Training in progress, epoch 1

logs/events.out.tfevents.1713587431.1376c752d37a.9760.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44cd5819a593ff75ba336a7d5849e22b773f8b25efb44c36650d5803a5b8221a
-size 6212
+oid sha256:7af3265f1bca4de0f19d0ffc3a1ecd1087e8cf64431e8e06ecddf3123b9c5cd5
+size 8402

logs/events.out.tfevents.1713587513.1376c752d37a.9760.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bbc7d49a788bc42fcdb68015c305ed5cc23d491db69a1d1e26ec5afa480a1f
+size 5483

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c3c42b544d533753f6546ee28d4ab56a0f0e58624081cd51b7116f00490a58
+oid sha256:b2a8d1bf2ff6a50e477b37106cfca04e0ceabd9d73f2aee2a15009204bbde72e
 size 17549312

run-5/checkpoint-642/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-5/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:049fbca9a20cad456a38dd2906c7bd313de0a7e252d9265eaddc486d03c6b0f6
+size 17549312

run-5/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed22d4e30c12ecc23fc421070044cd423d6fbedce2d03d86b2fb59be17377f83
+size 35123898

run-5/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b0c3fe82ed8fc0c5e4a46035e8c4191c362f7c18bb672613fb7c69885d7960
+size 14308

run-5/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a138a2e69be11f7604ba0f92224b3cac59c04f8cb268416ac60ad2679f3ccd
+size 1064

run-5/checkpoint-642/special_tokens_map.json

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

run-5/checkpoint-642/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-5/checkpoint-642/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.6877562975981254,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-428",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.334259033203125,
+      "learning_rate": 0.0007289392500735427,
+      "loss": 0.5536,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5510665774345398,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.1386,
+      "eval_samples_per_second": 543.88,
+      "eval_steps_per_second": 17.205,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9964511394500732,
+      "learning_rate": 0.0006074493750612857,
+      "loss": 0.5347,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6877562975981254,
+      "eval_f1": 0.17873651771956856,
+      "eval_loss": 0.5295280814170837,
+      "eval_mcc": 0.18423582600040866,
+      "eval_precision": 0.725,
+      "eval_recall": 0.10193321616871705,
+      "eval_runtime": 3.1376,
+      "eval_samples_per_second": 544.038,
+      "eval_steps_per_second": 17.21,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.638342022895813,
+      "learning_rate": 0.0004859595000490285,
+      "loss": 0.5214,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6736965436438196,
+      "eval_f1": 0.08837970540098199,
+      "eval_loss": 0.5322084426879883,
+      "eval_mcc": 0.10428403940757605,
+      "eval_precision": 0.6428571428571429,
+      "eval_recall": 0.04745166959578207,
+      "eval_runtime": 3.131,
+      "eval_samples_per_second": 545.187,
+      "eval_steps_per_second": 17.247,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1574326993320.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8578412183256148,
+    "learning_rate": 0.0008504291250857999,
+    "num_train_epochs": 7,
+    "temperature": 7
+  }
+}

run-5/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a105efa06002e83e7f7f9728fd07b6e3ab16420601aa1ff3b5c7d3c74b026e
+size 5048

run-5/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-5/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cdd439b767dd27f857cca9585bd78d3fa18d52d0dd0dd7715a9065dc6e05123
+size 17549312

run-5/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667fcc2d086c3450b4a8a632d2d16ee34af46d593b56bebec8e6ebc092ec51c
+size 35123898

run-5/checkpoint-856/rng_state.pth

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

run-5/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b71d73fca0accc068473da74181bcb5158ea0c23945d60b0366e539883533f
+size 1064

run-5/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-5/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-5/checkpoint-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.6983011130638547,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-856",
+  "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": 3.334259033203125,
+      "learning_rate": 0.0007289392500735427,
+      "loss": 0.5536,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0,
+      "eval_loss": 0.5510665774345398,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.1386,
+      "eval_samples_per_second": 543.88,
+      "eval_steps_per_second": 17.205,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9964511394500732,
+      "learning_rate": 0.0006074493750612857,
+      "loss": 0.5347,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6877562975981254,
+      "eval_f1": 0.17873651771956856,
+      "eval_loss": 0.5295280814170837,
+      "eval_mcc": 0.18423582600040866,
+      "eval_precision": 0.725,
+      "eval_recall": 0.10193321616871705,
+      "eval_runtime": 3.1376,
+      "eval_samples_per_second": 544.038,
+      "eval_steps_per_second": 17.21,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.638342022895813,
+      "learning_rate": 0.0004859595000490285,
+      "loss": 0.5214,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6736965436438196,
+      "eval_f1": 0.08837970540098199,
+      "eval_loss": 0.5322084426879883,
+      "eval_mcc": 0.10428403940757605,
+      "eval_precision": 0.6428571428571429,
+      "eval_recall": 0.04745166959578207,
+      "eval_runtime": 3.131,
+      "eval_samples_per_second": 545.187,
+      "eval_steps_per_second": 17.247,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8640382289886475,
+      "learning_rate": 0.00036446962503677133,
+      "loss": 0.5039,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6983011130638547,
+      "eval_f1": 0.33376455368693403,
+      "eval_loss": 0.503688633441925,
+      "eval_mcc": 0.2336907475795427,
+      "eval_precision": 0.6323529411764706,
+      "eval_recall": 0.22671353251318102,
+      "eval_runtime": 3.1488,
+      "eval_samples_per_second": 542.11,
+      "eval_steps_per_second": 17.149,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8578412183256148,
+    "learning_rate": 0.0008504291250857999,
+    "num_train_epochs": 7,
+    "temperature": 7
+  }
+}

run-5/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a105efa06002e83e7f7f9728fd07b6e3ab16420601aa1ff3b5c7d3c74b026e
+size 5048

run-6/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-6/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a8d1bf2ff6a50e477b37106cfca04e0ceabd9d73f2aee2a15009204bbde72e
+size 17549312

run-6/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff576419dd4f1a61a0e8cf67fee67af300c907edbc9d004458c41552c5aaf00b
+size 35123898

run-6/checkpoint-214/rng_state.pth

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

run-6/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55641a897b5e548702575c7a11a0e0252fbbbae59ca5bf073c9eb6972489b32
+size 1064

run-6/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-6/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-6/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6666666666666666,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-6/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": 1.7624236345291138,
+      "learning_rate": 1.5910505716425373e-05,
+      "loss": 0.3605,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.0,
+      "eval_loss": 0.3405539095401764,
+      "eval_mcc": 0.0,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.1408,
+      "eval_samples_per_second": 543.484,
+      "eval_steps_per_second": 17.193,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5123346903654048,
+    "learning_rate": 2.1214007621900497e-05,
+    "num_train_epochs": 4,
+    "temperature": 10
+  }
+}

run-6/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64fd20728a64720524b4d40e414ede4822f2d9cc5773b662dd9e1304e07af180
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a105efa06002e83e7f7f9728fd07b6e3ab16420601aa1ff3b5c7d3c74b026e
+oid sha256:64fd20728a64720524b4d40e414ede4822f2d9cc5773b662dd9e1304e07af180
 size 5048