End of training

README.md

@@ -0,0 +1,63 @@
+---
+license: mit
+base_model: ai-forever/ruElectra-medium
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: electra128b128l
+  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. -->
+
+# electra128b128l
+
+This model is a fine-tuned version of [ai-forever/ruElectra-medium](https://huggingface.co/ai-forever/ruElectra-medium) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9516
+- Accuracy: 0.6304
+
+## 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: 128
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 1.2708        | 1.0   | 1407 | 1.1104          | 0.5619   |
+| 1.0724        | 2.0   | 2814 | 1.0100          | 0.606    |
+| 0.9986        | 3.0   | 4221 | 0.9652          | 0.6258   |
+| 0.9596        | 4.0   | 5628 | 0.9516          | 0.6304   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "ai-forever/ruElectra-medium",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 576,
+  "generator_size": "0.25",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 576,
+  "id2label": {
+    "0": "Gogol",
+    "1": "Dostoevsky",
+    "2": "Chekhov",
+    "3": "Gorky",
+    "4": "Tolstoy"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 2304,
+  "label2id": {
+    "Chekhov": 2,
+    "Dostoevsky": 1,
+    "Gogol": 0,
+    "Gorky": 3,
+    "Tolstoy": 4
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cab1c1d950fa97f39514f2e74c7cebc0db4c1dcfc6d0bf7acf1d717be23a2f48
+size 341472356

runs/May15_10-12-19_a7e826714837/events.out.tfevents.1715767940.a7e826714837.266.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a56a37ac3ba446039788aa961394714db5497731540c672976cee4f388c6ccc7
+size 9062

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "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
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b1e580f98e9e3b956036608b40b21d31174964fd9a3d5b307a13cba1bf09df
+size 4984