End of training

README.md

@@ -0,0 +1,89 @@
+---
+license: apache-2.0
+base_model: projecte-aina/roberta-base-ca-v2-cased-te
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+- precision
+- recall
+- f1
+model-index:
+- name: SYN_300524_epoch_1
+  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. -->
+
+# SYN_300524_epoch_1
+
+This model is a fine-tuned version of [projecte-aina/roberta-base-ca-v2-cased-te](https://huggingface.co/projecte-aina/roberta-base-ca-v2-cased-te) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3748
+- Accuracy: 0.961
+- Precision: 0.9615
+- Recall: 0.961
+- F1: 0.9610
+- Ratio: 0.483
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 47
+- 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: 0.06
+- lr_scheduler_warmup_steps: 4
+- num_epochs: 1
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-----:|
+| 2.9367        | 0.0533 | 10   | 1.4668          | 0.65     | 0.7117    | 0.65   | 0.6225 | 0.77  |
+| 1.1009        | 0.1067 | 20   | 0.6674          | 0.856    | 0.8560    | 0.856  | 0.8560 | 0.502 |
+| 0.6993        | 0.16   | 30   | 0.5583          | 0.908    | 0.9095    | 0.9080 | 0.9079 | 0.53  |
+| 0.6377        | 0.2133 | 40   | 0.4923          | 0.934    | 0.9343    | 0.9340 | 0.9340 | 0.486 |
+| 0.5192        | 0.2667 | 50   | 0.4930          | 0.926    | 0.9282    | 0.9260 | 0.9259 | 0.464 |
+| 0.5189        | 0.32   | 60   | 0.4687          | 0.937    | 0.9383    | 0.937  | 0.9370 | 0.527 |
+| 0.5083        | 0.3733 | 70   | 0.4321          | 0.944    | 0.9445    | 0.944  | 0.9440 | 0.484 |
+| 0.4645        | 0.4267 | 80   | 0.4026          | 0.949    | 0.9490    | 0.949  | 0.9490 | 0.495 |
+| 0.4268        | 0.48   | 90   | 0.3990          | 0.949    | 0.9498    | 0.9490 | 0.9490 | 0.479 |
+| 0.4327        | 0.5333 | 100  | 0.3949          | 0.952    | 0.9524    | 0.952  | 0.9520 | 0.486 |
+| 0.4283        | 0.5867 | 110  | 0.3894          | 0.954    | 0.9540    | 0.954  | 0.9540 | 0.496 |
+| 0.4263        | 0.64   | 120  | 0.3829          | 0.957    | 0.9572    | 0.957  | 0.9570 | 0.489 |
+| 0.4205        | 0.6933 | 130  | 0.3800          | 0.962    | 0.9620    | 0.962  | 0.9620 | 0.496 |
+| 0.4291        | 0.7467 | 140  | 0.3760          | 0.962    | 0.9620    | 0.962  | 0.9620 | 0.502 |
+| 0.4124        | 0.8    | 150  | 0.3723          | 0.964    | 0.9641    | 0.964  | 0.9640 | 0.494 |
+| 0.4142        | 0.8533 | 160  | 0.3720          | 0.964    | 0.9641    | 0.964  | 0.9640 | 0.492 |
+| 0.4209        | 0.9067 | 170  | 0.3767          | 0.96     | 0.9605    | 0.96   | 0.9600 | 0.484 |
+| 0.3908        | 0.96   | 180  | 0.3748          | 0.96     | 0.9605    | 0.96   | 0.9600 | 0.484 |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "projecte-aina/roberta-base-ca-v2-cased-te",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "mnli",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "ENTAILMENT",
+    "1": "NEUTRAL",
+    "2": "CONTRADICTION"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "CONTRADICTION": 2,
+    "ENTAILMENT": 0,
+    "NEUTRAL": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

logs/events.out.tfevents.1717145900.f17a8cbca9b8.406.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21126c59cc963aa362b60e302e0545c840a69871809dcbb4854dc23a80c4dd86
+size 18694

logs/events.out.tfevents.1717147041.f17a8cbca9b8.406.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116ceb9c1ba512bb83961ae9120250dfa19918581533e222e1651c33f43fcc5e
+size 609

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bc324e4f5ca224162446d2eb52d455e5a8bca53b126f56ad7b84a52165da06
+size 498606684

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "max_len": 512,
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf7ae9f8857429ae93be07e9caf8951adc73fa865f17979220b29034126dfd6a
+size 5112