End of training

README.md

@@ -0,0 +1,85 @@
+---
+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: stocks
+  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. -->
+
+# stocks
+
+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: 0.7709
+- Accuracy: 0.7875
+- Precision: 0.5276
+- Recall: 0.5256
+- F1: 0.5261
+- Ratio: 0.5083
+
+## 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: 4
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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: 2
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy | Precision | Recall | F1     | Ratio  |
+|:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:------:|
+| 3.4508        | 0.1429 | 10   | 1.7714          | 0.5625   | 0.3772    | 0.3755 | 0.3758 | 0.5167 |
+| 1.3131        | 0.2857 | 20   | 1.2703          | 0.6083   | 0.6073    | 0.6066 | 0.6066 | 0.4542 |
+| 1.0393        | 0.4286 | 30   | 0.9366          | 0.6625   | 0.6623    | 0.6603 | 0.6604 | 0.4417 |
+| 0.8129        | 0.5714 | 40   | 0.8434          | 0.7167   | 0.7179    | 0.7179 | 0.7167 | 0.5208 |
+| 0.816         | 0.7143 | 50   | 0.9037          | 0.7042   | 0.7447    | 0.7122 | 0.6961 | 0.6833 |
+| 0.7914        | 0.8571 | 60   | 0.7575          | 0.7583   | 0.7586    | 0.7569 | 0.7573 | 0.4542 |
+| 0.7873        | 1.0    | 70   | 0.7795          | 0.75     | 0.7709    | 0.7555 | 0.7475 | 0.6208 |
+| 0.6177        | 1.1429 | 80   | 0.7027          | 0.7917   | 0.7914    | 0.7910 | 0.7911 | 0.4708 |
+| 0.5429        | 1.2857 | 90   | 0.7100          | 0.7917   | 0.7915    | 0.792  | 0.7915 | 0.4958 |
+| 0.5314        | 1.4286 | 100  | 0.7451          | 0.7875   | 0.5276    | 0.5256 | 0.5261 | 0.5083 |
+| 0.5945        | 1.5714 | 110  | 0.7605          | 0.8      | 0.5358    | 0.5324 | 0.5338 | 0.4542 |
+| 0.661         | 1.7143 | 120  | 0.7722          | 0.7792   | 0.5215    | 0.5195 | 0.5204 | 0.4917 |
+| 0.6144        | 1.8571 | 130  | 0.7688          | 0.7875   | 0.5273    | 0.5253 | 0.5260 | 0.5    |
+| 0.5695        | 2.0    | 140  | 0.7709          | 0.7875   | 0.5276    | 0.5256 | 0.5261 | 0.5083 |
+
+
+### Framework versions
+
+- Transformers 4.40.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.19.0
+- 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": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50262
+}

logs/events.out.tfevents.1713874916.d627388554e9.3459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e802120ebfe73433f79edacd3442ca9d6153dc70ccc349fdb1e6bebb61724b
+size 10965

logs/events.out.tfevents.1713875042.d627388554e9.3459.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08c9943e42f5c4cf93965c4807f8f346cfb11516a2bbe2f549ee84efb6fb103
+size 599

logs/events.out.tfevents.1713875326.d627388554e9.6190.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8e8bc9f4d1dbb49f7ce4cd380963e72600beb27f805c6818047e394a5006b0
+size 16025

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47519335ddfa653ccdb20a6e76090c9761d6d94c2bff3ceff494afcb926d8221
+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 sha256:08547342a5f33c932dd6efd8689f61bc591054ad5c7db7185f247e425778b010
+size 4920