Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51fb9887879e7731535630c099dee14cb777dff78dbf5ccc6fd9176a23bea52e
+oid sha256:982481fd3ffbd778cdcb14273c00726a5ba3ed5a1e7cde523147cbb155bb6724
 size 98470112

run-2/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ce5cba71ab627aa4d3b1694264448dd6b7c33fa58fdf00e3b68101b022d151
+oid sha256:540137d39291365f7824650a486a1cfac19ef52ae7195604089bd9d2c38a7bb2
 size 98470112

run-2/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf9090313f1d1e637238680271b34cf9e7a19532a6474f42fe7432fe43e0ff6
+oid sha256:34c3954f9d5c69a21026987e5a2f822665171405111208af2594a91ce0f04127
 size 197593757

run-2/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d07fb318ad742c1c4d329e1f07ad38c5c4a57d1f01ad4efb31257c2bccb417a
-size 14244
+oid sha256:74113234244fc59c10f06606eecdcf6b721037b8c5df7d0a6d0e8785fe5adefe
+size 14308

run-2/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b71680a09b19af463162c25c87905ddd0917ca13d590913abe6708a7d33215
+oid sha256:c95cbb4865a285b137707b40f5ecac3bf0e184eb2c4ca71a2c50d70f30cfe2ee
 size 1064

run-2/checkpoint-54/trainer_state.json

@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 18281.876953125,
+      "eval_loss": 72.75434112548828,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.4635,
-      "eval_samples_per_second": 423.379,
-      "eval_steps_per_second": 26.791,
+      "eval_runtime": 2.5623,
+      "eval_samples_per_second": 407.053,
+      "eval_steps_per_second": 25.758,
       "step": 27
     },
     {
       "epoch": 2.0,
-      "eval_loss": 866.8018798828125,
+      "eval_loss": 10.623336791992188,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 2.6773,
-      "eval_samples_per_second": 389.575,
-      "eval_steps_per_second": 24.652,
+      "eval_runtime": 2.7349,
+      "eval_samples_per_second": 381.366,
+      "eval_steps_per_second": 24.132,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 54,
+  "max_steps": 81,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.81582432447674e-05,
-    "num_train_epochs": 2,
+    "learning_rate": 3.553146470021689e-05,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 32,
-    "seed": 5
+    "seed": 20
   }
 }

run-2/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b81ffb403f14950689bf76af4de34d59644f8842de05b90ea8aa4ee6730d4b
+oid sha256:c4a07d48cd4cae2aa7c1351f9ead38dc0c59969fb1a8ad67e6d55ee9559d5a17
 size 4920

run-2/checkpoint-81/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "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": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "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,
+  "vocab_size": 30522
+}

run-2/checkpoint-81/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3738ca6347fd1f127642d598a7b3a19a903e4433bb5efecde23ac19a3acae679
+size 98470112

run-2/checkpoint-81/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7ace3ef14c24a134ce0da52b1a43ff2045995ecf02ec1f3ae6447690e7e000
+size 197593757

run-2/checkpoint-81/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54952032a35a217f046acb952da399620f982376d56f2ed574a821f837d6b3d0
+size 14308

run-2/checkpoint-81/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0780250fc8eb36278683f736501b86df6bf7614542c9d6a3799cc8cb351bb6
+size 1064

run-2/checkpoint-81/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-81/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-81/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.017987145841259707,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-2/checkpoint-81",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 81,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 72.75434112548828,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5623,
+      "eval_samples_per_second": 407.053,
+      "eval_steps_per_second": 25.758,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 10.623336791992188,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.7349,
+      "eval_samples_per_second": 381.366,
+      "eval_steps_per_second": 24.132,
+      "step": 54
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.500556707382202,
+      "eval_matthews_correlation": 0.017987145841259707,
+      "eval_runtime": 2.6161,
+      "eval_samples_per_second": 398.684,
+      "eval_steps_per_second": 25.228,
+      "step": 81
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 81,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.553146470021689e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 20
+  }
+}

run-2/checkpoint-81/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a07d48cd4cae2aa7c1351f9ead38dc0c59969fb1a8ad67e6d55ee9559d5a17
+size 4920

run-3/checkpoint-108/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68c1a9b3f0bef5f4c5d8933f6aadf43a5d25cf1e5fd3711ad4ee734f31ff5c2c
+oid sha256:38b355b3e5611301994aa0d7b523facf721d6461b99a5e5a493ff78a423d6c06
 size 98470112

run-3/checkpoint-108/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eeb150a98b573cd4f89207d5af2963be915b7797bfad8b8b75e9d6222e70369
+oid sha256:0427b96717b17debe88f508659c41b7c9981597d73895c6fb1c15faa2894bfd7
 size 197593757

run-3/checkpoint-108/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80287e3a3f24b9b81a61fdf60a7e439c30cafc7c85c637ed40d0db4ef194eee9
-size 14308
+oid sha256:5b6f4fa8c35e4cbe184ee3aca0c688132276e5921db6dd846d90d25701703ad5
+size 14244

run-3/checkpoint-108/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c5331ad403b52131b235442d04fdcd60e1af6ebb4f844c84f85483f181f5c5
+oid sha256:90cd5425ddfb5a55dfddfc4e04016b7b905cbe8b3ae46ed8c40efe875a2594bc
 size 1064

