Training in progress, epoch 2

logs/events.out.tfevents.1713587081.1376c752d37a.9760.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d7873e97e6aa604cec41f254af7b299c8220275ee2eca1220fa9df817dde412
-size 5483
+oid sha256:297f50f3641cdfba62fbd62fb3c236632efc18ff2bddf9ff5d73fcefa5fea6de
+size 6213

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a61439248471c62817c89323c5caa7b4350eb7c827fc7cd24810931f3852c1a
+oid sha256:59ddfe72b81e4efbf566f050cc5593e0bfc1ad802887aa06c88ff89265121f54
 size 17549312

run-2/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-2/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ddfe72b81e4efbf566f050cc5593e0bfc1ad802887aa06c88ff89265121f54
+size 17549312

run-2/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878a1bbb375ab80469b569f95f8e4b3b2fe87abbc95686c026ec45014f126741
+size 35123898

run-2/checkpoint-428/rng_state.pth

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

run-2/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a979f8a6a6de0fcacdbb7bcc808be39487353c946005197eb2031d2d6cfcb186
+size 1064

run-2/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-2/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-2/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7375512595196251,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 4.634866237640381,
+      "learning_rate": 0.00022230485769079655,
+      "loss": 0.4904,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7223198594024605,
+      "eval_f1": 0.4261501210653753,
+      "eval_loss": 0.456611692905426,
+      "eval_mcc": 0.31390897314151045,
+      "eval_precision": 0.6848249027237354,
+      "eval_recall": 0.3093145869947276,
+      "eval_runtime": 3.1485,
+      "eval_samples_per_second": 542.168,
+      "eval_steps_per_second": 17.151,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5362380743026733,
+      "learning_rate": 0.000194516750479447,
+      "loss": 0.4471,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7375512595196251,
+      "eval_f1": 0.4628297362110312,
+      "eval_loss": 0.44590938091278076,
+      "eval_mcc": 0.3591774667498448,
+      "eval_precision": 0.7283018867924528,
+      "eval_recall": 0.3391915641476274,
+      "eval_runtime": 3.1481,
+      "eval_samples_per_second": 542.232,
+      "eval_steps_per_second": 17.153,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1049551328880.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7932456774257669,
+    "learning_rate": 0.00025009296490214613,
+    "num_train_epochs": 9,
+    "temperature": 23
+  }
+}

run-2/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89992d1c1b0b499ec7dee4b5a730ed684159d7afeb30eaab398451703cc62b58
+size 5048