Upload 10 files

config.json

@@ -0,0 +1,36 @@
+{
+  "_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,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "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:dde4667a7321936ee745297a772281addb6243834a6328a7d6e504c49edae0d3
+size 216153096

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70745da66d211416cc452a2f6cc8d6a0458b57687c9b1f4790a69430901c3f9d
+size 432531949

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:a018338f993d0b5dcfbf7a895184258f431365ff2b8e11bd8f90258efecd65f3
+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 +1,90 @@
+{
+  "best_metric": 0.9620120357508649,
+  "best_model_checkpoint": "rubert_classification/checkpoint-2000",
+  "epoch": 4.566210045662101,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.14,
+      "eval_accuracy": 0.882,
+      "eval_f1": 0.8860252812063524,
+      "eval_loss": 0.3335667848587036,
+      "eval_precision": 0.9101706722396378,
+      "eval_recall": 0.882,
+      "eval_runtime": 7.9932,
+      "eval_samples_per_second": 187.659,
+      "eval_steps_per_second": 11.76,
+      "step": 500
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 54.402042388916016,
+      "learning_rate": 4.871134020618557e-05,
+      "loss": 0.3238,
+      "step": 600
+    },
+    {
+      "epoch": 2.28,
+      "eval_accuracy": 0.952,
+      "eval_f1": 0.952629531198857,
+      "eval_loss": 0.22119292616844177,
+      "eval_precision": 0.955250771109112,
+      "eval_recall": 0.952,
+      "eval_runtime": 7.4028,
+      "eval_samples_per_second": 202.626,
+      "eval_steps_per_second": 12.698,
+      "step": 1000
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 0.6686217188835144,
+      "learning_rate": 4.097938144329897e-05,
+      "loss": 0.1138,
+      "step": 1200
+    },
+    {
+      "epoch": 3.42,
+      "eval_accuracy": 0.9586666666666667,
+      "eval_f1": 0.9584488790426743,
+      "eval_loss": 0.19180671870708466,
+      "eval_precision": 0.9584916263909182,
+      "eval_recall": 0.9586666666666667,
+      "eval_runtime": 7.383,
+      "eval_samples_per_second": 203.169,
+      "eval_steps_per_second": 12.732,
+      "step": 1500
+    },
+    {
+      "epoch": 4.11,
+      "grad_norm": 0.031083475798368454,
+      "learning_rate": 3.3247422680412374e-05,
+      "loss": 0.0394,
+      "step": 1800
+    },
+    {
+      "epoch": 4.57,
+      "eval_accuracy": 0.962,
+      "eval_f1": 0.9620120357508649,
+      "eval_loss": 0.2063756138086319,
+      "eval_precision": 0.9620250729762693,
+      "eval_recall": 0.962,
+      "eval_runtime": 7.384,
+      "eval_samples_per_second": 203.142,
+      "eval_steps_per_second": 12.73,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 600,
+  "max_steps": 4380,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 936301011222528.0,
+  "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 sha256:4d81d80bd442b67059ef0313dd0ce5c0848a8b7e176c6d747d3432be45ed0847
+size 4856