Training in progress, epoch 1

logs/events.out.tfevents.1713588236.1376c752d37a.9760.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92d3f5f9f448b2eef640e18d8abf4cd35d15a284e72b7fb605e0d981b8a6789
-size 6212
+oid sha256:e1624e97ad64e72a526e244d0d5c0e8360f434a750e1b2989b794990dd5ec1fa
+size 9132

logs/events.out.tfevents.1713588335.1376c752d37a.9760.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bacf3f9541c058b404ab739b802c0dff6ec177165a51751d37c0f852d7073b58
+size 5483

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635da64a58870edd4e4b471c6ef5fd3150a3da6a7f079ad028658ac5ab8d2ade
+oid sha256:a81f915ec36103849a2e8eab87c823cf31b3c88bf3c78cc1155c0303f9f46ba0
 size 17549312

run-14/checkpoint-1070/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-14/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942b933523f5665a21f656eb6cd826df0b3463c42ca5155e4a46c71fcb0b7ff6
+size 17549312

run-14/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7532a2c5aeaea78f9bc86e385d6d76d25574fcde3fb73d15b6699ef6e8a002
+size 35123898

run-14/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8889b20d89ae20d68b3b1e02c508fe878c92c2f33b24682cc4f66bd3af9eea6
+size 14308

run-14/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d11102dd90234d2a5adac74fc3850dfce29617255a193d145ad6f73711de225
+size 1064

run-14/checkpoint-1070/special_tokens_map.json

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

run-14/checkpoint-1070/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-14/checkpoint-1070/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.7129466900995899,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-1070",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 6.930738925933838,
+      "learning_rate": 5.414014250397772e-05,
+      "loss": 0.6091,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6865846514352666,
+      "eval_f1": 0.37572928821470253,
+      "eval_loss": 0.564587414264679,
+      "eval_mcc": 0.2156910734882714,
+      "eval_precision": 0.5590277777777778,
+      "eval_recall": 0.28295254833040423,
+      "eval_runtime": 3.1483,
+      "eval_samples_per_second": 542.201,
+      "eval_steps_per_second": 17.152,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.107285499572754,
+      "learning_rate": 4.64058364319809e-05,
+      "loss": 0.5591,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6994727592267135,
+      "eval_f1": 0.5535248041775457,
+      "eval_loss": 0.5493428111076355,
+      "eval_mcc": 0.3271000794140795,
+      "eval_precision": 0.5482758620689655,
+      "eval_recall": 0.5588752196836555,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.358,
+      "eval_steps_per_second": 17.189,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.368832588195801,
+      "learning_rate": 3.867153035998409e-05,
+      "loss": 0.5413,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7053309900410076,
+      "eval_f1": 0.523222748815166,
+      "eval_loss": 0.5401688814163208,
+      "eval_mcc": 0.31393167816118617,
+      "eval_precision": 0.5679012345679012,
+      "eval_recall": 0.4850615114235501,
+      "eval_runtime": 3.1381,
+      "eval_samples_per_second": 543.954,
+      "eval_steps_per_second": 17.208,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.47548770904541,
+      "learning_rate": 3.093722428798727e-05,
+      "loss": 0.5333,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7053309900410076,
+      "eval_f1": 0.5381083562901744,
+      "eval_loss": 0.5343005061149597,
+      "eval_mcc": 0.32311150297426244,
+      "eval_precision": 0.5634615384615385,
+      "eval_recall": 0.5149384885764499,
+      "eval_runtime": 3.1464,
+      "eval_samples_per_second": 542.53,
+      "eval_steps_per_second": 17.163,
+      "step": 856
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 6.320547103881836,
+      "learning_rate": 2.320291821599045e-05,
+      "loss": 0.5244,
+      "step": 1070
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7129466900995899,
+      "eval_f1": 0.5167652859960552,
+      "eval_loss": 0.5274397730827332,
+      "eval_mcc": 0.32175825520567214,
+      "eval_precision": 0.5887640449438202,
+      "eval_recall": 0.46045694200351495,
+      "eval_runtime": 3.1507,
+      "eval_samples_per_second": 541.788,
+      "eval_steps_per_second": 17.139,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 2623878322200.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9740992948842065,
+    "learning_rate": 6.187444857597454e-05,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-14/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7957c24fcc5f109d1242da58460e07cf4b6b3343538fd03977a240662bdcface
+size 5048

