Initial import

README.md

@@ -0,0 +1,94 @@
+---
+license: apache-2.0
+language: en
+tags:
+- generated_from_trainer
+datasets:
+- squad_v2
+model-index:
+- name: distilroberta-base-squad_v2
+  results: []
+---
+
+# distilroberta-base-squad_v2
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) 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
+>>> model = AutoModelForQuestionAnswering.from_pretrained("squirro/distilroberta-base-squad_v2")
+>>> tokenizer = AutoTokenizer.from_pretrained("squirro/distilroberta-base-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: 64
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: tpu
+- num_devices: 8
+- total_train_batch_size: 512
+- 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
+
+| Metric                   |        Value |
+|:-------------------------|-------------:|
+| epoch                    |      3       |
+| eval_HasAns_exact        |     67.5776  |
+| eval_HasAns_f1           |     74.3594  |
+| eval_HasAns_total        |   5928       |
+| eval_NoAns_exact         |     62.91    |
+| eval_NoAns_f1            |     62.91    |
+| eval_NoAns_total         |   5945       |
+| eval_best_exact          |     65.2489  |
+| eval_best_exact_thresh   |      0       |
+| eval_best_f1             |     68.6349  |
+| eval_best_f1_thresh      |      0       |
+| eval_exact               |     65.2405  |
+| eval_f1                  |     68.6265  |
+| eval_samples             |  12165       |
+| eval_total               |  11873       |
+| train_loss               |      1.40336 |
+| train_runtime            |   1365.28    |
+| train_samples            | 131823       |
+| train_samples_per_second |    289.662   |
+| train_steps_per_second   |      0.567   |
+
+### Framework versions
+
+- Transformers 4.17.0.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": 67.57759784075573,
+    "eval_HasAns_f1": 74.35942116486743,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 62.91000841042893,
+    "eval_NoAns_f1": 62.91000841042893,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 65.24888402257223,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 68.63494050916684,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 65.24046155141919,
+    "eval_f1": 68.6265180380136,
+    "eval_samples": 12165,
+    "eval_total": 11873,
+    "train_loss": 1.403361870028868,
+    "train_runtime": 1365.2765,
+    "train_samples": 131823,
+    "train_samples_per_second": 289.662,
+    "train_steps_per_second": 0.567
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./distilroberta-base-squad_v2/",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "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": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_HasAns_exact": 67.57759784075573,
+    "eval_HasAns_f1": 74.35942116486743,
+    "eval_HasAns_total": 5928,
+    "eval_NoAns_exact": 62.91000841042893,
+    "eval_NoAns_f1": 62.91000841042893,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 65.24888402257223,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 68.63494050916684,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 65.24046155141919,
+    "eval_f1": 68.6265180380136,
+    "eval_samples": 12165,
+    "eval_total": 11873
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f323a5dec09e89692e1734d2c48e27f764681e0f04fff74d396768271fd4ad11
+size 326157245

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e09041fdc00c057cf9d19459de8885f534aeaf78970e01a886933f43b27f256b
+size 326154289

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "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 sha256:6295f48bc710694c362ce7572dfd8e66f35913d7f75cd8f4a3ae04e996173c7d
+size 326264448

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.403361870028868,
+    "train_runtime": 1365.2765,
+    "train_samples": 131823,
+    "train_samples_per_second": 289.662,
+    "train_steps_per_second": 0.567
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 774,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.7700258397932818e-05,
+      "loss": 1.5796,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 774,
+      "total_flos": 4854023972388864.0,
+      "train_loss": 1.403361870028868,
+      "train_runtime": 1365.2765,
+      "train_samples_per_second": 289.662,
+      "train_steps_per_second": 0.567
+    }
+  ],
+  "max_steps": 774,
+  "num_train_epochs": 3,
+  "total_flos": 4854023972388864.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04013c80b52dd2596cc4123eb08f6353ab42307060d89a6aa05bebf401a5617b
+size 3055