End of training

README.md

@@ -0,0 +1,88 @@
+---
+library_name: transformers
+license: mit
+base_model: intfloat/e5-small-v2
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: intfloat-e5-small-v2-english-fp16
+  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. -->
+
+# intfloat-e5-small-v2-english-fp16
+
+This model is a fine-tuned version of [intfloat/e5-small-v2](https://huggingface.co/intfloat/e5-small-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3427
+- Accuracy: 0.8782
+- Precision: 0.8776
+- Recall: 0.8782
+- F1: 0.8775
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.3
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 1.1017        | 0.3922 | 50   | 1.0911          | 0.4838   | 0.6437    | 0.4838 | 0.3167 |
+| 1.0722        | 0.7843 | 100  | 1.0402          | 0.4828   | 0.7503    | 0.4828 | 0.3144 |
+| 0.9617        | 1.1725 | 150  | 0.8690          | 0.6640   | 0.7296    | 0.6640 | 0.5914 |
+| 0.7693        | 1.5647 | 200  | 0.6639          | 0.7382   | 0.7779    | 0.7382 | 0.6929 |
+| 0.6056        | 1.9569 | 250  | 0.5194          | 0.8492   | 0.8489    | 0.8492 | 0.8475 |
+| 0.4773        | 2.3451 | 300  | 0.4449          | 0.8635   | 0.8630    | 0.8635 | 0.8614 |
+| 0.4215        | 2.7373 | 350  | 0.4152          | 0.8635   | 0.8645    | 0.8635 | 0.8613 |
+| 0.3754        | 3.1255 | 400  | 0.3933          | 0.8679   | 0.8699    | 0.8679 | 0.8654 |
+| 0.3225        | 3.5176 | 450  | 0.3570          | 0.8762   | 0.8755    | 0.8762 | 0.8754 |
+| 0.3221        | 3.9098 | 500  | 0.3455          | 0.8748   | 0.8742    | 0.8748 | 0.8736 |
+| 0.272         | 4.2980 | 550  | 0.3507          | 0.8821   | 0.8816    | 0.8821 | 0.8811 |
+| 0.2695        | 4.6902 | 600  | 0.3427          | 0.8782   | 0.8776    | 0.8782 | 0.8775 |
+| 0.2478        | 5.0784 | 650  | 0.3466          | 0.8792   | 0.8787    | 0.8792 | 0.8781 |
+| 0.2347        | 5.4706 | 700  | 0.3530          | 0.8821   | 0.8824    | 0.8821 | 0.8806 |
+| 0.222         | 5.8627 | 750  | 0.3399          | 0.8851   | 0.8851    | 0.8851 | 0.8837 |
+| 0.2053        | 6.2510 | 800  | 0.3487          | 0.8797   | 0.8794    | 0.8797 | 0.8789 |
+| 0.1989        | 6.6431 | 850  | 0.3481          | 0.8806   | 0.8802    | 0.8806 | 0.8796 |
+| 0.1914        | 7.0314 | 900  | 0.3536          | 0.8806   | 0.8805    | 0.8806 | 0.8796 |
+
+
+### Framework versions
+
+- Transformers 4.51.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "negative",
+    "1": "positive",
+    "2": "neutral"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "negative": 0,
+    "neutral": 2,
+    "positive": 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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1",
+  "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:bf54465d14f885750c9d78029d6d7b6e1064cb0ba72db5ea93b923be4330137a
+size 133467916

runs/Apr16_15-57-18_9424de0d1b18/events.out.tfevents.1744819047.9424de0d1b18.1160.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd5ef117df8f77535e7fcdf4479dd6708a13ab7aa716cd118b31c698c5c631f2
+size 17795

runs/Apr16_15-57-18_9424de0d1b18/events.out.tfevents.1744819495.9424de0d1b18.1160.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaf503d298324e220584171e2b2528b703b7d92916a9d4f7668ae26ee21a2a9
+size 560

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bb637d2ca68ca5e935f82225646b9da5f99b9075f51392efda2c5c7af7e4eeb
+size 5368