Training in progress, epoch 2

logs/events.out.tfevents.1709746826.d65e8524b0f6.5185.16

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c31fb9097de6b5e6623426f94dc8d1c3a8477f0c85915b68c4d9c3acbbcc3df
-size 5315
+oid sha256:402b8d21542a2d4fb68f084e5b7d05be2952069dd08cd450fee175627a20fd5c
+size 5985

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840f48c35da7a97bf8423c4d56b59abfff31d02d3333ba76897059f3fe2011af
+oid sha256:c1ae99479f844e3d5c0330ffce135ff0c0adcd53da25d99bf2a8b922d2f2ea41
 size 17549312

run-16/checkpoint-110/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-16/checkpoint-110/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1ae99479f844e3d5c0330ffce135ff0c0adcd53da25d99bf2a8b922d2f2ea41
+size 17549312

run-16/checkpoint-110/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:136f8b5641a78c98eb23981bbd984d7cfb9a96ef49660bd602adb93d172322e7
+size 35122746

run-16/checkpoint-110/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be1ffcfe67c08998f3ebfe69d54d9a75a4b43d0d5ac932651792bdaa39681ca
+size 14054

run-16/checkpoint-110/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bf38ff33dc49db1478a1ce63a02ec741056eee037a60a1f5d0f1526edf8488e
+size 1064

run-16/checkpoint-110/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-110/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-110/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.7906066536203522,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-110",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 110,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.115179181098938,
+      "learning_rate": 0.0001711445020920055,
+      "loss": 0.4773,
+      "step": 55
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7181996086105675,
+      "eval_f1": 0.7125748502994013,
+      "eval_loss": 0.4258935749530792,
+      "eval_precision": 0.7270875763747454,
+      "eval_recall": 0.6986301369863014,
+      "eval_runtime": 27.8796,
+      "eval_samples_per_second": 36.658,
+      "eval_steps_per_second": 1.148,
+      "step": 55
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.2601873874664307,
+      "learning_rate": 0.0001283583765690041,
+      "loss": 0.4242,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7906066536203522,
+      "eval_f1": 0.8018518518518519,
+      "eval_loss": 0.40127235651016235,
+      "eval_precision": 0.7609841827768014,
+      "eval_recall": 0.8473581213307241,
+      "eval_runtime": 27.9127,
+      "eval_samples_per_second": 36.614,
+      "eval_steps_per_second": 1.146,
+      "step": 110
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 275,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 56,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6575195229183988,
+    "learning_rate": 0.00021393062761500687,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 56,
+    "temperature": 22
+  }
+}

run-16/checkpoint-110/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853b9bd91d8e7500b2e68ab85992695ef180b9f0e29125c26ec58713c7d0700a
+size 4920