Add model and its dependencies

.gitattributes

@@ -9,6 +9,7 @@
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text

HateXplain-dev_results.json

@@ -0,0 +1,12 @@
+{
+    "HateXplain-dev_accuracy": 0.4162330905306972,
+    "HateXplain-dev_accuracy_0": 0.8145025295109612,
+    "HateXplain-dev_accuracy_1": 0.18950064020486557,
+    "HateXplain-dev_accuracy_2": 0.3083941605839416,
+    "HateXplain-dev_loss": 0.766707181930542,
+    "HateXplain-dev_runtime": 2.1526,
+    "HateXplain-dev_samples": 1922,
+    "HateXplain-dev_samples_per_second": 892.867,
+    "HateXplain-dev_steps_per_second": 28.338,
+    "epoch": 3.0
+}

HateXplain-test_results.json

@@ -0,0 +1,12 @@
+{
+    "HateXplain-test_accuracy": 0.41372141372141374,
+    "HateXplain-test_accuracy_0": 0.8383838383838383,
+    "HateXplain-test_accuracy_1": 0.18030690537084398,
+    "HateXplain-test_accuracy_2": 0.2864963503649635,
+    "HateXplain-test_loss": 0.7393361926078796,
+    "HateXplain-test_runtime": 2.1365,
+    "HateXplain-test_samples": 1924,
+    "HateXplain-test_samples_per_second": 900.535,
+    "HateXplain-test_steps_per_second": 28.551,
+    "epoch": 3.0
+}

README.md

@@ -0,0 +1,81 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- ''
+metrics:
+- accuracy
+model-index:
+- name: SEED0042
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: HATEXPLAIN
+      type: ''
+      args: hatexplain
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.4162330905306972
+---
+
+<!-- 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. -->
+
+# SEED0042
+
+This model is a fine-tuned version of [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator) on the HATEXPLAIN dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7667
+- Accuracy: 0.4162
+- Accuracy 0: 0.8145
+- Accuracy 1: 0.1895
+- Accuracy 2: 0.3084
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- distributed_type: not_parallel
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 150
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Accuracy 0 | Accuracy 1 | Accuracy 2 |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:----------:|:----------:|:----------:|
+| No log        | 1.0   | 481  | 0.7431          | 0.4152   | 0.7707     | 0.1805     | 0.3650     |
+| No log        | 2.0   | 962  | 0.7346          | 0.4152   | 0.8010     | 0.2190     | 0.2774     |
+| No log        | 3.0   | 1443 | 0.7667          | 0.4162   | 0.8145     | 0.1895     | 0.3084     |
+
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.10.0+cu113
+- Datasets 2.1.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,26 @@
+{
+    "HateXplain-dev_accuracy": 0.4162330905306972,
+    "HateXplain-dev_accuracy_0": 0.8145025295109612,
+    "HateXplain-dev_accuracy_1": 0.18950064020486557,
+    "HateXplain-dev_accuracy_2": 0.3083941605839416,
+    "HateXplain-dev_loss": 0.766707181930542,
+    "HateXplain-dev_runtime": 2.1526,
+    "HateXplain-dev_samples": 1922,
+    "HateXplain-dev_samples_per_second": 892.867,
+    "HateXplain-dev_steps_per_second": 28.338,
+    "HateXplain-test_accuracy": 0.41372141372141374,
+    "HateXplain-test_accuracy_0": 0.8383838383838383,
+    "HateXplain-test_accuracy_1": 0.18030690537084398,
+    "HateXplain-test_accuracy_2": 0.2864963503649635,
+    "HateXplain-test_loss": 0.7393361926078796,
+    "HateXplain-test_runtime": 2.1365,
+    "HateXplain-test_samples": 1924,
+    "HateXplain-test_samples_per_second": 900.535,
+    "HateXplain-test_steps_per_second": 28.551,
+    "epoch": 3.0,
+    "train_loss": 0.6979017356824974,
+    "train_runtime": 157.0033,
+    "train_samples": 15383,
+    "train_samples_per_second": 293.936,
+    "train_steps_per_second": 9.191
+}

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "google/electra-base-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "finetuning_task": "hatexplain",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "hatespeech",
+    "1": "normal",
+    "2": "offensive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "hatespeech": 0,
+    "normal": 1,
+    "offensive": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc44566720bcc9a14a2789e2c59182f776da68837ccbf696db1412665153870c
+size 438024493

