Training in progress, epoch 2

logs/events.out.tfevents.1711271348.73e3a81c01ef.4225.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b97de26d61f3863b5dc528a7834184a133d16afeae8566cc9f02ea1d9d8f6f
-size 5407
+oid sha256:c1cf09d166fe251a9e7f6f704d6d64a5df64c7ea95eb1e741ffae3dc34a685f2
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b4b5dc69cb0469a967756916d6a6944e64d282b3dddd187d83bb80ec725cf81
+oid sha256:ef73119b0b60c621a177a9d7f01aea5d725f8c75eebc2cdc75c069301fe48982
 size 17549312

run-2/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-2/checkpoint-384/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef73119b0b60c621a177a9d7f01aea5d725f8c75eebc2cdc75c069301fe48982
+size 17549312

run-2/checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90c36dfd31c14fa477357a9e7a5f3bda8f47d637ef3cad6f62e89577fbcc460b
+size 35122746

run-2/checkpoint-384/rng_state.pth

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

run-2/checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b12a6ada01fa3e4810bbb5aaaa2ea105f9590d844d997dfd8626858b304761a
+size 1064

run-2/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-2/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-2/checkpoint-384/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.5587084148727984,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 1.0371571779251099,
+      "learning_rate": 0.0001305282668790618,
+      "loss": 0.3216,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5499021526418787,
+      "eval_f1": 0.23841059602649006,
+      "eval_loss": 0.2955350875854492,
+      "eval_mcc": 0.17350853577425898,
+      "eval_precision": 0.7741935483870968,
+      "eval_recall": 0.14090019569471623,
+      "eval_runtime": 67.6225,
+      "eval_samples_per_second": 15.113,
+      "eval_steps_per_second": 0.473,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.1835968494415283,
+      "learning_rate": 0.00011421223351917907,
+      "loss": 0.2979,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5587084148727984,
+      "eval_f1": 0.2642740619902121,
+      "eval_loss": 0.29196101427078247,
+      "eval_mcc": 0.19586518668589045,
+      "eval_precision": 0.7941176470588235,
+      "eval_recall": 0.15851272015655576,
+      "eval_runtime": 67.5618,
+      "eval_samples_per_second": 15.127,
+      "eval_steps_per_second": 0.474,
+      "step": 384
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1728,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.4208671172864604,
+    "learning_rate": 0.00014684430023894452,
+    "num_train_epochs": 9,
+    "per_device_train_batch_size": 16,
+    "temperature": 48
+  }
+}

run-2/checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e5acc29cf7d39a1c2a69461e588dfa38fe51a74003ef00804ced1c8aab86d3
+size 4984