add large files

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: bert-base-multilingual-cased-42-QAData
+  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. -->
+
+# bert-base-multilingual-cased-42-QAData
+
+This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0873
+- Precision: 0.4420
+- Recall: 0.2887
+- F1: 0.3493
+- Accuracy: 0.9755
+
+## 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: 4e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1064        | 1.0   | 3118 | 0.0873          | 0.4420    | 0.2887 | 0.3493 | 0.9755   |
+
+
+### Framework versions
+
+- Transformers 4.24.0
+- Pytorch 1.12.1+cu113
+- Datasets 2.6.1
+- Tokenizers 0.13.1

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9755093109113304,
+    "eval_f1": 0.34928397084677487,
+    "eval_loss": 0.08728940039873123,
+    "eval_precision": 0.44204307346683086,
+    "eval_recall": 0.28870219099617667,
+    "eval_runtime": 1788.1641,
+    "eval_samples": 80069,
+    "eval_samples_per_second": 44.777,
+    "eval_steps_per_second": 2.799,
+    "train_loss": 0.10636317538786882,
+    "train_runtime": 5819.6703,
+    "train_samples": 49881,
+    "train_samples_per_second": 8.571,
+    "train_steps_per_second": 0.536
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "finetuning_task": "BIO",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B",
+    "1": "I",
+    "2": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B": 0,
+    "I": 1,
+    "O": 2
+  },
+  "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": "4.24.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.9755093109113304,
+    "eval_f1": 0.34928397084677487,
+    "eval_loss": 0.08728940039873123,
+    "eval_precision": 0.44204307346683086,
+    "eval_recall": 0.28870219099617667,
+    "eval_runtime": 1788.1641,
+    "eval_samples": 80069,
+    "eval_samples_per_second": 44.777,
+    "eval_steps_per_second": 2.799
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48d4e552623b648ef5ac6f4467448e273cdab8eeebbffe711bc49a93feb9119
+size 709131057

runs/Nov02_13-33-30_172f3140324b/1667396111.2042036/events.out.tfevents.1667396111.172f3140324b.1517.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f366c3b04985a2188defc596f570e15da4406fa3dbf7cdad4ebb5807cffe554
+size 5540

runs/Nov02_13-33-30_172f3140324b/events.out.tfevents.1667396111.172f3140324b.1517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f0c028a8438340de39d9b023e5902cc02dcaad45757c3db4c22728bf448f21
+size 5065

runs/Nov02_13-33-30_172f3140324b/events.out.tfevents.1667403722.172f3140324b.1517.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f40f43d9a17625062e3db3043c6be18f43355d812569454e7dc296a59f6c1d
+size 512

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 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "bert-base-multilingual-cased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.10636317538786882,
+    "train_runtime": 5819.6703,
+    "train_samples": 49881,
+    "train_samples_per_second": 8.571,
+    "train_steps_per_second": 0.536
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": 0.34928397084677487,
+  "best_model_checkpoint": "./bert-base-multilingual-cased-42-QAData/checkpoint-3118",
+  "epoch": 1.0,
+  "global_step": 3118,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.1064,
+      "step": 3118
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9755093109113304,
+      "eval_f1": 0.34928397084677487,
+      "eval_loss": 0.08728940039873123,
+      "eval_precision": 0.44204307346683086,
+      "eval_recall": 0.28870219099617667,
+      "eval_runtime": 1787.1962,
+      "eval_samples_per_second": 44.801,
+      "eval_steps_per_second": 2.8,
+      "step": 3118
+    },
+    {
+      "epoch": 1.0,
+      "step": 3118,
+      "total_flos": 1.1125436195108934e+16,
+      "train_loss": 0.10636317538786882,
+      "train_runtime": 5819.6703,
+      "train_samples_per_second": 8.571,
+      "train_steps_per_second": 0.536
+    }
+  ],
+  "max_steps": 3118,
+  "num_train_epochs": 1,
+  "total_flos": 1.1125436195108934e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a480e22687cf827fc780214f454e135204d7b5e069eeb009ebd11c3236acaa
+size 3439