Training in progress, epoch 1

logs/events.out.tfevents.1714699051.e992b94a7c88.3982.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6976c2cb3f6e40faf688d2de74b19f8ffcbad5745eadc000ab96c53714662fcf
+size 5482

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4229fc9e75bc118e79f8ea814d0ee9639b8d380d2872024babd1d6efaddcbfb1
+oid sha256:1527adeb85dac49900b7c0e2935bafcc3e88ee6d9c182bf5eea0d8a7fb783b74
 size 17549312

run-0/checkpoint-1588/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1588/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1527adeb85dac49900b7c0e2935bafcc3e88ee6d9c182bf5eea0d8a7fb783b74
+size 17549312

run-0/checkpoint-1588/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22047583a3b6b184cc87feabb4408e73f1b3ecde71a422b32c9eb95c78e0ad71
+size 35123898

run-0/checkpoint-1588/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937f4e47675de5e7170e218630c85dd36f459549fb8994b62c13ea83fc7a261c
+size 14308

run-0/checkpoint-1588/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17c50f31b1f83bf286c1ae759ea1c4fe961577f7533f73a1874b6ce831cc20c
+size 1064

run-0/checkpoint-1588/special_tokens_map.json

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

run-0/checkpoint-1588/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-0/checkpoint-1588/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6762159609633244,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-1588",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1588,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0009326934814453,
+      "learning_rate": 3.0645727808436554e-05,
+      "loss": 0.5665,
+      "step": 1588
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6762159609633244,
+      "eval_f1": 0.23045267489711932,
+      "eval_loss": 0.5539034605026245,
+      "eval_mcc": 0.1452179000925905,
+      "eval_precision": 0.5544554455445545,
+      "eval_recall": 0.14545454545454545,
+      "eval_runtime": 24.2515,
+      "eval_samples_per_second": 523.927,
+      "eval_steps_per_second": 16.411,
+      "step": 1588
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9528,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 3908894076300.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8938428030285009,
+    "learning_rate": 3.677487337012386e-05,
+    "num_train_epochs": 6,
+    "temperature": 20
+  }
+}

run-0/checkpoint-1588/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d81a1cb65c9dbcfca334e6ffd861fa3e7a117191813e4086b76fd566236b05
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150b15b1d19411a7e91166c553d8c2002694f55925d896e4f13fb5ee3aab8aaa
+oid sha256:68d81a1cb65c9dbcfca334e6ffd861fa3e7a117191813e4086b76fd566236b05
 size 4984