Training in progress, step 500

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": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

logs/events.out.tfevents.1722931054.e04c41ff77a6.336.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0b3d76d3ab902157f17e373806af0d73fc30fe664b25ba89bdb6c39c866282
+size 19252

logs/events.out.tfevents.1722932101.e04c41ff77a6.336.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d131633811bdd1d022a913d23a410fc2d31bec422680e04921e77717a62d3c
+size 19892

logs/events.out.tfevents.1722933484.e04c41ff77a6.336.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c77c933280fdcae383a9e68a5c8f8b8ffb5ef576f78a07c54f5b68e5225b26
+size 6023

logs/events.out.tfevents.1722933589.e04c41ff77a6.336.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a8813559f17f881926cc652c10514bce5f4d335034ac7bba5083a00f4f5e4e7
+size 4965

logs/events.out.tfevents.1722933640.e04c41ff77a6.336.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b6ae0748d54d1722a37e4e20533c89e1568dd7106c30334e635fbd0d742197
+size 13319

logs/events.out.tfevents.1722934212.e04c41ff77a6.336.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6d4d0ce8038e9d3d94fb013dccc40c8970e17645486bb739347a9c9fe293dfc
+size 10651

logs/events.out.tfevents.1722934596.e04c41ff77a6.336.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac13678f38d28f98eb51c768af6137f20096101635b4b44f65256edb3aafc143
+size 13319

logs/events.out.tfevents.1722935168.e04c41ff77a6.336.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b127376c85acd0dce610d7783eaf6517764c028a12961360cef67615bcb005d
+size 19194

logs/events.out.tfevents.1722936122.e04c41ff77a6.336.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:196bb1cfd87f28a11678a9c9cd1f77cadd945ad9b2e02cda28e83f7ca1f9f610
+size 10650

logs/events.out.tfevents.1722936514.e04c41ff77a6.336.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67bfd3e884c578a8aa8edfe5528cdafb3ee702f8192b988322a59c0eac3188ac
+size 5490

logs/events.out.tfevents.1722936550.e04c41ff77a6.336.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beff3f17b12c819e1173bd439496398f90e8aea517eedde779226663d321937b
+size 5490

logs/events.out.tfevents.1722936586.e04c41ff77a6.336.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706c2d960c5f11abd3bbdee91762e180b6f8fcc0a27e4559209d7f997aa5cd36
+size 5490

logs/events.out.tfevents.1722936621.e04c41ff77a6.336.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1f903d548ad32967eb368aa67f5ff827af515de2a4ef66f1cca58d3186785ec
+size 7091

logs/events.out.tfevents.1722936764.e04c41ff77a6.336.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a425787f8e966621105747f965d43754b29ab57d6101fa463b8c67e050841983
+size 7091

logs/events.out.tfevents.1722936954.e04c41ff77a6.336.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3cee075279045774d44dc80e2f9950660be9d317c2e70f2a5a68804e4a9b50
+size 10741

logs/events.out.tfevents.1722938062.e04c41ff77a6.336.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc9f0499024dcf8df470509a33ecade4c690f6ec3c7063eb0a82cad42f39b422
+size 7685

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0b50a7bd4175afee19f3b0f41ff9d038180d979fbe2df5489691317f5b2491
+size 17549312

run-0/checkpoint-1000/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": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cb8c0e30b457a05252f56ba5ddd342de48d44dbfdd76c029f676b33472fe02a
+size 17549312

run-0/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31c450729a57c05a7f14c9d2a3f1dbfba6381b016d94291cff973f23edd61b99
+size 35123898

run-0/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6c36e6cfde713b7d318184cedbf2b0e301159a504124877a79657a5ace6ecb
+size 14244

run-0/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6ef6f5890a520346297b5993f3a468c937120fc21fb6250c459639028e15d3
+size 1064

