Training in progress, epoch 1

logs/events.out.tfevents.1713973393.a9ae8da52b57.4950.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6cfd2df60169c60d99ac7c37ef79f042c8bea3c3a6005cfb8379e374166a815
-size 5823
+oid sha256:5884cea3220b599634b62127ddbd4c691691ef6e0e74f216d014b257cdbc8542
+size 10449

logs/events.out.tfevents.1713975353.a9ae8da52b57.4950.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b34d9bd51abb61bd8c9d73b7258e7665f4bab04ce0eba3bd94e141b225fcfa97
+size 5287

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a555fc26382e3e24c0d6b0c6b72d659b25253f6fb995b820809a64dab6200ff
+oid sha256:6f62a77fc748cbccd1e5bc6df151f11af87401735f9b1cf222023246515a6a3f
 size 17549312

run-2/checkpoint-4743/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-4743/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe258fdc10504f106f011921b615f731af23ad2db266ccc5cc397c289983877
+size 17549312

run-2/checkpoint-4743/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68176a5b9541fc3ab31d2242791f23f92c7c9377777011b50d10f486c37e794
+size 35123898

run-2/checkpoint-4743/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e885d27ff12c2d8e7f8a71b358892ece6c7eb3e93a62ecf472a32cfaceabd844
+size 14308

run-2/checkpoint-4743/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b3b301c0e7db9669de23f2ed9bdba7f8f37aa31c52324803cbe07f0166627a
+size 1064

run-2/checkpoint-4743/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-4743/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-2/checkpoint-4743/trainer_state.json

@@ -0,0 +1,170 @@
+{
+  "best_metric": 0.8291284403669725,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-4743",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 4743,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.8070333003997803,
+      "learning_rate": 3.0759690838398e-05,
+      "loss": 0.8585,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7821100917431193,
+      "eval_loss": 0.7264055609703064,
+      "eval_runtime": 2.6688,
+      "eval_samples_per_second": 326.736,
+      "eval_steps_per_second": 2.623,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.853734016418457,
+      "learning_rate": 2.7341947411909336e-05,
+      "loss": 0.593,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.6605227589607239,
+      "eval_runtime": 2.6986,
+      "eval_samples_per_second": 323.129,
+      "eval_steps_per_second": 2.594,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 16.325355529785156,
+      "learning_rate": 2.3924203985420664e-05,
+      "loss": 0.4923,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.6577484607696533,
+      "eval_runtime": 2.7139,
+      "eval_samples_per_second": 321.31,
+      "eval_steps_per_second": 2.579,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.374361038208008,
+      "learning_rate": 2.0506460558932e-05,
+      "loss": 0.4294,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 0.6493772268295288,
+      "eval_runtime": 2.6649,
+      "eval_samples_per_second": 327.215,
+      "eval_steps_per_second": 2.627,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.613460540771484,
+      "learning_rate": 1.7088717132443333e-05,
+      "loss": 0.3898,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 0.646411657333374,
+      "eval_runtime": 2.676,
+      "eval_samples_per_second": 325.862,
+      "eval_steps_per_second": 2.616,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 17.64072036743164,
+      "learning_rate": 1.3670973705954668e-05,
+      "loss": 0.3578,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.6898267269134521,
+      "eval_runtime": 2.721,
+      "eval_samples_per_second": 320.465,
+      "eval_steps_per_second": 2.573,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": Infinity,
+      "learning_rate": 1.025971556111019e-05,
+      "loss": 0.3419,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.68783038854599,
+      "eval_runtime": 2.7146,
+      "eval_samples_per_second": 321.231,
+      "eval_steps_per_second": 2.579,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 17.84471893310547,
+      "learning_rate": 6.841972134621525e-06,
+      "loss": 0.3264,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 0.693118691444397,
+      "eval_runtime": 2.6725,
+      "eval_samples_per_second": 326.285,
+      "eval_steps_per_second": 2.619,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.189917087554932,
+      "learning_rate": 3.4242287081328577e-06,
+      "loss": 0.3183,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.6944125294685364,
+      "eval_runtime": 2.7271,
+      "eval_samples_per_second": 319.754,
+      "eval_steps_per_second": 2.567,
+      "step": 4743
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 72758802681960.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9025220801031371,
+    "learning_rate": 3.4177434264886666e-05,
+    "num_train_epochs": 10,
+    "temperature": 12
+  }
+}

run-2/checkpoint-4743/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0beebefb12d041f1dcf06515119df79f0753e043a91d5e458722b2ea9abc44
+size 5048

run-2/checkpoint-5270/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-2/checkpoint-5270/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdba3ff1f6d40de4b5c1cf255b9ada327a84fdf0ff0ae61df6a8e80ead192c89
+size 17549312

run-2/checkpoint-5270/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae97aba917a664ee2ae6d9165718183ebf535a1d0b13b5a612d03c84752175a
+size 35123898

run-2/checkpoint-5270/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efea672fc4415b5b349722f101aff1306be4cda4be519dae5562cf04dac04afe
+size 14308

run-2/checkpoint-5270/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42057073822960001368e03cb6413b55070450184e7c3885baf6d3e6e90ec5da
+size 1064

run-2/checkpoint-5270/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-5270/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-2/checkpoint-5270/trainer_state.json

