Training in progress, epoch 1

logs/events.out.tfevents.1709737266.d65e8524b0f6.5185.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baf1422e381ab1138117c0e5242460e468af07f0534fdf6cd6579a203aebc074
-size 5997
+oid sha256:888ba986aaa291c3e5aab830aac71b9445affefd5f402f23d99f461e76fd2c7c
+size 11132

logs/events.out.tfevents.1709738331.d65e8524b0f6.5185.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a832e88c13a09772625ac9a420dc9c61014c73ebcee30fedb4bebfafc8b4a9c
+size 5313

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691fe6dae22dbcf425f6968004894acb3404da27e32c1c6aaa864221b6e71a6b
+oid sha256:b6b90a79be3ca94339f890984d53c30a13bcbdd8c2e140c3b6788efc13abf1ee
 size 17549312

run-0/checkpoint-486/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-0/checkpoint-486/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee05f8b9be0f5453e83844876ef2a8b21e389a1505be4377f9c6c6ec187d0e29
+size 17549312

run-0/checkpoint-486/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b600161b641adc4c5f19b980a57aec95951fcc4412b3024ff2f141dcbc09e0d7
+size 35122746

run-0/checkpoint-486/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c3673de8a74b585e61908dcf9f2cd648f988d9cb931bd93ef977a62b7245ce
+size 14054

run-0/checkpoint-486/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08be0c070f1ede228cbd9d552c6f6005293f9fd7637a074eebee603b59f600ac
+size 1064

run-0/checkpoint-486/special_tokens_map.json

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

run-0/checkpoint-486/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-0/checkpoint-486/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.6604696673189824,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-486",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 486,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.29800447821617126,
+      "learning_rate": 2.6647930950340397e-05,
+      "loss": 0.3887,
+      "step": 81
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.3728242516517639,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 30.0921,
+      "eval_samples_per_second": 33.962,
+      "eval_steps_per_second": 1.063,
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0294488668441772,
+      "learning_rate": 2.331693958154785e-05,
+      "loss": 0.3659,
+      "step": 162
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5371819960861057,
+      "eval_f1": 0.19145299145299144,
+      "eval_loss": 0.35036981105804443,
+      "eval_precision": 0.7567567567567568,
+      "eval_recall": 0.1095890410958904,
+      "eval_runtime": 30.0254,
+      "eval_samples_per_second": 34.038,
+      "eval_steps_per_second": 1.066,
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3886942863464355,
+      "learning_rate": 1.99859482127553e-05,
+      "loss": 0.3406,
+      "step": 243
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5802348336594912,
+      "eval_f1": 0.32863849765258213,
+      "eval_loss": 0.32384729385375977,
+      "eval_precision": 0.8203125,
+      "eval_recall": 0.2054794520547945,
+      "eval_runtime": 29.2219,
+      "eval_samples_per_second": 34.974,
+      "eval_steps_per_second": 1.095,
+      "step": 243
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.869124174118042,
+      "learning_rate": 1.665495684396275e-05,
+      "loss": 0.3253,
+      "step": 324
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6360078277886497,
+      "eval_f1": 0.48901098901098894,
+      "eval_loss": 0.31458520889282227,
+      "eval_precision": 0.8202764976958525,
+      "eval_recall": 0.34833659491193736,
+      "eval_runtime": 29.7469,
+      "eval_samples_per_second": 34.356,
+      "eval_steps_per_second": 1.076,
+      "step": 324
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3957839012145996,
+      "learning_rate": 1.3323965475170199e-05,
+      "loss": 0.3227,
+      "step": 405
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6487279843444227,
+      "eval_f1": 0.521970705725699,
+      "eval_loss": 0.3122331500053406,
+      "eval_precision": 0.8166666666666667,
+      "eval_recall": 0.3835616438356164,
+      "eval_runtime": 29.6103,
+      "eval_samples_per_second": 34.515,
+      "eval_steps_per_second": 1.081,
+      "step": 405
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.8226208686828613,
+      "learning_rate": 9.99297410637765e-06,
+      "loss": 0.3203,
+      "step": 486
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6604696673189824,
+      "eval_f1": 0.5522580645161289,
+      "eval_loss": 0.31177300214767456,
+      "eval_precision": 0.8106060606060606,
+      "eval_recall": 0.4187866927592955,
+      "eval_runtime": 29.3492,
+      "eval_samples_per_second": 34.822,
+      "eval_steps_per_second": 1.09,
+      "step": 486
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 729,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1414171183680.0,
+  "train_batch_size": 38,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.462182377373202,
+    "learning_rate": 2.997892231913295e-05,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 38,
+    "temperature": 10
+  }
+}

