Upload financial-sentiment-improved model

README.md

@@ -0,0 +1,94 @@
+---
+language: en
+license: apache-2.0
+tags:
+- financial-sentiment
+- sentiment-analysis
+- finance
+- nlp
+- transformers
+datasets:
+- zeroshot/twitter-financial-news-sentiment
+metrics:
+- accuracy
+- f1
+model-index:
+- name: financial-sentiment-improved
+  results:
+  - task:
+      type: text-classification
+      name: Financial Sentiment Analysis
+    dataset:
+      name: Twitter Financial News Sentiment
+      type: zeroshot/twitter-financial-news-sentiment
+    metrics:
+    - type: accuracy
+      value: 0.821
+      name: Accuracy
+---
+
+# financial-sentiment-improved
+
+## Model Description
+
+Improved financial sentiment analysis model with enhanced performance
+
+This model is fine-tuned from `distilbert-base-uncased` for financial sentiment analysis, capable of classifying financial text into three categories:
+- **Bearish** (0): Negative financial sentiment
+- **Neutral** (1): Neutral financial sentiment  
+- **Bullish** (2): Positive financial sentiment
+
+## Model Performance
+
+- **Accuracy**: 0.821
+- **Dataset**: Twitter Financial News Sentiment
+- **Base Model**: distilbert-base-uncased
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("codealchemist01/financial-sentiment-improved")
+model = AutoModelForSequenceClassification.from_pretrained("codealchemist01/financial-sentiment-improved")
+
+# Example usage
+text = "Apple stock is showing strong growth potential"
+inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+
+with torch.no_grad():
+    outputs = model(**inputs)
+    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+    predicted_class = torch.argmax(predictions, dim=-1).item()
+
+# Labels: 0=Bearish, 1=Neutral, 2=Bullish
+labels = ["Bearish", "Neutral", "Bullish"]
+print(f"Prediction: {labels[predicted_class]}")
+```
+
+## Training Details
+
+- **Training Dataset**: Twitter Financial News Sentiment
+- **Training Framework**: Transformers
+- **Optimization**: AdamW
+- **Hardware**: RTX GPU
+
+## Limitations
+
+This model is specifically trained for financial sentiment analysis and may not perform well on general sentiment analysis tasks.
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{financial-sentiment-improved,
+  author = {CodeAlchemist01},
+  title = {financial-sentiment-improved},
+  year = {2024},
+  publisher = {Hugging Face},
+  url = {https://huggingface.co/codealchemist01/financial-sentiment-improved}
+}
+```

checkpoint-3435/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "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-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",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-3435/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48c5865d66c0b5654a996d8e3a6977d1553f1e97e4973b34e5d80e25ea0a327
+size 437961724

checkpoint-3435/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57e62ecd4534984beb81579e61c918eeb2646d714908c1bf0272728fb73b6922
+size 876047755

checkpoint-3435/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5469a191031d902dc8de479caffb6492a9565ab51d74eec53f5e3aab4cd34ccb
+size 14645

checkpoint-3435/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bd55a1abc0131ea110babda0977af8e00e1cd77716845211c78a0cf5038a4d2
+size 1383

checkpoint-3435/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569147eb9f05b3d2f3e8065d6e6f437667bdb84690b928efbaba57dfa38cde5d
+size 1465

