Training in progress, epoch 7

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694234bdac1f2d448d2d78392db0f4664a133dc4eadda2115110a61be304303b
-size 9333
+oid sha256:e2eac9a15d289d3cc54762b51bf31a605845b40cddc04ed95878feddead575fb
+size 10058

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dc6ce35f52a182cccdad17ca446f66a7ec71e03ab5a9072a1aee3c9d4e7fb76
+oid sha256:27253dd78c8e106827441044e199b7863dd96814718a62687f1ee0adb89f8b98
 size 17549312

run-43/checkpoint-1204/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-1204/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27253dd78c8e106827441044e199b7863dd96814718a62687f1ee0adb89f8b98
+size 17549312

run-43/checkpoint-1204/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94d024193ab0c147b606472d7b5887e698f57999750e2f7f88d703d26a91e74c
+size 35123898

run-43/checkpoint-1204/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4404160742a334aa27fbb21c3241578919c1efefcab10b400b543b1d691ccc6d
+size 14308

run-43/checkpoint-1204/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b7b98401aa4ba4eac083d7e995916f69c393dd27e1ce878d589b5549048e34
+size 1064

run-43/checkpoint-1204/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-1204/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-1204/trainer_state.json

@@ -0,0 +1,178 @@
+{
+  "best_metric": 0.8233333333333334,
+  "best_model_checkpoint": "Bert_tinybert-distilled/run-43/checkpoint-1032",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1204,
+  "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
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 3.563457489013672,
+      "learning_rate": 5.205761015473592e-05,
+      "loss": 0.4326,
+      "step": 1032
+    },
+    {
+      "epoch": 6.0,
+      "eval_AUC": 0.8809404444444445,
+      "eval_BAC": 0.8233333333333334,
+      "eval_MCC": 0.6512684330406643,
+      "eval_PR_AUC": 0.8480684407173623,
+      "eval_accuracy": 0.8233333333333334,
+      "eval_loss": 0.4061877131462097,
+      "eval_runtime": 6.2566,
+      "eval_samples_per_second": 239.746,
+      "eval_steps_per_second": 7.512,
+      "step": 1032
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.526883363723755,
+      "learning_rate": 2.602880507736796e-05,
+      "loss": 0.4297,
+      "step": 1204
+    },
+    {
+      "epoch": 7.0,
+      "eval_AUC": 0.8827324444444444,
+      "eval_BAC": 0.8206666666666667,
+      "eval_MCC": 0.6467654032186204,
+      "eval_PR_AUC": 0.850530858753072,
+      "eval_accuracy": 0.8206666666666667,
+      "eval_loss": 0.4042230546474457,
+      "eval_runtime": 6.2645,
+      "eval_samples_per_second": 239.445,
+      "eval_steps_per_second": 7.503,
+      "step": 1204
+    }
+  ],
+  "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": 3152644110000.0,
+  "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-1204/training_args.bin

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