@@ -0,0 +1,186 @@
+{
+  "best_metric": 0.8291284403669725,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-4743",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 5270,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.8070333003997803,
+      "learning_rate": 3.0759690838398e-05,
+      "loss": 0.8585,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7821100917431193,
+      "eval_loss": 0.7264055609703064,
+      "eval_runtime": 2.6688,
+      "eval_samples_per_second": 326.736,
+      "eval_steps_per_second": 2.623,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.853734016418457,
+      "learning_rate": 2.7341947411909336e-05,
+      "loss": 0.593,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.6605227589607239,
+      "eval_runtime": 2.6986,
+      "eval_samples_per_second": 323.129,
+      "eval_steps_per_second": 2.594,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 16.325355529785156,
+      "learning_rate": 2.3924203985420664e-05,
+      "loss": 0.4923,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.6577484607696533,
+      "eval_runtime": 2.7139,
+      "eval_samples_per_second": 321.31,
+      "eval_steps_per_second": 2.579,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.374361038208008,
+      "learning_rate": 2.0506460558932e-05,
+      "loss": 0.4294,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 0.6493772268295288,
+      "eval_runtime": 2.6649,
+      "eval_samples_per_second": 327.215,
+      "eval_steps_per_second": 2.627,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.613460540771484,
+      "learning_rate": 1.7088717132443333e-05,
+      "loss": 0.3898,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 0.646411657333374,
+      "eval_runtime": 2.676,
+      "eval_samples_per_second": 325.862,
+      "eval_steps_per_second": 2.616,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 17.64072036743164,
+      "learning_rate": 1.3670973705954668e-05,
+      "loss": 0.3578,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.6898267269134521,
+      "eval_runtime": 2.721,
+      "eval_samples_per_second": 320.465,
+      "eval_steps_per_second": 2.573,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": Infinity,
+      "learning_rate": 1.025971556111019e-05,
+      "loss": 0.3419,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.68783038854599,
+      "eval_runtime": 2.7146,
+      "eval_samples_per_second": 321.231,
+      "eval_steps_per_second": 2.579,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 17.84471893310547,
+      "learning_rate": 6.841972134621525e-06,
+      "loss": 0.3264,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 0.693118691444397,
+      "eval_runtime": 2.6725,
+      "eval_samples_per_second": 326.285,
+      "eval_steps_per_second": 2.619,
+      "step": 4216
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 4.189917087554932,
+      "learning_rate": 3.4242287081328577e-06,
+      "loss": 0.3183,
+      "step": 4743
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 0.6944125294685364,
+      "eval_runtime": 2.7271,
+      "eval_samples_per_second": 319.754,
+      "eval_steps_per_second": 2.567,
+      "step": 4743
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 9.059575080871582,
+      "learning_rate": 6.4852816441910186e-09,
+      "loss": 0.3142,
+      "step": 5270
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 0.6985101699829102,
+      "eval_runtime": 2.7236,
+      "eval_samples_per_second": 320.16,
+      "eval_steps_per_second": 2.57,
+      "step": 5270
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 80830646058420.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9025220801031371,
+    "learning_rate": 3.4177434264886666e-05,
+    "num_train_epochs": 10,
+    "temperature": 12
+  }
+}

run-2/checkpoint-5270/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0beebefb12d041f1dcf06515119df79f0753e043a91d5e458722b2ea9abc44
+size 5048

run-3/checkpoint-527/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f62a77fc748cbccd1e5bc6df151f11af87401735f9b1cf222023246515a6a3f
+size 17549312

run-3/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83905812c39e6f39a5e32c21ad39650a1882697eb2cbab5845679d29a0307192
+size 35123898

run-3/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
+size 14308

run-3/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da042e1d45e62e8e94893384e2c446bc1361c3e752340ec02ae038f59fc664d
+size 1064

run-3/checkpoint-527/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-527/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-3/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.805045871559633,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.870479583740234,
+      "learning_rate": 8.893046706823292e-05,
+      "loss": 1.9749,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 1.55028235912323,
+      "eval_runtime": 2.6975,
+      "eval_samples_per_second": 323.263,
+      "eval_steps_per_second": 2.595,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.31543852233103564,
+    "learning_rate": 0.0001016348195065519,
+    "num_train_epochs": 8,
+    "temperature": 11
+  }
+}

run-3/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da24167155160cf44b77d966c48df19607917d58321b47eb6a2d952430ef1c52
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0beebefb12d041f1dcf06515119df79f0753e043a91d5e458722b2ea9abc44
+oid sha256:da24167155160cf44b77d966c48df19607917d58321b47eb6a2d952430ef1c52
 size 5048