End of training

README.md

@@ -0,0 +1,77 @@
+---
+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: 080524_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. -->
+
+# 080524_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: 0.8412
+- Accuracy: 0.6261
+- Precision: 0.6471
+- Recall: 0.6261
+- F1: 0.6122
+- Ratio: 0.6891
+
+## 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: 10
+- eval_batch_size: 2
+- seed: 47
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 20
+- 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  |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 3.4777        | 0.1626 | 10   | 1.9887          | 0.5336   | 0.5436    | 0.5336 | 0.5052 | 0.7395 |
+| 1.6106        | 0.3252 | 20   | 1.2180          | 0.5504   | 0.5532    | 0.5504 | 0.5446 | 0.3866 |
+| 0.9895        | 0.4878 | 30   | 0.9875          | 0.5672   | 0.5736    | 0.5672 | 0.5577 | 0.6471 |
+| 0.9363        | 0.6504 | 40   | 0.8740          | 0.6176   | 0.6183    | 0.6176 | 0.6171 | 0.4622 |
+| 0.8844        | 0.8130 | 50   | 0.8591          | 0.6134   | 0.6378    | 0.6134 | 0.5956 | 0.7101 |
+| 0.8565        | 0.9756 | 60   | 0.8416          | 0.6218   | 0.6433    | 0.6218 | 0.6072 | 0.6933 |
+
+
+### Framework versions
+
+- Transformers 4.40.1
+- Pytorch 2.2.1+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": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

logs/events.out.tfevents.1715153401.4eb47db37635.5225.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fa8e6814f1a67811cbbe4548439104b82ccde79bb922d6e21610efa21e9439
+size 9865

logs/events.out.tfevents.1715153501.4eb47db37635.5225.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892293f693f287aea1f6be9dfc8da0ff08255fbbccb78a9a4b7642333165c823
+size 599

logs/events.out.tfevents.1715153602.4eb47db37635.5225.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e46abdc1b1fe20ffc29d90a28e1716822ac6f19785cbeddd44dd2589e7b46dd
+size 9837

logs/events.out.tfevents.1715153702.4eb47db37635.5225.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ce1419c774c786be3e96d177c17b9cd33503518276545c6c0842631b0788d6
+size 10376

logs/events.out.tfevents.1715154355.4eb47db37635.5225.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f9a61ddec6b7f5d8e96e3b27e9dd2baafeb384d6b45a1fd8a7820be329197d
+size 9837

logs/events.out.tfevents.1715154455.4eb47db37635.5225.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c5a1ee70a41ff4db6f42ac22d4d4eae0246777f1402af369ad8994d9aaa7a0
+size 599

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58d33f501fbaa18689a3471eb0864a18dde1e29c0cdbd5d7530270dfa9cccc47
+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:f406aa9dd26d931a9caca9ea78ea3263e7c5f1bfef9114c96964f6030f420cad
+size 4984