Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f32e5640b9eb046467134f5894ead207a8d3dc7d4623a80edcd35eeac15e7e
+oid sha256:73e4d6a6e947f36beb3343b91199b7400ab1fad9f13965ee5f2f874b0f4d0ea0
 size 116795404

run-0/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-0/checkpoint-276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bcd7c2ba087478902bec87198bbfc395d9170615dcda8459fd5f5868301910
+size 116795404

run-0/checkpoint-276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6130c1f0b84cd8875308e0397a9194c0e29f648e5d011dfe783d7777f4bd366
+size 233621882

run-0/checkpoint-276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34484519685471c38c820207c6b35fdd7b6f7e64b8bd3a85b1fc1f7723ffcfdf
+size 14054

run-0/checkpoint-276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91741b941cdce64e6988989aac06e0b3e8566b42e106031c66308a3e0797266
+size 1064

run-0/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-0/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-0/checkpoint-276/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.3795918367346939,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-0\\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": 0.3020408163265306,
+      "eval_loss": 2.3561618328094482,
+      "eval_runtime": 1.19,
+      "eval_samples_per_second": 205.883,
+      "eval_steps_per_second": 13.445,
+      "step": 138
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3795918367346939,
+      "eval_loss": 2.3379552364349365,
+      "eval_runtime": 1.134,
+      "eval_samples_per_second": 216.049,
+      "eval_steps_per_second": 14.109,
+      "step": 276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9293281802514436e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 33
+  }
+}

run-0/checkpoint-276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0ab7702ae4415e642689783fea2e033c6ef407829d3b51fc4fdfd2e6f2726d
+size 4728

run-1/checkpoint-138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ad1bb5f5b9373e318b3dccf40fdcc1f68f700fb28ef9bae27e5e923d25f4a2
+oid sha256:ddb5c5b6b1f3c5373ab1e050b4843fccc13eb472d0d37303b12aa72f266e40c8
 size 116795404

run-1/checkpoint-138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbcb1e896d42f6a7207062d2d27fe06090e4dc2a3015125cf92b1cf505935252
+oid sha256:4aeebf43b1ade4aa19097b47374b189545d575da3b604de9e6ff7cbecb97e14f
 size 233621882

run-1/checkpoint-138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef1a7cff33c3fcd8791af5ee2d44aa31eb2da2c87b311112381c93b0bd32636
-size 13990
+oid sha256:469ae9cf81045371d11224ce5127dd885163059075a4a480383c9201a35def49
+size 14054

run-1/checkpoint-138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd9e931d8f654ec1c07be066dc06c47d2cd2a33c04e1faceb7bed1886ff31874
+oid sha256:1c9ab2bee8e535b5e1f3209e0feffe923dc7b1fe1f4e2de0a9b684197df6a5f8
 size 1064

run-1/checkpoint-138/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.7714285714285715,
-  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-1\\checkpoint-138",
-  "epoch": 1.0,
+  "best_metric": 0.1836734693877551,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-1\\checkpoint-69",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 138,
   "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7714285714285715,
-      "eval_loss": 1.5001928806304932,
-      "eval_runtime": 1.124,
-      "eval_samples_per_second": 217.972,
-      "eval_steps_per_second": 14.235,
+      "eval_accuracy": 0.1836734693877551,
+      "eval_loss": 2.384721279144287,
+      "eval_runtime": 1.179,
+      "eval_samples_per_second": 207.804,
+      "eval_steps_per_second": 13.571,
+      "step": 69
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.1836734693877551,
+      "eval_loss": 2.3813865184783936,
+      "eval_runtime": 1.1696,
+      "eval_samples_per_second": 209.477,
+      "eval_steps_per_second": 13.68,
       "step": 138
     }
   ],
   "logging_steps": 500,
-  "max_steps": 414,
+  "max_steps": 138,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.266288376624928e-05,
-    "num_train_epochs": 3,
-    "per_device_train_batch_size": 16,
-    "seed": 36
+    "learning_rate": 1.0017079803752642e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 24
   }
 }

run-1/checkpoint-138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6ba06e4df241930f59a2cb2d75e387e78b0cbefe51f6381c073f2e08285e49e
+oid sha256:0894e2266e57f86a345acd6d6c72fc47fca08a4fcfa3fe123573316bf1eef568
 size 4728

