Training in progress epoch 0

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: silviacamplani/distilbert-finetuned-tapt-ner-ai
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# silviacamplani/distilbert-finetuned-tapt-ner-ai
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.5750
+- Validation Loss: 1.7754
+- Train Precision: 0.0
+- Train Recall: 0.0
+- Train F1: 0.0
+- Train Accuracy: 0.6480
+- Epoch: 0
+
+## 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:
+- optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 350, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 2.5750     | 1.7754          | 0.0             | 0.0          | 0.0      | 0.6480         | 0     |
+
+
+### Framework versions
+
+- Transformers 4.20.1
+- TensorFlow 2.6.4
+- Datasets 2.1.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,85 @@
+{
+  "_name_or_path": "silviacamplani/distilbert-finetuned-tapt-lm-ai",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForTokenClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "O",
+    "1": "B-algorithm",
+    "2": "I-algorithm",
+    "3": "B-conference",
+    "4": "I-conference",
+    "5": "B-country",
+    "6": "I-country",
+    "7": "B-field",
+    "8": "I-field",
+    "9": "B-location",
+    "10": "I-location",
+    "11": "B-metrics",
+    "12": "I-metrics",
+    "13": "B-misc",
+    "14": "I-misc",
+    "15": "B-organisation",
+    "16": "I-organisation",
+    "17": "B-person",
+    "18": "I-person",
+    "19": "B-product",
+    "20": "I-product",
+    "21": "B-programlang",
+    "22": "I-programlang",
+    "23": "B-researcher",
+    "24": "I-researcher",
+    "25": "B-task",
+    "26": "I-task",
+    "27": "B-university",
+    "28": "I-university"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "B-algorithm": 1,
+    "B-conference": 3,
+    "B-country": 5,
+    "B-field": 7,
+    "B-location": 9,
+    "B-metrics": 11,
+    "B-misc": 13,
+    "B-organisation": 15,
+    "B-person": 17,
+    "B-product": 19,
+    "B-programlang": 21,
+    "B-researcher": 23,
+    "B-task": 25,
+    "B-university": 27,
+    "I-algorithm": 2,
+    "I-conference": 4,
+    "I-country": 6,
+    "I-field": 8,
+    "I-location": 10,
+    "I-metrics": 12,
+    "I-misc": 14,
+    "I-organisation": 16,
+    "I-person": 18,
+    "I-product": 20,
+    "I-programlang": 22,
+    "I-researcher": 24,
+    "I-task": 26,
+    "I-university": 28,
+    "O": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.20.1",
+  "vocab_size": 30522
+}

logs/train/events.out.tfevents.1661442665.1a16df506db2.17.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abad9124b81329f0c3cdd8c87be42b48c5e791ba9b15f324ec12ef04c1d92c06
+size 1868311

logs/train/events.out.tfevents.1661442676.1a16df506db2.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0b40383b3f68699a846d93e7004ff89ca08f2ed4ec50c2c635684ffa7e9ec9
+size 40

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bcd7cbd01bb6ba8a19aa77e4b9926444fc6b0fe6607967329206e3d60fd091
+size 3048

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:869f71d71e7d7e190028fb5a5dd90a5ea0b75bdbc8be8922d029254c3e9a46fa
+size 287493

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3bdc25b3c899d59ba63fb5f7cd583ca6718cd1105d508ce8d2d9732428e2876
+size 38791

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:191aecd64658a16710ea7cd7375afba58e712d652a6cfea7a03df1cbd036e053
+size 5957

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a9e61a8fa71c39364284c049e2322aad39ecd8a21d4ca2a338ca173d28e606
+size 193399

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c0cb62405074eb53554313636215e417a51d00c6523199c9ced6349e1478ea
+size 186484

logs/train/plugins/profile/2022_08_25_15_51_16/1a16df506db2.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec2ea571a7d56b0e02790a29e58709ff1da50045925637b3ee01f1c85c378f2c
+size 1476535

logs/validation/events.out.tfevents.1661442680.1a16df506db2.17.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af124c96baee7698775eac71c8ce79948ed375a488a389a1faf7eb1d88201291
+size 193

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa80c39afccb8fa963d69f04fd7c511c63e5d4b535c0201b512bafda5a7a134
+size 265666912

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "silviacamplani/distilbert-finetuned-tapt-lm-ai",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}