Training in progress, epoch 2

logs/events.out.tfevents.1713587634.1376c752d37a.9760.8

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4927c927d763e2df773d94f6259db98b0e7b3ba0dbb756dc0a1a094669314464
-size 5482
+oid sha256:64c5713b993f00fd305b0a33ff9689deaf9ef3193b8e12f8399324033377bb6a
+size 6212

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a73004b9dc99b72b324deca926b44e10440c4ec20c871cf4bdd5f18fc308a3e0
+oid sha256:025acb7c5748fa49c234383216909cbb29d33e640a60bb34108f8e17b66d18a0
 size 17549312

run-8/checkpoint-428/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:025acb7c5748fa49c234383216909cbb29d33e640a60bb34108f8e17b66d18a0
+size 17549312

run-8/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfede0fcf3aa78b3fc4169a5a8b58866c53a29f20c94586692eb0597f01d63cf
+size 35123898

run-8/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0c3b463a8fb08b95f5c77916114776bad3339b633df010e4ffd9b5ddabab1e
+size 14308

run-8/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f46d2f286c3d05f8f36b1dc17f91f61e56f664882c6a44344a7b4ea17c1ae97
+size 1064

run-8/checkpoint-428/special_tokens_map.json

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

run-8/checkpoint-428/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-8/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6877562975981254,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-8/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.8868563175201416,
+      "learning_rate": 0.00018706603069859162,
+      "loss": 0.3842,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6848271821909784,
+      "eval_f1": 0.1487341772151899,
+      "eval_loss": 0.3658275604248047,
+      "eval_mcc": 0.17137932324690125,
+      "eval_precision": 0.746031746031746,
+      "eval_recall": 0.08260105448154657,
+      "eval_runtime": 3.1455,
+      "eval_samples_per_second": 542.68,
+      "eval_steps_per_second": 17.167,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3482353687286377,
+      "learning_rate": 0.0001247106871323944,
+      "loss": 0.3585,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6877562975981254,
+      "eval_f1": 0.14446227929373995,
+      "eval_loss": 0.35682281851768494,
+      "eval_mcc": 0.19170644527903724,
+      "eval_precision": 0.8333333333333334,
+      "eval_recall": 0.07908611599297012,
+      "eval_runtime": 3.1465,
+      "eval_samples_per_second": 542.514,
+      "eval_steps_per_second": 17.162,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6014075049725551,
+    "learning_rate": 0.0002494213742647888,
+    "num_train_epochs": 4,
+    "temperature": 26
+  }
+}

run-8/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e51c19591d13eae2025648c30e5aa9d6d00ba5f9201e4264bd6d9c66f33e8d
+size 5048