Training in progress, epoch 1

logs/events.out.tfevents.1721966710.98acc6742512.15262.35

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494367e2893b8506a534075e5a8c941baf8fe2c88f102d9634a953316c6350ae
-size 10782
+oid sha256:444e5bd72139a2732b071ab1b87e6fb41e55e2c8b76f73d417f54dc56cb757bf
+size 11861

logs/events.out.tfevents.1721966993.98acc6742512.15262.36

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0cc048e0707f5b9388f57b25e78be9232f3f49a92756325cd7c8e64bba7ff2
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f60b01c10b9905ffe95fa9a16e4dc9bdfb0a5ae03d216ec0b3491f64063fbbae
+oid sha256:312a271b731e20b7d1f777c67f095e3cbc7347d3df6d0dd6ecbbd0cd22f6318d
 size 17549312

run-34/checkpoint-1548/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": "4.43.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-34/checkpoint-1548/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddb2a620513c6041985c391f41d1c495849e240bcd8848b0b630d63383952f3
+size 17549312

run-34/checkpoint-1548/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7182b0cd6549a0f08f5ebece0c473a0641655d4582e85751e5cf2268aac924a2
+size 35123898

run-34/checkpoint-1548/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ddbbc87b36b5871313fc71dae1a22c3ede13ff5a31af8b745553ca14ae3bba
+size 14308

run-34/checkpoint-1548/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:848a9c5c87632cba8fbde015f75eb3069bcc528a752c5bcf8b7cdcbd56109ee8
+size 1064

run-34/checkpoint-1548/special_tokens_map.json

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

run-34/checkpoint-1548/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-34/checkpoint-1548/trainer_state.json

@@ -0,0 +1,218 @@
+{
+  "best_metric": 0.8313333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-34/checkpoint-1376",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1548,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2015043497085571,
+      "learning_rate": 0.00027537877162579386,
+      "loss": 0.5903,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8227715555555557,
+      "eval_BAC": 0.7293333333333334,
+      "eval_MCC": 0.462798882269463,
+      "eval_PR_AUC": 0.7817423653297785,
+      "eval_accuracy": 0.7293333333333333,
+      "eval_loss": 0.524067223072052,
+      "eval_runtime": 6.2657,
+      "eval_samples_per_second": 239.398,
+      "eval_steps_per_second": 7.501,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.673234224319458,
+      "learning_rate": 0.00024095642517256964,
+      "loss": 0.5391,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8590240000000001,
+      "eval_BAC": 0.7893333333333333,
+      "eval_MCC": 0.6018126794174047,
+      "eval_PR_AUC": 0.8177888157143621,
+      "eval_accuracy": 0.7893333333333333,
+      "eval_loss": 0.48427751660346985,
+      "eval_runtime": 6.2417,
+      "eval_samples_per_second": 240.319,
+      "eval_steps_per_second": 7.53,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.158290147781372,
+      "learning_rate": 0.00020653407871934538,
+      "loss": 0.5144,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.874496,
+      "eval_BAC": 0.8166666666666667,
+      "eval_MCC": 0.6357253352621931,
+      "eval_PR_AUC": 0.8445948803832817,
+      "eval_accuracy": 0.8166666666666667,
+      "eval_loss": 0.45355746150016785,
+      "eval_runtime": 6.2253,
+      "eval_samples_per_second": 240.953,
+      "eval_steps_per_second": 7.55,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.349181890487671,
+      "learning_rate": 0.00017211173226612116,
+      "loss": 0.4983,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8846435555555555,
+      "eval_BAC": 0.8160000000000001,
+      "eval_MCC": 0.6361963355504687,
+      "eval_PR_AUC": 0.8646294269782169,
+      "eval_accuracy": 0.816,
+      "eval_loss": 0.43939444422721863,
+      "eval_runtime": 6.2032,
+      "eval_samples_per_second": 241.81,
+      "eval_steps_per_second": 7.577,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.5103800296783447,
+      "learning_rate": 0.00013768938581289693,
+      "loss": 0.4834,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8878346666666667,
+      "eval_BAC": 0.8213333333333334,
+      "eval_MCC": 0.6458179094010764,
+      "eval_PR_AUC": 0.8644689328040056,
+      "eval_accuracy": 0.8213333333333334,
+      "eval_loss": 0.4339253008365631,
+      "eval_runtime": 6.2328,
+      "eval_samples_per_second": 240.664,
+      "eval_steps_per_second": 7.541,
+      "step": 860
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 5.336594581604004,
+      "learning_rate": 0.00010326703935967269,
+      "loss": 0.4746,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8907893333333334,
+      "eval_BAC": 0.8106666666666666,
+      "eval_MCC": 0.6252673865062606,
+      "eval_PR_AUC": 0.878022223565124,
+      "eval_accuracy": 0.8106666666666666,
+      "eval_loss": 0.4312085807323456,
+      "eval_runtime": 6.2382,
+      "eval_samples_per_second": 240.453,
+      "eval_steps_per_second": 7.534,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 4.427212715148926,
+      "learning_rate": 6.884469290644847e-05,
+      "loss": 0.4628,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8948551111111112,
+      "eval_BAC": 0.8200000000000001,
+      "eval_MCC": 0.64296966214199,
+      "eval_PR_AUC": 0.8703491534724792,
+      "eval_accuracy": 0.82,
+      "eval_loss": 0.4243921637535095,
+      "eval_runtime": 6.2243,
+      "eval_samples_per_second": 240.991,
+      "eval_steps_per_second": 7.551,
+      "step": 1204
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 2.8170576095581055,
+      "learning_rate": 3.442234645322423e-05,
+      "loss": 0.4578,
+      "step": 1376
+    },
+    {
+      "epoch": 8.0,
+      "eval_AUC": 0.8961244444444444,
+      "eval_BAC": 0.8313333333333333,
+      "eval_MCC": 0.6644557228059642,
+      "eval_PR_AUC": 0.8713602352456045,
+      "eval_accuracy": 0.8313333333333334,
+      "eval_loss": 0.41359227895736694,
+      "eval_runtime": 6.2342,
+      "eval_samples_per_second": 240.608,
+      "eval_steps_per_second": 7.539,
+      "step": 1376
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 2.8956260681152344,
+      "learning_rate": 0.0,
+      "loss": 0.4536,
+      "step": 1548
+    },
+    {
+      "epoch": 9.0,
+      "eval_AUC": 0.8958453333333334,
+      "eval_BAC": 0.8213333333333334,
+      "eval_MCC": 0.6484565734124452,
+      "eval_PR_AUC": 0.8730956163096388,
+      "eval_accuracy": 0.8213333333333334,
+      "eval_loss": 0.42589640617370605,
+      "eval_runtime": 6.2483,
+      "eval_samples_per_second": 240.065,
+      "eval_steps_per_second": 7.522,
+      "step": 1548
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1548,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 4053399570000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9233020385816241,
+    "learning_rate": 0.0003098011180790181,
+    "num_train_epochs": 9,
+    "temperature": 6
+  }
+}

