Training in progress, epoch 1

logs/events.out.tfevents.1709748963.fcc57e6e3903.3035.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275bf9e297cfba3ef263fd8cd860d5274169ee9597945c1a75f0a20755fc391f
-size 6011
+oid sha256:fdd732889ec2d636195d1ea33ca743418d2356a404cd41d0bc7eb73fcc2448a7
+size 10463

logs/events.out.tfevents.1709751293.fcc57e6e3903.3035.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe65b50e68473a92662cbd1f1b1d6308016100b63527890735140728cb324a50
+size 5327

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d484c43b36dd95bcbe1e28af252b83a91507c6c6aa11bc49024d09f6feca6d35
+oid sha256:9300b6cdb4e6db86e99e008e1e9505ffbeb343055a5564701c5f5534016a08eb
 size 17549312

run-8/checkpoint-2079/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-8/checkpoint-2079/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637a6aeeaf4ed07dbc7780fefd1e6715f2dda80656cf5a4e9917962745d9ee37
+size 17549312

run-8/checkpoint-2079/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0de7a45585df6c634185620a9fb274ede96bd70cac4d92f9518032cde93efe
+size 35122746

run-8/checkpoint-2079/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ddf4483b0cc001197871d638833a4a3bbdd0c0a8ea4710051f83b263dbe74c2
+size 14054

run-8/checkpoint-2079/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc445dd588edde05a8e870cd876b74684ad8ae99a7d1749c41ba16cd01db65c
+size 1064

run-8/checkpoint-2079/special_tokens_map.json

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

run-8/checkpoint-2079/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-8/checkpoint-2079/trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": 0.5564356435643565,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-2079",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 2079,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.24534238874912262,
+      "learning_rate": 0.0002919829387820306,
+      "loss": 0.3074,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.16382252559726962,
+      "eval_loss": 0.30149543285369873,
+      "eval_precision": 0.5853658536585366,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 14.7271,
+      "eval_samples_per_second": 34.291,
+      "eval_steps_per_second": 1.086,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5045191645622253,
+      "learning_rate": 0.00025027109038459764,
+      "loss": 0.3009,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.1643835616438356,
+      "eval_loss": 0.2990603744983673,
+      "eval_precision": 0.6,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 15.7792,
+      "eval_samples_per_second": 32.004,
+      "eval_steps_per_second": 1.014,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6056041121482849,
+      "learning_rate": 0.00020855924198716472,
+      "loss": 0.2956,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_f1": 0.17687074829931973,
+      "eval_loss": 0.2930928170681,
+      "eval_precision": 0.6190476190476191,
+      "eval_recall": 0.10317460317460317,
+      "eval_runtime": 14.6946,
+      "eval_samples_per_second": 34.366,
+      "eval_steps_per_second": 1.089,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4732127785682678,
+      "learning_rate": 0.00016684739358973177,
+      "loss": 0.2915,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_f1": 0.16551724137931034,
+      "eval_loss": 0.2868767976760864,
+      "eval_precision": 0.631578947368421,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 14.9872,
+      "eval_samples_per_second": 33.695,
+      "eval_steps_per_second": 1.068,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4796178936958313,
+      "learning_rate": 0.00012513554519229882,
+      "loss": 0.2881,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5188118811881188,
+      "eval_f1": 0.15916955017301038,
+      "eval_loss": 0.2868916988372803,
+      "eval_precision": 0.6216216216216216,
+      "eval_recall": 0.09126984126984126,
+      "eval_runtime": 14.7705,
+      "eval_samples_per_second": 34.19,
+      "eval_steps_per_second": 1.083,
+      "step": 1485
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5560742616653442,
+      "learning_rate": 8.342369679486588e-05,
+      "loss": 0.2859,
+      "step": 1782
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5544554455445545,
+      "eval_f1": 0.25742574257425743,
+      "eval_loss": 0.2852015793323517,
+      "eval_precision": 0.7647058823529411,
+      "eval_recall": 0.15476190476190477,
+      "eval_runtime": 15.1062,
+      "eval_samples_per_second": 33.43,
+      "eval_steps_per_second": 1.059,
+      "step": 1782
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5270741581916809,
+      "learning_rate": 4.171184839743294e-05,
+      "loss": 0.2835,
+      "step": 2079
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5564356435643565,
+      "eval_f1": 0.28205128205128205,
+      "eval_loss": 0.28437066078186035,
+      "eval_precision": 0.7333333333333333,
+      "eval_recall": 0.1746031746031746,
+      "eval_runtime": 14.6907,
+      "eval_samples_per_second": 34.375,
+      "eval_steps_per_second": 1.089,
+      "step": 2079
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 5444902981980.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.37248229271478195,
+    "learning_rate": 0.00033369478717946353,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 32,
+    "temperature": 11
+  }
+}

