Training in progress epoch 0

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- generated_from_keras_callback
+model-index:
+- name: silviacamplani/distilbert-finetuned-dapt_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-dapt_tapt-ner-ai
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.5333
+- Validation Loss: 1.7392
+- 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 |
+|:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
+| 2.5333     | 1.7392          | 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-dapt_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.1661598559.b2f2cf3de367.17.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba6a3bc37f72ef6a96e257aadd543d14307d2b047942cb651751fdc4906b6af
+size 1868311

logs/train/events.out.tfevents.1661598570.b2f2cf3de367.profile-empty

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:022bbc6ced37511b9619a6a1321deaba18b3ba4d5ca6216c05ee3723a80cd830
+size 40

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.input_pipeline.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e88839b168344ab6a0c7212c0a92aab3209d0cd3c36e9c7dd324688b531c15
+size 3048

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.kernel_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9907706d6bb8080ef5d10a5bc5566c818a200407b87253f9fa683e7ed47e1fba
+size 318213

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.memory_profile.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baec2e815c63752afe47305a3c7be00f0f95726ee70d9073698dc3b5c7cc3d9b
+size 37973

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.overview_page.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a9a00c640a2a2ea97e6c38c4530c05f3f24377db9578e2a272e5fbb353d57f
+size 6020

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.tensorflow_stats.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703a682a4c979a412e3c24ad578660553f1c0cab75c9fba60dea6d6070f4fe41
+size 191501

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.trace.json.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d915dcbd7c3d826cca7bb95fa7f6135c544bb961aa109ac971a31c12f656e865
+size 217571

logs/train/plugins/profile/2022_08_27_11_09_30/b2f2cf3de367.xplane.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:494c54d4cd062b74565e8e972a5333bc816d622e1911fc9403d5a89c2c11aa8f
+size 1671428

logs/validation/events.out.tfevents.1661598574.b2f2cf3de367.17.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a314b8b9922d3965e38522012ad7214e617d68961440f84b46f1f863a3f3f7
+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 sha256:5e97e8d9e5bf1f84faf17fc1a80c3fda84c25462fcee4fe0ac75ffcd899c1641
+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-dapt_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]"
+}