Training in progress, epoch 1

logs/events.out.tfevents.1721965588.98acc6742512.15262.26

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37ad6698a68647e75f4a0ae679fabd88a9fa06ce936470c667d33cf07bc196d9
-size 5707
+oid sha256:9ab301dfa5a5edf716d36d9fc6972d2b693bc8d1338bcbee7394b8c0e090efc6
+size 6786

logs/events.out.tfevents.1721965657.98acc6742512.15262.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814a1bebca4c8274fac93b0fbaa31688468bac8dc28b8a038ed87d30465735d7
+size 5708

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8213352dae50cc3d57ccecacdd43708a479e7c2a90ef60b2d454c41f70088f34
+oid sha256:d27fff27a895cc4f25e12ba78b4dc602cb1aaa67d2f291bc54bcd2465922ed01
 size 17549312

run-25/checkpoint-344/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-25/checkpoint-344/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233f12d2abb0fded24bb691c398fa016ea65580245f0c0d8d60341d9143c6111
+size 17549312

run-25/checkpoint-344/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b9f54fa30027879392d308fdeb3e7c92e577782260b332c401fef874ea4e6e9
+size 35123898

run-25/checkpoint-344/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2379c4b3c857cec440f9d16a9c9688b7d4e4a6884412fa1520c2361c4ae0b74c
+size 14308

run-25/checkpoint-344/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257ee158b2968d1577c2f095e4b63c3acf63d4357efa1791285815703590a7d7
+size 1064

run-25/checkpoint-344/special_tokens_map.json

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

run-25/checkpoint-344/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-25/checkpoint-344/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.7853333333333333,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-25/checkpoint-344",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 344,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8690188527107239,
+      "learning_rate": 0.0001732793884765621,
+      "loss": 0.484,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8223413333333331,
+      "eval_BAC": 0.7413333333333333,
+      "eval_MCC": 0.48280573474696187,
+      "eval_PR_AUC": 0.7777897109751378,
+      "eval_accuracy": 0.7413333333333333,
+      "eval_loss": 0.43229565024375916,
+      "eval_runtime": 6.2362,
+      "eval_samples_per_second": 240.531,
+      "eval_steps_per_second": 7.537,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3578239679336548,
+      "learning_rate": 0.0,
+      "loss": 0.4504,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8412373333333333,
+      "eval_BAC": 0.7853333333333333,
+      "eval_MCC": 0.5824342277284446,
+      "eval_PR_AUC": 0.7975545459624105,
+      "eval_accuracy": 0.7853333333333333,
+      "eval_loss": 0.4189279079437256,
+      "eval_runtime": 6.2433,
+      "eval_samples_per_second": 240.256,
+      "eval_steps_per_second": 7.528,
+      "step": 344
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 900755460000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7425109383729434,
+    "learning_rate": 0.0003465587769531242,
+    "num_train_epochs": 2,
+    "temperature": 5
+  }
+}

run-25/checkpoint-344/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a7265c224cfadd9cbeae7323bf17185f780b87c258a3ceb7edb6382228834d
+size 5240

run-26/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-26/checkpoint-172/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27fff27a895cc4f25e12ba78b4dc602cb1aaa67d2f291bc54bcd2465922ed01
+size 17549312

run-26/checkpoint-172/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fb2d14dd36139896dbfaf220913bc19acea33bd8b2643979b0bd20a4ae83bcd
+size 35123898

run-26/checkpoint-172/rng_state.pth

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

run-26/checkpoint-172/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc4e2d6bbdc7813f3a054b009038b1d5b612b3064d021866a1f6582b7cd2a33
+size 1064

run-26/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-26/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-26/checkpoint-172/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.7366666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-26/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": 2.019540548324585,
+      "learning_rate": 0.00010368996748543682,
+      "loss": 0.5941,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.819072,
+      "eval_BAC": 0.7366666666666667,
+      "eval_MCC": 0.47336741701441504,
+      "eval_PR_AUC": 0.7723271954821734,
+      "eval_accuracy": 0.7366666666666667,
+      "eval_loss": 0.5035012364387512,
+      "eval_runtime": 6.3714,
+      "eval_samples_per_second": 235.425,
+      "eval_steps_per_second": 7.377,
+      "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": 0.9196094567227121,
+    "learning_rate": 0.00011665121342111642,
+    "num_train_epochs": 9,
+    "temperature": 22
+  }
+}

run-26/checkpoint-172/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d42d4503454c744ad29b146a95868f7aa17157675037f45e91972dc2de9576d5
+size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a7265c224cfadd9cbeae7323bf17185f780b87c258a3ceb7edb6382228834d
+oid sha256:d42d4503454c744ad29b146a95868f7aa17157675037f45e91972dc2de9576d5
 size 5240