run-8/checkpoint-2079/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f042525736aa17960ee8344101391e82f28237778df28fde71ca14364b664f
+size 4920

run-8/checkpoint-2376/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-8/checkpoint-2376/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb1dff5d533d9ae0cf4a9f7b66c8e57ea8eee63d075a483d1b90e980824f9156
+size 17549312

run-8/checkpoint-2376/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e8df7bf04eddceb422ba0c6ee007163f8cc00b44a16517e739f161a6316469
+size 35122746

run-8/checkpoint-2376/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:320c6c1f6ed30b4911b04b28c6438e2080a79dae7ced95dc38dd41943259c269
+size 14054

run-8/checkpoint-2376/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0f261760ead24cc68947edcc9f0fd34e8f4c66e6f402a8b210ed75923f6f6e
+size 1064

run-8/checkpoint-2376/special_tokens_map.json

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

run-8/checkpoint-2376/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-8/checkpoint-2376/trainer_state.json

@@ -0,0 +1,179 @@
+{
+  "best_metric": 0.5603960396039604,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-2376",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 2376,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.24534238874912262,
+      "learning_rate": 0.0002919829387820306,
+      "loss": 0.3074,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.16382252559726962,
+      "eval_loss": 0.30149543285369873,
+      "eval_precision": 0.5853658536585366,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 14.7271,
+      "eval_samples_per_second": 34.291,
+      "eval_steps_per_second": 1.086,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5045191645622253,
+      "learning_rate": 0.00025027109038459764,
+      "loss": 0.3009,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.1643835616438356,
+      "eval_loss": 0.2990603744983673,
+      "eval_precision": 0.6,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 15.7792,
+      "eval_samples_per_second": 32.004,
+      "eval_steps_per_second": 1.014,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6056041121482849,
+      "learning_rate": 0.00020855924198716472,
+      "loss": 0.2956,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_f1": 0.17687074829931973,
+      "eval_loss": 0.2930928170681,
+      "eval_precision": 0.6190476190476191,
+      "eval_recall": 0.10317460317460317,
+      "eval_runtime": 14.6946,
+      "eval_samples_per_second": 34.366,
+      "eval_steps_per_second": 1.089,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.4732127785682678,
+      "learning_rate": 0.00016684739358973177,
+      "loss": 0.2915,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_f1": 0.16551724137931034,
+      "eval_loss": 0.2868767976760864,
+      "eval_precision": 0.631578947368421,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 14.9872,
+      "eval_samples_per_second": 33.695,
+      "eval_steps_per_second": 1.068,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.4796178936958313,
+      "learning_rate": 0.00012513554519229882,
+      "loss": 0.2881,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5188118811881188,
+      "eval_f1": 0.15916955017301038,
+      "eval_loss": 0.2868916988372803,
+      "eval_precision": 0.6216216216216216,
+      "eval_recall": 0.09126984126984126,
+      "eval_runtime": 14.7705,
+      "eval_samples_per_second": 34.19,
+      "eval_steps_per_second": 1.083,
+      "step": 1485
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5560742616653442,
+      "learning_rate": 8.342369679486588e-05,
+      "loss": 0.2859,
+      "step": 1782
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5544554455445545,
+      "eval_f1": 0.25742574257425743,
+      "eval_loss": 0.2852015793323517,
+      "eval_precision": 0.7647058823529411,
+      "eval_recall": 0.15476190476190477,
+      "eval_runtime": 15.1062,
+      "eval_samples_per_second": 33.43,
+      "eval_steps_per_second": 1.059,
+      "step": 1782
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.5270741581916809,
+      "learning_rate": 4.171184839743294e-05,
+      "loss": 0.2835,
+      "step": 2079
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5564356435643565,
+      "eval_f1": 0.28205128205128205,
+      "eval_loss": 0.28437066078186035,
+      "eval_precision": 0.7333333333333333,
+      "eval_recall": 0.1746031746031746,
+      "eval_runtime": 14.6907,
+      "eval_samples_per_second": 34.375,
+      "eval_steps_per_second": 1.089,
+      "step": 2079
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.5982300639152527,
+      "learning_rate": 0.0,
+      "loss": 0.2815,
+      "step": 2376
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5603960396039604,
+      "eval_f1": 0.30625,
+      "eval_loss": 0.28472816944122314,
+      "eval_precision": 0.7205882352941176,
+      "eval_recall": 0.19444444444444445,
+      "eval_runtime": 15.1706,
+      "eval_samples_per_second": 33.288,
+      "eval_steps_per_second": 1.055,
+      "step": 2376
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 6222746265120.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.37248229271478195,
+    "learning_rate": 0.00033369478717946353,
+    "num_train_epochs": 8,
+    "per_device_train_batch_size": 32,
+    "temperature": 11
+  }
+}

