Training in progress, epoch 1

logs/events.out.tfevents.1699951579.45c71320b2c6.349.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068fca4d6e96866918e5e61c92b6fe0ea48fef33974575a02b3a4c85bb07b643
-size 5253
+oid sha256:10edb707c9a3841299bba73236ae1c6da2e0cdaaa13ecc552c3285c8aaf47fc4
+size 6693

logs/events.out.tfevents.1699951912.45c71320b2c6.349.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e523d0acc66fbd573b12192ca426d217c483c239f66196179a985c2d340db2ce
+size 4773

logs/events.out.tfevents.1699951978.45c71320b2c6.349.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6895a28f60e0c6646068bba3d8ff46aa606314340928f6685bc5475f635a65e3
+size 4774

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:547855f29317799f424aa06e2e3d320fba598afa0ddf0660e56b1ce2a5ae33aa
+oid sha256:6ad12479391050a950745b11ae9df966699640be40d918815f1a97413e9e7226
 size 17549312

run-13/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf28d89f18693031d65ed18a9b804ddc5973ff92c0fe6b49f8a4fd40d5f8c639
+size 17549312

run-13/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f1bf0cf9f977f6fbb99099f93bfeda2f7ee92221f3ce7020abae41e20f69c67
+size 35123898

run-13/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0145a794c4550fd779295bb332661a545e0c28f08ca5060bf05d2337c4c7b4d2
+size 14308

run-13/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d51d90cf5ea88a02dcf513bd31f98055d39cc877565f00fcd611d7db1d08e765
+size 1064

run-13/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-13/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-13/checkpoint-1581/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.8314220183486238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1581",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.290547661378887e-05,
+      "loss": 0.4418,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 0.4441070556640625,
+      "eval_runtime": 0.9514,
+      "eval_samples_per_second": 916.522,
+      "eval_steps_per_second": 7.357,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.106183709753333e-05,
+      "loss": 0.2905,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.4509088099002838,
+      "eval_runtime": 0.8398,
+      "eval_samples_per_second": 1038.39,
+      "eval_steps_per_second": 8.336,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.921819758127777e-05,
+      "loss": 0.2346,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.4710235595703125,
+      "eval_runtime": 0.8314,
+      "eval_samples_per_second": 1048.779,
+      "eval_steps_per_second": 8.419,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 24280106603460.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9928258166586904,
+    "learning_rate": 9.474911613004443e-05,
+    "num_train_epochs": 8,
+    "temperature": 26
+  }
+}

run-13/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22d1954fb5f2031f95ddeab15d35636742f3c5363e24071e8a4adfc8ae29403
+size 4664

run-13/checkpoint-2108/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-13/checkpoint-2108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7df42ea39f9aaf8f531392054ae67ba7f0ca2c7ad38a906581d0caeedcefd5
+size 17549312

run-13/checkpoint-2108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1922ad3ab662185069a0585d53dd42f5710ed2fe81631a5402c3d819dba7acac
+size 35123898

run-13/checkpoint-2108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5380d7490ac96d7f61709bde5d4086c1114991ed50d41459765b29873c758add
+size 14308

run-13/checkpoint-2108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14771ecb6a81601a5584bcf59b85eaebbc2eb9d25e99c4ee407da152912b80ae
+size 1064

run-13/checkpoint-2108/special_tokens_map.json

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

run-13/checkpoint-2108/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-13/checkpoint-2108/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.8314220183486238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1581",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.290547661378887e-05,
+      "loss": 0.4418,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8027522935779816,
+      "eval_loss": 0.4441070556640625,
+      "eval_runtime": 0.9514,
+      "eval_samples_per_second": 916.522,
+      "eval_steps_per_second": 7.357,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.106183709753333e-05,
+      "loss": 0.2905,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.4509088099002838,
+      "eval_runtime": 0.8398,
+      "eval_samples_per_second": 1038.39,
+      "eval_steps_per_second": 8.336,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.921819758127777e-05,
+      "loss": 0.2346,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.4710235595703125,
+      "eval_runtime": 0.8314,
+      "eval_samples_per_second": 1048.779,
+      "eval_steps_per_second": 8.419,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.737455806502222e-05,
+      "loss": 0.2058,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.819954128440367,
+      "eval_loss": 0.5080426335334778,
+      "eval_runtime": 0.9138,
+      "eval_samples_per_second": 954.244,
+      "eval_steps_per_second": 7.66,
+      "step": 2108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 32320254802260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9928258166586904,
+    "learning_rate": 9.474911613004443e-05,
+    "num_train_epochs": 8,
+    "temperature": 26
+  }
+}

run-13/checkpoint-2108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22d1954fb5f2031f95ddeab15d35636742f3c5363e24071e8a4adfc8ae29403
+size 4664

run-15/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-15/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad12479391050a950745b11ae9df966699640be40d918815f1a97413e9e7226
+size 17549312

run-15/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a8ef44bf162bf9ff38bbf9d5298fd0b727c1172200d87edfd103f7628958c5
+size 35123898

run-15/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
+size 14308

run-15/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f265c5a595535860b9de6c92ef7aac1c924a9d421d9249df2ce59b7613f7be50
+size 1064

run-15/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-15/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-15/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8222477064220184,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-15/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,
+      "learning_rate": 0.00013229254069684757,
+      "loss": 1.2719,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.2621331214904785,
+      "eval_runtime": 0.8355,
+      "eval_samples_per_second": 1043.631,
+      "eval_steps_per_second": 8.378,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.47101299888546155,
+    "learning_rate": 0.00026458508139369513,
+    "num_train_epochs": 2,
+    "temperature": 26
+  }
+}

run-15/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a801cf7834d6494cd07ec6db97798e01750d2b0f659a8e62f25937880ad601f
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e22d1954fb5f2031f95ddeab15d35636742f3c5363e24071e8a4adfc8ae29403
+oid sha256:6a801cf7834d6494cd07ec6db97798e01750d2b0f659a8e62f25937880ad601f
 size 4664