mehdie/fine_tuned_xlm-roberta

.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 +1,96 @@
+---
+license: mit
+base_model: FacebookAI/xlm-roberta-base
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- precision
+- recall
+model-index:
+- name: fine_tuned_roberta
+  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_roberta
+
+This model is a fine-tuned version of [FacebookAI/xlm-roberta-base](https://huggingface.co/FacebookAI/xlm-roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3472
+- F1: 0.4364
+- F5: 0.4521
+- Precision: 0.4
+- Recall: 0.48
+
+## 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: 5e-05
+- train_batch_size: 128
+- eval_batch_size: 128
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | F5     | Precision | Recall |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------:|
+| No log        | 1.0   | 17   | 0.2280          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 2.0   | 34   | 0.2387          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 3.0   | 51   | 0.2550          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 4.0   | 68   | 0.2357          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 5.0   | 85   | 0.2311          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 6.0   | 102  | 0.2319          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 7.0   | 119  | 0.2380          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 8.0   | 136  | 0.2160          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 9.0   | 153  | 0.2329          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 10.0  | 170  | 0.2216          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 11.0  | 187  | 0.2187          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 12.0  | 204  | 0.2311          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 13.0  | 221  | 0.2216          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 14.0  | 238  | 0.2320          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 15.0  | 255  | 0.2472          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 16.0  | 272  | 0.2486          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 17.0  | 289  | 0.2607          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 18.0  | 306  | 0.2394          | 0.0    | 0.0    | 0.0       | 0.0    |
+| No log        | 19.0  | 323  | 0.2566          | 0.1053 | 0.0835 | 0.3333    | 0.0625 |
+| No log        | 20.0  | 340  | 0.3055          | 0.3019 | 0.3557 | 0.2162    | 0.5    |
+| No log        | 21.0  | 357  | 0.2681          | 0.3902 | 0.4260 | 0.32      | 0.5    |
+| No log        | 22.0  | 374  | 0.2436          | 0.3529 | 0.3611 | 0.3333    | 0.375  |
+| No log        | 23.0  | 391  | 0.2390          | 0.2667 | 0.2600 | 0.2857    | 0.25   |
+| No log        | 24.0  | 408  | 0.2663          | 0.4444 | 0.4641 | 0.4       | 0.5    |
+| No log        | 25.0  | 425  | 0.2556          | 0.5143 | 0.5317 | 0.4737    | 0.5625 |
+| No log        | 26.0  | 442  | 0.2492          | 0.4571 | 0.4726 | 0.4211    | 0.5    |
+| No log        | 27.0  | 459  | 0.2555          | 0.5    | 0.5222 | 0.45      | 0.5625 |
+| No log        | 28.0  | 476  | 0.2607          | 0.4865 | 0.5130 | 0.4286    | 0.5625 |
+| No log        | 29.0  | 493  | 0.2393          | 0.4706 | 0.4814 | 0.4444    | 0.5    |
+| 0.2307        | 30.0  | 510  | 0.2577          | 0.5    | 0.5222 | 0.45      | 0.5625 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "FacebookAI/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,
+  "id2label": {
+    "0": "NO_MATCH",
+    "1": "MATCH"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "MATCH": 1,
+    "NO_MATCH": 0
+  },
+  "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": "4.38.2",
+  "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 sha256:7e9a738d0e46a878fb33668697e378b50eeb20c7783966d1c00f30f727f65fb2
+size 1112205008

runs/Apr16_08-50-08_nv-ai-03.srv.aau.dk/events.out.tfevents.1713250213.nv-ai-03.srv.aau.dk.3533336.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4116b8c88ee68bb8e377c965c9a7fd57b0c9bc9eb7bc8d5b53591c43d917970
+size 14543

runs/Apr16_08-50-08_nv-ai-03.srv.aau.dk/events.out.tfevents.1713250419.nv-ai-03.srv.aau.dk.3533336.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b54a5ab3670ceea642b9768969c981e1db4742b3b6f0da351a9153aaff801f
+size 506

runs/Apr16_09-34-44_nv-ai-03.srv.aau.dk/events.out.tfevents.1713252885.nv-ai-03.srv.aau.dk.3562090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec8a2821c7417e18688f2feaca58f752c1f2c18bf31ec4ba12628681bf62dc2
+size 19169

runs/Apr16_09-34-44_nv-ai-03.srv.aau.dk/events.out.tfevents.1713253110.nv-ai-03.srv.aau.dk.3562090.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7533cfca81de82c53f072b9a035362a7d2ebe9e136bb6fa43b282d4ba6255b26
+size 506

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 sha256:9a4661b2cb6b8a1007906509fe18cbfbc03062a086102bf7b80cfedb80f16c37
+size 17082854

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 sha256:75e5fc63ef2df204fc379464525fa245ae4133443263f18bda0c30999b41a919
+size 4920