Training in progress, epoch 5

logs/events.out.tfevents.1721967807.98acc6742512.15262.44

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733aed5ab4df0db92eb14b8e7bd1c0e36d4787fb5ffe455f4d1b4cb61f10b0d0
-size 7883
+oid sha256:905d83cb25822a69350cffd3d8c4cd345ef43365cf7a1872b4f26f6003214f90
+size 8608

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a455a212bbda7fa03c04c87de56ce781ef1e7826e3cfd2d832578ab84085cea4
+oid sha256:3c671b76e22cf96a842bb0e28b40c07e07db54859f63f81491bdbdaf667b53a4
 size 17549312

run-43/checkpoint-860/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-43/checkpoint-860/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c671b76e22cf96a842bb0e28b40c07e07db54859f63f81491bdbdaf667b53a4
+size 17549312

run-43/checkpoint-860/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bee8b403c6f45341b0554f13e6528d0634113848194241326f5ee554499c02d
+size 35123898

run-43/checkpoint-860/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9f0bc35f961ba3eec992b81bac90971267fe149efd92cea3c10af23980c570
+size 14308

run-43/checkpoint-860/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2788102a44e7ae9988ac1c98c06c373f013efae42ac758286a815bdbf83063
+size 1064

run-43/checkpoint-860/special_tokens_map.json

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

run-43/checkpoint-860/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-43/checkpoint-860/trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_metric": 0.8166666666666667,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-43/checkpoint-688",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 860,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9297363758087158,
+      "learning_rate": 0.00018220163554157572,
+      "loss": 0.5109,
+      "step": 172
+    },
+    {
+      "epoch": 1.0,
+      "eval_AUC": 0.8338702222222223,
+      "eval_BAC": 0.7526666666666666,
+      "eval_MCC": 0.5054631978951394,
+      "eval_PR_AUC": 0.7906860159456152,
+      "eval_accuracy": 0.7526666666666667,
+      "eval_loss": 0.45379385352134705,
+      "eval_runtime": 6.2406,
+      "eval_samples_per_second": 240.361,
+      "eval_steps_per_second": 7.531,
+      "step": 172
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4736577272415161,
+      "learning_rate": 0.00015617283046420776,
+      "loss": 0.4701,
+      "step": 344
+    },
+    {
+      "epoch": 2.0,
+      "eval_AUC": 0.8569777777777778,
+      "eval_BAC": 0.7826666666666666,
+      "eval_MCC": 0.5934186315088451,
+      "eval_PR_AUC": 0.8041841872474981,
+      "eval_accuracy": 0.7826666666666666,
+      "eval_loss": 0.4416643977165222,
+      "eval_runtime": 6.2534,
+      "eval_samples_per_second": 239.869,
+      "eval_steps_per_second": 7.516,
+      "step": 344
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.348161220550537,
+      "learning_rate": 0.0001301440253868398,
+      "loss": 0.4558,
+      "step": 516
+    },
+    {
+      "epoch": 3.0,
+      "eval_AUC": 0.8637493333333333,
+      "eval_BAC": 0.804,
+      "eval_MCC": 0.6085541718553057,
+      "eval_PR_AUC": 0.8226621073554637,
+      "eval_accuracy": 0.804,
+      "eval_loss": 0.4197617471218109,
+      "eval_runtime": 6.2546,
+      "eval_samples_per_second": 239.825,
+      "eval_steps_per_second": 7.515,
+      "step": 516
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.7102890014648438,
+      "learning_rate": 0.00010411522030947184,
+      "loss": 0.4473,
+      "step": 688
+    },
+    {
+      "epoch": 4.0,
+      "eval_AUC": 0.8772622222222222,
+      "eval_BAC": 0.8166666666666667,
+      "eval_MCC": 0.6370595622544093,
+      "eval_PR_AUC": 0.8431382446127011,
+      "eval_accuracy": 0.8166666666666667,
+      "eval_loss": 0.40485522150993347,
+      "eval_runtime": 6.2302,
+      "eval_samples_per_second": 240.762,
+      "eval_steps_per_second": 7.544,
+      "step": 688
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.8933205604553223,
+      "learning_rate": 7.808641523210388e-05,
+      "loss": 0.4369,
+      "step": 860
+    },
+    {
+      "epoch": 5.0,
+      "eval_AUC": 0.8801617777777779,
+      "eval_BAC": 0.8153333333333334,
+      "eval_MCC": 0.6421162229151887,
+      "eval_PR_AUC": 0.8430902218812605,
+      "eval_accuracy": 0.8153333333333334,
+      "eval_loss": 0.4066833555698395,
+      "eval_runtime": 6.2576,
+      "eval_samples_per_second": 239.71,
+      "eval_steps_per_second": 7.511,
+      "step": 860
+    }
+  ],
+  "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": 2251888650000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.788436760671977,
+    "learning_rate": 0.00020823044061894368,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-43/checkpoint-860/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a92756ef89f8e47d74c8dbb99b95636b4c11a42f430916a18a4047589b3d76f
+size 5240