run-0/checkpoint-1000/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-1000/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-1000/trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": 0.7970183486238532,
+  "best_model_checkpoint": "tiny-bert-sst2/run-0/checkpoint-1000",
+  "epoch": 1.8975332068311195,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18975332068311196,
+      "grad_norm": 0.7187711000442505,
+      "learning_rate": 2.4275077059878603e-05,
+      "loss": 1.2604,
+      "step": 100
+    },
+    {
+      "epoch": 0.18975332068311196,
+      "eval_accuracy": 0.6169724770642202,
+      "eval_loss": 1.181114673614502,
+      "eval_runtime": 2.4577,
+      "eval_samples_per_second": 354.806,
+      "eval_steps_per_second": 2.848,
+      "step": 100
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "grad_norm": 1.8982616662979126,
+      "learning_rate": 2.3789299271608236e-05,
+      "loss": 1.1808,
+      "step": 200
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "eval_accuracy": 0.7121559633027523,
+      "eval_loss": 1.0743426084518433,
+      "eval_runtime": 2.4969,
+      "eval_samples_per_second": 349.235,
+      "eval_steps_per_second": 2.803,
+      "step": 200
+    },
+    {
+      "epoch": 0.5692599620493358,
+      "grad_norm": 2.6504175662994385,
+      "learning_rate": 2.2812529230666033e-05,
+      "loss": 1.0583,
+      "step": 300
+    },
+    {
+      "epoch": 0.5692599620493358,
+      "eval_accuracy": 0.7591743119266054,
+      "eval_loss": 0.9464107155799866,
+      "eval_runtime": 2.4114,
+      "eval_samples_per_second": 361.611,
+      "eval_steps_per_second": 2.903,
+      "step": 300
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "grad_norm": 2.9992282390594482,
+      "learning_rate": 2.138601927608547e-05,
+      "loss": 0.9339,
+      "step": 400
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.8676859736442566,
+      "eval_runtime": 2.5023,
+      "eval_samples_per_second": 348.476,
+      "eval_steps_per_second": 2.797,
+      "step": 400
+    },
+    {
+      "epoch": 0.9487666034155597,
+      "grad_norm": 2.979876756668091,
+      "learning_rate": 1.9570015801402756e-05,
+      "loss": 0.8783,
+      "step": 500
+    },
+    {
+      "epoch": 0.9487666034155597,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.836247980594635,
+      "eval_runtime": 2.4279,
+      "eval_samples_per_second": 359.162,
+      "eval_steps_per_second": 2.883,
+      "step": 500
+    },
+    {
+      "epoch": 1.1385199240986716,
+      "grad_norm": 3.8972060680389404,
+      "learning_rate": 1.7441214843436652e-05,
+      "loss": 0.8286,
+      "step": 600
+    },
+    {
+      "epoch": 1.1385199240986716,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.8169480562210083,
+      "eval_runtime": 2.4359,
+      "eval_samples_per_second": 357.985,
+      "eval_steps_per_second": 2.874,
+      "step": 600
+    },
+    {
+      "epoch": 1.3282732447817835,
+      "grad_norm": 4.094536304473877,
+      "learning_rate": 1.5089522946380597e-05,
+      "loss": 0.7808,
+      "step": 700
+    },
+    {
+      "epoch": 1.3282732447817835,
+      "eval_accuracy": 0.7878440366972477,
+      "eval_loss": 0.8050708770751953,
+      "eval_runtime": 2.4399,
+      "eval_samples_per_second": 357.397,
+      "eval_steps_per_second": 2.869,
+      "step": 700
+    },
+    {
+      "epoch": 1.5180265654648957,
+      "grad_norm": 6.467775344848633,
+      "learning_rate": 1.2614260100993157e-05,
+      "loss": 0.765,
+      "step": 800
+    },
+    {
+      "epoch": 1.5180265654648957,
+      "eval_accuracy": 0.7889908256880734,
+      "eval_loss": 0.7935003042221069,
+      "eval_runtime": 2.4349,
+      "eval_samples_per_second": 358.121,
+      "eval_steps_per_second": 2.875,
+      "step": 800
+    },
+    {
+      "epoch": 1.7077798861480076,
+      "grad_norm": 7.3176445960998535,
+      "learning_rate": 1.0119965121749416e-05,
+      "loss": 0.742,
+      "step": 900
+    },
+    {
+      "epoch": 1.7077798861480076,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.7913622260093689,
+      "eval_runtime": 2.505,
+      "eval_samples_per_second": 348.1,
+      "eval_steps_per_second": 2.794,
+      "step": 900
+    },
+    {
+      "epoch": 1.8975332068311195,
+      "grad_norm": 4.671020030975342,
+      "learning_rate": 7.711980615220306e-06,
+      "loss": 0.7379,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8975332068311195,
+      "eval_accuracy": 0.7970183486238532,
+      "eval_loss": 0.7775447964668274,
+      "eval_runtime": 2.4368,
+      "eval_samples_per_second": 357.839,
+      "eval_steps_per_second": 2.873,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1581,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 15348240276300.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8670086094179865,
+    "learning_rate": 2.432723709409012e-05,
+    "num_train_epochs": 3,
+    "temperature": 13,
+    "warmup_ratio": 0.03434495454544933
+  }
+}

