Training in progress, epoch 1

logs/events.out.tfevents.1711302805.73e3a81c01ef.4225.39

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acd320d146dbc2c6b6ae8a9b327aa082b11297851931753c34eed692fbd11eb0
-size 6137
+oid sha256:69392487e4d5b405a7074432b8feb4ff49c80576b2799d038bb80457bfdaa893
+size 6867

logs/events.out.tfevents.1711303658.73e3a81c01ef.4225.40

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f4d462a23a762f0df25fc857e287661a2db81df3638097d3b201bd6134257cd
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5318e337251228991fef333f3bce7d142ac73243f769096a9026b15b7fadfbf6
+oid sha256:704f96b09d0922e81eb8621af59ed27b6b35cacd7365b9d0fed7675a0031cf08
 size 17549312

run-40/checkpoint-192/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-40/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:704f96b09d0922e81eb8621af59ed27b6b35cacd7365b9d0fed7675a0031cf08
+size 17549312

run-40/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d5d90598962e3ab4c9334febde752ff154b7755ea276f16a614e851644e0f6f
+size 35122746

run-40/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
+size 14054

run-40/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9f370535ecd9f9ee5464800f6cb488e325f6ae2cd629abdb4874ebbd8d7041
+size 1064

run-40/checkpoint-192/special_tokens_map.json

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

run-40/checkpoint-192/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-40/checkpoint-192/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.8033268101761253,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-40/checkpoint-192",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 7.570804595947266,
+      "learning_rate": 9.127982348433665e-05,
+      "loss": 0.5774,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8033268101761253,
+      "eval_f1": 0.8222811671087534,
+      "eval_loss": 0.45489490032196045,
+      "eval_mcc": 0.6209445541298213,
+      "eval_precision": 0.75,
+      "eval_recall": 0.9099804305283757,
+      "eval_runtime": 67.0612,
+      "eval_samples_per_second": 15.24,
+      "eval_steps_per_second": 0.477,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 768,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9602502972445941,
+    "learning_rate": 0.00012170643131244887,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 29
+  }
+}

run-40/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9eb176719296b7eda907810ef79c5712ba925be55e9de51dc1da95d3b26e91c
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac6423a3ed6a784bdda8d419fff51372698dadb8e3f72fa7fe1bb692c0ab80b
+oid sha256:d9eb176719296b7eda907810ef79c5712ba925be55e9de51dc1da95d3b26e91c
 size 4984