Training in progress, epoch 1

logs/events.out.tfevents.1709741707.d65e8524b0f6.5185.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a363d36fbe5e4f6c01510ea4374bb7e8d7acfb9a4345ed21ca4fe1550b32962
-size 5984
+oid sha256:f52da54b80e8c8833f41c943eb8f7c30e11872c3624b946017a3b6ce09e9e6e4
+size 10436

logs/events.out.tfevents.1709742573.d65e8524b0f6.5185.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96748cdfcd06c6c426eb94a6f81a99bcc47d02a19f74d08588633d31d394483e
+size 5327

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97780c69f05de76f9d89d5b245a3979297519b2bb08ee6e324817933a1e9732d
+oid sha256:aa4a2dbb12f15a9bce478c0731de2b246c40960f0a4c70a62b930099e4c5a821
 size 17549312

run-6/checkpoint-300/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae679e9f6447ce13cd3a60eecfa5d3bb5f51619277a01ebe9859a32ca4dc988
+size 17549312

run-6/checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbae545a38dcd29e3555c7d921301162c45111097e3ee2f5f5dd3d5ba870414
+size 35122746

run-6/checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ee249217b03322429e44fe94b312e6213830e42cccc74ae577663391edccef
+size 14054

run-6/checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d99d99d45e1ea5a1b97fe0a1f9582ae3e0ff5613a4b7981bebc93ef59262fe9
+size 1064

run-6/checkpoint-300/special_tokens_map.json

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

run-6/checkpoint-300/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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-300/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.7367906066536204,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/checkpoint-300",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0887755155563354,
+      "learning_rate": 0.0002701514784814016,
+      "loss": 0.3405,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5440313111545988,
+      "eval_f1": 0.21548821548821548,
+      "eval_loss": 0.3118150532245636,
+      "eval_precision": 0.7710843373493976,
+      "eval_recall": 0.12524461839530332,
+      "eval_runtime": 28.2208,
+      "eval_samples_per_second": 36.214,
+      "eval_steps_per_second": 1.134,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1933519840240479,
+      "learning_rate": 0.00023155841012691565,
+      "loss": 0.3081,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6154598825831703,
+      "eval_f1": 0.43776824034334766,
+      "eval_loss": 0.2966625690460205,
+      "eval_precision": 0.8138297872340425,
+      "eval_recall": 0.299412915851272,
+      "eval_runtime": 28.3705,
+      "eval_samples_per_second": 36.023,
+      "eval_steps_per_second": 1.128,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.296247124671936,
+      "learning_rate": 0.00019296534177242969,
+      "loss": 0.2998,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6379647749510763,
+      "eval_f1": 0.4917582417582418,
+      "eval_loss": 0.29152899980545044,
+      "eval_precision": 0.8248847926267281,
+      "eval_recall": 0.350293542074364,
+      "eval_runtime": 28.0611,
+      "eval_samples_per_second": 36.421,
+      "eval_steps_per_second": 1.14,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9188393950462341,
+      "learning_rate": 0.00015437227341794375,
+      "loss": 0.2935,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5724070450097848,
+      "eval_f1": 0.2962962962962963,
+      "eval_loss": 0.29398053884506226,
+      "eval_precision": 0.8363636363636363,
+      "eval_recall": 0.18003913894324852,
+      "eval_runtime": 27.6467,
+      "eval_samples_per_second": 36.966,
+      "eval_steps_per_second": 1.157,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5853505730628967,
+      "learning_rate": 0.00011577920506345782,
+      "loss": 0.291,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7270058708414873,
+      "eval_f1": 0.6698224852071005,
+      "eval_loss": 0.29069557785987854,
+      "eval_precision": 0.8473053892215568,
+      "eval_recall": 0.5538160469667319,
+      "eval_runtime": 28.5484,
+      "eval_samples_per_second": 35.799,
+      "eval_steps_per_second": 1.121,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0324815511703491,
+      "learning_rate": 7.718613670897188e-05,
+      "loss": 0.2884,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7367906066536204,
+      "eval_f1": 0.6911595866819747,
+      "eval_loss": 0.2900073230266571,
+      "eval_precision": 0.8361111111111111,
+      "eval_recall": 0.589041095890411,
+      "eval_runtime": 28.0011,
+      "eval_samples_per_second": 36.499,
+      "eval_steps_per_second": 1.143,
+      "step": 300
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1414171183680.0,
+  "train_batch_size": 62,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.43186153278710804,
+    "learning_rate": 0.0003087445468358875,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 62,
+    "temperature": 10
+  }
+}

