End of training

README.md

@@ -0,0 +1,69 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: SentimentT2_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. -->
+
+# SentimentT2_GPT2
+
+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: 0.7249
+- Accuracy: 0.8669
+- F1: 0.8749
+- Auc Roc: 0.9317
+- Log Loss: 0.7249
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Auc Roc | Log Loss |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:-------:|:--------:|
+| 1.1736        | 1.0   | 1618 | 0.6146          | 0.8507   | 0.8592 | 0.9256  | 0.6146   |
+| 0.6452        | 2.0   | 3236 | 0.7249          | 0.8669   | 0.8749 | 0.9317  | 0.7249   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_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,
+  "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 sha256:02f0b5d0a85a3b873b4a183a19c22b0acf256a4c08e0f9b1355b1c34211241e5
+size 497780432

runs/Jan24_14-37-05_579ed4a51ca4/events.out.tfevents.1706107026.579ed4a51ca4.457.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9793fe0c6556e907b1c614be0ace204cb95291a8b77b8a77fb2966750c729a64
+size 7042

runs/Jan24_14-37-05_579ed4a51ca4/events.out.tfevents.1706107294.579ed4a51ca4.457.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a839574f814954dbb18f4b789b2bf531497e649d8830ae90a2484a723adc8d1e
+size 560

runs/Jan24_17-57-00_7d2b1e2d4e1a/events.out.tfevents.1706119022.7d2b1e2d4e1a.2199.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd2d584b67487707bc9efea3ec34eb13466a73d8f15f61b3954cc69b9c0715d8
+size 4184

runs/Jan24_17-57-30_7d2b1e2d4e1a/events.out.tfevents.1706119051.7d2b1e2d4e1a.2199.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade5df7e518384ed3538208ee6c86b7c11214a6eceaa75b0e2a65effdbec6729
+size 5784

runs/Jan24_17-57-30_7d2b1e2d4e1a/events.out.tfevents.1706119493.7d2b1e2d4e1a.2199.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3214ab547043011326ad1369c0d723f88faf092bab310c987101761c07b531
+size 560

runs/Jan24_17-59-31_7d2b1e2d4e1a/events.out.tfevents.1706119172.7d2b1e2d4e1a.2199.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a61710090d075321d12b7f8cacff814f10e9b8b64a06b7373eadc10dd1dee00
+size 5905

runs/Jan24_17-59-31_7d2b1e2d4e1a/events.out.tfevents.1706119503.7d2b1e2d4e1a.2199.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebeb647374b9b6ed5833b093f646e9c089c5a8ac9c0be5fd010d01d22832d1ca
+size 560

runs/Jan24_18-39-04_7d2b1e2d4e1a/events.out.tfevents.1706121545.7d2b1e2d4e1a.2199.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa18069c9bab305333570793f1aaab2ebe626ed027930529345da1d81bd1924
+size 10938

runs/Jan24_19-20-11_7d2b1e2d4e1a/events.out.tfevents.1706124012.7d2b1e2d4e1a.2199.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ff5cea8170bbdd6e49c9181719bfa37e826252a7912b96c5bfd3379d9ac8e9
+size 4544

runs/Jan24_19-23-12_7d2b1e2d4e1a/events.out.tfevents.1706124192.7d2b1e2d4e1a.2199.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48965daa51cd8c292e9726fa9ce868c27b7b7a0b26953610a1284b0a3244db0
+size 4544

runs/Jan24_19-23-37_7d2b1e2d4e1a/events.out.tfevents.1706124217.7d2b1e2d4e1a.2199.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ce18dee6663fdd82856765199eafdf48f24704820cb05dea5b7f9a1d3e3b4d
+size 4543

runs/Jan24_19-31-14_7d2b1e2d4e1a/events.out.tfevents.1706124675.7d2b1e2d4e1a.26662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f052f9d74b7d2a9b38e8f79422b89a997f4df9ad34e859927deefd6aeb99e59c
+size 4543

runs/Jan24_19-32-18_7d2b1e2d4e1a/events.out.tfevents.1706124738.7d2b1e2d4e1a.26662.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983fea0d1e6ed2f5a2d7d497e5a5e25f161ea62d41b9150f99dd72d0af6a2211
+size 4543

runs/Jan24_19-33-23_7d2b1e2d4e1a/events.out.tfevents.1706124804.7d2b1e2d4e1a.26662.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d826890967001774b0ee65bd6c10a7a5ac575902f6bff7de0c7a97a409809e58
+size 4543

runs/Jan24_19-33-53_7d2b1e2d4e1a/events.out.tfevents.1706124834.7d2b1e2d4e1a.26662.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53026ad3317456be6c8ffc66d5cc581d9e09640d1bfb7ae3af5c1f947ca13845
+size 4700

runs/Jan24_19-39-23_7d2b1e2d4e1a/events.out.tfevents.1706125164.7d2b1e2d4e1a.26662.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0106f7873903e963089ccc4d13d050b3100e0bccfd2c4fb500c1e0835913c4
+size 6154

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de59719afd225fb332ed6d1b42b6d228a99601e6a3b5db147d421b6288ddab6
+size 4664