run-0/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13ac8bd9d7d909b6ca7c92c43736d482f4dacbc0fe997a6e1760536a654848f
+size 5240

run-0/checkpoint-1500/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": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43043ea874abdba0f21dd5cef24eb9122cdc34a46513b4cc1ef3712873915f80
+size 17549312

run-0/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f634820cff3105d542eaacea5d62aafb6466b78c1534d182d50fc9b2e821d6
+size 35123898

run-0/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b5f7d6520a4fe62ffd553a2788d8b3d45cec7e270ca8ce56dd0afd6f16514d
+size 14244

run-0/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdff4cb64def19622d59a8f9199ee696765a6e017e1bcee21b47a8beb7bd39d6
+size 1064

run-0/checkpoint-1500/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-1500/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-1500/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_metric": 0.7981651376146789,
+  "best_model_checkpoint": "tiny-bert-sst2/run-0/checkpoint-1500",
+  "epoch": 2.846299810246679,
+  "eval_steps": 100,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18975332068311196,
+      "grad_norm": 0.7187711000442505,
+      "learning_rate": 2.4275077059878603e-05,
+      "loss": 1.2604,
+      "step": 100
+    },
+    {
+      "epoch": 0.18975332068311196,
+      "eval_accuracy": 0.6169724770642202,
+      "eval_loss": 1.181114673614502,
+      "eval_runtime": 2.4577,
+      "eval_samples_per_second": 354.806,
+      "eval_steps_per_second": 2.848,
+      "step": 100
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "grad_norm": 1.8982616662979126,
+      "learning_rate": 2.3789299271608236e-05,
+      "loss": 1.1808,
+      "step": 200
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "eval_accuracy": 0.7121559633027523,
+      "eval_loss": 1.0743426084518433,
+      "eval_runtime": 2.4969,
+      "eval_samples_per_second": 349.235,
+      "eval_steps_per_second": 2.803,
+      "step": 200
+    },
+    {
+      "epoch": 0.5692599620493358,
+      "grad_norm": 2.6504175662994385,
+      "learning_rate": 2.2812529230666033e-05,
+      "loss": 1.0583,
+      "step": 300
+    },
+    {
+      "epoch": 0.5692599620493358,
+      "eval_accuracy": 0.7591743119266054,
+      "eval_loss": 0.9464107155799866,
+      "eval_runtime": 2.4114,
+      "eval_samples_per_second": 361.611,
+      "eval_steps_per_second": 2.903,
+      "step": 300
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "grad_norm": 2.9992282390594482,
+      "learning_rate": 2.138601927608547e-05,
+      "loss": 0.9339,
+      "step": 400
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.8676859736442566,
+      "eval_runtime": 2.5023,
+      "eval_samples_per_second": 348.476,
+      "eval_steps_per_second": 2.797,
+      "step": 400
+    },
+    {
+      "epoch": 0.9487666034155597,
+      "grad_norm": 2.979876756668091,
+      "learning_rate": 1.9570015801402756e-05,
+      "loss": 0.8783,
+      "step": 500
+    },
+    {
+      "epoch": 0.9487666034155597,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.836247980594635,
+      "eval_runtime": 2.4279,
+      "eval_samples_per_second": 359.162,
+      "eval_steps_per_second": 2.883,
+      "step": 500
+    },
+    {
+      "epoch": 1.1385199240986716,
+      "grad_norm": 3.8972060680389404,
+      "learning_rate": 1.7441214843436652e-05,
+      "loss": 0.8286,
+      "step": 600
+    },
+    {
+      "epoch": 1.1385199240986716,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.8169480562210083,
+      "eval_runtime": 2.4359,
+      "eval_samples_per_second": 357.985,
+      "eval_steps_per_second": 2.874,
+      "step": 600
+    },
+    {
+      "epoch": 1.3282732447817835,
+      "grad_norm": 4.094536304473877,
+      "learning_rate": 1.5089522946380597e-05,
+      "loss": 0.7808,
+      "step": 700
+    },
+    {
+      "epoch": 1.3282732447817835,
+      "eval_accuracy": 0.7878440366972477,
+      "eval_loss": 0.8050708770751953,
+      "eval_runtime": 2.4399,
+      "eval_samples_per_second": 357.397,
+      "eval_steps_per_second": 2.869,
+      "step": 700
+    },
+    {
+      "epoch": 1.5180265654648957,
+      "grad_norm": 6.467775344848633,
+      "learning_rate": 1.2614260100993157e-05,
+      "loss": 0.765,
+      "step": 800
+    },
+    {
+      "epoch": 1.5180265654648957,
+      "eval_accuracy": 0.7889908256880734,
+      "eval_loss": 0.7935003042221069,