run-6/checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3160888fc83e22e4969d14bdc1e1ab59cf563521f038a2cd8ce1deb5244204
+size 4920

run-6/checkpoint-400/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64083a97a25bbe6a9b6883e44b4c00456c19567209f6488484e5ae656295ff4d
+size 17549312

run-6/checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f481352f5dbe5b960cfd80ca1cd86a17ddcc4ee78d1af26d15e7a80487121ba
+size 35122746

run-6/checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e051b23e2c830076efea051830e83dfccd95c592633e98b1c2225c16c5d345
+size 14054

run-6/checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae38adba2a1dd06b489c4ab4d7913f6e61c9f8164accf94c8f6d5358538c17a7
+size 1064

run-6/checkpoint-400/special_tokens_map.json

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

run-6/checkpoint-400/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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-400/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.7367906066536204,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/checkpoint-300",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0887755155563354,
+      "learning_rate": 0.0002701514784814016,
+      "loss": 0.3405,
+      "step": 50
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5440313111545988,
+      "eval_f1": 0.21548821548821548,
+      "eval_loss": 0.3118150532245636,
+      "eval_precision": 0.7710843373493976,
+      "eval_recall": 0.12524461839530332,
+      "eval_runtime": 28.2208,
+      "eval_samples_per_second": 36.214,
+      "eval_steps_per_second": 1.134,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.1933519840240479,
+      "learning_rate": 0.00023155841012691565,
+      "loss": 0.3081,
+      "step": 100
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6154598825831703,
+      "eval_f1": 0.43776824034334766,
+      "eval_loss": 0.2966625690460205,
+      "eval_precision": 0.8138297872340425,
+      "eval_recall": 0.299412915851272,
+      "eval_runtime": 28.3705,
+      "eval_samples_per_second": 36.023,
+      "eval_steps_per_second": 1.128,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.296247124671936,
+      "learning_rate": 0.00019296534177242969,
+      "loss": 0.2998,
+      "step": 150
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6379647749510763,
+      "eval_f1": 0.4917582417582418,
+      "eval_loss": 0.29152899980545044,
+      "eval_precision": 0.8248847926267281,
+      "eval_recall": 0.350293542074364,
+      "eval_runtime": 28.0611,
+      "eval_samples_per_second": 36.421,
+      "eval_steps_per_second": 1.14,
+      "step": 150
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.9188393950462341,
+      "learning_rate": 0.00015437227341794375,
+      "loss": 0.2935,
+      "step": 200
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5724070450097848,
+      "eval_f1": 0.2962962962962963,
+      "eval_loss": 0.29398053884506226,
+      "eval_precision": 0.8363636363636363,
+      "eval_recall": 0.18003913894324852,
+      "eval_runtime": 27.6467,
+      "eval_samples_per_second": 36.966,
+      "eval_steps_per_second": 1.157,
+      "step": 200
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5853505730628967,
+      "learning_rate": 0.00011577920506345782,
+      "loss": 0.291,
+      "step": 250
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7270058708414873,
+      "eval_f1": 0.6698224852071005,
+      "eval_loss": 0.29069557785987854,
+      "eval_precision": 0.8473053892215568,
+      "eval_recall": 0.5538160469667319,
+      "eval_runtime": 28.5484,
+      "eval_samples_per_second": 35.799,
+      "eval_steps_per_second": 1.121,
+      "step": 250
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.0324815511703491,
+      "learning_rate": 7.718613670897188e-05,
+      "loss": 0.2884,
+      "step": 300
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7367906066536204,
+      "eval_f1": 0.6911595866819747,
+      "eval_loss": 0.2900073230266571,
+      "eval_precision": 0.8361111111111111,
+      "eval_recall": 0.589041095890411,
+      "eval_runtime": 28.0011,
+      "eval_samples_per_second": 36.499,
+      "eval_steps_per_second": 1.143,
+      "step": 300
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.71778804063797,
+      "learning_rate": 3.859306835448594e-05,
+      "loss": 0.2865,
+      "step": 350
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7270058708414873,
+      "eval_f1": 0.6690391459074733,
+      "eval_loss": 0.2876945436000824,
+      "eval_precision": 0.8493975903614458,
+      "eval_recall": 0.5518590998043053,
+      "eval_runtime": 28.1437,
+      "eval_samples_per_second": 36.314,
+      "eval_steps_per_second": 1.137,
+      "step": 350
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.9981019496917725,
+      "learning_rate": 0.0,
+      "loss": 0.2859,
+      "step": 400
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7113502935420744,
+      "eval_f1": 0.6380368098159509,
+      "eval_loss": 0.28506672382354736,
+      "eval_precision": 0.8552631578947368,
+      "eval_recall": 0.5088062622309197,
+      "eval_runtime": 28.385,
+      "eval_samples_per_second": 36.005,
+      "eval_steps_per_second": 1.127,
+      "step": 400
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1885561578240.0,
+  "train_batch_size": 62,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.43186153278710804,
+    "learning_rate": 0.0003087445468358875,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 62,
+    "temperature": 10
+  }
+}

