add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- null
+model-index:
+- name: distilgpt2-finetuned-pgt
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+---
+
+<!-- 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-finetuned-pgt
+
+This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0132
+
+## 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: 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
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 31   | 5.0513          |
+| No log        | 2.0   | 62   | 5.0175          |
+| No log        | 3.0   | 93   | 5.0132          |
+
+
+### Framework versions
+
+- Transformers 4.10.0
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,45 @@
+{
+  "_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,
+  "gradient_checkpointing": false,
+  "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,
+  "resid_pdrop": 0.1,
+  "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": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87aaca36a21c9826353924ff25636aae44c2cf05193939981e6cca66572eb2bb
+size 333972957

runs/Sep04_11-15-27_945072ab5905/1630754140.0514774/events.out.tfevents.1630754140.945072ab5905.88.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac54487461cc4818a19f3a52b4d067d7b589daa48214ee4454daf2343894854
+size 4185

runs/Sep04_11-15-27_945072ab5905/events.out.tfevents.1630754140.945072ab5905.88.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e883c607492e892b246f52b3cdcb6b94b84976d14750bf70444f0fc080e6d4d1
+size 4393

runs/Sep04_11-15-27_945072ab5905/events.out.tfevents.1630754157.945072ab5905.88.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad77e839e55fef15d3c2725564609cf816c4acca78a677421e92d15bae3b5039
+size 306

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7db8261b1c1d815ff14d590b6c5bf1b22161ffbf299d6040e0b3c1094616e12
+size 2671