+      "eval_runtime": 2.4349,
+      "eval_samples_per_second": 358.121,
+      "eval_steps_per_second": 2.875,
+      "step": 800
+    },
+    {
+      "epoch": 1.7077798861480076,
+      "grad_norm": 7.3176445960998535,
+      "learning_rate": 1.0119965121749416e-05,
+      "loss": 0.742,
+      "step": 900
+    },
+    {
+      "epoch": 1.7077798861480076,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.7913622260093689,
+      "eval_runtime": 2.505,
+      "eval_samples_per_second": 348.1,
+      "eval_steps_per_second": 2.794,
+      "step": 900
+    },
+    {
+      "epoch": 1.8975332068311195,
+      "grad_norm": 4.671020030975342,
+      "learning_rate": 7.711980615220306e-06,
+      "loss": 0.7379,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8975332068311195,
+      "eval_accuracy": 0.7970183486238532,
+      "eval_loss": 0.7775447964668274,
+      "eval_runtime": 2.4368,
+      "eval_samples_per_second": 357.839,
+      "eval_steps_per_second": 2.873,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0872865275142316,
+      "grad_norm": 3.548794984817505,
+      "learning_rate": 5.492004001563045e-06,
+      "loss": 0.7169,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0872865275142316,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.7763888239860535,
+      "eval_runtime": 2.4327,
+      "eval_samples_per_second": 358.447,
+      "eval_steps_per_second": 2.877,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2770398481973433,
+      "grad_norm": 2.657698392868042,
+      "learning_rate": 3.5537924846990686e-06,
+      "loss": 0.7053,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2770398481973433,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 0.7718890905380249,
+      "eval_runtime": 2.4731,
+      "eval_samples_per_second": 352.601,
+      "eval_steps_per_second": 2.831,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4667931688804554,
+      "grad_norm": 8.931977272033691,
+      "learning_rate": 1.9792033649762944e-06,
+      "loss": 0.7001,
+      "step": 1300
+    },
+    {
+      "epoch": 2.4667931688804554,
+      "eval_accuracy": 0.7958715596330275,
+      "eval_loss": 0.7761191129684448,
+      "eval_runtime": 2.4453,
+      "eval_samples_per_second": 356.608,
+      "eval_steps_per_second": 2.863,
+      "step": 1300
+    },
+    {
+      "epoch": 2.656546489563567,
+      "grad_norm": 5.575241565704346,
+      "learning_rate": 8.347369254527042e-07,
+      "loss": 0.6988,
+      "step": 1400
+    },
+    {
+      "epoch": 2.656546489563567,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.7722569108009338,
+      "eval_runtime": 2.492,
+      "eval_samples_per_second": 349.916,
+      "eval_steps_per_second": 2.809,
+      "step": 1400
+    },
+    {
+      "epoch": 2.846299810246679,
+      "grad_norm": 6.262284278869629,
+      "learning_rate": 1.6872789753562043e-07,
+      "loss": 0.7135,
+      "step": 1500
+    },
+    {
+      "epoch": 2.846299810246679,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.7717686891555786,
+      "eval_runtime": 2.443,
+      "eval_samples_per_second": 356.945,
+      "eval_steps_per_second": 2.865,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1581,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 23032282372320.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8670086094179865,
+    "learning_rate": 2.432723709409012e-05,
+    "num_train_epochs": 3,
+    "temperature": 13,
+    "warmup_ratio": 0.03434495454544933
+  }
+}

run-0/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13ac8bd9d7d909b6ca7c92c43736d482f4dacbc0fe997a6e1760536a654848f
+size 5240

run-0/checkpoint-1581/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": "4.43.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14329b99347952dbe663cde12a2ce6b60addc3a44a079e557314f9cc1938bbdc
+size 17549312

run-0/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958dee26f9b52fe7d248a0a3f6a9992ec067bb77e768e0cfb84a189e6ec3a71a
+size 35123898

run-0/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:500e46e3000dbe3b0d1b816b0b22c728e6ae48546c227ef671208deca89f6ee6
+size 14244

run-0/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b88526ab27fa08f283c42f464e9f33716cc03da0d3e2bdd6607a7e2b59fea01
+size 1064

run-0/checkpoint-1581/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-1581/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-1581/trainer_state.json

