Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44988826b54072d044357f8425fa0a91bcd3725d659e4b2645fb44f303b0e3fa
+oid sha256:118018f1532ea28ce419b2344b3bfd47216b78c4bb9b21ea5014bd54536f9bb6
 size 116795404

run-10/checkpoint-276/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-10/checkpoint-276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36fbd817855fb0d660209814f63f60004f7bcd9a72486c5d8b3eb87b7627d724
+size 116795404

run-10/checkpoint-276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b410d744af9216621798145b383e34a921ca68596ed0e48dc486a9d8351030
+size 233621882

run-10/checkpoint-276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:642a3a0438abe23672d7bbaae3dd0f4f6e63175df4486c039e5365ad3377f90c
+size 13990

run-10/checkpoint-276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee67bab6b0b7cc83caf1b58c1da64ddf2b87a720017891818b644ec5fbc81389
+size 1064

run-10/checkpoint-276/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
+  }
+}

run-10/checkpoint-276/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-276/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.889795918367347,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-10\\checkpoint-276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.7101830244064331,
+      "eval_runtime": 1.1461,
+      "eval_samples_per_second": 213.774,
+      "eval_steps_per_second": 13.961,
+      "step": 138
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.889795918367347,
+      "eval_loss": 0.43645206093788147,
+      "eval_runtime": 1.148,
+      "eval_samples_per_second": 213.415,
+      "eval_steps_per_second": 13.937,
+      "step": 276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.797006170440622e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 40
+  }
+}

run-10/checkpoint-276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbc66dfc85fc28533356433b6cc2bc58c7a1923646623ba9bfda5f13c617358
+size 4728

run-10/checkpoint-414/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-10/checkpoint-414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e2e7c0f7fba2c3bef2b16c7de3e43f6331fcb5132146cf5e722d891e1668ae5
+size 116795404

run-10/checkpoint-414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19071b413358b11feaaf01738892278d1159d9aed18943ecc2c3ba3ab84cda0
+size 233621882

run-10/checkpoint-414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b311ae4522811e5f8ec086d90b60bc3ba89bdd5c18b7dc31550b49148e5e6f58
+size 13990

run-10/checkpoint-414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2278004475b7c5bed3c8b2f8ea78cc8e1306a7e1d1b7beb26bb205e353cbd0f8
+size 1064

run-10/checkpoint-414/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
+  }
+}

run-10/checkpoint-414/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-414/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.9224489795918367,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-10\\checkpoint-414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.7101830244064331,
+      "eval_runtime": 1.1461,
+      "eval_samples_per_second": 213.774,
+      "eval_steps_per_second": 13.961,
+      "step": 138
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.889795918367347,
+      "eval_loss": 0.43645206093788147,
+      "eval_runtime": 1.148,
+      "eval_samples_per_second": 213.415,
+      "eval_steps_per_second": 13.937,
+      "step": 276
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9224489795918367,
+      "eval_loss": 0.35530897974967957,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 209.582,
+      "eval_steps_per_second": 13.687,
+      "step": 414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.797006170440622e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 40
+  }
+}

run-10/checkpoint-414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbc66dfc85fc28533356433b6cc2bc58c7a1923646623ba9bfda5f13c617358
+size 4728

run-10/checkpoint-552/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-10/checkpoint-552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7adea655c6679b60e62dac0056a5e8236b381b07d804d6b301d2a59e4038a9cf
+size 116795404

run-10/checkpoint-552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7cc815df196074a526bc6a855c918a7dc63c588bac828fe7d988989acf0afc
+size 233621882

run-10/checkpoint-552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29979aadb898158ead13cbbce34d94a07335326c6102da81d7fe3e150d1d4d9f
+size 13990

run-10/checkpoint-552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b890273fd6896558e246730082b9a6b956096111a5b143e4b88551e3e12b0a1
+size 1064

run-10/checkpoint-552/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
+  }
+}

run-10/checkpoint-552/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-552/trainer_state.json