run-8/checkpoint-2376/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f042525736aa17960ee8344101391e82f28237778df28fde71ca14364b664f
+size 4920

run-9/checkpoint-396/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-9/checkpoint-396/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9300b6cdb4e6db86e99e008e1e9505ffbeb343055a5564701c5f5534016a08eb
+size 17549312

run-9/checkpoint-396/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594ad22dcd4a3442c41d7fb9f47e3c5e7a382d16e586755c890f56487c9b7f1d
+size 35122746

run-9/checkpoint-396/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b5041f3a47d0f397983ee7f6b60c7aad8e7b43fc600a3bfe48ab26019c72c98
+size 14054

run-9/checkpoint-396/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5715a3bf62e2d918bfe97bec134976e6c297c8dc17f079cb62a2fc5939a18161
+size 1064

run-9/checkpoint-396/special_tokens_map.json

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

run-9/checkpoint-396/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-9/checkpoint-396/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5168316831683168,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-9/checkpoint-396",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 396,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.3266456127166748,
+      "learning_rate": 0.00047485708344336834,
+      "loss": 0.1574,
+      "step": 396
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.18120805369127518,
+      "eval_loss": 0.15217570960521698,
+      "eval_precision": 0.5869565217391305,
+      "eval_recall": 0.10714285714285714,
+      "eval_runtime": 14.9861,
+      "eval_samples_per_second": 33.698,
+      "eval_steps_per_second": 1.068,
+      "step": 396
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2772,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "train_batch_size": 24,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.17422929745790272,
+    "learning_rate": 0.0005539999306839298,
+    "num_train_epochs": 7,
+    "per_device_train_batch_size": 24,
+    "temperature": 12
+  }
+}

run-9/checkpoint-396/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73c802f5f517b25edfbe87e6b655b1a10931ee811a3ed96445c8dd0bf6c9d82
+size 4920

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3427d367c6681566932cafa2f6b6a62ba9e8ebfdfa8d9ebafbc1230e1c415890
+oid sha256:b73c802f5f517b25edfbe87e6b655b1a10931ee811a3ed96445c8dd0bf6c9d82
 size 4920