Training in progress, epoch 1

logs/events.out.tfevents.1713589659.1376c752d37a.9760.33

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a055f0c10438db0baa34a2fd7ae19b57fcb58bd11c7c92eeff6effa716cde88
-size 6942
+oid sha256:5937391009c7a3a50d3e63810e50a0aef5298a0e97e096021019fac4cf0769ec
+size 8402

logs/events.out.tfevents.1713589743.1376c752d37a.9760.34

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6d56413b88a65d3fe41d53ecf83847cc9fbf5feff41183a207e1d7ef26c8fd
+size 5482

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3634d006206df5e2759d8d8a64629a1a3335229c4eb1bce1fd4748bdd814c344
+oid sha256:6c7083431eb6fcd2c2ec7a4ec7a14fc1a11f2f8d6805544e01a2036c2d71a045
 size 17549312

run-33/checkpoint-856/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-33/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b88e412d6a4afe008e7d53eaa7bb7092566e79c10312df120498a84f96d4ad7
+size 17549312

run-33/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcca72e8d0a92ca2b530d1833f49afcaca0b69c0ed037770f4e3a08d83f5443c
+size 35123898

run-33/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
+size 14308

run-33/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73dec94c92d90907b7ac0fcff54750ffb7e414b2e6bdd4ac4cf4340bf7efe580
+size 1064

run-33/checkpoint-856/special_tokens_map.json

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

run-33/checkpoint-856/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-33/checkpoint-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.7141183362624487,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-33/checkpoint-642",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.1991143226623535,
+      "learning_rate": 6.724081136915917e-05,
+      "loss": 0.5853,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6924428822495606,
+      "eval_f1": 0.46373850868232896,
+      "eval_loss": 0.5429773330688477,
+      "eval_mcc": 0.26278004135127175,
+      "eval_precision": 0.5536585365853659,
+      "eval_recall": 0.3989455184534271,
+      "eval_runtime": 3.1406,
+      "eval_samples_per_second": 543.53,
+      "eval_steps_per_second": 17.194,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.212712287902832,
+      "learning_rate": 5.883570994801428e-05,
+      "loss": 0.5367,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7070884592852958,
+      "eval_f1": 0.536178107606679,
+      "eval_loss": 0.5276417136192322,
+      "eval_mcc": 0.32417590252227235,
+      "eval_precision": 0.5677799607072691,
+      "eval_recall": 0.507908611599297,
+      "eval_runtime": 3.1564,
+      "eval_samples_per_second": 540.802,
+      "eval_steps_per_second": 17.108,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.126155376434326,
+      "learning_rate": 5.043060852686938e-05,
+      "loss": 0.5195,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7141183362624487,
+      "eval_f1": 0.5080645161290324,
+      "eval_loss": 0.519816517829895,
+      "eval_mcc": 0.31950417692011085,
+      "eval_precision": 0.5957446808510638,
+      "eval_recall": 0.4428822495606327,
+      "eval_runtime": 3.148,
+      "eval_samples_per_second": 542.251,
+      "eval_steps_per_second": 17.154,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.7698822021484375,
+      "learning_rate": 4.202550710572449e-05,
+      "loss": 0.5103,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7123608670181605,
+      "eval_f1": 0.5246853823814134,
+      "eval_loss": 0.5106622576713562,
+      "eval_mcc": 0.3249495011032671,
+      "eval_precision": 0.584051724137931,
+      "eval_recall": 0.47627416520210897,
+      "eval_runtime": 3.1481,
+      "eval_samples_per_second": 542.224,
+      "eval_steps_per_second": 17.153,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1926,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9360715938313949,
+    "learning_rate": 7.564591279030407e-05,
+    "num_train_epochs": 9,
+    "temperature": 28
+  }
+}

run-33/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c639803f3f95121766bce4b0b8c45655fd41650358eae72e2f53e8b3c3ab6ba2
+size 5048

run-34/checkpoint-214/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-34/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7083431eb6fcd2c2ec7a4ec7a14fc1a11f2f8d6805544e01a2036c2d71a045
+size 17549312

run-34/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a7dd6ea8b4a003ae40bd338d39aba7c39cc5234fde961ed1b6ede9ff5b68b3
+size 35123898

run-34/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
+size 14308

run-34/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7297f056c7e590504a6416f2c2944b2500a4658d87dd7a87b4a9d568a8f6dba6
+size 1064

run-34/checkpoint-214/special_tokens_map.json

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

run-34/checkpoint-214/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-34/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.7041593438781488,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-34/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.8471832275390625,
+      "learning_rate": 0.0003084590636066452,
+      "loss": 0.4895,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7041593438781488,
+      "eval_f1": 0.3631778058007566,
+      "eval_loss": 0.4574507474899292,
+      "eval_mcc": 0.25518418317792835,
+      "eval_precision": 0.6428571428571429,
+      "eval_recall": 0.2530755711775044,
+      "eval_runtime": 3.1432,
+      "eval_samples_per_second": 543.077,
+      "eval_steps_per_second": 17.18,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7948524745832855,
+    "learning_rate": 0.0003855738295083065,
+    "num_train_epochs": 5,
+    "temperature": 15
+  }
+}

run-34/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051fab5723c44be17f791f8c45489e1552a330ef8815754068f2bb19eae15a1c
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c639803f3f95121766bce4b0b8c45655fd41650358eae72e2f53e8b3c3ab6ba2
+oid sha256:051fab5723c44be17f791f8c45489e1552a330ef8815754068f2bb19eae15a1c
 size 5048