run-1/checkpoint-69/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-1/checkpoint-69/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94eed3cb1bf3c92f0c022b908c09c8be3173e1bb47ce2bcc41a6cba5b30d977a
+size 116795404

run-1/checkpoint-69/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538baecab6814677a904adc0a1e8f6f4b090fb2a7454ae8eadbbd754fbebd1bb
+size 233621882

run-1/checkpoint-69/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de45a089e6be136120b29123a757a0ab38e94acdbca5a7fc5e8849dbef4bed79
+size 14054

run-1/checkpoint-69/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5bfe90d8b336a070529c72ae6a488cb9507237bfdd03cdc21f1ddeaabf6ec31
+size 1064

run-1/checkpoint-69/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-1/checkpoint-69/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-1/checkpoint-69/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.1836734693877551,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-1\\checkpoint-69",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 69,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.1836734693877551,
+      "eval_loss": 2.384721279144287,
+      "eval_runtime": 1.179,
+      "eval_samples_per_second": 207.804,
+      "eval_steps_per_second": 13.571,
+      "step": 69
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0017079803752642e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 24
+  }
+}

run-1/checkpoint-69/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0894e2266e57f86a345acd6d6c72fc47fca08a4fcfa3fe123573316bf1eef568
+size 4728

run-2/checkpoint-550/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786b91ea6b51c37c5c5c71181e85ad3c0759ca9b5c43fbb15119271b98789a48
+oid sha256:73e4d6a6e947f36beb3343b91199b7400ab1fad9f13965ee5f2f874b0f4d0ea0
 size 116795404

run-2/checkpoint-550/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3535b9bd5c858f2c0272a73160456e2e494d16c5e211cba23c94fe015d4692fb
+oid sha256:05a5724247cdb00b11448545ce0999dfc91ad37c6b30ddeb241cb648f42a515a
 size 233621882

run-2/checkpoint-550/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976bef9f47b4eda4dcb60d384d346e96d3247e0dc76fc7bfef99b529300cbfb5
+oid sha256:0693f5c5c5bcfe227ff6741359c6c12f4956bfc105c83db08973b51b53d463c8
 size 13990

run-2/checkpoint-550/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8911f29fc6713bdd0c9f9a56f8f625ed4bbea5ffb92f2b5c67d723a478a23d82
+oid sha256:efc9ccd32911bfeeeaa66614ef0a44193d7d501edb97f62db92a1aab9d1a315e
 size 1064

run-2/checkpoint-550/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.7224489795918367,
+  "best_metric": 0.6326530612244898,
   "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-550",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 0.91,
-      "learning_rate": 1.5039435145104783e-05,
-      "loss": 1.8268,
+      "learning_rate": 7.123150895957912e-06,
+      "loss": 2.1151,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7224489795918367,
-      "eval_loss": 1.1639864444732666,
-      "eval_runtime": 1.3165,
-      "eval_samples_per_second": 186.096,
-      "eval_steps_per_second": 12.153,
+      "eval_accuracy": 0.6326530612244898,
+      "eval_loss": 1.7264677286148071,
+      "eval_runtime": 1.125,
+      "eval_samples_per_second": 217.778,
+      "eval_steps_per_second": 14.222,
       "step": 550
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2200,
+  "max_steps": 2750,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 973499410800.0,
+  "total_flos": 969634944600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.946279842307678e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 8.706073317281892e-06,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 4,
-    "seed": 23
+    "seed": 1
   }
 }

run-2/checkpoint-550/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24844b54c4e4c2ebe3c69bc8bd3a5158a5ee05c4aebe057006cf6ebf084d9bab
+oid sha256:6bf6249fcaffd3bf1a6e41efb7044edf4d8222cdd0729549fa8f87e1c5b20556
 size 4728

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705269566.DESKTOP-RFEED41.20976.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f98ace43e9cd66ae7f6f3db2c2de16f3cf01f26b61a769fe24cbe65ef31d52
+size 5947

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705269786.DESKTOP-RFEED41.20976.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4578bfa83675a3cce33be98262b633d695f981f70048612e5dda786f2becb1cc
+size 5430

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd0ab7702ae4415e642689783fea2e033c6ef407829d3b51fc4fdfd2e6f2726d
+oid sha256:6bf6249fcaffd3bf1a6e41efb7044edf4d8222cdd0729549fa8f87e1c5b20556
 size 4728