Training in progress, epoch 1

logs/events.out.tfevents.1721962879.98acc6742512.15262.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e7ed31bd396810349a842c00856a17e89d65d2b246a2593dc6f721a810f833f
-size 6432
+oid sha256:6a085f721b375c339921c5b0d70bfa539cdecea0ca92c32fcc6f1c21bbb8db9f
+size 8236

logs/events.out.tfevents.1721963007.98acc6742512.15262.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b08262395687f09567ba99b8406ed22bf974ce956ec3283c7806ce465b9f205
+size 5707

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d5aafec3c3eefba72f5789326d565df7f1ea5527e599f78ee9a9fc113495cc
+oid sha256:253af992d0b5e4f5ef28901c40cd9afaaf0a488f67946ac1595fc5d0ba076271
 size 17549312

run-3/checkpoint-688/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-3/checkpoint-688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f492c804703cbc6f13c7eb3ec22a19233d6dcedafb7ca298c89204f346989d3
+size 17549312

run-3/checkpoint-688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b011eeb317602e65630fd2e63e2e3dc37505d04ed368266ce5c78e5cadcf0ab
+size 35123898

run-3/checkpoint-688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b1fea9cda5ce8cfa36db49d92878d70e7ecc73c289b2b17c8c4949a715ba6e
+size 14308

run-3/checkpoint-688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e329956b7390b0a0d9d894c8fbe302d97ea89159873c9ac8bfce269c5511f547
+size 1064

run-3/checkpoint-688/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-688/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-3/checkpoint-688/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.5853333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-3/checkpoint-688",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 688,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.06025523692369461,
+      "learning_rate": 1.750045443660438e-05,
+      "loss": 0.0574,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.6860142222222222,
+      "eval_BAC": 0.5333333333333333,
+      "eval_MCC": 0.14834770727423166,
+      "eval_PR_AUC": 0.6557725052787473,
+      "eval_accuracy": 0.5333333333333333,
+      "eval_loss": 0.05601842328906059,
+      "eval_runtime": 6.3117,
+      "eval_samples_per_second": 237.654,
+      "eval_steps_per_second": 7.446,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.07936638593673706,
+      "learning_rate": 1.166696962440292e-05,
+      "loss": 0.0568,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.7200666666666666,
+      "eval_BAC": 0.5813333333333334,
+      "eval_MCC": 0.2649445737463828,
+      "eval_PR_AUC": 0.6792464061936596,
+      "eval_accuracy": 0.5813333333333334,
+      "eval_loss": 0.055815439671278,
+      "eval_runtime": 6.3074,
+      "eval_samples_per_second": 237.814,
+      "eval_steps_per_second": 7.452,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.04040193930268288,
+      "learning_rate": 5.83348481220146e-06,
+      "loss": 0.0566,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.7501155555555555,
+      "eval_BAC": 0.5459999999999999,
+      "eval_MCC": 0.20593895569506218,
+      "eval_PR_AUC": 0.7066874964455367,
+      "eval_accuracy": 0.546,
+      "eval_loss": 0.05583466589450836,
+      "eval_runtime": 6.177,
+      "eval_samples_per_second": 242.837,
+      "eval_steps_per_second": 7.609,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.08884396404027939,
+      "learning_rate": 0.0,
+      "loss": 0.0565,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.755400888888889,
+      "eval_BAC": 0.5853333333333333,
+      "eval_MCC": 0.28444444444444444,
+      "eval_PR_AUC": 0.7101770336776432,
+      "eval_accuracy": 0.5853333333333334,
+      "eval_loss": 0.05574020370841026,
+      "eval_runtime": 6.2726,
+      "eval_samples_per_second": 239.137,
+      "eval_steps_per_second": 7.493,
+      "step": 688
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "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": 1801510920000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.07282268127135982,
+    "learning_rate": 2.333393924880584e-05,
+    "num_train_epochs": 4,
+    "temperature": 19
+  }
+}

run-3/checkpoint-688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ac229c98c6bdd9f587e559a419af2e54959e4f4e987fa74451dc16869d3838c
+size 5240

run-4/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-4/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:253af992d0b5e4f5ef28901c40cd9afaaf0a488f67946ac1595fc5d0ba076271
+size 17549312

run-4/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72bb42e0e2436d65012b29ce9e906d173fce23653abf3e6e269c8f1be33dc90
+size 35123898

run-4/checkpoint-172/rng_state.pth

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

run-4/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1939777f5def065f8fe7328a1e5c3d8834c7c4fd24c93823964b83fcb082e29
+size 1064

run-4/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-4/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-4/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.73,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-4/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": 1.065812110900879,
+      "learning_rate": 8.050072712118835e-05,
+      "loss": 0.5092,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8145119999999999,
+      "eval_BAC": 0.73,
+      "eval_MCC": 0.4608302423279951,
+      "eval_PR_AUC": 0.7678112276484446,
+      "eval_accuracy": 0.73,
+      "eval_loss": 0.4519721269607544,
+      "eval_runtime": 6.3105,
+      "eval_samples_per_second": 237.697,
+      "eval_steps_per_second": 7.448,
+      "step": 172
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 0.7709874476999774,
+    "learning_rate": 9.200083099564382e-05,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-4/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e822dd3e5d511c55cbe15ff5f987d7e223bc685f4a2426244b24b30556862387
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac229c98c6bdd9f587e559a419af2e54959e4f4e987fa74451dc16869d3838c
+oid sha256:e822dd3e5d511c55cbe15ff5f987d7e223bc685f4a2426244b24b30556862387
 size 5240