Duplicate from lewtun/sagemaker-distilbert-emotion

Co-authored-by: Lewis Tunstall <lewtun@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

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

README.md

@@ -0,0 +1,150 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- emotion
+metrics:
+- accuracy
+model-index:
+- name: sagemaker-distilbert-emotion
+  results:
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: emotion
+      type: emotion
+      args: default
+    metrics:
+    - type: accuracy
+      value: 0.921
+      name: Accuracy
+  - task:
+      type: text-classification
+      name: Text Classification
+    dataset:
+      name: emotion
+      type: emotion
+      config: default
+      split: test
+    metrics:
+    - type: accuracy
+      value: 0.921
+      name: Accuracy
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGRkMDBjODEwZWI2OTlhZmQ4ZGQ2MjRhZDMzZjA1ZTNkMWU0OTdhZTA3NjAzZGI1ZGFiMjFlNGQxY2MyM2Y2NiIsInZlcnNpb24iOjF9.lk_zOxIIclaySp7edHaCoBD4hSHBJkUNcv1z-2vhO_8Af5JYOgRjlNloztRJd9SuRISEyH4srmqsRx8hqiivAA
+    - type: precision
+      value: 0.8870419502496194
+      name: Precision Macro
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTZhNTg0ODU0YmYxZGMxNDZhOTg4M2Y2OTUzZGZmZmQ3ZDdmMmQyMWQ1MTc3ZDIzM2ZlYjg3NGVhOTBhNzJiMiIsInZlcnNpb24iOjF9._ZojNfDN63jqrciNdn8xWhJ38IkaeIy_y8gOU0r9Wf3Ki06ZcrX4qAz8KVF9LIQffmK4EupUAlNFycxf3SZYBA
+    - type: precision
+      value: 0.921
+      name: Precision Micro
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2Y0ZGRhYWMxYTIwOGQzYzQ1MGIxOGZkMzM5YWYxN2RhZTgyZjJiNzc2MDY3YTk4YWYyOGI0MDE0M2JiYTk0NCIsInZlcnNpb24iOjF9.tPd-tWnKPt13vGMXk_OGpCgllvinP0Pry5YAvvcjnIKo33eJ5RCKay8u5Q2TTLCU71Lndf_x-A2qWInLXEk-AA
+    - type: precision
+      value: 0.9208079974712109
+      name: Precision Weighted
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNGUxYjkzM2MzOWNhYjIyZGE4ODYyY2E1MTRiMGNiMGM3NDk1Y2Q3ZjEyZDAzY2ZhZTFjYmE3YzY1MjM0YWMzZiIsInZlcnNpb24iOjF9.XNf83HOOYCJmb_BKpNM-ullwiqLoRBQLbA4FAa6v3bfH_BLwK3vve_Ym3xa7uNRkuJGM-clvkeXEaEqAz99JBA
+    - type: recall
+      value: 0.8688429370077566
+      name: Recall Macro
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2U0MmYzNTkyY2U0MDNiMDBjY2I3YWI0OGViZDBlZjJhNDBmZWE3NGYxMWFjMDFmMmVhM2RhZmY4ZWVlNzNkMiIsInZlcnNpb24iOjF9.J3qsAJm9T7kqmuOFs67Fq7RLEN2-cQ2RgUhqvvyO_OWXu3JVucTgCqQhpoKa1GHWVX0illbbozmAQ5OK5wBXCg
+    - type: recall
+      value: 0.921
+      name: Recall Micro
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGQ2NGNkYWQwMWY3ZmIyNzBiMTEwM2M4MWVlNzJiMGExMjk5MmY4ODgxYjM1YjUwNGIwMjNkZDk3NTBlNjI5NCIsInZlcnNpb24iOjF9.iZgzAfNdWlyEKAWwE32o3D6Ely76ZJ2ySVxl0jBetL4YGWgOHSybrYvcZ2kB8sx3QfOc5L_vWyWNSbY5HAVeAA
+    - type: recall
+      value: 0.921
+      name: Recall Weighted
