Training in progress, epoch 2

logs/events.out.tfevents.1711298377.8cc2eef2edb7.2942.23

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbbc565826ee3bbdb73a6c5ad22421a4f21feaebcbd8a6c344025ea04aa7888
-size 5407
+oid sha256:42ffb7e4e4f5c611c64917746758fb5bbaffabe7267ebdec749c48a4c177789a
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f01780a229ee2eabe716b8cc84e6bb9c22daa03c8cc81186440efc669053d3d
+oid sha256:dcbdb84b7ba667855307dfcd0c324cdfa8c1caedd5ee92e39ba6b11a8e80b6b1
 size 17549312

run-23/checkpoint-594/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-23/checkpoint-594/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbdb84b7ba667855307dfcd0c324cdfa8c1caedd5ee92e39ba6b11a8e80b6b1
+size 17549312

run-23/checkpoint-594/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2deb7307918178f84ced5fb962c3a53d2da15eef09f33ce03ebd17215a06ba21
+size 35123898

run-23/checkpoint-594/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07703232e8862ddf942921f960a4672ac4604f89da896da8b4bab92d3ecc94f2
+size 14308

run-23/checkpoint-594/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a02cdb57de490b8d5be7e86d89291dccddd33207be3ebc26145baab4ac20172d
+size 1064

run-23/checkpoint-594/special_tokens_map.json

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

run-23/checkpoint-594/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-23/checkpoint-594/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6237623762376238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-594",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 594,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.666294813156128,
+      "learning_rate": 0.00034226276676608983,
+      "loss": 0.688,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5900990099009901,
+      "eval_f1": 0.5389755011135857,
+      "eval_loss": 0.6901505589485168,
+      "eval_mcc": 0.18426952240167496,
+      "eval_precision": 0.6142131979695431,
+      "eval_recall": 0.4801587301587302,
+      "eval_runtime": 0.9313,
+      "eval_samples_per_second": 542.229,
+      "eval_steps_per_second": 17.18,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4357942342758179,
+      "learning_rate": 0.00029336808579950554,
+      "loss": 0.6503,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6237623762376238,
+      "eval_f1": 0.6895424836601307,
+      "eval_loss": 0.641117513179779,
+      "eval_mcc": 0.27448731892832257,
+      "eval_precision": 0.5861111111111111,
+      "eval_recall": 0.8373015873015873,
+      "eval_runtime": 0.9311,
+      "eval_samples_per_second": 542.381,
+      "eval_steps_per_second": 17.184,
+      "step": 594
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2376,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1461402531960.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9955244977733414,
+    "learning_rate": 0.00039115744773267407,
+    "num_train_epochs": 8,
+    "temperature": 44
+  }
+}

run-23/checkpoint-594/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ca7c7c08b7a76c03d0e0693b58755b1f2d1740559f1524ae92203199ea260ef
+size 4920