First commit

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,44 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- emotion
+metrics:
+- accuracy
+model-index:
+- name: twitter-emotion-deberta-v3-base
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: emotion
+      type: emotion
+      args: default
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.937
+---
+
+# twitter-emotion-deberta-v3-base
+
+This model is a fine-tuned version of [DeBERTa-v3](https://huggingface.co/microsoft/deberta-v3-base). It achieves the following results on the evaluation set:
+- Loss: 0.1474
+- Accuracy: 0.937
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 80
+- eval_batch_size: 80
+- lr_scheduler_type: linear
+- num_epochs: 6.0 
+
+### Framework versions
+- Transformers 4.12.5
+- Pytorch 1.10.0+cu113
+- Datasets 1.15.1
+- Tokenizers 0.10.3

added_tokens.json

@@ -0,0 +1 @@
+{"[MASK]": 128000}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.937,
+    "eval_loss": 0.14741940796375275,
+    "eval_runtime": 4.2315,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 472.644,
+    "eval_steps_per_second": 5.908,
+    "train_loss": 0.2273927664756775,
+    "train_runtime": 627.7316,
+    "train_samples": 16000,
+    "train_samples_per_second": 152.932,
+    "train_steps_per_second": 1.912
+}

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "emotion",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_accuracy": 0.937,
+    "eval_loss": 0.14741940796375275,
+    "eval_runtime": 4.2315,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 472.644,
+    "eval_steps_per_second": 5.908
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af18ebb6513b6f503acddbff051b2a5d6a7a7629dc7e35242d7336effd1ac08
+size 737794027

runs/Nov22_00-56-03_ws1/1637542597.4744098/events.out.tfevents.1637542597.ws1.28080.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe155866bb97f3c8a128026677ea6e8c94c4341e27688f1c11fe2f44f98cd53
+size 4599

runs/Nov22_00-56-03_ws1/events.out.tfevents.1637542597.ws1.28080.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad846f1700ed1279bb43cc9e52dadb8cf43f36767b98a328736f821ca152d980
+size 8209

runs/Nov22_00-56-03_ws1/events.out.tfevents.1637543230.ws1.28080.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d13694ae44ba581e7f5943095124ff255b556533eb1960c0d76548c979369d8d
+size 363

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": "[MASK]"}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-base", "tokenizer_class": "DebertaV2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 6.0,
+    "train_loss": 0.2273927664756775,
+    "train_runtime": 627.7316,
+    "train_samples": 16000,
+    "train_samples_per_second": 152.932,
+    "train_steps_per_second": 1.912
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": 0.14741940796375275,
+  "best_model_checkpoint": "./trained_models/twitter-emotion-deberta-v3-base/checkpoint-500",
+  "epoch": 6.0,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.8405,
+      "eval_loss": 0.5359936952590942,
+      "eval_runtime": 4.1757,
+      "eval_samples_per_second": 478.965,
+      "eval_steps_per_second": 5.987,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.915,
+      "eval_loss": 0.28240880370140076,
+      "eval_runtime": 4.2049,
+      "eval_samples_per_second": 475.638,
+      "eval_steps_per_second": 5.945,
+      "step": 200
+    },
+    {
+      "epoch": 1.5,
+      "eval_accuracy": 0.93,
+      "eval_loss": 0.19999809563159943,
+      "eval_runtime": 4.2283,
+      "eval_samples_per_second": 473.002,
+      "eval_steps_per_second": 5.913,
+      "step": 300
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.936,
+      "eval_loss": 0.13397051393985748,
+      "eval_runtime": 4.2488,
+      "eval_samples_per_second": 470.716,
+      "eval_steps_per_second": 5.884,
+      "step": 400
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 0.4142,
+      "step": 500
+    },
+    {
+      "epoch": 2.5,
+      "eval_accuracy": 0.937,
+      "eval_loss": 0.14741940796375275,
+      "eval_runtime": 4.2278,
+      "eval_samples_per_second": 473.054,
+      "eval_steps_per_second": 5.913,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.936,
+      "eval_loss": 0.15366272628307343,
+      "eval_runtime": 4.2318,
+      "eval_samples_per_second": 472.612,
+      "eval_steps_per_second": 5.908,
+      "step": 600
+    },
+    {
+      "epoch": 3.5,
+      "eval_accuracy": 0.939,
+      "eval_loss": 0.13712549209594727,
+      "eval_runtime": 4.2434,
+      "eval_samples_per_second": 471.315,
+      "eval_steps_per_second": 5.891,
+      "step": 700
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.941,
+      "eval_loss": 0.13440823554992676,
+      "eval_runtime": 4.2389,
+      "eval_samples_per_second": 471.816,
+      "eval_steps_per_second": 5.898,
+      "step": 800
+    },
+    {
+      "epoch": 4.5,
+      "eval_accuracy": 0.939,
+      "eval_loss": 0.13154806196689606,
+      "eval_runtime": 4.244,
+      "eval_samples_per_second": 471.257,
+      "eval_steps_per_second": 5.891,
+      "step": 900
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.1013,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.936,
+      "eval_loss": 0.15716207027435303,
+      "eval_runtime": 4.2453,
+      "eval_samples_per_second": 471.109,
+      "eval_steps_per_second": 5.889,
+      "step": 1000
+    },
+    {
+      "epoch": 5.5,
+      "eval_accuracy": 0.938,
+      "eval_loss": 0.15671509504318237,
+      "eval_runtime": 4.2362,
+      "eval_samples_per_second": 472.124,
+      "eval_steps_per_second": 5.902,
+      "step": 1100
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.939,
+      "eval_loss": 0.15347838401794434,
+      "eval_runtime": 4.2428,
+      "eval_samples_per_second": 471.385,
+      "eval_steps_per_second": 5.892,
+      "step": 1200
+    },
+    {
+      "epoch": 6.0,
+      "step": 1200,
+      "total_flos": 6907037114880000.0,
+      "train_loss": 0.2273927664756775,
+      "train_runtime": 627.7316,
+      "train_samples_per_second": 152.932,
+      "train_steps_per_second": 1.912
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 6,
+  "total_flos": 6907037114880000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03739130cd1582bcaf3563fccebb1cd25b3deb859e7b8de441010915b02dcdb
+size 2863