Training in progress, epoch 1

logs/events.out.tfevents.1699954629.45c71320b2c6.349.30

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e88696d757df5bd9a2a5be55dfd4c0aeaa22a41e3c61b55e1092731a960395cc
-size 4773
+oid sha256:dd332a7b5ea2c1af1e72909ab4628157a41ce779678069d8212614fd6bfd861b
+size 5253

logs/events.out.tfevents.1699954767.45c71320b2c6.349.31

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:318dbd76827f62a58a5921cba2c70953d5e57ec0240610d7c79e9023220b093e
+size 4774

logs/events.out.tfevents.1699954834.45c71320b2c6.349.32

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8012bd86dc003ce956e9b5fd1c283465a92c705929ca8dcd774475883ce107ac
+size 4773

logs/events.out.tfevents.1699954902.45c71320b2c6.349.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6123bca2562ddf2c727554f79af98e313b408db6b105aeaf87e9cf13b5b828
+size 4773

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a840ab5f1b6d72646288436be217d5a501b94fa1dc90b8b84bc504fa7af692
+oid sha256:782ffe01b4beda62fb400f6942db2041d3248fe49f8c5101c3811dff7d036de1
 size 17549312

run-32/checkpoint-527/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-32/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:782ffe01b4beda62fb400f6942db2041d3248fe49f8c5101c3811dff7d036de1
+size 17549312

run-32/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83507c1366013404bf6ac4aef552ee4870000df3327ea33991aac01a8a801769
+size 35123898

run-32/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
+size 14308

run-32/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f310856d3960ce2d018b3299e91c71d435006e740bfc1f1580e874612caf0f2
+size 1064

run-32/checkpoint-527/special_tokens_map.json

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

run-32/checkpoint-527/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-32/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8153669724770642,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-32/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001480668498108177,
+      "loss": 1.0549,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.1070313453674316,
+      "eval_runtime": 0.838,
+      "eval_samples_per_second": 1040.515,
+      "eval_steps_per_second": 8.353,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5932726903126535,
+    "learning_rate": 0.0002961336996216354,
+    "num_train_epochs": 2,
+    "temperature": 30
+  }
+}

run-32/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74038a83ebb35a8cbfff68c5d73e772fea907e3b5c2b28485a640127c16f490
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0b1b05df4e956a9bd2288cd9b983e42ca707c0b619a8b0dbab965b149c3960
+oid sha256:b74038a83ebb35a8cbfff68c5d73e772fea907e3b5c2b28485a640127c16f490
 size 4664