Training in progress, epoch 2

logs/events.out.tfevents.1711299404.73e3a81c01ef.4225.31

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff4c45af4d3663e28d9491ff93e5cd4cd2fbaf0646d4e4f637011d9a72ee849
-size 5406
+oid sha256:1cfc5b805f4c45b973d15540ed14bc41ec106a3670f9a3c132e9e69cd8413982
+size 6136

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901a1097107793d8240b87db4dd0744ff001d193ebe8477cee119191f0920b96
+oid sha256:9a9eb2d011937667a03ac6d6b2ad0c9bae7e14cb2a2711214991cbc22c9d74c0
 size 17549312

run-31/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-31/checkpoint-384/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9eb2d011937667a03ac6d6b2ad0c9bae7e14cb2a2711214991cbc22c9d74c0
+size 17549312

run-31/checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02feb4354d983f4788e201cd79941b377caf5dab2a9011553938140a74ad742c
+size 35122746

run-31/checkpoint-384/rng_state.pth

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

run-31/checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff25e450142e583c19a4dc312929efe9736af8a3c6ba4fab401dd7bbadef21ca
+size 1064

run-31/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-31/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-31/checkpoint-384/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.7808219178082192,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/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": 2.0108234882354736,
+      "learning_rate": 0.0005125121117318405,
+      "loss": 0.5275,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7720156555772995,
+      "eval_f1": 0.8043660789252729,
+      "eval_loss": 0.45868822932243347,
+      "eval_mcc": 0.5764707637440674,
+      "eval_precision": 0.7044117647058824,
+      "eval_recall": 0.9373776908023483,
+      "eval_runtime": 66.8111,
+      "eval_samples_per_second": 15.297,
+      "eval_steps_per_second": 0.479,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.709124565124512,
+      "learning_rate": 0.00038438408379888036,
+      "loss": 0.4786,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7808219178082192,
+      "eval_f1": 0.7773359840954275,
+      "eval_loss": 0.45048943161964417,
+      "eval_mcc": 0.5619193527696978,
+      "eval_precision": 0.7898989898989899,
+      "eval_recall": 0.7651663405088063,
+      "eval_runtime": 67.4944,
+      "eval_samples_per_second": 15.142,
+      "eval_steps_per_second": 0.474,
+      "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": 0.8160345152304423,
+    "learning_rate": 0.0006406401396648006,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "temperature": 43
+  }
+}

run-31/checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c096343b9527bbdd82bd00bc265d1adc282a998f9dc111465e8a46e5d89909
+size 4984