Training in progress, epoch 2

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6976c2cb3f6e40faf688d2de74b19f8ffcbad5745eadc000ab96c53714662fcf
-size 5482
+oid sha256:2b1aa86991be18d55caccd812fcd88c2e17b51eb7436d95aad20a55b0b95f1b9
+size 6212

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1527adeb85dac49900b7c0e2935bafcc3e88ee6d9c182bf5eea0d8a7fb783b74
+oid sha256:9ae2cfffaea7553ac5a5fc59df6133129d6967fa6574fdf206084b5674ce3f2b
 size 17549312

run-0/checkpoint-3176/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-3176/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae2cfffaea7553ac5a5fc59df6133129d6967fa6574fdf206084b5674ce3f2b
+size 17549312

run-0/checkpoint-3176/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d264b0b33a218190e4553ac49254ad31f19c8a9d9a274c4d270cdc79d5f5203
+size 35123898

run-0/checkpoint-3176/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1a5639c0ad118ba9a8c782a537e44e599d8a964db5e9d2de1ad5a8f5134ec48
+size 14308

run-0/checkpoint-3176/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5630a729ef130f9622ab8023564f8a1f63fdddf82f44dd633158d5fef29fe60
+size 1064

run-0/checkpoint-3176/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-3176/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-3176/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6808594364866992,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-3176",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3176,
+  "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
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.73245108127594,
+      "learning_rate": 2.4516582246749238e-05,
+      "loss": 0.5518,
+      "step": 3176
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6808594364866992,
+      "eval_f1": 0.21338506304558677,
+      "eval_loss": 0.5477257370948792,
+      "eval_mcc": 0.15677700026841318,
+      "eval_precision": 0.5978260869565217,
+      "eval_recall": 0.12987012987012986,
+      "eval_runtime": 23.7421,
+      "eval_samples_per_second": 535.167,
+      "eval_steps_per_second": 16.763,
+      "step": 3176
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9528,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 7817788152600.0,
+  "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-3176/training_args.bin

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