Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e4ef8b613bd9e8406b4299b39501e74183f4c10216f270ffc5132b266f9de0
+oid sha256:8d263e1e80ba448eb1b1f39c55b66c7452b73cfc20e976747dee6abe1dd66960
 size 116795404

run-2/checkpoint-2200/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-2/checkpoint-2200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d263e1e80ba448eb1b1f39c55b66c7452b73cfc20e976747dee6abe1dd66960
+size 116795404

run-2/checkpoint-2200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c635c0de1fcfa90a05c0f753298e5912e5c9d74e88eb89ca53d415d4ad30f8d
+size 233621882

run-2/checkpoint-2200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f72fc0f61abbc2db662d57ab9e91e827cf6f9beefe315a19b395e3d16254ca1
+size 13990

run-2/checkpoint-2200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:430d51ce4ae3d85dc692d3578bef2a7f5451a4a681cb37a4971f05544ecc06bc
+size 1064

run-2/checkpoint-2200/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-2/checkpoint-2200/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-2/checkpoint-2200/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.8734693877551021,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-2\\checkpoint-1650",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2200,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.5039435145104783e-05,
+      "loss": 1.8268,
+      "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,
+      "step": 550
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0616071867132787e-05,
+      "loss": 1.0445,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8571428571428571,
+      "eval_loss": 0.730604887008667,
+      "eval_runtime": 1.103,
+      "eval_samples_per_second": 222.131,
+      "eval_steps_per_second": 14.507,
+      "step": 1100
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.192708589160794e-06,
+      "loss": 0.7493,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8734693877551021,
+      "eval_loss": 0.5868724584579468,
+      "eval_runtime": 1.1252,
+      "eval_samples_per_second": 217.733,
+      "eval_steps_per_second": 14.219,
+      "step": 1650
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.7693453111887982e-06,
+      "loss": 0.5909,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8693877551020408,
+      "eval_loss": 0.5535635352134705,
+      "eval_runtime": 1.079,
+      "eval_samples_per_second": 227.063,
+      "eval_steps_per_second": 14.829,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 3892671035400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.946279842307678e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 23
+  }
+}

run-2/checkpoint-2200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24844b54c4e4c2ebe3c69bc8bd3a5158a5ee05c4aebe057006cf6ebf084d9bab
+size 4728

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705259794.DESKTOP-RFEED41.20976.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4580c31485b84b2bffd9146d16bfbb663e9d7559c27350dbe7ae9d86c27c7b09
-size 6391
+oid sha256:be3d76ce795f7d658c690e07246467a6af63416cfc6b61b77a0d136af9573be4
+size 7225