End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,82 @@
+---
+license: mit
+base_model: xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: HODravidianLangTech
+  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. -->
+
+# HODravidianLangTech
+
+This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5859
+- F1: 0.6908
+
+## 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: 1e-06
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 1234
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| No log        | 1.0   | 100  | 0.6926          | 0.3377 |
+| No log        | 2.0   | 200  | 0.6916          | 0.5490 |
+| No log        | 3.0   | 300  | 0.6856          | 0.6050 |
+| No log        | 4.0   | 400  | 0.6701          | 0.6287 |
+| 0.6833        | 5.0   | 500  | 0.6601          | 0.6396 |
+| 0.6833        | 6.0   | 600  | 0.6511          | 0.6466 |
+| 0.6833        | 7.0   | 700  | 0.6447          | 0.6458 |
+| 0.6833        | 8.0   | 800  | 0.6250          | 0.6560 |
+| 0.6833        | 9.0   | 900  | 0.6113          | 0.6516 |
+| 0.624         | 10.0  | 1000 | 0.6051          | 0.6658 |
+| 0.624         | 11.0  | 1100 | 0.6075          | 0.6567 |
+| 0.624         | 12.0  | 1200 | 0.6038          | 0.6671 |
+| 0.624         | 13.0  | 1300 | 0.5997          | 0.6716 |
+| 0.624         | 14.0  | 1400 | 0.5949          | 0.6805 |
+| 0.5739        | 15.0  | 1500 | 0.5958          | 0.6885 |
+| 0.5739        | 16.0  | 1600 | 0.5924          | 0.6905 |
+| 0.5739        | 17.0  | 1700 | 0.5957          | 0.6875 |
+| 0.5739        | 18.0  | 1800 | 0.5839          | 0.6976 |
+| 0.5739        | 19.0  | 1900 | 0.5865          | 0.6908 |
+| 0.5598        | 20.0  | 2000 | 0.5859          | 0.6908 |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "xlm-roberta-base",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "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": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96a6e3ed85575abf7aa3cb002d53809b3e05d4cb964c0e167564a0315771f151
+size 1112205008

runs/Nov16_18-08-24_db92c7a45d3a/events.out.tfevents.1700158122.db92c7a45d3a.762.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43b198d069b726629ab4fc9c4ea85257feaeafceba1174277bc34056089f61dc
+size 6858

runs/Nov16_18-22-33_db92c7a45d3a/events.out.tfevents.1700158968.db92c7a45d3a.762.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecfec5e77a918667e777b6658da5e66306bc5b38ab43ef16dcb76372d356eb38
+size 6857

runs/Nov16_18-36-04_db92c7a45d3a/events.out.tfevents.1700159793.db92c7a45d3a.762.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1fde1d883b928afbbe7cb8d78e85c8fd2ae26ecc552c3eb698a2410ba71a55
+size 5010

runs/Nov16_18-42-43_db92c7a45d3a/events.out.tfevents.1700160189.db92c7a45d3a.762.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0985760f59f6bf27d9becdf7b6a77d73b4f361be0a2de488d1b45d5821a5b9b4
+size 6659

runs/Nov16_19-03-14_db92c7a45d3a/events.out.tfevents.1700161408.db92c7a45d3a.762.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84044229562afb0f220ccc89e711ae0de45656e9db6b7a9746b63093d4ff2e48
+size 11579

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
+size 17083009

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf79e50a658fe009ea197dde0ddd182ab683c3648827c229488cacb7ae39216c
+size 4600