End of training

README.md

@@ -0,0 +1,85 @@
+---
+license: mit
+base_model: gpt2
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: gpt2-finetuned-depression
+  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-depression
+
+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: 0.6647
+- Precision: 0.8917
+- Recall: 0.8648
+- F1: 0.8772
+- Accuracy: 0.9104
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 469  | 0.4102          | 0.8382    | 0.7154 | 0.7590 | 0.8614   |
+| 0.652         | 2.0   | 938  | 0.3335          | 0.8669    | 0.8254 | 0.8439 | 0.8838   |
+| 0.3283        | 3.0   | 1407 | 0.4627          | 0.8978    | 0.8464 | 0.8689 | 0.9041   |
+| 0.1988        | 4.0   | 1876 | 0.5853          | 0.9021    | 0.8324 | 0.8628 | 0.8987   |
+| 0.1613        | 5.0   | 2345 | 0.6426          | 0.9034    | 0.8385 | 0.8672 | 0.8987   |
+| 0.1013        | 6.0   | 2814 | 0.6247          | 0.8682    | 0.8611 | 0.8643 | 0.9041   |
+| 0.0863        | 7.0   | 3283 | 0.7673          | 0.8930    | 0.8375 | 0.8617 | 0.8987   |
+| 0.0757        | 8.0   | 3752 | 0.6647          | 0.8917    | 0.8648 | 0.8772 | 0.9104   |
+| 0.0511        | 9.0   | 4221 | 0.6658          | 0.8768    | 0.8674 | 0.8720 | 0.9030   |
+| 0.0581        | 10.0  | 4690 | 0.7686          | 0.9104    | 0.8595 | 0.8824 | 0.9094   |
+| 0.0311        | 11.0  | 5159 | 0.6830          | 0.8918    | 0.8488 | 0.8685 | 0.8977   |
+| 0.0537        | 12.0  | 5628 | 0.7438          | 0.9078    | 0.8563 | 0.8795 | 0.9062   |
+| 0.0436        | 13.0  | 6097 | 0.7950          | 0.8933    | 0.8438 | 0.8663 | 0.8987   |
+| 0.042         | 14.0  | 6566 | 0.7248          | 0.8986    | 0.8507 | 0.8726 | 0.9030   |
+| 0.0374        | 15.0  | 7035 | 0.6973          | 0.8884    | 0.8504 | 0.8681 | 0.9009   |
+| 0.0371        | 16.0  | 7504 | 0.7294          | 0.8874    | 0.8554 | 0.8703 | 0.9030   |
+| 0.0371        | 17.0  | 7973 | 0.7649          | 0.8937    | 0.8486 | 0.8692 | 0.9030   |
+| 0.0318        | 18.0  | 8442 | 0.7576          | 0.8879    | 0.8467 | 0.8657 | 0.9009   |
+| 0.0307        | 19.0  | 8911 | 0.7556          | 0.8937    | 0.8486 | 0.8692 | 0.9030   |
+| 0.0264        | 20.0  | 9380 | 0.7647          | 0.8930    | 0.8486 | 0.8689 | 0.9030   |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,51 @@
+{
+  "_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,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE",
+    "2": "MODERATE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "MODERATE": 2,
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "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": 50256,
+  "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": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99715ca024f35ab359c65be38762b6e97934f4a1f13f8cd638ece299f4ee912b
+size 497783504

runs/Jun23_14-39-02_fc0c4a274fb1/events.out.tfevents.1719153550.fc0c4a274fb1.161.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ae7263440ba1f0284a3eddfce4850a13262540202615d2a4eccdba8193eef0
+size 12231

runs/Jun23_15-05-30_fc0c4a274fb1/events.out.tfevents.1719155140.fc0c4a274fb1.161.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d2adb22c172fa0e8fe6767fcafb7090dbfeadfb08267fbb3c166e3ddf985ce4
+size 18850

runs/Jun23_15-05-30_fc0c4a274fb1/events.out.tfevents.1719157547.fc0c4a274fb1.161.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df517bc9888b15a0abadca6bed3bb13ed94e8d22fd861764cc03eb0ae458f29
+size 560

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "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 sha256:448539a2f7fdc2540ab90904c094e96e6bcf89a86de60c00277e227b3b47fa7f
+size 5112