Model files

Signed-off-by: Diwank Singh Tomer <diwank.singh@gmail.com>

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,58 @@
+---
+license: mit
+---
+
+# diwank/silicone-deberta-pair
+
+`deberta-large`-based dialog acts classifier. Trained on [silicone-merged](https://huggingface.co/datasets/diwank/silicone-merged): a simplified dialog act datasets from the silicone collection. 
+
+Takes two sentences as inputs (one previous and one current utterance of a dialog). The previous sentence can be an empty string if this is the first utterance of a speaker in a dialog. **Outputs one of 11 labels**:
+
+```python
+[
+    (0, 'acknowledge')
+    (1, 'answer')
+    (2, 'backchannel')
+    (3, 'reply_yes')
+    (4, 'exclaim')
+    (5, 'say')
+    (6, 'reply_no')
+    (7, 'hold')
+    (8, 'ask')
+    (9, 'intent')
+    (10, 'ask_yes_no')
+]
+```
+
+## Example:
+
+```python
+from simpletransformers.classification import (
+    ClassificationModel, ClassificationArgs
+)
+
+model = ClassificationModel("deberta", "diwank/dyda-deberta-pair")
+convert_to_label = lambda n: [
+    ['acknowledge',
+     'answer',
+     'backchannel',
+     'reply_yes',
+     'exclaim',
+     'say',
+     'reply_no',
+     'hold',
+     'ask',
+     'intent',
+     'ask_yes_no'
+    ][i] for i in n
+]
+
+predictions, raw_outputs = model.predict([["Say what is the meaning of life?", "I dont know"]])
+convert_to_label(predictions)  # answer
+
+```
+
+
+## Report from W&B
+
+https://wandb.ai/diwank/da-silicone-combined/reports/silicone-deberta-pair--VmlldzoxNTczNjE5?accessToken=yj1jz4c365z0y5b3olgzye7qgsl7qv9lxvqhmfhtb6300hql6veqa5xiq1skn8ys

README.md

@@ -1,3 +1,58 @@
 ---
 license: mit
 ---
+
+# diwank/silicone-deberta-pair
+
+`deberta-large`-based dialog acts classifier. Trained on [silicone-merged](https://huggingface.co/datasets/diwank/silicone-merged): a simplified dialog act datasets from the silicone collection. 
+
+Takes two sentences as inputs (one previous and one current utterance of a dialog). The previous sentence can be an empty string if this is the first utterance of a speaker in a dialog. **Outputs one of 11 labels**:
+
+```python
+[
+    (0, 'acknowledge')
+    (1, 'answer')
+    (2, 'backchannel')
+    (3, 'reply_yes')
+    (4, 'exclaim')
+    (5, 'say')
+    (6, 'reply_no')
+    (7, 'hold')
+    (8, 'ask')
+    (9, 'intent')
+    (10, 'ask_yes_no')
+]
+```
+
+## Example:
+
+```python
+from simpletransformers.classification import (
+    ClassificationModel, ClassificationArgs
+)
+
+model = ClassificationModel("deberta", "diwank/dyda-deberta-pair")
+convert_to_label = lambda n: [
+    ['acknowledge',
+     'answer',
+     'backchannel',
+     'reply_yes',
+     'exclaim',
+     'say',
+     'reply_no',
+     'hold',
+     'ask',
+     'intent',
+     'ask_yes_no'
+    ][i] for i in n
+]
+
+predictions, raw_outputs = model.predict([["Say what is the meaning of life?", "I dont know"]])
+convert_to_label(predictions)  # answer
+
+```
+
+
+## Report from W&B
+
+https://wandb.ai/diwank/da-silicone-combined/reports/silicone-deberta-pair--VmlldzoxNTczNjE5?accessToken=yj1jz4c365z0y5b3olgzye7qgsl7qv9lxvqhmfhtb6300hql6veqa5xiq1skn8ys

