fine_tuned_rte_croslo

README.md

@@ -0,0 +1,69 @@
+---
+license: cc-by-4.0
+base_model: EMBEDDIA/crosloengual-bert
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- f1
+model-index:
+- name: fine_tuned_rte_croslo
+  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. -->
+
+# fine_tuned_rte_croslo
+
+This model is a fine-tuned version of [EMBEDDIA/crosloengual-bert](https://huggingface.co/EMBEDDIA/crosloengual-bert) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7816
+- Accuracy: 0.6207
+- F1: 0.5951
+
+## 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
+- training_steps: 400
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-------:|:----:|:---------------:|:--------:|:------:|
+| 0.6484        | 1.7241  | 50   | 0.6137          | 0.6897   | 0.6523 |
+| 0.3676        | 3.4483  | 100  | 0.6570          | 0.6897   | 0.6290 |
+| 0.108         | 5.1724  | 150  | 1.1262          | 0.6207   | 0.5466 |
+| 0.0117        | 6.8966  | 200  | 1.5598          | 0.5862   | 0.5666 |
+| 0.0019        | 8.6207  | 250  | 1.6851          | 0.5862   | 0.5483 |
+| 0.0012        | 10.3448 | 300  | 1.7394          | 0.6207   | 0.5951 |
+| 0.001         | 12.0690 | 350  | 1.7780          | 0.6207   | 0.5951 |
+| 0.0024        | 13.7931 | 400  | 1.7816          | 0.6207   | 0.5951 |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.1.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "EMBEDDIA/crosloengual-bert",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "not_entailment",
+    "1": "entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 1,
+    "not_entailment": 0
+  },
+  "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": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 49601
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e3400c64bf6772e43161a54c9605a4e765b2e8bc3d0db0dfbf3197ba41f0db1
+size 496569344

runs/May22_18-05-13_DESKTOP-22QTFDR/events.out.tfevents.1716393914.DESKTOP-22QTFDR.27760.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9ff65016d6f5d5003a4d3c00d350f114b817842ae3f5823f70d41f20d98b01b
+size 4779

runs/May22_18-06-10_DESKTOP-22QTFDR/events.out.tfevents.1716393971.DESKTOP-22QTFDR.27760.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6916bf702e9de3ba049cf21f71e3d2223480d837a61c13f50e7f71cc262c9fad
+size 4779

runs/May22_18-07-39_DESKTOP-22QTFDR/events.out.tfevents.1716394060.DESKTOP-22QTFDR.27760.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9477ba08baa45852884f9849d4d6a96da604c23d9dc4abd7b1b4ca3981edd2f
+size 4779

runs/May22_18-08-41_DESKTOP-22QTFDR/events.out.tfevents.1716394122.DESKTOP-22QTFDR.27760.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d09a5402289695f2cc3d646f2ee08c9f0944ac29c1447efb758c316930362a
+size 4795

runs/May22_18-10-18_DESKTOP-22QTFDR/events.out.tfevents.1716394219.DESKTOP-22QTFDR.27760.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bc251c96060c864dd090b9b21eae5b38b2499f301f8d31778cb01867987b87
+size 4795

runs/May22_18-10-42_DESKTOP-22QTFDR/events.out.tfevents.1716394242.DESKTOP-22QTFDR.27760.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e15a9c0666521ff00f67a9368d74ddc5b0372a12b5fa12f446e3308be3164a7
+size 4795

runs/May22_18-11-08_DESKTOP-22QTFDR/events.out.tfevents.1716394269.DESKTOP-22QTFDR.27760.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326213b36765d011ea3fd3d7fb3c629b586d6de0f42881359fd74aa3cad43d1c
+size 4795

runs/May22_18-13-16_DESKTOP-22QTFDR/events.out.tfevents.1716394397.DESKTOP-22QTFDR.27760.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de592a1f4d5132abd9dea4c55db74ac90f7eded26ce10a3169fd97d4648caba8
+size 4795

runs/May22_18-13-52_DESKTOP-22QTFDR/events.out.tfevents.1716394432.DESKTOP-22QTFDR.27760.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3883ca95e9b8e2f53d62258545ffe654b26cc6bffa692b821ad2163b69d8f31d
+size 4795

runs/May22_18-16-21_DESKTOP-22QTFDR/events.out.tfevents.1716394581.DESKTOP-22QTFDR.27760.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c885c14e73ddb5ef951174c30994dbf06389d06e199c840382126b67b5408d7c
+size 9767

runs/May22_18-16-21_DESKTOP-22QTFDR/events.out.tfevents.1716394661.DESKTOP-22QTFDR.27760.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfacf136cf10695176dd915b61eb56fc754e40bae4a8c1599cdf1f36a5f11c2f
+size 457

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
+    },
+    "102": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "105": {
+      "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": false,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "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 sha256:29661fe73f9b3fa2b8d4cf4b4ca994cc68f834a46f68938f84184ddab2f8b9b7
+size 5048