run-14/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-14/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6be0cab61ca59241918a7b420e471d6de8cce666874af510d5b73c221261460
+size 17549312

run-14/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d963a71e61761401445ca179132d20f331da328e444b84e4f807ea56dde48d3
+size 35123898

run-14/checkpoint-856/rng_state.pth

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

run-14/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3108b25e55ac2110b066fd4279e40d681a4251d13d6c2d83fd15439be0e1bc1
+size 1064

run-14/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-14/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-14/checkpoint-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.7053309900410076,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/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": 6.930738925933838,
+      "learning_rate": 5.414014250397772e-05,
+      "loss": 0.6091,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6865846514352666,
+      "eval_f1": 0.37572928821470253,
+      "eval_loss": 0.564587414264679,
+      "eval_mcc": 0.2156910734882714,
+      "eval_precision": 0.5590277777777778,
+      "eval_recall": 0.28295254833040423,
+      "eval_runtime": 3.1483,
+      "eval_samples_per_second": 542.201,
+      "eval_steps_per_second": 17.152,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.107285499572754,
+      "learning_rate": 4.64058364319809e-05,
+      "loss": 0.5591,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6994727592267135,
+      "eval_f1": 0.5535248041775457,
+      "eval_loss": 0.5493428111076355,
+      "eval_mcc": 0.3271000794140795,
+      "eval_precision": 0.5482758620689655,
+      "eval_recall": 0.5588752196836555,
+      "eval_runtime": 3.1416,
+      "eval_samples_per_second": 543.358,
+      "eval_steps_per_second": 17.189,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.368832588195801,
+      "learning_rate": 3.867153035998409e-05,
+      "loss": 0.5413,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7053309900410076,
+      "eval_f1": 0.523222748815166,
+      "eval_loss": 0.5401688814163208,
+      "eval_mcc": 0.31393167816118617,
+      "eval_precision": 0.5679012345679012,
+      "eval_recall": 0.4850615114235501,
+      "eval_runtime": 3.1381,
+      "eval_samples_per_second": 543.954,
+      "eval_steps_per_second": 17.208,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.47548770904541,
+      "learning_rate": 3.093722428798727e-05,
+      "loss": 0.5333,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7053309900410076,
+      "eval_f1": 0.5381083562901744,
+      "eval_loss": 0.5343005061149597,
+      "eval_mcc": 0.32311150297426244,
+      "eval_precision": 0.5634615384615385,
+      "eval_recall": 0.5149384885764499,
+      "eval_runtime": 3.1464,
+      "eval_samples_per_second": 542.53,
+      "eval_steps_per_second": 17.163,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9740992948842065,
+    "learning_rate": 6.187444857597454e-05,
+    "num_train_epochs": 8,
+    "temperature": 3
+  }
+}

run-14/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7957c24fcc5f109d1242da58460e07cf4b6b3343538fd03977a240662bdcface
+size 5048

run-15/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-15/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81f915ec36103849a2e8eab87c823cf31b3c88bf3c78cc1155c0303f9f46ba0
+size 17549312

run-15/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a9a255b10b55975b4c30647afdbbe3c244985cefbd4a75dfa490fe2236cdf2
+size 35123898

run-15/checkpoint-214/rng_state.pth

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

run-15/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4a6cf7fbe86eddad2a1bf2d2614bb368297983d9580a9d850eb3126d5f8e02
+size 1064

run-15/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-15/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-15/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6654950205038078,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-15/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": 0.24385033547878265,
+      "learning_rate": 0.00027237519894122124,
+      "loss": 0.0406,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6654950205038078,
+      "eval_f1": 0.017211703958691912,
+      "eval_loss": 0.03144706040620804,
+      "eval_mcc": 0.01487410293271824,
+      "eval_precision": 0.4166666666666667,
+      "eval_recall": 0.008787346221441126,
+      "eval_runtime": 3.1499,
+      "eval_samples_per_second": 541.926,
+      "eval_steps_per_second": 17.144,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1284,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.037718713604154464,
+    "learning_rate": 0.00032685023872946545,
+    "num_train_epochs": 6,
+    "temperature": 24
+  }
+}

run-15/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806af46e7362e6f3407b7f78e04625d24ef8c221003ad26e1f3a3bdd0faccbb8
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7957c24fcc5f109d1242da58460e07cf4b6b3343538fd03977a240662bdcface
+oid sha256:806af46e7362e6f3407b7f78e04625d24ef8c221003ad26e1f3a3bdd0faccbb8
 size 5048