Training in progress, epoch 1

logs/events.out.tfevents.1709746175.d65e8524b0f6.5185.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ecec07a177dcf2b6ae665ae520fd099fa27d68685668142e0573a93c11a0919
-size 5985
+oid sha256:8d435472f55d161fe7bb026e89d9690d7fe4cab1b16adb090dfbe328c1a0bc15
+size 8388

logs/events.out.tfevents.1709746719.d65e8524b0f6.5185.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4346fec82fe37cc151fb8d7fc72058bbdc5ffd10f9574882c4368b3f846799a4
+size 5315

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c31fb9097de6b5e6623426f94dc8d1c3a8477f0c85915b68c4d9c3acbbcc3df
+size 5315

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97e822578ca6d8998b5b28997a7474a57ef297433f7c30959ed9f117abc6e623
+oid sha256:840f48c35da7a97bf8423c4d56b59abfff31d02d3333ba76897059f3fe2011af
 size 17549312

run-14/checkpoint-196/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-14/checkpoint-196/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2295b7e48286c79db173661971c047924eade017265de90326321524f679f31d
+size 17549312

run-14/checkpoint-196/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3cee671de739e7b50e880e304f8e32cb2a7ce327104d50edeec5cf77a548e4
+size 35122746

run-14/checkpoint-196/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9569c132b78af182a75b126495eb19599bcc7d757d8aa23b142d6678c6b23bf
+size 14054

run-14/checkpoint-196/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dad2624a96739394d21738b94d277594eaec288b5723af012115c96cc2899f2
+size 1064

run-14/checkpoint-196/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-196/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-196/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.8228962818003914,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-196",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 196,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3073023557662964,
+      "learning_rate": 0.00021800841920007835,
+      "loss": 0.5666,
+      "step": 49
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7720156555772995,
+      "eval_f1": 0.8010247651579846,
+      "eval_loss": 0.48246321082115173,
+      "eval_precision": 0.7106060606060606,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 28.2754,
+      "eval_samples_per_second": 36.145,
+      "eval_steps_per_second": 1.132,
+      "step": 49
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.786695957183838,
+      "learning_rate": 0.00016350631440005875,
+      "loss": 0.4698,
+      "step": 98
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8023483365949119,
+      "eval_f1": 0.8212389380530973,
+      "eval_loss": 0.436308890581131,
+      "eval_precision": 0.7495961227786753,
+      "eval_recall": 0.9080234833659491,
+      "eval_runtime": 28.7331,
+      "eval_samples_per_second": 35.569,
+      "eval_steps_per_second": 1.114,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.9201297760009766,
+      "learning_rate": 0.00010900420960003918,
+      "loss": 0.4418,
+      "step": 147
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8197945845004668,
+      "eval_loss": 0.41809919476509094,
+      "eval_precision": 0.7839285714285714,
+      "eval_recall": 0.8590998043052838,
+      "eval_runtime": 27.7463,
+      "eval_samples_per_second": 36.834,
+      "eval_steps_per_second": 1.153,
+      "step": 147
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8454147577285767,
+      "learning_rate": 5.450210480001959e-05,
+      "loss": 0.4241,
+      "step": 196
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8340971585701191,
+      "eval_loss": 0.41074350476264954,
+      "eval_precision": 0.7844827586206896,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 27.5953,
+      "eval_samples_per_second": 37.035,
+      "eval_steps_per_second": 1.16,
+      "step": 196
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 245,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 942780789120.0,
+  "train_batch_size": 63,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8444228810359851,
+    "learning_rate": 0.00027251052400009793,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 63,
+    "temperature": 21
+  }
+}

run-14/checkpoint-196/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a93046ce295ef56d7e5753c2ad419c6bb89f07af26dc70719f2b8f995444c3d
+size 4920

run-14/checkpoint-245/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-14/checkpoint-245/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd40f2db7e1cb181ebdc9edae6c62e7a8ad5a6acf52a9f5676872ac293882353
+size 17549312

run-14/checkpoint-245/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74c990e2e48a0964cc6902a241e1b76969b468bab49a8cdd0191edcb595ea1cf
+size 35122746

