Training in progress, epoch 5

logs/events.out.tfevents.1711298809.8cc2eef2edb7.2942.31

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec56d7fd513a19bcaaff0a3b66061a6350fb80a3ccad409adb3642f0be69f387
-size 7597
+oid sha256:ac96198a01357f92af47100af2f36a15fef9535dd89da44a39d6c685d3093de9
+size 8327

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa188e8cf7b6789b6452ac403b5dad5c9f7dd5f039e1207bae5c32c79faea80a
+oid sha256:29cc9bc8212bbd2dddabfcabad96f67006e7065179d3e66c0ebced9d32615c5a
 size 17549312

run-31/checkpoint-1485/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-31/checkpoint-1485/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29cc9bc8212bbd2dddabfcabad96f67006e7065179d3e66c0ebced9d32615c5a
+size 17549312

run-31/checkpoint-1485/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751032a92f93a0e95e67d184f6aac4d70ab9cb377b57febe35b06d529d28eaca
+size 35123898

run-31/checkpoint-1485/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60c532b5f010242990de7c2dd8b4cd2d14624b3c168e0dbeb7940a12d466a7dc
+size 14308

run-31/checkpoint-1485/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fc0a609f8cbae6c125d114a93999d8cd558f0efaff861135192f609a3a57c8
+size 1064

run-31/checkpoint-1485/special_tokens_map.json

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

run-31/checkpoint-1485/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-31/checkpoint-1485/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.6752475247524753,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/checkpoint-1485",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1485,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7863609790802002,
+      "learning_rate": 0.00019509013723494322,
+      "loss": 0.6459,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5504950495049505,
+      "eval_f1": 0.3605633802816901,
+      "eval_loss": 0.6387978196144104,
+      "eval_mcc": 0.12386197513513038,
+      "eval_precision": 0.6213592233009708,
+      "eval_recall": 0.25396825396825395,
+      "eval_runtime": 0.929,
+      "eval_samples_per_second": 543.623,
+      "eval_steps_per_second": 17.224,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.8095519542694092,
+      "learning_rate": 0.0001625751143624527,
+      "loss": 0.6195,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6633663366336634,
+      "eval_f1": 0.7007042253521126,
+      "eval_loss": 0.5977084636688232,
+      "eval_mcc": 0.33809736315331057,
+      "eval_precision": 0.629746835443038,
+      "eval_recall": 0.7896825396825397,
+      "eval_runtime": 0.9344,
+      "eval_samples_per_second": 540.431,
+      "eval_steps_per_second": 17.123,
+      "step": 594
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.1215713024139404,
+      "learning_rate": 0.00013006009148996216,
+      "loss": 0.5905,
+      "step": 891
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6554455445544555,
+      "eval_f1": 0.712871287128713,
+      "eval_loss": 0.602749228477478,
+      "eval_mcc": 0.34040109061689877,
+      "eval_precision": 0.6101694915254238,
+      "eval_recall": 0.8571428571428571,
+      "eval_runtime": 0.9266,
+      "eval_samples_per_second": 545.023,
+      "eval_steps_per_second": 17.268,
+      "step": 891
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.1008222103118896,
+      "learning_rate": 9.754506861747161e-05,
+      "loss": 0.5654,
+      "step": 1188
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6712871287128713,
+      "eval_f1": 0.7224080267558528,
+      "eval_loss": 0.59177166223526,
+      "eval_mcc": 0.36958040539129916,
+      "eval_precision": 0.6242774566473989,
+      "eval_recall": 0.8571428571428571,
+      "eval_runtime": 0.9407,
+      "eval_samples_per_second": 536.843,
+      "eval_steps_per_second": 17.009,
+      "step": 1188
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.422161817550659,
+      "learning_rate": 6.503004574498108e-05,
+      "loss": 0.5459,
+      "step": 1485
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6752475247524753,
+      "eval_f1": 0.7018181818181819,
+      "eval_loss": 0.5669044852256775,
+      "eval_mcc": 0.356691478314268,
+      "eval_precision": 0.6476510067114094,
+      "eval_recall": 0.7658730158730159,
+      "eval_runtime": 0.9343,
+      "eval_samples_per_second": 540.495,
+      "eval_steps_per_second": 17.125,
+      "step": 1485
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2079,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 3653506329900.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9148462770396972,
+    "learning_rate": 0.00022760516010743377,
+    "num_train_epochs": 7,
+    "temperature": 11
+  }
+}

run-31/checkpoint-1485/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8131558b780b77bdf48e590f1c8267970dee97d61ef55d4d3c8bc00b44e025a2
+size 4920