run-6/checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3160888fc83e22e4969d14bdc1e1ab59cf563521f038a2cd8ce1deb5244204
+size 4920

run-7/checkpoint-146/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-7/checkpoint-146/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4a2dbb12f15a9bce478c0731de2b246c40960f0a4c70a62b930099e4c5a821
+size 17549312

run-7/checkpoint-146/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4137182fd1e164a4cf9cea8ea27ad337d13045cd646eb5da8160d2172ad31f05
+size 35122746

run-7/checkpoint-146/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48d98163df5dbaa8ee8cc5c2cf33fca19facaccb0f11991aefb0abdd15b12af
+size 14054

run-7/checkpoint-146/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1afcb4b63b3ef7d87b7d0ad141cf22d611013195c04981070df52c60b135990
+size 1064

run-7/checkpoint-146/special_tokens_map.json

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

run-7/checkpoint-146/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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-7/checkpoint-146/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5420743639921722,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-7/checkpoint-146",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 146,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4084218442440033,
+      "learning_rate": 0.0002846359367487843,
+      "loss": 0.0564,
+      "step": 146
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5420743639921722,
+      "eval_f1": 0.21212121212121213,
+      "eval_loss": 0.042483557015657425,
+      "eval_precision": 0.7590361445783133,
+      "eval_recall": 0.1232876712328767,
+      "eval_runtime": 28.2636,
+      "eval_samples_per_second": 36.16,
+      "eval_steps_per_second": 1.132,
+      "step": 146
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 876,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 21,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.04464648890006717,
+    "learning_rate": 0.0003415631240985412,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 21,
+    "temperature": 2
+  }
+}

run-7/checkpoint-146/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fccab1cf160e9a976a6e2833e6b2e52a870fecc8101aaab94f3f44ebbc487e
+size 4920

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 33,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e3fa9f35ba1a109d4dbcaa99a0da7b79ffac3932fc22f17787de76b9701cac
+oid sha256:28fccab1cf160e9a976a6e2833e6b2e52a870fecc8101aaab94f3f44ebbc487e
 size 4920