Training in progress, epoch 1

logs/events.out.tfevents.1699955052.45c71320b2c6.349.34

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17dc0b0e12df46ea2d1a8d1a00a70cc69997692504f99163fbaa79f605f24cb8
+size 4772

logs/events.out.tfevents.1699955120.45c71320b2c6.349.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f94ae47e9588fc2f20c6f6461aa80f9047514469b022e19d9bf112aebfec99f
+size 4772

logs/events.out.tfevents.1699955188.45c71320b2c6.349.36

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcda1723c457294c3f52d74403ee79a436cbecab53fafebbbdb86292ce63728
+size 4774

logs/events.out.tfevents.1699955256.45c71320b2c6.349.37

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717f033d13ef9b9b8094bfa9abbaf694ec3adc57964dc871e555c59261e1f5fb
+size 4774

logs/events.out.tfevents.1699955324.45c71320b2c6.349.38

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c17e3959c8413d3bc1ca473cc2a22d4ce085a2db6d42441762e3ed8c13ad5af
+size 4773

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6156c55e4bbf85b719663804844a8dd5c8bd4226c802fde8cc61bb0e5f1fc825
+oid sha256:d9d6fb435e3b4cccacb6a812c316e391205dd348cf5db2de5d98d0bc92bdaacd
 size 17549312

run-37/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-37/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d6fb435e3b4cccacb6a812c316e391205dd348cf5db2de5d98d0bc92bdaacd
+size 17549312

run-37/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a5ddc799bba8c639ea137d2a480dc8e9e1b2476ea7f3507bd19bc2266a836b
+size 35123898

run-37/checkpoint-527/rng_state.pth

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

run-37/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fca05647385833c06e4d6855782190c09e9565941f6f96ffbce282363e75fdd1
+size 1064

run-37/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-37/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-37/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-37/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": 0.00017523679418200662,
+      "loss": 0.9724,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.9702022671699524,
+      "eval_runtime": 0.921,
+      "eval_samples_per_second": 946.755,
+      "eval_steps_per_second": 7.6,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6866431858339781,
+    "learning_rate": 0.0002044429265456744,
+    "num_train_epochs": 7,
+    "temperature": 25
+  }
+}

run-37/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d435b3679d2a1f714478822e22782f8637eede037690bc95e46b9954583343cf
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b74038a83ebb35a8cbfff68c5d73e772fea907e3b5c2b28485a640127c16f490
+oid sha256:d435b3679d2a1f714478822e22782f8637eede037690bc95e46b9954583343cf
 size 4664