checkpoint-3435/trainer_state.json

@@ -0,0 +1,407 @@
+{
+  "best_global_step": 2500,
+  "best_metric": 0.8745242401633876,
+  "best_model_checkpoint": "models\\improved_model\\checkpoint-2500",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 3435,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14556040756914118,
+      "grad_norm": 5.4006147384643555,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 1.0779,
+      "step": 100
+    },
+    {
+      "epoch": 0.29112081513828236,
+      "grad_norm": 7.964382171630859,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 0.3444,
+      "step": 200
+    },
+    {
+      "epoch": 0.4366812227074236,
+      "grad_norm": 6.473100185394287,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 0.2621,
+      "step": 300
+    },
+    {
+      "epoch": 0.5822416302765647,
+      "grad_norm": 2.3269290924072266,
+      "learning_rate": 3.99e-05,
+      "loss": 0.2215,
+      "step": 400
+    },
+    {
+      "epoch": 0.727802037845706,
+      "grad_norm": 1.0794602632522583,
+      "learning_rate": 4.99e-05,
+      "loss": 0.1994,
+      "step": 500
+    },
+    {
+      "epoch": 0.727802037845706,
+      "eval_accuracy": 0.8291404612159329,
+      "eval_f1": 0.8347849048667186,
+      "eval_f1_bearish": 0.7192982456140351,
+      "eval_f1_bullish": 0.8773747841105354,
+      "eval_f1_neutral": 0.7843137254901961,
+      "eval_loss": 0.16642487049102783,
+      "eval_precision": 0.8522584333905088,
+      "eval_precision_bearish": 0.6212121212121212,
+      "eval_precision_bullish": 0.9407407407407408,
+      "eval_precision_neutral": 0.7407407407407407,
+      "eval_recall": 0.8291404612159329,
+      "eval_recall_bearish": 0.8541666666666666,
+      "eval_recall_bullish": 0.8220064724919094,
+      "eval_recall_neutral": 0.8333333333333334,
+      "eval_runtime": 8.1987,
+      "eval_samples_per_second": 116.359,
+      "eval_steps_per_second": 3.659,
+      "step": 500
+    },
+    {
+      "epoch": 0.8733624454148472,
+      "grad_norm": 10.456722259521484,
+      "learning_rate": 4.831345826235094e-05,
+      "loss": 0.1798,
+      "step": 600
+    },
+    {
+      "epoch": 1.0189228529839884,
+      "grad_norm": 0.8317745327949524,
+      "learning_rate": 4.660988074957411e-05,
+      "loss": 0.1477,
+      "step": 700
+    },
+    {
+      "epoch": 1.1644832605531295,
+      "grad_norm": 13.93519401550293,
+      "learning_rate": 4.490630323679728e-05,
+      "loss": 0.1027,
+      "step": 800
+    },
+    {
+      "epoch": 1.3100436681222707,
+      "grad_norm": 5.650792598724365,
+      "learning_rate": 4.320272572402044e-05,
+      "loss": 0.1093,
+      "step": 900
+    },
+    {
+      "epoch": 1.455604075691412,
+      "grad_norm": 2.2038004398345947,
+      "learning_rate": 4.1499148211243615e-05,
+      "loss": 0.1091,
+      "step": 1000
+    },
+    {
+      "epoch": 1.455604075691412,
+      "eval_accuracy": 0.8542976939203354,
+      "eval_f1": 0.854962642061992,
+      "eval_f1_bearish": 0.7436823104693141,
+      "eval_f1_bullish": 0.9034369885433715,
+      "eval_f1_neutral": 0.78239608801956,
+      "eval_loss": 0.22784079611301422,
+      "eval_precision": 0.85731689649448,
+      "eval_precision_bearish": 0.7744360902255639,
+      "eval_precision_bullish": 0.9139072847682119,
+      "eval_precision_neutral": 0.7373271889400922,
+      "eval_recall": 0.8542976939203354,
+      "eval_recall_bearish": 0.7152777777777778,
+      "eval_recall_bullish": 0.8932038834951457,
+      "eval_recall_neutral": 0.8333333333333334,
+      "eval_runtime": 8.8257,
+      "eval_samples_per_second": 108.094,
+      "eval_steps_per_second": 3.399,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6011644832605532,
+      "grad_norm": 4.665580749511719,
+      "learning_rate": 3.9795570698466784e-05,
+      "loss": 0.0851,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7467248908296944,
+      "grad_norm": 0.20554736256599426,
+      "learning_rate": 3.809199318568995e-05,