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODcwOWIxMzFjM2VmM2E1MmZlOGM1N2JiNjQwMGM0MzEzNzQ5NzJlM2I3MDdkYTMzN2NlYzU5ZDQwODBjYWFmZiIsInZlcnNpb24iOjF9.PlvoxtJ9Bj5G2w_E6Cx5VG5maRPP5dn4YzOX0xYPu_J7iiXRRLvwp12Q6vIUwsZMoBM4jACrh-rQKZ_g_yyHCw
+    - type: f1
+      value: 0.87642650638535
+      name: F1 Macro
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiM2RiMzFkMGVhYjc3MmJjOGFkYTZiYzAxMGUyOTBmYWJhYmQ3NTg2M2MxZGExOGI4NTkwOWM2ODRlMGJjZjM3ZSIsInZlcnNpb24iOjF9.hVbjwMlCeyjJ-0BEhGuaI5T8MOsAkAgLTnp7zlhUEi2cireIEfAkpdsmBPuQJyZYaGZ5ZXmSybAP08X1ouNoBw
+    - type: f1
+      value: 0.9209999999999999
+      name: F1 Micro
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTk0ODExMTliNTJlYjExNWExNDQ2NDUwNjkyMjA3ODg5YTk0NmFhNmMxZGQ0MzMxZjgxNGFjMmNkZWI1MTMzOCIsInZlcnNpb24iOjF9.dqucaDtPQ0A1KZkT4q9Ojfgtf2wZiJmjaKrvTdbhsvf7gNfYnJsMGaDIOxp_YoCEXGRMXKsknANx_VA7mOKSDA
+    - type: f1
+      value: 0.9203938811554648
+      name: F1 Weighted
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDQ1MTYxMTFiNWYwZDExYThjMDVmODdiMmRjMmQzMzJmMWY5MWE0M2VhZmExZTEwMzFlMDQ2MWIyOTFjZDc4MyIsInZlcnNpb24iOjF9.T-HlP7Fl6NuPmqps7wHkTuGi_8wF6u6BuulCxX0sp8ocEP3j8GNH9goydsKTEHyLMmch9QuCrzqFmmGAW-wVAA
+    - type: loss
+      value: 0.23216550052165985
+      name: loss
+      verified: true
+      verifyToken: >-
+        eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzVhNzYwZWIyN2QzMjU2OThiZjRmMjFlYTQ2MDA3ZTVmNmFkYzE1NDA1OWQzOTM4ZmRiMmQ0OGE2MzY4ZTY1ZCIsInZlcnNpb24iOjF9.Zj38hE02ePkNK7m1dhPq_N25CC9p0ZekFyCSBAS534GfhFuNhtUFhcgr6DDjyPTbn906RJDmVNxu7g01eCarAw
+duplicated_from: lewtun/sagemaker-distilbert-emotion
+---
+
+<!-- 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. -->
+
+# sagemaker-distilbert-emotion
+
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2322
+- Accuracy: 0.921
+
+## 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: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.9306        | 1.0   | 500  | 0.2322          | 0.921    |
+
+
+### Framework versions
+
+- Transformers 4.12.3
+- Pytorch 1.9.1
+- Datasets 1.15.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "sadness",
+    "1": "joy",
+    "2": "love",
+    "3": "anger",
+    "4": "fear",
+    "5": "surprise"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "anger": "3",
+    "fear": "4",
+    "joy": "1",
+    "love": "2",
+    "sadness": "0",
+    "surprise": "5"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.3",
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9812bba875f65c877a613edb2d23f9ad3811398b14dff9e0d4826d659c4a672
+size 267872369

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": "distilbert-base-uncased", "tokenizer_class": "DistilBertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7de9c48c371674852a1528b6c20d6fdf2b5c17659ff12c001c486c0769537c
+size 2991