@@ -0,0 +1,279 @@
+{
+  "best_metric": 0.7981651376146789,
+  "best_model_checkpoint": "tiny-bert-sst2/run-0/checkpoint-1500",
+  "epoch": 3.0,
+  "eval_steps": 100,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18975332068311196,
+      "grad_norm": 0.7187711000442505,
+      "learning_rate": 2.4275077059878603e-05,
+      "loss": 1.2604,
+      "step": 100
+    },
+    {
+      "epoch": 0.18975332068311196,
+      "eval_accuracy": 0.6169724770642202,
+      "eval_loss": 1.181114673614502,
+      "eval_runtime": 2.4577,
+      "eval_samples_per_second": 354.806,
+      "eval_steps_per_second": 2.848,
+      "step": 100
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "grad_norm": 1.8982616662979126,
+      "learning_rate": 2.3789299271608236e-05,
+      "loss": 1.1808,
+      "step": 200
+    },
+    {
+      "epoch": 0.3795066413662239,
+      "eval_accuracy": 0.7121559633027523,
+      "eval_loss": 1.0743426084518433,
+      "eval_runtime": 2.4969,
+      "eval_samples_per_second": 349.235,
+      "eval_steps_per_second": 2.803,
+      "step": 200
+    },
+    {
+      "epoch": 0.5692599620493358,
+      "grad_norm": 2.6504175662994385,
+      "learning_rate": 2.2812529230666033e-05,
+      "loss": 1.0583,
+      "step": 300
+    },
+    {
+      "epoch": 0.5692599620493358,
+      "eval_accuracy": 0.7591743119266054,
+      "eval_loss": 0.9464107155799866,
+      "eval_runtime": 2.4114,
+      "eval_samples_per_second": 361.611,
+      "eval_steps_per_second": 2.903,
+      "step": 300
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "grad_norm": 2.9992282390594482,
+      "learning_rate": 2.138601927608547e-05,
+      "loss": 0.9339,
+      "step": 400
+    },
+    {
+      "epoch": 0.7590132827324478,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.8676859736442566,
+      "eval_runtime": 2.5023,
+      "eval_samples_per_second": 348.476,
+      "eval_steps_per_second": 2.797,
+      "step": 400
+    },
+    {
+      "epoch": 0.9487666034155597,
+      "grad_norm": 2.979876756668091,
+      "learning_rate": 1.9570015801402756e-05,
+      "loss": 0.8783,
+      "step": 500
+    },
+    {
+      "epoch": 0.9487666034155597,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.836247980594635,
+      "eval_runtime": 2.4279,
+      "eval_samples_per_second": 359.162,
+      "eval_steps_per_second": 2.883,
+      "step": 500
+    },
+    {
+      "epoch": 1.1385199240986716,
+      "grad_norm": 3.8972060680389404,
+      "learning_rate": 1.7441214843436652e-05,
+      "loss": 0.8286,
+      "step": 600
+    },
+    {
+      "epoch": 1.1385199240986716,
+      "eval_accuracy": 0.786697247706422,
+      "eval_loss": 0.8169480562210083,
+      "eval_runtime": 2.4359,
+      "eval_samples_per_second": 357.985,
+      "eval_steps_per_second": 2.874,
+      "step": 600
+    },
+    {
+      "epoch": 1.3282732447817835,
+      "grad_norm": 4.094536304473877,
+      "learning_rate": 1.5089522946380597e-05,
+      "loss": 0.7808,
+      "step": 700
+    },
+    {
+      "epoch": 1.3282732447817835,
+      "eval_accuracy": 0.7878440366972477,
+      "eval_loss": 0.8050708770751953,
+      "eval_runtime": 2.4399,
+      "eval_samples_per_second": 357.397,
+      "eval_steps_per_second": 2.869,
+      "step": 700
+    },
+    {
+      "epoch": 1.5180265654648957,
+      "grad_norm": 6.467775344848633,
+      "learning_rate": 1.2614260100993157e-05,
+      "loss": 0.765,
+      "step": 800
+    },
+    {
+      "epoch": 1.5180265654648957,
+      "eval_accuracy": 0.7889908256880734,
+      "eval_loss": 0.7935003042221069,
+      "eval_runtime": 2.4349,
