Training in progress, epoch 2

logs/events.out.tfevents.1713587889.1376c752d37a.9760.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe6176881c666021d81515c11f3e5c55bbe3b52cf87fb25c9bc285453aaa6be
-size 5482
+oid sha256:4b4f351159d55bb7acdf33bead71c5c36d5be6dabe6f2c70b5eea867de86a1b7
+size 6212

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bf217176616957db81afaa727013dd843ec597db5ad1173a132bcd96a179788
+oid sha256:e3b84a61c3ccfff50f3e1e582b590a88411d8954c88388b4974f57c18f97b93e
 size 17549312

run-11/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-11/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3b84a61c3ccfff50f3e1e582b590a88411d8954c88388b4974f57c18f97b93e
+size 17549312

run-11/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90a238daf5f6c66aa50b0ec7e1b904316147df98747dd5ad58bc5975d3a742b3
+size 35123898

run-11/checkpoint-428/rng_state.pth

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

run-11/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cbc8e9787413be3cd236bbef343a3965ece2b9cc6f93132987190ae7f5db587
+size 1064

run-11/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-11/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-11/checkpoint-428/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.7311072056239016,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/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": 7.572170734405518,
+      "learning_rate": 0.00012123385931636098,
+      "loss": 0.5934,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7082601054481547,
+      "eval_f1": 0.435374149659864,
+      "eval_loss": 0.5416340827941895,
+      "eval_mcc": 0.28153811271695595,
+      "eval_precision": 0.6134185303514377,
+      "eval_recall": 0.3374340949033392,
+      "eval_runtime": 3.1348,
+      "eval_samples_per_second": 544.534,
+      "eval_steps_per_second": 17.226,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.894651412963867,
+      "learning_rate": 0.00010607962690181587,
+      "loss": 0.5286,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7311072056239016,
+      "eval_f1": 0.5069817400644469,
+      "eval_loss": 0.5141445398330688,
+      "eval_mcc": 0.35062725647270626,
+      "eval_precision": 0.6519337016574586,
+      "eval_recall": 0.4147627416520211,
+      "eval_runtime": 3.1601,
+      "eval_samples_per_second": 540.173,
+      "eval_steps_per_second": 17.088,
+      "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": 0.9696180923551023,
+    "learning_rate": 0.0001363880917309061,
+    "num_train_epochs": 9,
+    "temperature": 20
+  }
+}

run-11/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf09225d27944ca78423d64d6c64a16677c929bc8b03065b895767c7cb1b599b
+size 5048