Training in progress, epoch 1

logs/events.out.tfevents.1713440172.ec9626078864.14834.37

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc247875deb68c274ebe90e52e8260f677779ab5c56b04542b75b2cb19e1bca
-size 6137
+oid sha256:b2d2fb68bdc7115d83a48796f330a7d2126c193f19b68bf7622a8a49fa775eb5
+size 6867

logs/events.out.tfevents.1713440327.ec9626078864.14834.38

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4af3bb693e3d353a6e0229348fe8dbc672fb2fb41d9e153fc98ff240e52c5dd
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a832fe0e87ed1c401c936d873dc5b84aea5bc7739ccb8d953ff5bcee7e7ef2c0
+oid sha256:15cf5898a22b16102f891e57f4c9088e0e9375229b4ef5c46ae012291f92aaf5
 size 17549312

run-37/checkpoint-645/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-37/checkpoint-645/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cf5898a22b16102f891e57f4c9088e0e9375229b4ef5c46ae012291f92aaf5
+size 17549312

run-37/checkpoint-645/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f6ad4f8b9656ee2677319ab1f435a5f3abf9a16f5cb537f3cd228a12265acdb
+size 35123898

run-37/checkpoint-645/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f64cda8af0c2d214cf65bdf171fde38f18025a5a08f9a451c61fdf726867d7c2
+size 14308

run-37/checkpoint-645/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de570a5e23c89a1014250db19f8cb37d18c1349296e23a3bf15c11f70140a589
+size 1064

run-37/checkpoint-645/special_tokens_map.json

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

run-37/checkpoint-645/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-37/checkpoint-645/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.8949205118262893,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-37/checkpoint-645",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 645,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3864041566848755,
+      "learning_rate": 0.00016868362667848253,
+      "loss": 0.2983,
+      "step": 645
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8949205118262893,
+      "eval_f1": 0.2322946175637394,
+      "eval_loss": 0.2774158716201782,
+      "eval_mcc": 0.257425944719354,
+      "eval_precision": 0.5985401459854015,
+      "eval_recall": 0.14411247803163443,
+      "eval_runtime": 9.9039,
+      "eval_samples_per_second": 520.804,
+      "eval_steps_per_second": 16.357,
+      "step": 645
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1586942532600.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8497931576459636,
+    "learning_rate": 0.0001874262518649806,
+    "num_train_epochs": 10,
+    "temperature": 17
+  }
+}

run-37/checkpoint-645/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09573e66bd1616796d5c7cf2c8e806aea231a9366717caf7c85276193ae906a9
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55b9441e34a21e4a66798da0660dd78cfbc1fc134f718f844bfafae288bd059
+oid sha256:09573e66bd1616796d5c7cf2c8e806aea231a9366717caf7c85276193ae906a9
 size 4984