Training in progress, epoch 4

logs/events.out.tfevents.1713441600.ec9626078864.14834.43

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f3ec64cc354a66a388f97a269557bdb6d42c149dc9a484522509027b8dc8108
-size 6867
+oid sha256:497af15d9ae51653a422a59d1659d0b8a94f68eea17641572ebb9e879ca22d71
+size 7597

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7e7df1fd3131296a450359cacd1c2a72a789053523c89229b289ea26111ad8
+oid sha256:a54cf9d8ced238affe019cd58f1d22e589e16e5a7a943ae2a209e8467079267b
 size 17549312

run-42/checkpoint-2580/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": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-42/checkpoint-2580/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54cf9d8ced238affe019cd58f1d22e589e16e5a7a943ae2a209e8467079267b
+size 17549312

run-42/checkpoint-2580/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de84f8c6beb4d7d9dc9e04979a4d472df7b6bbb848ae354d2e779aecc9ae4fc9
+size 35123898

run-42/checkpoint-2580/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a023a654d9d331ee734f6327c4a0681d27975c593b68916f513cbf43ea84370
+size 14308

run-42/checkpoint-2580/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd0a5e0e99f4d98ada014ff40ea65ef5c430243fe80aa4defd6df9ccc4b795e
+size 1064

run-42/checkpoint-2580/special_tokens_map.json

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

run-42/checkpoint-2580/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-42/checkpoint-2580/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9034509499806126,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-42/checkpoint-2580",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2580,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0985572338104248,
+      "learning_rate": 0.00015144713450034053,
+      "loss": 0.3039,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8945327646374563,
+      "eval_f1": 0.19287833827893175,
+      "eval_loss": 0.2821837365627289,
+      "eval_mcc": 0.23408659817261018,
+      "eval_precision": 0.6190476190476191,
+      "eval_recall": 0.11423550087873462,
+      "eval_runtime": 9.9917,
+      "eval_samples_per_second": 516.228,
+      "eval_steps_per_second": 16.213,
+      "step": 645
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5096140503883362,
+      "learning_rate": 0.0001135853508752554,
+      "loss": 0.2797,
+      "step": 1290
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8972469949592865,
+      "eval_f1": 0.2182890855457227,
+      "eval_loss": 0.27733176946640015,
+      "eval_mcc": 0.26666876109371096,
+      "eval_precision": 0.6788990825688074,
+      "eval_recall": 0.13005272407732865,
+      "eval_runtime": 9.9433,
+      "eval_samples_per_second": 518.739,
+      "eval_steps_per_second": 16.292,
+      "step": 1290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6613279581069946,
+      "learning_rate": 7.572356725017026e-05,
+      "loss": 0.2739,
+      "step": 1935
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8986041101202016,
+      "eval_f1": 0.2015267175572519,
+      "eval_loss": 0.2698163688182831,
+      "eval_mcc": 0.27313390239686397,
+      "eval_precision": 0.7674418604651163,
+      "eval_recall": 0.11599297012302284,
+      "eval_runtime": 9.9136,
+      "eval_samples_per_second": 520.296,
+      "eval_steps_per_second": 16.341,
+      "step": 1935
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.9136298894882202,
+      "learning_rate": 3.786178362508513e-05,
+      "loss": 0.2687,
+      "step": 2580
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9034509499806126,
+      "eval_f1": 0.37121212121212127,
+      "eval_loss": 0.26799800992012024,
+      "eval_mcc": 0.37243582190582525,
+      "eval_precision": 0.6591928251121076,
+      "eval_recall": 0.2583479789103691,
+      "eval_runtime": 9.9335,
+      "eval_samples_per_second": 519.254,
+      "eval_steps_per_second": 16.308,
+      "step": 2580
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3225,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6347770130400.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8695064116191267,
+    "learning_rate": 0.00018930891812542566,
+    "num_train_epochs": 5,
+    "temperature": 14
+  }
+}

run-42/checkpoint-2580/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f487547e1a6bc80b9d25d87862de09d85f194b31f8fd35327451c8ac970dbb9
+size 4984