Training in progress, step 500

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: google-bert/bert-large-uncased-whole-word-masking-finetuned-squad
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-large-uncased-whole-word-masking-finetuned-squad-I-5000
+  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-large-uncased-whole-word-masking-finetuned-squad-I-5000
+
+This model is a fine-tuned version of [google-bert/bert-large-uncased-whole-word-masking-finetuned-squad](https://huggingface.co/google-bert/bert-large-uncased-whole-word-masking-finetuned-squad) on the None dataset.
+
+## 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: 3e-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
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "google-bert/bert-large-uncased-whole-word-masking-finetuned-squad",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aea65a0ba64b4eb6d77be39ba25146712b85d496caa5316a284e2d70f910dec
+size 1336424168

runs/Jun20_09-44-09_ca0b135eea7a/events.out.tfevents.1718876792.ca0b135eea7a.1340.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4651a9257ff119a553fb131e191566cd8fe4c36aaba01b63c577e1eb719dd260
+size 10123

runs/Jun20_10-09-04_ca0b135eea7a/events.out.tfevents.1718878188.ca0b135eea7a.18329.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed05f4b69b987f64e3412512a8db46ef8981c8e55df3ce8b051cbbd13b2bffe7
+size 5565

runs/Jun20_10-09-04_ca0b135eea7a/events.out.tfevents.1718879346.ca0b135eea7a.18329.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39b628fad9828b883ae1955e7953818bfe0c4436e2b23bb7bee0ebcbdbd702b
+size 5028

runs/Jun20_10-09-04_ca0b135eea7a/events.out.tfevents.1718879375.ca0b135eea7a.18329.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:296bf583201a4918b471c0d9e2b12c9a31ca634e13528239352c7794682e5035
+size 5239

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 sha256:177e6ca86c887dd0cf60c580c804a7a3ab4b3620360e785f3839ab7584022642
+size 5240