Upload 10 files

config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7226ec89c61561e510caf725b4135cc8d9016b1228d83edc727bcc560fdb142
+size 216163356

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7030a5969836b4f3d6d6fa50089ad172fbb3d2756a2927f5b245e50cf72a3c6d
+size 432552429

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18f5eab34762f1b8722a679a1169dde0d3eddd3f77c37cc89392b3ec3f781a60
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1daa1dc07e65e2db40a843fa0b5a4d4d6c2ed7ea1c80401febe5d58e59be2a24
+size 1064

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
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

trainer_state.json

@@ -0,0 +1,140 @@
+{
+  "best_metric": 0.9008125554721984,
+  "best_model_checkpoint": "rubert_classification/checkpoint-3500",
+  "epoch": 1.674641148325359,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.7823053307284399,
+      "eval_f1": 0.7752692727748154,
+      "eval_loss": 0.6053181886672974,
+      "eval_precision": 0.7849961270931392,
+      "eval_recall": 0.7823053307284399,
+      "eval_runtime": 38.9969,
+      "eval_samples_per_second": 183.758,
+      "eval_steps_per_second": 11.488,
+      "step": 500
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 22.682289123535156,
+      "learning_rate": 4.975490196078432e-05,
+      "loss": 0.9433,
+      "step": 600
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.8368685459112476,
+      "eval_f1": 0.8330214371969107,
+      "eval_loss": 0.46620890498161316,
+      "eval_precision": 0.840415327990016,
+      "eval_recall": 0.8368685459112476,
+      "eval_runtime": 36.1817,
+      "eval_samples_per_second": 198.056,
+      "eval_steps_per_second": 12.382,
+      "step": 1000
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 12.139711380004883,
+      "learning_rate": 4.82843137254902e-05,
+      "loss": 0.5182,
+      "step": 1200
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.8428691041027072,
+      "eval_f1": 0.8319455570081821,
+      "eval_loss": 0.4372938573360443,
+      "eval_precision": 0.8395761804457677,
+      "eval_recall": 0.8428691041027072,
+      "eval_runtime": 35.6356,
+      "eval_samples_per_second": 201.091,
+      "eval_steps_per_second": 12.572,
+      "step": 1500
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 37.54426574707031,
+      "learning_rate": 4.681372549019608e-05,
+      "loss": 0.4508,
+      "step": 1800
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.8644990231649455,
+      "eval_f1": 0.8633019943338417,
+      "eval_loss": 0.39909306168556213,
+      "eval_precision": 0.8707480255460968,
+      "eval_recall": 0.8644990231649455,
+      "eval_runtime": 35.6445,
+      "eval_samples_per_second": 201.041,
+      "eval_steps_per_second": 12.569,
+      "step": 2000
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 3.496920108795166,
+      "learning_rate": 4.5343137254901966e-05,
+      "loss": 0.3875,
+      "step": 2400
+    },
+    {
+      "epoch": 1.2,
+      "eval_accuracy": 0.8898967345799609,
+      "eval_f1": 0.8875919037418019,
+      "eval_loss": 0.33941856026649475,
+      "eval_precision": 0.8906320921346105,
+      "eval_recall": 0.8898967345799609,
+      "eval_runtime": 35.5422,
+      "eval_samples_per_second": 201.619,
+      "eval_steps_per_second": 12.605,
+      "step": 2500
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 16.364843368530273,
+      "learning_rate": 4.387254901960784e-05,
+      "loss": 0.3401,
+      "step": 3000
+    },
+    {
+      "epoch": 1.44,
+      "eval_accuracy": 0.8869662294166899,
+      "eval_f1": 0.8851872123624062,
+      "eval_loss": 0.3447243273258209,
+      "eval_precision": 0.8869707495957468,
+      "eval_recall": 0.8869662294166899,
+      "eval_runtime": 35.7225,
+      "eval_samples_per_second": 200.602,
+      "eval_steps_per_second": 12.541,
+      "step": 3000
+    },
+    {
+      "epoch": 1.67,
+      "eval_accuracy": 0.9016187552330449,
+      "eval_f1": 0.9008125554721984,
+      "eval_loss": 0.325568288564682,
+      "eval_precision": 0.9021842242763984,
+      "eval_recall": 0.9016187552330449,
+      "eval_runtime": 35.7388,
+      "eval_samples_per_second": 200.51,
+      "eval_steps_per_second": 12.535,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 600,
+  "max_steps": 20900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1640277252096000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7e679bb9df7a1d953e06a86a8b03683c9d16b1660d3f4d9aa2f2cb139de3edf
+size 4856