first commit

README.md

@@ -1,3 +1,51 @@
----
-license: mit
----
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: distilgpt2-imdb
+  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. -->
+
+# distilgpt2-imdb
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the [imdb](https://www.kaggle.com/lakshmi25npathi/imdb-dataset-of-50k-movie-reviews) 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: 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 4.17.0.dev0
+- Pytorch 1.10.2
+- Datasets 1.18.3
+- Tokenizers 0.11.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.7688379650812514,
+    "train_runtime": 1023.2122,
+    "train_samples": 13721,
+    "train_samples_per_second": 40.229,
+    "train_steps_per_second": 5.031
+}

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": "4.17.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0af69317cc81688f163983649c7a0ba1992df58842a8eac756090d2d6674a842
+size 333973213

special_tokens_map.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.7688379650812514,
+    "train_runtime": 1023.2122,
+    "train_samples": 13721,
+    "train_samples_per_second": 40.229,
+    "train_steps_per_second": 5.031
+}

trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 5148,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.5143745143745146e-05,
+      "loss": 3.9164,
+      "step": 500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.028749028749029e-05,
+      "loss": 3.8467,
+      "step": 1000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.5431235431235434e-05,
+      "loss": 3.8141,
+      "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.057498057498058e-05,
+      "loss": 3.7751,
+      "step": 2000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.571872571872572e-05,
+      "loss": 3.7493,
+      "step": 2500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0862470862470865e-05,
+      "loss": 3.7472,
+      "step": 3000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.600621600621601e-05,
+      "loss": 3.7349,
+      "step": 3500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.114996114996115e-05,
+      "loss": 3.7125,
+      "step": 4000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.2937062937062944e-06,
+      "loss": 3.7034,
+      "step": 4500
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.4374514374514376e-06,
+      "loss": 3.704,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "step": 5148,
+      "total_flos": 1.0755758144618496e+16,
+      "train_loss": 3.7688379650812514,
+      "train_runtime": 1023.2122,
+      "train_samples_per_second": 40.229,
+      "train_steps_per_second": 5.031
+    }
+  ],
+  "max_steps": 5148,
+  "num_train_epochs": 3,
+  "total_flos": 1.0755758144618496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e60c55b22d0bfab35d7a49a85992435c6aee240d72cfe763fb708c3fc0ddeaf
+size 2991