Training in progress, epoch 1

logs/events.out.tfevents.1709880700.6c1c016b0e3e.7263.22

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e629391b037fc2da3c18218a8b5e912b0603498e4c7ec3bfaa0fe22a4d39721
-size 5984
+oid sha256:befcd532f3f764a0320a0fd5fea069c26ec10f374ec2c383c9f7dd3a49bb947d
+size 6667

logs/events.out.tfevents.1709881034.6c1c016b0e3e.7263.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf19423d2124bd21a8bfe929f60970f322dbf765c34ead67e2e89e7b2b2ea3a
+size 5313

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df70405d100f7bf9dc1a1db0091dad4f85aa97b8025df5765e911bc8fa60588e
+oid sha256:36d9b2604570e6a88b9e5a95f8bdfe25badec2bf01898c41786487afce793499
 size 17549312

run-23/checkpoint-48/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-23/checkpoint-48/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d9b2604570e6a88b9e5a95f8bdfe25badec2bf01898c41786487afce793499
+size 17549312

run-23/checkpoint-48/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99d73385412458cba73dd558f6b2397c34a52f90f3817f77edbea8ec24c8c596
+size 35122746

run-23/checkpoint-48/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f731098665929ed6a815501631b54240caaac6508207c5c55cf0fe36ad39b17
+size 14054

run-23/checkpoint-48/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e51e3fe74fdb62188ad69973968190c4d665b35b8da2ec4b503fee159d0ba0b
+size 1064

run-23/checkpoint-48/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-48/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-48/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.7632093933463796,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-48",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 48,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.5342754125595093,
+      "learning_rate": 0.00022562537376582823,
+      "loss": 0.5823,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7632093933463796,
+      "eval_f1": 0.7962962962962963,
+      "eval_loss": 0.48644715547561646,
+      "eval_precision": 0.6986706056129985,
+      "eval_recall": 0.9256360078277887,
+      "eval_runtime": 26.8879,
+      "eval_samples_per_second": 38.01,
+      "eval_steps_per_second": 0.595,
+      "step": 48
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 192,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9259836100395409,
+    "learning_rate": 0.000300833831687771,
+    "num_train_epochs": 4,
+    "temperature": 27
+  }
+}

run-23/checkpoint-48/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72cddafb614267648e2058beccba005678ef941672ddb888715c22a753d1de0
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a3368b5b0af1d21214eacb240625f81c73bbf2fea6c8e26456256938e253883
+oid sha256:d72cddafb614267648e2058beccba005678ef941672ddb888715c22a753d1de0
 size 4920