run-0/checkpoint-486/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c234fefe2007f16535ef723e1425baa7c9b3f0aec93243168de7f22031da2d1
+size 4920

run-0/checkpoint-729/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-0/checkpoint-729/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f41950eb38a99a667d1a671cbab9b140855a4852b2a59e9119099d8a781bc57
+size 17549312

run-0/checkpoint-729/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83dc4ac52f75802a7f908a63d841fdeacb6e399a96044fa1566cb86f7179b931
+size 35122746

run-0/checkpoint-729/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725d98176e939e32dfbdc9cd657bec028fe2a4a82c3583ea2a6c767d457a7576
+size 14054

run-0/checkpoint-729/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9eab59d94a98d7f65a98e191d9ad61c61449e320e760878080ced2876690ba
+size 1064

run-0/checkpoint-729/special_tokens_map.json

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

run-0/checkpoint-729/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-0/checkpoint-729/trainer_state.json

@@ -0,0 +1,198 @@
+{
+  "best_metric": 0.6604696673189824,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-486",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 729,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.29800447821617126,
+      "learning_rate": 2.6647930950340397e-05,
+      "loss": 0.3887,
+      "step": 81
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.0,
+      "eval_loss": 0.3728242516517639,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 30.0921,
+      "eval_samples_per_second": 33.962,
+      "eval_steps_per_second": 1.063,
+      "step": 81
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.0294488668441772,
+      "learning_rate": 2.331693958154785e-05,
+      "loss": 0.3659,
+      "step": 162
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5371819960861057,
+      "eval_f1": 0.19145299145299144,
+      "eval_loss": 0.35036981105804443,
+      "eval_precision": 0.7567567567567568,
+      "eval_recall": 0.1095890410958904,
+      "eval_runtime": 30.0254,
+      "eval_samples_per_second": 34.038,
+      "eval_steps_per_second": 1.066,
+      "step": 162
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3886942863464355,
+      "learning_rate": 1.99859482127553e-05,
+      "loss": 0.3406,
+      "step": 243
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5802348336594912,
+      "eval_f1": 0.32863849765258213,
+      "eval_loss": 0.32384729385375977,
+      "eval_precision": 0.8203125,
+      "eval_recall": 0.2054794520547945,
+      "eval_runtime": 29.2219,
+      "eval_samples_per_second": 34.974,
+      "eval_steps_per_second": 1.095,
+      "step": 243
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.869124174118042,
+      "learning_rate": 1.665495684396275e-05,
+      "loss": 0.3253,
+      "step": 324
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6360078277886497,
+      "eval_f1": 0.48901098901098894,
+      "eval_loss": 0.31458520889282227,
+      "eval_precision": 0.8202764976958525,
+      "eval_recall": 0.34833659491193736,
+      "eval_runtime": 29.7469,
+      "eval_samples_per_second": 34.356,
+      "eval_steps_per_second": 1.076,
+      "step": 324
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.3957839012145996,
+      "learning_rate": 1.3323965475170199e-05,
+      "loss": 0.3227,
+      "step": 405
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6487279843444227,
+      "eval_f1": 0.521970705725699,
+      "eval_loss": 0.3122331500053406,
+      "eval_precision": 0.8166666666666667,
+      "eval_recall": 0.3835616438356164,
+      "eval_runtime": 29.6103,
+      "eval_samples_per_second": 34.515,
+      "eval_steps_per_second": 1.081,
+      "step": 405
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.8226208686828613,
+      "learning_rate": 9.99297410637765e-06,
+      "loss": 0.3203,
+      "step": 486
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6604696673189824,
+      "eval_f1": 0.5522580645161289,
+      "eval_loss": 0.31177300214767456,
+      "eval_precision": 0.8106060606060606,
+      "eval_recall": 0.4187866927592955,
+      "eval_runtime": 29.3492,
+      "eval_samples_per_second": 34.822,
+      "eval_steps_per_second": 1.09,
+      "step": 486
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.4845212697982788,
+      "learning_rate": 6.661982737585099e-06,
+      "loss": 0.3188,
+      "step": 567
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6340508806262231,
+      "eval_f1": 0.48484848484848486,
+      "eval_loss": 0.3102571964263916,
+      "eval_precision": 0.8186046511627907,
+      "eval_recall": 0.34442270058708413,
+      "eval_runtime": 29.5252,
+      "eval_samples_per_second": 34.614,
+      "eval_steps_per_second": 1.084,
+      "step": 567
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.0866426229476929,
+      "learning_rate": 3.3309913687925497e-06,
+      "loss": 0.3164,
+      "step": 648
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6545988258317026,
+      "eval_f1": 0.5397653194263363,
+      "eval_loss": 0.3101910948753357,
+      "eval_precision": 0.80859375,
+      "eval_recall": 0.4050880626223092,
+      "eval_runtime": 30.0772,
+      "eval_samples_per_second": 33.979,
+      "eval_steps_per_second": 1.064,
+      "step": 648
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.8858753442764282,
+      "learning_rate": 0.0,
+      "loss": 0.316,
+      "step": 729
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.649706457925636,
+      "eval_f1": 0.5289473684210527,
+      "eval_loss": 0.30977755784988403,
+      "eval_precision": 0.8072289156626506,
+      "eval_recall": 0.3933463796477495,
+      "eval_runtime": 30.1686,
+      "eval_samples_per_second": 33.876,
+      "eval_steps_per_second": 1.061,
+      "step": 729
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 729,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 2121256775520.0,
+  "train_batch_size": 38,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.462182377373202,
+    "learning_rate": 2.997892231913295e-05,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 38,
+    "temperature": 10
+  }
+}

