End of training

README.md

@@ -0,0 +1,49 @@
+---
+base_model: DeepPavlov/rubert-base-cased
+tags:
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: my_awesome_wnut_model
+  results: []
+---
+
+<!-- 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. -->
+
+# my_awesome_wnut_model
+
+This model is a fine-tuned version of [DeepPavlov/rubert-base-cased](https://huggingface.co/DeepPavlov/rubert-base-cased) on the generator dataset.
+
+## 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: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Framework versions
+
+- Transformers 4.36.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6de8363342171997e5001d514bddf5501fb129796bfabcc602fc383b91420f
+oid sha256:234caf298b869b17e8fa4fee350e051af24094acddd3733df88e94d91283b12f
 size 709096284

runs/Dec16_15-18-46_22b8ff6fbb32/events.out.tfevents.1702739926.22b8ff6fbb32.1415.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180943c2a223b217e2761b224c41fc643e30bdd1bb729868e5f1fbcc45c5a63b
-size 11472
+oid sha256:b1fb10e8fb8de3644712846633b94e8954800e07687f77ac2d2d42f6695dfdd6
+size 11944

runs/Dec16_15-36-06_22b8ff6fbb32/events.out.tfevents.1702740967.22b8ff6fbb32.1415.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89ec71f0195ed5a8acba8365c2418e2a19f4c27025eea4e45615b6bc1b2d58b
+size 4910

tmp-checkpoint-1792/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "DeepPavlov/rubert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Object",
+    "2": "I-Object",
+    "3": "B-Aspect",
+    "4": "I-Aspect",
+    "5": "B-Predicate",
+    "6": "I-Predicate"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-Aspect": 3,
+    "B-Object": 1,
+    "B-Predicate": 5,
+    "I-Aspect": 4,
+    "I-Object": 2,
+    "I-Predicate": 6,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

tmp-checkpoint-1792/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f6ea197c00e9006e0ef518f1db3252c2056eec381288356e89c8db94908c283
+size 666894336

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f17bf6fd3129951b22a2986fa98ba11029e27c81a46c4e137459bd0a4e7400
+oid sha256:84402991a76e6feae1289d4ecd3110be57a1c9923fba3b50ac8317722e61ba29
 size 4728