Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76707e678e420dead52178d88d619b95e7e71ee61a1e8b2736ba99496ef6639
+oid sha256:bca4f83e77e430177f1bee6ffd9c57ecd2364107a77cc848abe414e2a222457d
 size 116795404

run-0/checkpoint-105/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-0/checkpoint-105/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5590a56fac44516691bbd3b532661218831261f8b95e6b6662d072dab1250e
+size 116795404

run-0/checkpoint-105/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a976ee490c20c9ab5f3dc84fde56323949b533e9fa305096a71923fa93b91b5
+size 233621882

run-0/checkpoint-105/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bc8314e284e6eb19c4148a570a68baba6798bb6588ab7fd30859669bd32bde
+size 13990

run-0/checkpoint-105/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410af8c2fd8aef68215bc32244a6d776e14e21169a6660a8cc95491826af8cbc
+size 1064

run-0/checkpoint-105/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-0/checkpoint-105/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-0/checkpoint-105/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.8204081632653061,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-0\\checkpoint-105",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 105,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5142857142857142,
+      "eval_loss": 1.8266521692276,
+      "eval_runtime": 1.249,
+      "eval_samples_per_second": 196.157,
+      "eval_steps_per_second": 12.81,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7387755102040816,
+      "eval_loss": 1.3899593353271484,
+      "eval_runtime": 1.192,
+      "eval_samples_per_second": 205.538,
+      "eval_steps_per_second": 13.423,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8204081632653061,
+      "eval_loss": 1.1317118406295776,
+      "eval_runtime": 1.127,
+      "eval_samples_per_second": 217.391,
+      "eval_steps_per_second": 14.197,
+      "step": 105
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.723967938193154e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 40
+  }
+}

run-0/checkpoint-105/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf30298e8e2e3d70c6b83e014c63bac7fbca10e5fe524ad7f608198d8195428
+size 4728

run-0/checkpoint-140/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-0/checkpoint-140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca4f83e77e430177f1bee6ffd9c57ecd2364107a77cc848abe414e2a222457d
+size 116795404

run-0/checkpoint-140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71e3c02486d9817ecc212148b0bd2e4e79e2138e6743b785df77d2fa9e3fe71
+size 233621882

run-0/checkpoint-140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23beccfe725296bb15f8825d28ebba19c00e2cc509b17c211bf153c204bb5495
+size 13990

run-0/checkpoint-140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbee453c4749dc6c3790590531bccb5cb661c104b0a91889a5b9c7ee8810835b
+size 1064

run-0/checkpoint-140/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-0/checkpoint-140/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-0/checkpoint-140/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.8367346938775511,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-0\\checkpoint-140",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5142857142857142,
+      "eval_loss": 1.8266521692276,
+      "eval_runtime": 1.249,
+      "eval_samples_per_second": 196.157,
+      "eval_steps_per_second": 12.81,
+      "step": 35
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7387755102040816,
+      "eval_loss": 1.3899593353271484,
+      "eval_runtime": 1.192,
+      "eval_samples_per_second": 205.538,
+      "eval_steps_per_second": 13.423,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8204081632653061,
+      "eval_loss": 1.1317118406295776,
+      "eval_runtime": 1.127,
+      "eval_samples_per_second": 217.391,
+      "eval_steps_per_second": 14.197,
+      "step": 105
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8367346938775511,
+      "eval_loss": 0.9972113370895386,
+      "eval_runtime": 1.106,
+      "eval_samples_per_second": 221.52,
+      "eval_steps_per_second": 14.467,
+      "step": 140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.723967938193154e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 40
+  }
+}

run-0/checkpoint-140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf30298e8e2e3d70c6b83e014c63bac7fbca10e5fe524ad7f608198d8195428
+size 4728

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705259198.DESKTOP-RFEED41.20976.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15fcd3fe023f2c0ba611955061a08994b72925ac9fbba59e945bd81366081e99
-size 5586
+oid sha256:cf8d5155d731c07ce961abab28a22ba9645bd217b721568cb5a9fa9b1a8d3b77
+size 6226