Training in progress, epoch 2

logs/events.out.tfevents.1711302805.73e3a81c01ef.4225.39

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee0bc51549ae149dd994e547f08e98778d6e71ad0991fddd0cc0a0c9f0e5dce7
-size 5407
+oid sha256:acd320d146dbc2c6b6ae8a9b327aa082b11297851931753c34eed692fbd11eb0
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a892b746a07276e399f4f46cb6c3beae26ad1334fed3d95d95bcd54c663c739e
+oid sha256:5318e337251228991fef333f3bce7d142ac73243f769096a9026b15b7fadfbf6
 size 17549312

run-39/checkpoint-384/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-39/checkpoint-384/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5318e337251228991fef333f3bce7d142ac73243f769096a9026b15b7fadfbf6
+size 17549312

run-39/checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca86038bfee7d44a450792c3a8347752dc4f784b9496e00852293dfab17debc
+size 35122746

run-39/checkpoint-384/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2558f72cda987826e5e7caf54cc6282fe335ebecbddfed7bb83f0184d1f54cc
+size 14054

run-39/checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25e030688308e0dd73054b7f6b089b6645a224a62703d9c7609658de2472d95
+size 1064

run-39/checkpoint-384/special_tokens_map.json

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

run-39/checkpoint-384/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-39/checkpoint-384/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.8072407045009785,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-39/checkpoint-384",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 384,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.2173728942871094,
+      "learning_rate": 0.00014443994065802148,
+      "loss": 0.5028,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7964774951076321,
+      "eval_f1": 0.8142857142857143,
+      "eval_loss": 0.43328145146369934,
+      "eval_mcc": 0.6041697213986457,
+      "eval_precision": 0.7487684729064039,
+      "eval_recall": 0.8923679060665362,
+      "eval_runtime": 67.0422,
+      "eval_samples_per_second": 15.244,
+      "eval_steps_per_second": 0.477,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.414307594299316,
+      "learning_rate": 0.0001083299554935161,
+      "loss": 0.4349,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8072407045009785,
+      "eval_f1": 0.8078048780487805,
+      "eval_loss": 0.4155944585800171,
+      "eval_mcc": 0.6144919988734048,
+      "eval_precision": 0.8054474708171206,
+      "eval_recall": 0.8101761252446184,
+      "eval_runtime": 67.2386,
+      "eval_samples_per_second": 15.2,
+      "eval_steps_per_second": 0.476,
+      "step": 384
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.799928647191713,
+    "learning_rate": 0.00018054992582252683,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "temperature": 50
+  }
+}

run-39/checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ac6423a3ed6a784bdda8d419fff51372698dadb8e3f72fa7fe1bb692c0ab80b
+size 4984