Training in progress, epoch 1

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+base_model: MiMe-MeMo/MeMo-BERT-03
+tags:
+- generated_from_trainer
+model-index:
+- name: memobert3_ED1
+  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. -->
+
+# memobert3_ED1
+
+This model is a fine-tuned version of [MiMe-MeMo/MeMo-BERT-03](https://huggingface.co/MiMe-MeMo/MeMo-BERT-03) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6065
+- F1-score: 0.9098
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1-score |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 69   | 0.3808          | 0.8439   |
+| No log        | 2.0   | 138  | 0.4234          | 0.8432   |
+| No log        | 3.0   | 207  | 0.4577          | 0.9013   |
+| No log        | 4.0   | 276  | 0.6278          | 0.8851   |
+| No log        | 5.0   | 345  | 0.6449          | 0.8517   |
+| No log        | 6.0   | 414  | 0.7495          | 0.8678   |
+| No log        | 7.0   | 483  | 0.6065          | 0.9098   |
+| 0.1663        | 8.0   | 552  | 0.6217          | 0.9098   |
+| 0.1663        | 9.0   | 621  | 0.6420          | 0.9098   |
+| 0.1663        | 10.0  | 690  | 0.6514          | 0.9098   |
+| 0.1663        | 11.0  | 759  | 0.6627          | 0.9098   |
+| 0.1663        | 12.0  | 828  | 0.6726          | 0.9098   |
+| 0.1663        | 13.0  | 897  | 0.6828          | 0.9016   |
+| 0.1663        | 14.0  | 966  | 0.6904          | 0.9016   |
+| 0.0001        | 15.0  | 1035 | 0.6942          | 0.9016   |
+| 0.0001        | 16.0  | 1104 | 0.6976          | 0.9016   |
+| 0.0001        | 17.0  | 1173 | 0.7007          | 0.9016   |
+| 0.0001        | 18.0  | 1242 | 0.7027          | 0.9016   |
+| 0.0001        | 19.0  | 1311 | 0.7038          | 0.9016   |
+| 0.0001        | 20.0  | 1380 | 0.7037          | 0.9016   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "MiMe-MeMo/MeMo-BERT-03",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852b90cbbc9a0ebeaad12660349ce7b824b5845f1ec99de9b8f4e4c1750f3fa5
+size 497814104

runs/Sep10_11-50-18_1ee6a001a4ad/events.out.tfevents.1725969033.1ee6a001a4ad.946.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d576399e843c7902fcf35ec853c4e86d6f8e81be2916f42fdce2a7b9a3a6df64
+size 12374

runs/Sep10_11-50-18_1ee6a001a4ad/events.out.tfevents.1725970055.1ee6a001a4ad.946.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7924ba361f6847104c321c3e1ffc00cf319941567474d27860a2aa1c332dfca9
+size 411

runs/Sep11_13-34-16_93370bd2ff25/events.out.tfevents.1726061696.93370bd2ff25.1056.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d6d5cded3afde3b5f981e597c8ef180517ebcce82d0e48ea44bedbeb1ed9c9
+size 5461

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5226668718de0dc99d8087af7d07618fb79b6edfe028ad89c7a32576178006b6
+size 1090291

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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
+    },
+    "50004": {
+      "content": "<mask>",
+      "lstrip": false,
+      "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>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "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:b9cc201967fc210d51e4781fd70396863256c789c1fcef502b5897a6ec385a7b
+size 5304