Initital import.

README.md

@@ -0,0 +1,114 @@
+---
+license: apache-2.0
+language: en
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: albert-base-v2-squad_v2
+  results:
+  - task:
+      name: Question Answering
+      type: question-answering
+    dataset:
+      type: squad_v2  # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
+      name: The Stanford Question Answering Dataset
+      args: en
+    metrics:
+        - type: eval_exact
+          value: 78.8175
+        - type: eval_f1
+          value: 81.9984
+        - type: eval_HasAns_exact
+          value: 75.3374
+        - type: eval_HasAns_f1
+          value: 81.7083
+        - type: eval_NoAns_exact
+          value: 82.2876
+        - type: eval_NoAns_f1
+          value: 82.2876
+---
+
+# albert-base-v2-squad_v2
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad_v2 dataset.
+
+## Model description
+
+This model is fine-tuned on the extractive question answering task -- The Stanford Question Answering Dataset -- [SQuAD2.0](https://rajpurkar.github.io/SQuAD-explorer/).
+
+For convenience this model is prepared to be used with the frameworks `PyTorch`, `Tensorflow` and `ONNX`.
+
+## Intended uses & limitations
+
+This model can handle mismatched question-context pairs. Make sure to specify `handle_impossible_answer=True` when using `QuestionAnsweringPipeline`.
+
+__Example usage:__
+
+```python
+>>> from transformers import AutoModelForQuestionAnswering, AutoTokenizer, QuestionAnsweringPipeline
+>>> model = AutoModelForQuestionAnswering.from_pretrained("squirro/albert-base-v2-squad_v2")
+>>> tokenizer = AutoTokenizer.from_pretrained("squirro/albert-base-v2-squad_v2")
+>>> qa_model = QuestionAnsweringPipeline(model, tokenizer)
+>>> qa_model(
+>>>    question="What's your name?",
+>>>    context="My name is Clara and I live in Berkeley.",
+>>>    handle_impossible_answer=True  # important!
+>>> )
+{'score': 0.9027367830276489, 'start': 11, 'end': 16, 'answer': 'Clara'}
+```
+
+## Training and evaluation data
+
+Training and evaluation was done on [SQuAD2.0](https://huggingface.co/datasets/squad_v2).
+
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- num_devices: 8
+- total_train_batch_size: 256
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| key                      |         value |
+|:-------------------------|--------------:|
+| epoch                    |      3        |
+| eval_HasAns_exact        |     75.3374   |
+| eval_HasAns_f1           |     81.7083   |
+| eval_HasAns_total        |   5928        |
+| eval_NoAns_exact         |     82.2876   |
+| eval_NoAns_f1            |     82.2876   |
+| eval_NoAns_total         |   5945        |
+| eval_best_exact          |     78.8175   |
+| eval_best_exact_thresh   |      0        |
+| eval_best_f1             |     81.9984   |
+| eval_best_f1_thresh      |      0        |
+| eval_exact               |     78.8175   |
+| eval_f1                  |     81.9984   |
+| eval_samples             |  12171        |
+| eval_total               |  11873        |
+| train_loss               |      0.775293 |
+| train_runtime            |   1402        |
+| train_samples            | 131958        |
+| train_samples_per_second |    282.363    |
+| train_steps_per_second   |      1.104    |
+
+### Framework versions
+
+- Transformers 4.18.0.dev0
+- Pytorch 1.9.0+cu111
+- Datasets 1.18.3
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 3.0,
+    "eval_HasAns_exact": 75.33738191632928,
+    "eval_HasAns_f1": 81.70829499095663,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 82.28763666947015,
+    "eval_NoAns_f1": 82.28763666947015,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 78.8174850501137,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 81.99838058674217,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 78.8174850501137,
+    "eval_f1": 81.99838058674229,
+    "eval_samples": 12171,
+    "eval_total": 11873,
+    "train_loss": 0.7752933292733915,
+    "train_runtime": 1402.0046,
+    "train_samples": 131958,
+    "train_samples_per_second": 282.363,
+    "train_steps_per_second": 1.104
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "./models/albert-base-v2-squad_v2/",
+  "architectures": [
+    "AlbertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_HasAns_exact": 75.33738191632928,
+    "eval_HasAns_f1": 81.70829499095663,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 82.28763666947015,
+    "eval_NoAns_f1": 82.28763666947015,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 78.8174850501137,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 81.99838058674217,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 78.8174850501137,
+    "eval_f1": 81.99838058674229,
+    "eval_samples": 12171,
+    "eval_total": 11873
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658aad40a3a1a3d70258678bf96c14c11fc730f758e27a2f67220b33f644c627
+size 355875424

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9047ad8b56c90c6a13ed5f747e19434145f503fbea005768815b1af9fa24eef5
+size 44390231

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4968f90f9953e804e961bdb0c7ef02db917a12eca02f76366a41c553fd3b100c
+size 44417752

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.7752933292733915,
+    "train_runtime": 1402.0046,
+    "train_samples": 131958,
+    "train_samples_per_second": 282.363,
+    "train_steps_per_second": 1.104
+}

trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1548,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.3850129198966415e-05,
+      "loss": 1.1055,
+      "step": 500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7700258397932818e-05,
+      "loss": 0.7112,
+      "step": 1000
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 1.550387596899225e-06,
+      "loss": 0.529,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1548,
+      "total_flos": 820457454108672.0,
+      "train_loss": 0.7752933292733915,
+      "train_runtime": 1402.0046,
+      "train_samples_per_second": 282.363,
+      "train_steps_per_second": 1.104
+    }
+  ],
+  "max_steps": 1548,
+  "num_train_epochs": 3,
+  "total_flos": 820457454108672.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d67a6850c1f3efa60973ae320dd1a905b01971e66bbc29f8ac0409e32b66c9
+size 3055