Training in progress, epoch 2

logs/events.out.tfevents.1711298025.8cc2eef2edb7.2942.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eae5eab5c2678aa462f4134430de32998d68b3eb88b8536b4fcd9cdde051b5e
-size 5407
+oid sha256:9e135f564bfe5361558eda1a54e02747357b3662444d10b36dbdaace1f71f194
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1f39de00193a7f5cb459cd8ed44763bfd2bf066a762af7ec50ec37dcba522a
+oid sha256:3f44df878d28abc84112bb60946d51999835ba4c8390b93448ebdfea2803581c
 size 17549312

run-16/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-16/checkpoint-594/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f44df878d28abc84112bb60946d51999835ba4c8390b93448ebdfea2803581c
+size 17549312

run-16/checkpoint-594/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b0a057c9254d063a27a42aae09b82527974d15d0b4e19a8fc05ea987fd9f0ff
+size 35123898

run-16/checkpoint-594/rng_state.pth

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

run-16/checkpoint-594/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fa438eaddbd274bf781d037a148e85701be52713fdbee39df50e35fdf02122
+size 1064

run-16/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-16/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-16/checkpoint-594/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.6,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/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": 1.6842290163040161,
+      "learning_rate": 0.00013702102722124262,
+      "loss": 0.6194,
+      "step": 297
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5069306930693069,
+      "eval_f1": 0.023529411764705882,
+      "eval_loss": 0.6244187951087952,
+      "eval_mcc": 0.07745844229442526,
+      "eval_precision": 1.0,
+      "eval_recall": 0.011904761904761904,
+      "eval_runtime": 0.9461,
+      "eval_samples_per_second": 533.75,
+      "eval_steps_per_second": 16.911,
+      "step": 297
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.26532781124115,
+      "learning_rate": 0.0001096168217769941,
+      "loss": 0.6076,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6,
+      "eval_f1": 0.6366906474820144,
+      "eval_loss": 0.6058114767074585,
+      "eval_mcc": 0.20470740045924352,
+      "eval_precision": 0.5822368421052632,
+      "eval_recall": 0.7023809523809523,
+      "eval_runtime": 0.946,
+      "eval_samples_per_second": 533.844,
+      "eval_steps_per_second": 16.914,
+      "step": 594
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1782,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1461402531960.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8675008492554994,
+    "learning_rate": 0.00016442523266549115,
+    "num_train_epochs": 6,
+    "temperature": 44
+  }
+}

run-16/checkpoint-594/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a760801f195b6d23ef8a34d598b151e1a6b3508f20799769efbe955042d9987a
+size 4920