+      "eval_samples_per_second": 358.121,
+      "eval_steps_per_second": 2.875,
+      "step": 800
+    },
+    {
+      "epoch": 1.7077798861480076,
+      "grad_norm": 7.3176445960998535,
+      "learning_rate": 1.0119965121749416e-05,
+      "loss": 0.742,
+      "step": 900
+    },
+    {
+      "epoch": 1.7077798861480076,
+      "eval_accuracy": 0.7901376146788991,
+      "eval_loss": 0.7913622260093689,
+      "eval_runtime": 2.505,
+      "eval_samples_per_second": 348.1,
+      "eval_steps_per_second": 2.794,
+      "step": 900
+    },
+    {
+      "epoch": 1.8975332068311195,
+      "grad_norm": 4.671020030975342,
+      "learning_rate": 7.711980615220306e-06,
+      "loss": 0.7379,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8975332068311195,
+      "eval_accuracy": 0.7970183486238532,
+      "eval_loss": 0.7775447964668274,
+      "eval_runtime": 2.4368,
+      "eval_samples_per_second": 357.839,
+      "eval_steps_per_second": 2.873,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0872865275142316,
+      "grad_norm": 3.548794984817505,
+      "learning_rate": 5.492004001563045e-06,
+      "loss": 0.7169,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0872865275142316,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.7763888239860535,
+      "eval_runtime": 2.4327,
+      "eval_samples_per_second": 358.447,
+      "eval_steps_per_second": 2.877,
+      "step": 1100
+    },
+    {
+      "epoch": 2.2770398481973433,
+      "grad_norm": 2.657698392868042,
+      "learning_rate": 3.5537924846990686e-06,
+      "loss": 0.7053,
+      "step": 1200
+    },
+    {
+      "epoch": 2.2770398481973433,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 0.7718890905380249,
+      "eval_runtime": 2.4731,
+      "eval_samples_per_second": 352.601,
+      "eval_steps_per_second": 2.831,
+      "step": 1200
+    },
+    {
+      "epoch": 2.4667931688804554,
+      "grad_norm": 8.931977272033691,
+      "learning_rate": 1.9792033649762944e-06,
+      "loss": 0.7001,
+      "step": 1300
+    },
+    {
+      "epoch": 2.4667931688804554,
+      "eval_accuracy": 0.7958715596330275,
+      "eval_loss": 0.7761191129684448,
+      "eval_runtime": 2.4453,
+      "eval_samples_per_second": 356.608,
+      "eval_steps_per_second": 2.863,
+      "step": 1300
+    },
+    {
+      "epoch": 2.656546489563567,
+      "grad_norm": 5.575241565704346,
+      "learning_rate": 8.347369254527042e-07,
+      "loss": 0.6988,
+      "step": 1400
+    },
+    {
+      "epoch": 2.656546489563567,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.7722569108009338,
+      "eval_runtime": 2.492,
+      "eval_samples_per_second": 349.916,
+      "eval_steps_per_second": 2.809,
+      "step": 1400
+    },
+    {
+      "epoch": 2.846299810246679,
+      "grad_norm": 6.262284278869629,
+      "learning_rate": 1.6872789753562043e-07,
+      "loss": 0.7135,
+      "step": 1500
+    },
+    {
+      "epoch": 2.846299810246679,
+      "eval_accuracy": 0.7981651376146789,
+      "eval_loss": 0.7717686891555786,
+      "eval_runtime": 2.443,
+      "eval_samples_per_second": 356.945,
+      "eval_steps_per_second": 2.865,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1581,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 23032282372320.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8670086094179865,
+    "learning_rate": 2.432723709409012e-05,
+    "num_train_epochs": 3,
+    "temperature": 13,
+    "warmup_ratio": 0.03434495454544933
+  }
+}

run-0/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13ac8bd9d7d909b6ca7c92c43736d482f4dacbc0fe997a6e1760536a654848f
+size 5240