Training in progress, epoch 2

logs/events.out.tfevents.1699955672.45c71320b2c6.349.39

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6629d7a15d1c273f09a2142d1d0bf6c739377faf1237374f4352951ff7a455b
-size 4774
+oid sha256:82225a380b013322c92c5265036c294f6d99f8cc2678ed4c2122666de5fe4b8b
+size 5254

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc7b42ae7dab5c655a6e000e6e618833a70b34d566b70bc91c300d25971bea7
+oid sha256:7850e4e2f660a302ff8dd9b2539d0de3f2559e8ceef2959a7d799638d9d69059
 size 17549312

run-38/checkpoint-1054/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-38/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7850e4e2f660a302ff8dd9b2539d0de3f2559e8ceef2959a7d799638d9d69059
+size 17549312

run-38/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d15234386a7b60e400253ce2054b8ca92239bd61728592e665d04d4c3153478
+size 35123898

run-38/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57fdff683e14337980bac7da3d561a7fdab384be06942739a4198db7026ad4c6
+size 14308

run-38/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0306e888b090b6aa91b22335a5714a92c3bdc1e697bb11f7c5e6e778143432a3
+size 1064

run-38/checkpoint-1054/special_tokens_map.json

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

run-38/checkpoint-1054/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-38/checkpoint-1054/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8268348623853211,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-38/checkpoint-1054",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00012948443285046093,
+      "loss": 1.4057,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.2933424711227417,
+      "eval_runtime": 0.8552,
+      "eval_samples_per_second": 1019.641,
+      "eval_steps_per_second": 8.185,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.635023808927704e-05,
+      "loss": 0.6974,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.3485634326934814,
+      "eval_runtime": 0.8351,
+      "eval_samples_per_second": 1044.162,
+      "eval_steps_per_second": 8.382,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2108,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 16194449161860.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.44460291675011115,
+    "learning_rate": 0.00017253677904473553,
+    "num_train_epochs": 4,
+    "temperature": 10
+  }
+}

run-38/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2702df95ba1ba1e300ababdd324a5323d1148b7262e3da30ea7f850f2739e956
+size 4664