run-0/checkpoint-729/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c234fefe2007f16535ef723e1425baa7c9b3f0aec93243168de7f22031da2d1
+size 4920

run-1/checkpoint-99/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-1/checkpoint-99/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b90a79be3ca94339f890984d53c30a13bcbdd8c2e140c3b6788efc13abf1ee
+size 17549312

run-1/checkpoint-99/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5035defd48ceda80dfd8eceb8d88c2dd770395c66cb4783c13c473fc0300b8
+size 35122746

run-1/checkpoint-99/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c205047444770f4773b4c7cd8498f63ed529253a37db59a0a7ad8b6427a8ae56
+size 14054

run-1/checkpoint-99/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c87cf4b87dd895897b97899dbae84fa8bab5711ade1ebbd852a161546bda988
+size 1064

run-1/checkpoint-99/special_tokens_map.json

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

run-1/checkpoint-99/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-1/checkpoint-99/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5684931506849316,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-99",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 99,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8574622273445129,
+      "learning_rate": 0.0005047460143242413,
+      "loss": 0.4026,
+      "step": 99
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5684931506849316,
+      "eval_f1": 0.28985507246376807,
+      "eval_loss": 0.3736521005630493,
+      "eval_precision": 0.8181818181818182,
+      "eval_recall": 0.1761252446183953,
+      "eval_runtime": 30.2349,
+      "eval_samples_per_second": 33.802,
+      "eval_steps_per_second": 1.058,
+      "step": 99
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 297,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 31,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.571532167699631,
+    "learning_rate": 0.000757119021486362,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 31,
+    "temperature": 19
+  }
+}

run-1/checkpoint-99/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a22962199e8db5aed7f91cc38b31e6e9016a67071067e10647b0bbadfffa51
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c83b924ef70318ad972d6c481c684f04bf59974ceae562e8816ac4c289de55
+oid sha256:c9a22962199e8db5aed7f91cc38b31e6e9016a67071067e10647b0bbadfffa51
 size 4920