mehdie/extended_mBERT

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-base-multilingual-uncased
+tags:
+- generated_from_trainer
+model-index:
+- name: MEHDIE_mBERT
+  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. -->
+
+# MEHDIE_mBERT
+
+This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0261
+
+## 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: 64
+- eval_batch_size: 64
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 512
+- total_eval_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 1.5096        | 1.0   | 51630  | 1.2459          |
+| 1.2498        | 2.0   | 103260 | 1.1339          |
+| 1.1693        | 3.0   | 154890 | 1.0784          |
+| 1.1233        | 4.0   | 206520 | 1.0425          |
+| 1.0951        | 5.0   | 258150 | 1.0263          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.3.0a0+ebedce2
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 105879
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b32e720c54fa2bf2ebc0d53a9b56bbb373ac67a10521cf4b0a6a7308506476
+size 669879044

runs/May09_11-15-57_nv-ai-03.srv.aau.dk/events.out.tfevents.1715249405.nv-ai-03.srv.aau.dk.940885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe5d7c5f611853f0452931efcbff95d53359f855de7751250fe4007aac95672
+size 4910

runs/May09_13-44-44_nv-ai-01.srv.aau.dk/events.out.tfevents.1715256880.nv-ai-01.srv.aau.dk.344958.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a30217ad90577848ff5b9060b0b54074d402aec7ebc7f079e634097611dc35
+size 4912

runs/May09_14-52-25_nv-ai-01.srv.aau.dk/events.out.tfevents.1715260772.nv-ai-01.srv.aau.dk.408990.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1be5c92d43c48307993bc11a2f460ef36ff41927166e1f290e6a4f7bc908f9
+size 7725

runs/May09_14-52-25_nv-ai-01.srv.aau.dk/events.out.tfevents.1715472151.nv-ai-01.srv.aau.dk.408990.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ad237648667f2066fb2754a04510d39d727c8c959c9574ac532f053e0f0a36
+size 316

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dc4c943fd4e4a3576e55af19a2a5437c202e67c5d73d567a8deb1192d6e6e9
+size 4920