+      "loss": 0.0983,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8922852983988356,
+      "grad_norm": 2.3172614574432373,
+      "learning_rate": 3.638841567291312e-05,
+      "loss": 0.0908,
+      "step": 1300
+    },
+    {
+      "epoch": 2.037845705967977,
+      "grad_norm": 0.20416907966136932,
+      "learning_rate": 3.468483816013629e-05,
+      "loss": 0.072,
+      "step": 1400
+    },
+    {
+      "epoch": 2.183406113537118,
+      "grad_norm": 0.08527473360300064,
+      "learning_rate": 3.298126064735946e-05,
+      "loss": 0.0316,
+      "step": 1500
+    },
+    {
+      "epoch": 2.183406113537118,
+      "eval_accuracy": 0.8616352201257862,
+      "eval_f1": 0.8636672911856373,
+      "eval_f1_bearish": 0.7516339869281046,
+      "eval_f1_bullish": 0.9054726368159204,
+      "eval_f1_neutral": 0.8131313131313131,
+      "eval_loss": 0.24344488978385925,
+      "eval_precision": 0.8675144411363428,
+      "eval_precision_bearish": 0.7098765432098766,
+      "eval_precision_bullish": 0.9285714285714286,
+      "eval_precision_neutral": 0.7892156862745098,
+      "eval_recall": 0.8616352201257862,
+      "eval_recall_bearish": 0.7986111111111112,
+      "eval_recall_bullish": 0.883495145631068,
+      "eval_recall_neutral": 0.8385416666666666,
+      "eval_runtime": 8.6074,
+      "eval_samples_per_second": 110.835,
+      "eval_steps_per_second": 3.485,
+      "step": 1500
+    },
+    {
+      "epoch": 2.328966521106259,
+      "grad_norm": 7.853630065917969,
+      "learning_rate": 3.1277683134582626e-05,
+      "loss": 0.0363,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4745269286754,
+      "grad_norm": 0.3771085739135742,
+      "learning_rate": 2.957410562180579e-05,
+      "loss": 0.0347,
+      "step": 1700
+    },
+    {
+      "epoch": 2.6200873362445414,
+      "grad_norm": 3.0605719089508057,
+      "learning_rate": 2.787052810902896e-05,
+      "loss": 0.0319,
+      "step": 1800
+    },
+    {
+      "epoch": 2.7656477438136826,
+      "grad_norm": 3.2105116844177246,
+      "learning_rate": 2.616695059625213e-05,
+      "loss": 0.0359,
+      "step": 1900
+    },
+    {
+      "epoch": 2.911208151382824,
+      "grad_norm": 3.7454285621643066,
+      "learning_rate": 2.44633730834753e-05,
+      "loss": 0.0361,
+      "step": 2000
+    },
+    {
+      "epoch": 2.911208151382824,
+      "eval_accuracy": 0.8584905660377359,
+      "eval_f1": 0.8593807235316668,
+      "eval_f1_bearish": 0.7571428571428571,
+      "eval_f1_bullish": 0.9074529074529074,
+      "eval_f1_neutral": 0.7813267813267813,
+      "eval_loss": 0.2744849622249603,
+      "eval_precision": 0.8616426481335732,
+      "eval_precision_bearish": 0.7794117647058824,
+      "eval_precision_bullish": 0.9187396351575456,
+      "eval_precision_neutral": 0.7395348837209302,
+      "eval_recall": 0.8584905660377359,
+      "eval_recall_bearish": 0.7361111111111112,
+      "eval_recall_bullish": 0.8964401294498382,
+      "eval_recall_neutral": 0.828125,
+      "eval_runtime": 8.1534,
+      "eval_samples_per_second": 117.007,
+      "eval_steps_per_second": 3.679,
+      "step": 2000
+    },
+    {
+      "epoch": 3.056768558951965,
+      "grad_norm": 0.04752872511744499,
+      "learning_rate": 2.2759795570698465e-05,
+      "loss": 0.0169,
+      "step": 2100
+    },
+    {
+      "epoch": 3.2023289665211063,
+      "grad_norm": 3.445439100265503,
+      "learning_rate": 2.1056218057921637e-05,
+      "loss": 0.0094,
+      "step": 2200
+    },
+    {
+      "epoch": 3.3478893740902476,
+      "grad_norm": 1.7491494417190552,
+      "learning_rate": 1.9352640545144805e-05,
+      "loss": 0.0084,
+      "step": 2300
+    },
+    {
+      "epoch": 3.493449781659389,
+      "grad_norm": 1.3558599948883057,
+      "learning_rate": 1.7649063032367974e-05,
+      "loss": 0.0155,
+      "step": 2400
+    },
+    {
+      "epoch": 3.6390101892285296,
+      "grad_norm": 0.7178720235824585,
+      "learning_rate": 1.5945485519591142e-05,
+      "loss": 0.0166,
+      "step": 2500
