draft_del1

README.md

@@ -0,0 +1,61 @@
+---
+base_model: yiyanghkust/finbert-pretrain
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: temp
+  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. -->
+
+# temp
+
+This model is a fine-tuned version of [yiyanghkust/finbert-pretrain](https://huggingface.co/yiyanghkust/finbert-pretrain) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0850
+- Accuracy: 0.9815
+
+## 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: 48
+- eval_batch_size: 48
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 51   | 0.1629          | 0.9407   |
+| No log        | 2.0   | 102  | 0.0894          | 0.9778   |
+| No log        | 3.0   | 153  | 0.0850          | 0.9815   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "yiyanghkust/finbert-pretrain",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30873
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c62b664ac46e10ea4e7e02dfe24e00dcc27c4c42ce3dde3118ff4879e3033e
+size 439039996

runs/Dec21_14-18-14_8e3e33c7e2e3/events.out.tfevents.1703168295.8e3e33c7e2e3.4795.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c6beaf3ea92b7e953a2072437fd17794e39ec8b88926d5065b76b4cc9a0b11
+size 5616

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0feaf1b3bac136a3ee4e75d13c7f38c8318b0d760003409d9491b2c0aa82dce
+size 4536