End of training

README.md

@@ -0,0 +1,72 @@
+---
+base_model: AIRI-Institute/gena-lm-bigbird-base-t2t
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: test_run
+  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. -->
+
+# test_run
+
+This model is a fine-tuned version of [AIRI-Institute/gena-lm-bigbird-base-t2t](https://huggingface.co/AIRI-Institute/gena-lm-bigbird-base-t2t) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2397
+- F1: 0.8195
+- Mcc Score: 0.5808
+- Accuracy: 0.7933
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Mcc Score | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:--------:|
+| 0.6329        | 1.0   | 94   | 0.5532          | 0.7711 | 0.4531    | 0.7335   |
+| 0.4921        | 2.0   | 188  | 0.4789          | 0.8359 | 0.5501    | 0.7832   |
+| 0.3981        | 3.0   | 282  | 0.4760          | 0.8347 | 0.5789    | 0.7987   |
+| 0.3579        | 4.0   | 376  | 0.6767          | 0.7737 | 0.5377    | 0.7587   |
+| 0.2488        | 5.0   | 470  | 0.5478          | 0.8327 | 0.5887    | 0.8015   |
+| 0.1889        | 6.0   | 564  | 0.7844          | 0.8231 | 0.5846    | 0.7962   |
+| 0.1569        | 7.0   | 658  | 0.8773          | 0.8254 | 0.5868    | 0.7978   |
+| 0.1034        | 8.0   | 752  | 1.4445          | 0.7499 | 0.4939    | 0.7353   |
+| 0.0832        | 9.0   | 846  | 1.6405          | 0.7195 | 0.4955    | 0.7205   |
+| 0.1051        | 10.0  | 940  | 1.2397          | 0.8195 | 0.5808    | 0.7933   |
+
+
+### Framework versions
+
+- Transformers 4.38.1
+- Pytorch 2.1.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "AIRI-Institute/gena-lm-bigbird-base-t2t",
+  "architectures": [
+    "BigBirdForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "attention_type": "block_sparse",
+  "block_size": 64,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 4096,
+  "model_type": "big_bird",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_random_blocks": 3,
+  "pad_token_id": 3,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "rescale_embeddings": false,
+  "sep_token_id": 66,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 2,
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c4b861c9ad78747dffa771651c86e2a56796f4c02cf9f32eb6e0c9cb7789cd
+size 455871688

runs/Mar02_10-13-22_9068c6418652/events.out.tfevents.1709374403.9068c6418652.937.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb6c29a90653bcbc2be3edac4edc5870ab7ff62948f603cb9179d3d6393879d
+size 11451

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[UNK]",
+      "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": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "-",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8340f3429bccd22d53ee9565636a420beeb4a8495c6da31a0c9c7863004389d3
+size 4856