run_arguments.json

@@ -0,0 +1,24 @@
+{
+    "model_name_or_path": "google/electra-base-discriminator",
+    "task_name": "hatexplain",
+    "output_dir": "./output/electra/hatexplain/0001/SEED0042/",
+    "learning_rate": 3e-05,
+    "num_train_epochs": 3,
+    "per_device_eval_batch_size": 32,
+    "per_device_train_batch_size": 32,
+    "seed": 42,
+    "warmup_steps": 150,
+    "do_train": true,
+    "do_eval": true,
+    "do_predict": false,
+    "pad_to_max_length": false,
+    "max_seq_length": 128,
+    "report_to": [],
+    "save_strategy": "epoch",
+    "evaluation_strategy": "epoch",
+    "logging_steps": 2500,
+    "use_fast_tokenizer": true,
+    "group_by_length": true,
+    "save_training_dynamics": true,
+    "save_training_dynamics_after_epoch": true
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-base-discriminator", "tokenizer_class": "ElectraTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.6979017356824974,
+    "train_runtime": 157.0033,
+    "train_samples": 15383,
+    "train_samples_per_second": 293.936,
+    "train_steps_per_second": 9.191
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 1443,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.41519250780437045,
+      "eval_accuracy_0": 0.7706576728499157,
+      "eval_accuracy_1": 0.18053777208706787,
+      "eval_accuracy_2": 0.36496350364963503,
+      "eval_loss": 0.7430521249771118,
+      "eval_runtime": 2.1482,
+      "eval_samples_per_second": 894.711,
+      "eval_steps_per_second": 28.396,
+      "step": 481
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.41519250780437045,
+      "eval_accuracy_0": 0.8010118043844857,
+      "eval_accuracy_1": 0.21895006402048656,
+      "eval_accuracy_2": 0.2773722627737226,
+      "eval_loss": 0.734639585018158,
+      "eval_runtime": 2.1556,
+      "eval_samples_per_second": 891.64,
+      "eval_steps_per_second": 28.299,
+      "step": 962
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4162330905306972,
+      "eval_accuracy_0": 0.8145025295109612,
+      "eval_accuracy_1": 0.18950064020486557,
+      "eval_accuracy_2": 0.3083941605839416,
+      "eval_loss": 0.766707181930542,
+      "eval_runtime": 2.1595,
+      "eval_samples_per_second": 890.029,
+      "eval_steps_per_second": 28.248,
+      "step": 1443
+    },
+    {
+      "epoch": 3.0,
+      "step": 1443,
+      "total_flos": 736655902431120.0,
+      "train_loss": 0.6979017356824974,
+      "train_runtime": 157.0033,
+      "train_samples_per_second": 293.936,
+      "train_steps_per_second": 9.191
+    }
+  ],
+  "max_steps": 1443,
+  "num_train_epochs": 3,
+  "total_flos": 736655902431120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76ce4485b64a5702a8ce31c3289572d54aa1f7a4c942883f18cf217dec8fd48
+size 3119

training_dynamics/epoch0_train_idxs_[15383].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaeb19d32c0db5eb6d632f80136c429247902cb6e3a95a6d4d4f2daf0cd645f1
+size 123755

training_dynamics/epoch0_train_logits_[15383, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a43f29c6ac9cf4849562db9c00c40a44c884ff55a8c016391318964c57279f23
+size 185323

training_dynamics/epoch1_train_idxs_[15383].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6dd61b3ec2c4dc9d2dc665245fc26d21e992f6dd2eab38b2d77320edeac737
+size 123755

training_dynamics/epoch1_train_logits_[15383, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f10754de63a72449f28e485e6ebb2d0f1c1c43d88b2a754fd4be5b547e41fc8f
+size 185323

training_dynamics/epoch2_train_idxs_[15383].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de065ee9319875e5da724bad1d4af75c0b934a23469933dbe73c80267ce11e65
+size 123755

training_dynamics/epoch2_train_logits_[15383, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9021069b7b7fffcd4e9bf372759a20f4faa5809604b01cc0d5dee7693ce94c89
+size 185323

training_dynamics_after_epoch/epoch0_after_epoch_train_idxs_[15383].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261a744bdb762ff1c3e893f2b06e2d5ad525bd0b8a06d5f8f521a4fcfd2a283e
+size 123755

training_dynamics_after_epoch/epoch0_after_epoch_train_logits_[15383, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116f53edc75e134b07da7486b77f42cdae644b88b2796cef469dc66c848dc70e
+size 185323

training_dynamics_after_epoch/epoch1_after_epoch_train_idxs_[15383].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:808c04cd270c54d3f25a7bd1ba9c1096f018e5f3d5ca1e0bd805cb6d9792e556
+size 123755

training_dynamics_after_epoch/epoch1_after_epoch_train_logits_[15383, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3062d3da16afe3af760044477167e2d9804d1b0e36720998673779650a1181bf
+size 185323

training_dynamics_after_epoch/epoch2_after_epoch_train_idxs_[15383].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e261a8570af9e80feb199bb5e32d88073bc23f3b2ad781f170d83699467714d8
+size 123755

training_dynamics_after_epoch/epoch2_after_epoch_train_logits_[15383, 3].pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33daacc01ffcad1f8501c6b6580d265183dcd350ce113db615ff9d9450a2efbe
+size 185323

val_sals.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1372397754bf861b8c5b7c9510fc344e4f515433f1d684e148f383996ae0c04f
+size 1968256