run-14/checkpoint-245/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71858aa009ee75396c24a85135d9a9552bdda497e94f0a0ebf3e44e140711e9
+size 14054

run-14/checkpoint-245/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e1b5c2b971bf5bf7e19bf20021cabc7cd11f07fcae17ab9a6ba7e2a364c95d
+size 1064

run-14/checkpoint-245/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-245/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-245/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 0.8287671232876712,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/checkpoint-245",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 245,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3073023557662964,
+      "learning_rate": 0.00021800841920007835,
+      "loss": 0.5666,
+      "step": 49
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7720156555772995,
+      "eval_f1": 0.8010247651579846,
+      "eval_loss": 0.48246321082115173,
+      "eval_precision": 0.7106060606060606,
+      "eval_recall": 0.9178082191780822,
+      "eval_runtime": 28.2754,
+      "eval_samples_per_second": 36.145,
+      "eval_steps_per_second": 1.132,
+      "step": 49
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.786695957183838,
+      "learning_rate": 0.00016350631440005875,
+      "loss": 0.4698,
+      "step": 98
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8023483365949119,
+      "eval_f1": 0.8212389380530973,
+      "eval_loss": 0.436308890581131,
+      "eval_precision": 0.7495961227786753,
+      "eval_recall": 0.9080234833659491,
+      "eval_runtime": 28.7331,
+      "eval_samples_per_second": 35.569,
+      "eval_steps_per_second": 1.114,
+      "step": 98
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.9201297760009766,
+      "learning_rate": 0.00010900420960003918,
+      "loss": 0.4418,
+      "step": 147
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8197945845004668,
+      "eval_loss": 0.41809919476509094,
+      "eval_precision": 0.7839285714285714,
+      "eval_recall": 0.8590998043052838,
+      "eval_runtime": 27.7463,
+      "eval_samples_per_second": 36.834,
+      "eval_steps_per_second": 1.153,
+      "step": 147
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8454147577285767,
+      "learning_rate": 5.450210480001959e-05,
+      "loss": 0.4241,
+      "step": 196
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8340971585701191,
+      "eval_loss": 0.41074350476264954,
+      "eval_precision": 0.7844827586206896,
+      "eval_recall": 0.8904109589041096,
+      "eval_runtime": 27.5953,
+      "eval_samples_per_second": 37.035,
+      "eval_steps_per_second": 1.16,
+      "step": 196
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.8352748155593872,
+      "learning_rate": 0.0,
+      "loss": 0.4122,
+      "step": 245
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8287671232876712,
+      "eval_f1": 0.839596700274977,
+      "eval_loss": 0.4070187509059906,
+      "eval_precision": 0.7896551724137931,
+      "eval_recall": 0.8962818003913894,
+      "eval_runtime": 28.0192,
+      "eval_samples_per_second": 36.475,
+      "eval_steps_per_second": 1.142,
+      "step": 245
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 245,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1178475986400.0,
+  "train_batch_size": 63,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8444228810359851,
+    "learning_rate": 0.00027251052400009793,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 63,
+    "temperature": 21
+  }
+}

run-14/checkpoint-245/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a93046ce295ef56d7e5753c2ad419c6bb89f07af26dc70719f2b8f995444c3d
+size 4920

run-16/checkpoint-55/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-55/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840f48c35da7a97bf8423c4d56b59abfff31d02d3333ba76897059f3fe2011af
+size 17549312

run-16/checkpoint-55/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8fecbfd4eb601d2b2ebaf5ef4cebfe7b026cb621336b10df98c6d2afcdd919
+size 35122746

run-16/checkpoint-55/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b588f6b58c8f950c9442cf99e4b25f82e10f4a04910349fe09a3ddec4d480990
+size 14054

run-16/checkpoint-55/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c8ef987310ab0df3dc5e384122633d92955c5ca55290486fcda2f6d0a2e51c
+size 1064

run-16/checkpoint-55/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-55/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-55/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.7181996086105675,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-55",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 55,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 275,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "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-55/training_args.bin

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

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 33,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f66704597a58fe4c3198b90885da31fa130a7935fb216d72d9dce5631df173
+oid sha256:853b9bd91d8e7500b2e68ab85992695ef180b9f0e29125c26ec58713c7d0700a
 size 4920