run-3/checkpoint-108/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.1820081432026257,
+  "best_metric": 0.04097530686838422,
   "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-3/checkpoint-108",
-  "epoch": 4.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 108,
   "is_hyper_param_search": true,
@@ -10,53 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.7651640176773071,
-      "eval_matthews_correlation": 0.00286100001416597,
-      "eval_runtime": 2.6861,
-      "eval_samples_per_second": 388.297,
-      "eval_steps_per_second": 24.571,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.6181267499923706,
-      "eval_matthews_correlation": 0.07738463889453959,
-      "eval_runtime": 2.7756,
-      "eval_samples_per_second": 375.772,
-      "eval_steps_per_second": 23.778,
+      "eval_loss": 196.7971649169922,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5752,
+      "eval_samples_per_second": 405.024,
+      "eval_steps_per_second": 25.63,
       "step": 54
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 0.6142112612724304,
-      "eval_matthews_correlation": 0.10436722000562923,
-      "eval_runtime": 2.8806,
-      "eval_samples_per_second": 362.077,
-      "eval_steps_per_second": 22.912,
-      "step": 81
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.6295883059501648,
-      "eval_matthews_correlation": 0.1820081432026257,
-      "eval_runtime": 2.6099,
-      "eval_samples_per_second": 399.635,
-      "eval_steps_per_second": 25.289,
+      "epoch": 2.0,
+      "eval_loss": 3.1003661155700684,
+      "eval_matthews_correlation": 0.04097530686838422,
+      "eval_runtime": 2.7354,
+      "eval_samples_per_second": 381.302,
+      "eval_steps_per_second": 24.128,
       "step": 108
     }
   ],
   "logging_steps": 500,
-  "max_steps": 135,
+  "max_steps": 270,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 7.240804873707743e-05,
+    "learning_rate": 1.6103502735474484e-05,
     "num_train_epochs": 5,
-    "per_device_train_batch_size": 32,
-    "seed": 26
+    "per_device_train_batch_size": 16,
+    "seed": 6
   }
 }

run-3/checkpoint-108/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36785e41a5c6212d878c92ad6ba2710c2bfea93bb0742241dc2ee9d2b361a3a8
+oid sha256:cc97d4fded77640ee20a5deba4627ded60c972cf60dd6d6c19e1214346bf5c66
 size 4920

run-3/checkpoint-162/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "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": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "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,
+  "vocab_size": 30522
+}

run-3/checkpoint-162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad09e78a65667a6d70a803c7bf5922b369a4dc06befdb5003990e2b81f550fb
+size 98470112

run-3/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c42bd7e1675c99c5d39e16233f020cbc33eba62f8249e6ae5fe6eabeb69231
+size 197593757

run-3/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c02ad87af1fadff9f05de95e8b3889ce91684ff9706a07526c0936bc54f646
+size 14244

run-3/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f02b6f673c982dda014ce1d94bfe20abc9359cf878f1331b47a02a753187972f
+size 1064

run-3/checkpoint-162/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-162/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-162/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.04097530686838422,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-3/checkpoint-108",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 196.7971649169922,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5752,
+      "eval_samples_per_second": 405.024,
+      "eval_steps_per_second": 25.63,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.1003661155700684,
+      "eval_matthews_correlation": 0.04097530686838422,
+      "eval_runtime": 2.7354,
+      "eval_samples_per_second": 381.302,
+      "eval_steps_per_second": 24.128,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.9685006141662598,
+      "eval_matthews_correlation": -0.005957385967432711,
+      "eval_runtime": 2.5346,
+      "eval_samples_per_second": 411.508,
+      "eval_steps_per_second": 26.04,
+      "step": 162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6103502735474484e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 6
+  }
+}

run-3/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc97d4fded77640ee20a5deba4627ded60c972cf60dd6d6c19e1214346bf5c66
+size 4920

run-3/checkpoint-216/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "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": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "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,
+  "vocab_size": 30522
+}

run-3/checkpoint-216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65341f6c3ec2278bc5b711c0f713221af18dde894e801cd0e71b7e7447a6e371
+size 98470112

run-3/checkpoint-216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db70ea0e8015143abe7343270b839b150026b0720c86e14d573a850b14dda820
+size 197593757

run-3/checkpoint-216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee9b3783190c1317315fb76c619ca924c1add831ec42ba404c15552f94086da
+size 14244

run-3/checkpoint-216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb220ca70173bbc62a4e296abdd4ec2140fde11a49e105764310c081b50be40
+size 1064

run-3/checkpoint-216/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-216/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-216/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.04097530686838422,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-3/checkpoint-108",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 196.7971649169922,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5752,
+      "eval_samples_per_second": 405.024,
+      "eval_steps_per_second": 25.63,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.1003661155700684,
+      "eval_matthews_correlation": 0.04097530686838422,
+      "eval_runtime": 2.7354,
+      "eval_samples_per_second": 381.302,
+      "eval_steps_per_second": 24.128,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.9685006141662598,
+      "eval_matthews_correlation": -0.005957385967432711,
+      "eval_runtime": 2.5346,
+      "eval_samples_per_second": 411.508,
+      "eval_steps_per_second": 26.04,
+      "step": 162
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.4282734394073486,
+      "eval_matthews_correlation": 0.00286100001416597,
+      "eval_runtime": 2.3378,
+      "eval_samples_per_second": 446.151,
+      "eval_steps_per_second": 28.232,
+      "step": 216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.6103502735474484e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 6
+  }
+}

run-3/checkpoint-216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc97d4fded77640ee20a5deba4627ded60c972cf60dd6d6c19e1214346bf5c66
+size 4920

run-3/checkpoint-270/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "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": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "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,
+  "vocab_size": 30522
+}

run-3/checkpoint-270/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a2c17bc9d87b8143082f24f5be0029f79fd313c910d347877b7c483915addc6
+size 98470112

run-3/checkpoint-270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bb59a0437619462e22672017e9657acea9d24429718a867fec9221d581c78a0
+size 197593757

run-3/checkpoint-270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1fc33b1ee8e300f7c89ce269a0d25460f295944da1e930073487c841a79c04c
+size 14244