539,
+    "eval_samples": 1274,
+    "eval_samples_per_second": 126.717,
+    "eval_steps_per_second": 5.371,
+    "train_loss": 0.689463275015069,
+    "train_runtime": 490.8844,
+    "train_samples": 4999,
+    "train_samples_per_second": 50.918,
+    "train_steps_per_second": 2.129
+}

models/gpt2/config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassificationCustom"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5
+  },
+  "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,
+  "problem_type": "single_label_classification",
+  "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": "4.26.1",
+  "use_cache": true,
+  "use_hidden_states": true,
+  "vocab_size": 50257
+}

models/gpt2/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9230769276618958,
+    "eval_loss": 0.2177695333957672,
+    "eval_runtime": 10.0539,
+    "eval_samples": 1274,
+    "eval_samples_per_second": 126.717,
+    "eval_steps_per_second": 5.371
+}

models/gpt2/special_tokens_map.json

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

models/gpt2/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

models/gpt2/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.689463275015069,
+    "train_runtime": 490.8844,
+    "train_samples": 4999,
+    "train_samples_per_second": 50.918,
+    "train_steps_per_second": 2.129
+}

models/gpt2/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 1045,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.39,
+      "learning_rate": 1.0430622009569378e-05,
+      "loss": 1.0247,
+      "step": 500
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 8.612440191387561e-07,
+      "loss": 0.3843,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "step": 1045,
+      "total_flos": 1723489601126400.0,
+      "train_loss": 0.689463275015069,
+      "train_runtime": 490.8844,
+      "train_samples_per_second": 50.918,
+      "train_steps_per_second": 2.129
+    }
+  ],
+  "max_steps": 1045,
+  "num_train_epochs": 5,
+  "total_flos": 1723489601126400.0,
+  "trial_name": null,
+  "trial_params": null
+}