+    },
+    {
+      "epoch": 3.6390101892285296,
+      "eval_accuracy": 0.8752620545073375,
+      "eval_f1": 0.8745242401633876,
+      "eval_f1_bearish": 0.7612456747404844,
+      "eval_f1_bullish": 0.9131474103585657,
+      "eval_f1_neutral": 0.8351648351648352,
+      "eval_loss": 0.27798759937286377,
+      "eval_precision": 0.8750783502197678,
+      "eval_precision_bearish": 0.7586206896551724,
+      "eval_precision_bullish": 0.8995290423861853,
+      "eval_precision_neutral": 0.8837209302325582,
+      "eval_recall": 0.8752620545073375,
+      "eval_recall_bearish": 0.7638888888888888,
+      "eval_recall_bullish": 0.9271844660194175,
+      "eval_recall_neutral": 0.7916666666666666,
+      "eval_runtime": 8.5538,
+      "eval_samples_per_second": 111.529,
+      "eval_steps_per_second": 3.507,
+      "step": 2500
+    },
+    {
+      "epoch": 3.7845705967976713,
+      "grad_norm": 0.5409824252128601,
+      "learning_rate": 1.424190800681431e-05,
+      "loss": 0.0072,
+      "step": 2600
+    },
+    {
+      "epoch": 3.930131004366812,
+      "grad_norm": 0.007624503690749407,
+      "learning_rate": 1.253833049403748e-05,
+      "loss": 0.0051,
+      "step": 2700
+    },
+    {
+      "epoch": 4.075691411935954,
+      "grad_norm": 0.03979913145303726,
+      "learning_rate": 1.0834752981260648e-05,
+      "loss": 0.0106,
+      "step": 2800
+    },
+    {
+      "epoch": 4.2212518195050945,
+      "grad_norm": 0.025390487164258957,
+      "learning_rate": 9.131175468483816e-06,
+      "loss": 0.003,
+      "step": 2900
+    },
+    {
+      "epoch": 4.366812227074236,
+      "grad_norm": 8.90622615814209,
+      "learning_rate": 7.427597955706985e-06,
+      "loss": 0.0066,
+      "step": 3000
+    },
+    {
+      "epoch": 4.366812227074236,
+      "eval_accuracy": 0.8742138364779874,
+      "eval_f1": 0.8740584051302639,
+      "eval_f1_bearish": 0.7659574468085106,
+      "eval_f1_bullish": 0.9174757281553398,
+      "eval_f1_neutral": 0.8153846153846154,
+      "eval_loss": 0.3259490132331848,
+      "eval_precision": 0.8740853986957351,
+      "eval_precision_bearish": 0.782608695652174,
+      "eval_precision_bullish": 0.9174757281553398,
+      "eval_precision_neutral": 0.803030303030303,
+      "eval_recall": 0.8742138364779874,
+      "eval_recall_bearish": 0.75,
+      "eval_recall_bullish": 0.9174757281553398,
+      "eval_recall_neutral": 0.828125,
+      "eval_runtime": 9.0626,
+      "eval_samples_per_second": 105.268,
+      "eval_steps_per_second": 3.31,
+      "step": 3000
+    },
+    {
+      "epoch": 4.512372634643377,
+      "grad_norm": 0.0042578354477882385,
+      "learning_rate": 5.724020442930154e-06,
+      "loss": 0.0021,
+      "step": 3100
+    },
+    {
+      "epoch": 4.657933042212518,
+      "grad_norm": 0.0550072155892849,
+      "learning_rate": 4.0204429301533224e-06,
+      "loss": 0.0065,
+      "step": 3200
+    },
+    {
+      "epoch": 4.8034934497816595,
+      "grad_norm": 0.019497277215123177,
+      "learning_rate": 2.3168654173764905e-06,
+      "loss": 0.0023,
+      "step": 3300
+    },
+    {
+      "epoch": 4.9490538573508,
+      "grad_norm": 0.012889917939901352,
+      "learning_rate": 6.132879045996593e-07,
+      "loss": 0.0031,
+      "step": 3400
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3435,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.444624220035584e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3435/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb2ecd9bb017dca59b8123a0bc341b04a5a2fec62dea1faccf98aad898c9162
+size 5841

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "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-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",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ced80768c631b64def495b70ac51d8211c6136626c4846a5ccca1d3423f96fb
+size 437961724

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb2ecd9bb017dca59b8123a0bc341b04a5a2fec62dea1faccf98aad898c9162
+size 5841