fine-tuned model

README.md

@@ -1,3 +1,69 @@
 ---
 license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
+model-index:
+- name: distilgpt2-wikitext2
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-raw-v1
+      type: wikitext
+      args: wikitext-2-raw-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.39321440208536984
 ---
+
+<!-- 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. -->
+
+# distilgpt2-wikitext2
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the wikitext wikitext-2-raw-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3259
+- Accuracy: 0.3932
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.21.1
+- Pytorch 1.12.1+cu116
+- Datasets 2.4.0
+- Tokenizers 0.12.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.39321440208536984,
+    "eval_loss": 3.3258824348449707,
+    "eval_runtime": 10.0973,
+    "eval_samples": 240,
+    "eval_samples_per_second": 23.769,
+    "eval_steps_per_second": 2.971,
+    "perplexity": 27.82354027433018,
+    "train_loss": 3.429908208737428,
+    "train_runtime": 1005.8166,
+    "train_samples": 2318,
+    "train_samples_per_second": 6.914,
+    "train_steps_per_second": 0.865
+}

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "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": "4.21.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.39321440208536984,
+    "eval_loss": 3.3258824348449707,
+    "eval_runtime": 10.0973,
+    "eval_samples": 240,
+    "eval_samples_per_second": 23.769,
+    "eval_steps_per_second": 2.971,
+    "perplexity": 27.82354027433018
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6bca2083a5b1bf1680e71ef31d9ea0067525d25fed3ee09c37df413bbb8d80
+size 333969117

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "distilgpt2",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.429908208737428,
+    "train_runtime": 1005.8166,
+    "train_samples": 2318,
+    "train_samples_per_second": 6.914,
+    "train_steps_per_second": 0.865
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 870,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.1264367816091954e-05,
+      "loss": 3.4843,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 870,
+      "total_flos": 1817057603616768.0,
+      "train_loss": 3.429908208737428,
+      "train_runtime": 1005.8166,
+      "train_samples_per_second": 6.914,
+      "train_steps_per_second": 0.865
+    }
+  ],
+  "max_steps": 870,
+  "num_train_epochs": 3,
+  "total_flos": 1817057603616768.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa22f551164641d7a8c276c960eb60ba1071de5d9cf719aef76fbed8653c0abe
+size 3311