aapoliakova/bsf_cls

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+license: mit
+base_model: microsoft/deberta-v3-small
+tags:
+- generated_from_trainer
+model-index:
+- name: cls_level_bsf
+  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. -->
+
+# cls_level_bsf
+
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 1.5422
+- eval_accuracy: 0.4860
+- eval_runtime: 7.168
+- eval_samples_per_second: 39.899
+- eval_steps_per_second: 2.511
+- epoch: 3.2308
+- step: 1050
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 6
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "beginner",
+    "1": "intermediate",
+    "2": "advanced"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "advanced": 2,
+    "beginner": 0,
+    "intermediate": 1
+  },
+  "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": 6,
+  "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": "4.44.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05bce8b50732d5120a22c782d4131cade8617527addad6690966cd68097d9a63
+size 567601628

runs/Oct01_15-02-15_36a7c0a38235/events.out.tfevents.1727794937.36a7c0a38235.1511.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf370ca0657c70ee43bf70936ba1a1571ee77e20b55fed7518b16f885771e6b
+size 6208

runs/Oct01_15-09-23_36a7c0a38235/events.out.tfevents.1727795363.36a7c0a38235.1511.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8206d834a2f5a68ef573cd6e5aa964fd699b150fd17e643a6635d7fa28bbc9ee
+size 7803

runs/Oct01_15-31-36_36a7c0a38235/events.out.tfevents.1727796696.36a7c0a38235.1511.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2001794ea49b3ab25da7b78f1f980d37dee9d825c4b9e73c4644f1991014fe7
+size 6028

runs/Oct01_15-32-41_36a7c0a38235/events.out.tfevents.1727796762.36a7c0a38235.1511.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd28612655bdeb306dfb82d2d389730c62a793ee929a98462078ffd1e658b27
+size 16603

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a685d7ab4afbd2ef2ba2de5c90952fb016438bf574c829139c844bfa18dff28
+size 5176