Training completed!

README.md

@@ -0,0 +1,71 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: gpt2-finetuned-stationary-update
+  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-finetuned-stationary-update
+
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6156
+- Accuracy: 0.7067
+- F1: 0.6780
+
+## 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: 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.6691        | 1.0   | 38   | 0.6355          | 0.6667   | 0.5333 |
+| 0.6204        | 2.0   | 76   | 0.6287          | 0.69     | 0.6342 |
+| 0.5971        | 3.0   | 114  | 0.6185          | 0.6867   | 0.6287 |
+| 0.5875        | 4.0   | 152  | 0.6268          | 0.68     | 0.5831 |
+| 0.5494        | 5.0   | 190  | 0.6000          | 0.6967   | 0.6420 |
+| 0.5272        | 6.0   | 228  | 0.6156          | 0.69     | 0.6180 |
+| 0.5026        | 7.0   | 266  | 0.6364          | 0.6833   | 0.6201 |
+| 0.4789        | 8.0   | 304  | 0.6179          | 0.71     | 0.6703 |
+| 0.4742        | 9.0   | 342  | 0.6198          | 0.7033   | 0.6693 |
+| 0.4528        | 10.0  | 380  | 0.6156          | 0.7067   | 0.6780 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForSequenceClassification"
+  ],
+  "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": 50257,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca6b2afa97ad5bb97c4b6a94d09e37c52bd8abf0133b06e826178ed1868b266
+size 497780432

runs/Dec13_13-24-28_2da5916a0ce0/events.out.tfevents.1702473873.2da5916a0ce0.344.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f46e3ef9151029a7b5360f58bd9879adff69aaa88316e72232345523546b479
+size 4493

runs/Dec13_13-24-28_2da5916a0ce0/events.out.tfevents.1702473888.2da5916a0ce0.344.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28ff8f71426a09c3de2640afc24fc850a631e254b7326a0700345b73c73fc39c
+size 4493

runs/Dec13_13-26-26_2da5916a0ce0/events.out.tfevents.1702473989.2da5916a0ce0.344.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896944d39a104ace9bc3f35f9a26c81f4b194e3a78b726d75f6f368eb40b6dd2
+size 4493

runs/Dec13_13-27-30_2da5916a0ce0/events.out.tfevents.1702474053.2da5916a0ce0.344.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db11312d979dd51a44661ace9a6112bc0d10e902e83969fbd93dc9dc7bd61987
+size 10102

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750e75fda9a497468a0aeb8703e805992c590aaf0a5e6486e70827435c08003c
+size 4600