@@ -0,0 +1,68 @@
+{
+  "best_metric": 0.9224489795918367,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-10\\checkpoint-414",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 552,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.7101830244064331,
+      "eval_runtime": 1.1461,
+      "eval_samples_per_second": 213.774,
+      "eval_steps_per_second": 13.961,
+      "step": 138
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.889795918367347,
+      "eval_loss": 0.43645206093788147,
+      "eval_runtime": 1.148,
+      "eval_samples_per_second": 213.415,
+      "eval_steps_per_second": 13.937,
+      "step": 276
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9224489795918367,
+      "eval_loss": 0.35530897974967957,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 209.582,
+      "eval_steps_per_second": 13.687,
+      "step": 414
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 2.4223640179474175e-05,
+      "loss": 0.6984,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9183673469387755,
+      "eval_loss": 0.3266046643257141,
+      "eval_runtime": 1.145,
+      "eval_samples_per_second": 213.974,
+      "eval_steps_per_second": 13.974,
+      "step": 552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6141098220600.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.797006170440622e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 40
+  }
+}

run-10/checkpoint-552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbc66dfc85fc28533356433b6cc2bc58c7a1923646623ba9bfda5f13c617358
+size 4728

run-10/checkpoint-690/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-10/checkpoint-690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be2d7ecbec9fad34efbfbdf6fab11ae706730b31aaf6c825eb8845f9f33e517
+size 116795404

run-10/checkpoint-690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66db949ada1bf642758426fa74a26730dcda811fa04ee0381240f2680a349b15
+size 233621882

run-10/checkpoint-690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad2d1e88dfe5d2ef8b2602d8a5546c3f9036941cf734a62d6104a848699ec2f
+size 13990

run-10/checkpoint-690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a61a9f1fabfeec8ae89eb646d4feb84ed5f5abddb0ab4ee2d4566df325d834d
+size 1064

run-10/checkpoint-690/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
+  }
+}

run-10/checkpoint-690/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-10/checkpoint-690/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.9224489795918367,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-10\\checkpoint-414",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 690,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.7101830244064331,
+      "eval_runtime": 1.1461,
+      "eval_samples_per_second": 213.774,
+      "eval_steps_per_second": 13.961,
+      "step": 138
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.889795918367347,
+      "eval_loss": 0.43645206093788147,
+      "eval_runtime": 1.148,
+      "eval_samples_per_second": 213.415,
+      "eval_steps_per_second": 13.937,
+      "step": 276
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9224489795918367,
+      "eval_loss": 0.35530897974967957,
+      "eval_runtime": 1.169,
+      "eval_samples_per_second": 209.582,
+      "eval_steps_per_second": 13.687,
+      "step": 414
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 2.4223640179474175e-05,
+      "loss": 0.6984,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9183673469387755,
+      "eval_loss": 0.3266046643257141,
+      "eval_runtime": 1.145,
+      "eval_samples_per_second": 213.974,
+      "eval_steps_per_second": 13.974,
+      "step": 552
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9183673469387755,
+      "eval_loss": 0.3250439763069153,
+      "eval_runtime": 1.235,
+      "eval_samples_per_second": 198.38,
+      "eval_steps_per_second": 12.955,
+      "step": 690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6141098220600.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.797006170440622e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 40
+  }
+}

run-10/checkpoint-690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbc66dfc85fc28533356433b6cc2bc58c7a1923646623ba9bfda5f13c617358
+size 4728

run-11/checkpoint-138/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-11/checkpoint-138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505426cfec173d434e1ada82903f2c2c324e17a8cd9c076ff72da78999e8423b
+size 116795404

run-11/checkpoint-138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d31ab1b910a5061503dccd0e1265cdee9f9d39a3579483f8d90f4d8b3b18126
+size 233621882

run-11/checkpoint-138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6160489d6082e78a3b3883d67d678fcfb4930a95cfbceef30bb885f266c3aaee
+size 13990

run-11/checkpoint-138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aed2f571c3d2b7fe97a414a5b38e12a58b586c09e235494c9f3344ff1fe13f1
+size 1064