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "microsoft/deberta-large",
+  "architectures": [
+    "DebertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "c2p",
+    "p2c"
+  ],
+  "position_biased_input": false,
+  "relative_attention": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "type_vocab_size": 0,
+  "vocab_size": 50265
+}

eval_results.txt

@@ -0,0 +1,2 @@
+eval_loss = 0.39992852896930425
+mcc = 0.8192827881469071

model_args.json

@@ -0,0 +1 @@
+{"adafactor_beta1": null, "adafactor_clip_threshold": 1.0, "adafactor_decay_rate": -0.8, "adafactor_eps": [1e-30, 0.001], "adafactor_relative_step": true, "adafactor_scale_parameter": true, "adafactor_warmup_init": true, "adam_epsilon": 1e-08, "best_model_dir": "outputs/best_model", "cache_dir": "cache_dir/", "config": {}, "cosine_schedule_num_cycles": 0.5, "custom_layer_parameters": [], "custom_parameter_groups": [], "dataloader_num_workers": 0, "do_lower_case": false, "dynamic_quantize": false, "early_stopping_consider_epochs": false, "early_stopping_delta": 0, "early_stopping_metric": "eval_loss", "early_stopping_metric_minimize": true, "early_stopping_patience": 3, "encoding": null, "eval_batch_size": 80, "evaluate_during_training": true, "evaluate_during_training_silent": true, "evaluate_during_training_steps": 1000, "evaluate_during_training_verbose": true, "evaluate_each_epoch": true, "fp16": true, "gradient_accumulation_steps": 1, "learning_rate": 3e-05, "local_rank": -1, "logging_steps": 50, "loss_type": null, "loss_args": {}, "manual_seed": null, "max_grad_norm": 1.0, "max_seq_length": 128, "model_name": "microsoft/deberta-large", "model_type": "deberta", "multiprocessing_chunksize": -1, "n_gpu": 4, "no_cache": false, "no_save": false, "not_saved_args": [], "num_train_epochs": 8, "optimizer": "AdamW", "output_dir": "outputs/", "overwrite_output_dir": true, "polynomial_decay_schedule_lr_end": 1e-07, "polynomial_decay_schedule_power": 1.0, "process_count": 6, "quantized_model": false, "reprocess_input_data": true, "save_best_model": true, "save_eval_checkpoints": true, "save_model_every_epoch": true, "save_optimizer_and_scheduler": true, "save_steps": 2000, "scheduler": "polynomial_decay_schedule_with_warmup", "silent": false, "skip_special_tokens": true, "tensorboard_dir": null, "thread_count": null, "tokenizer_name": "microsoft/deberta-large", "tokenizer_type": null, "train_batch_size": 80, "train_custom_parameters_only": false, "use_cached_eval_features": false, "use_early_stopping": true, "use_hf_datasets": false, "use_multiprocessing": false, "use_multiprocessing_for_evaluation": true, "wandb_kwargs": {}, "wandb_project": "da-silicone-combined", "warmup_ratio": 0.06, "warmup_steps": 1890, "weight_decay": 0.0, "model_class": "ClassificationModel", "labels_list": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10], "labels_map": {}, "lazy_delimiter": "\t", "lazy_labels_column": 1, "lazy_loading": false, "lazy_loading_start_line": 1, "lazy_text_a_column": null, "lazy_text_b_column": null, "lazy_text_column": 0, "onnx": false, "regression": false, "sliding_window": false, "special_tokens_list": [], "stride": 0.8, "tie_value": 1}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd774e8ca54ca41d2965a1c0f091c7a37960eadaa6b6b78fd285345e5367e1d4
+size 3250019105

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4a006c9aeea8b200ff7ef9259a41620d77a3eabe537ca48cf5b382b40b7cea
+size 1625061487

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3316684e35605f8683498fce834658644b50c870295247e6e9515a6c9ec644ae
+size 623

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88ec143a0678a3bfcaec4a45468a8a90ffe716305f8d768af992b169576c1f93
+size 1249

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "sep_token": {"content": "[SEP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "[CLS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "do_lower_case": false, "vocab_type": "gpt2", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-large", "tokenizer_class": "DebertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39bb4b4659c47156a95fb9f7f6fec8fa4d29eb5389cb0cea6f379d804d7d116b
+size 3183