cryptobertRefined

README.md

@@ -0,0 +1,72 @@
+---
+base_model: ElKulako/cryptobert
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [ElKulako/cryptobert](https://huggingface.co/ElKulako/cryptobert) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8983
+- Accuracy: 0.6433
+- Precision: 0.6614
+- Recall: 0.6433
+- F1: 0.6461
+
+## 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: 3.5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 69420
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.9586        | 0.19  | 100  | 0.8746          | 0.6033   | 0.5990    | 0.6033 | 0.5944 |
+| 0.7362        | 0.38  | 200  | 0.8187          | 0.63     | 0.6322    | 0.63   | 0.6232 |
+| 0.577         | 0.57  | 300  | 0.8065          | 0.6767   | 0.6821    | 0.6767 | 0.6761 |
+| 0.4632        | 0.76  | 400  | 0.8437          | 0.63     | 0.6411    | 0.63   | 0.6321 |
+| 0.3243        | 0.95  | 500  | 0.8983          | 0.6433   | 0.6614    | 0.6433 | 0.6461 |
+| 0.2257        | 1.14  | 600  | 1.3704          | 0.6033   | 0.6863    | 0.6033 | 0.6046 |
+| 0.1333        | 1.33  | 700  | 1.2951          | 0.6033   | 0.6201    | 0.6033 | 0.6052 |
+| 0.0574        | 1.52  | 800  | 1.5119          | 0.6333   | 0.6331    | 0.6333 | 0.6309 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "ElKulako/cryptobert",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Bearish",
+    "1": "Neutral",
+    "2": "Bullish"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Bearish": 0,
+    "Bullish": 2,
+    "Neutral": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50414
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:487aaa0fcb01e6cd53220d550de02291576acd98af25863f9b92aaa086ec18f3
+size 499073628

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2a260ff67d8f2963077a1016f76ce32d4aaa23d7d788ac51376f8ed11072b9
+size 4536