run-34/checkpoint-1548/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d877c1dfe97f2e408bebc774c8e31f32af08cd31e93d90cb40f8126e5d0bc9a5
+size 5240

run-35/checkpoint-172/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": "4.43.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-35/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:312a271b731e20b7d1f777c67f095e3cbc7347d3df6d0dd6ecbbd0cd22f6318d
+size 17549312

run-35/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2356cd304e7c86b9d6395ae931489fd66343b841c81f4a77b5279a590239d6d5
+size 35123898

run-35/checkpoint-172/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b99cb6263c36c5c191e9bbbef2d3167790018df547076ed69608752e2b4353d4
+size 14308

run-35/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede55c67cea28c7b190d15981487091bb7838e01a38dc55cf101c8279d0b998e
+size 1064

run-35/checkpoint-172/special_tokens_map.json

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

run-35/checkpoint-172/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-35/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.7433333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-35/checkpoint-172",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 172,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3695982694625854,
+      "learning_rate": 0.00048733207447753345,
+      "loss": 0.6009,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8118062222222222,
+      "eval_BAC": 0.7433333333333333,
+      "eval_MCC": 0.4918891779800642,
+      "eval_PR_AUC": 0.7768672216647132,
+      "eval_accuracy": 0.7433333333333333,
+      "eval_loss": 0.5214411020278931,
+      "eval_runtime": 6.3049,
+      "eval_samples_per_second": 237.911,
+      "eval_steps_per_second": 7.455,
+      "step": 172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1548,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "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": 450377730000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9281099402760982,
+    "learning_rate": 0.0005482485837872251,
+    "num_train_epochs": 9,
+    "temperature": 4
+  }
+}

run-35/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65273dfbef8625f249d573182bc1b958e8b029f6742bf2394e83becaf1af6299
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d877c1dfe97f2e408bebc774c8e31f32af08cd31e93d90cb40f8126e5d0bc9a5
+oid sha256:65273dfbef8625f249d573182bc1b958e8b029f6742bf2394e83becaf1af6299
 size 5240