Training in progress, epoch 1

logs/events.out.tfevents.1700292047.1d5d6d420ef6.278.19

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d839fcfc90a762d158a7a5b43d31be9e41f4f74794c64b52b482221578330ef5
-size 4937
+oid sha256:5181dc3bf43e580db3cd13edeb443e7ec764242d1209d0fc5457fa31af341839
+size 5771

logs/events.out.tfevents.1700292097.1d5d6d420ef6.278.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1378130cac2329cee0ce2f19280d8980fec69897251d83316a808009f1f09fd2
+size 4938

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874363e8eef9de09f036cf94468666a6b31340dcb28aa94bce81792871fe969e
+oid sha256:e605cf555b04d8c06312fe6abcb93d5b1568d6847d42c543fba057287fbec91e
 size 17558633

run-6/checkpoint-1054/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "jysh1023/tiny-bert-sst2-distilled_qat_test",
+  "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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-6/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0612c354ef75eb812eb39c4a14b01fe16a08daaa0fcfc693235d8c1063def3b9
+size 35123898

run-6/checkpoint-1054/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00bcf43f608650788eb39bd0ae93f03d5e4461ed77fb6e997753f8dbdafea985
+size 17558633

run-6/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d02e30429de40fdda90f7983d1b5c7be43f4e66ef3adec58563bb6cd1546fd04
+size 14308

run-6/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70e347c409c2a58eaef17a18df6efd1d1a8926ec722b52b4fdc376b89551c4c8
+size 1064

run-6/checkpoint-1054/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-6/checkpoint-1054/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-6/checkpoint-1054/trainer_state.json

@@ -0,0 +1,52 @@
+{
+  "best_metric": 0.7809633027522935,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_qat/run-6/checkpoint-1054",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.896069009757012e-05,
+      "loss": 0.0097,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 1.3993580341339111,
+      "eval_runtime": 0.1553,
+      "eval_samples_per_second": 5615.77,
+      "eval_steps_per_second": 45.081,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.032,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7809633027522935,
+      "eval_loss": 1.0637930631637573,
+      "eval_runtime": 0.164,
+      "eval_samples_per_second": 5317.312,
+      "eval_steps_per_second": 42.685,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 22053322479600.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.792138019514024e-05,
+    "num_train_epochs": 2
+  }
+}

run-6/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3436304f4bd91f2949ec10fed41876aed94708b948956ff07d9c4996847c95
+size 4600

run-7/checkpoint-527/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "jysh1023/tiny-bert-sst2-distilled_qat_test",
+  "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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-7/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2adf43732498759280cc292b35b8bfea04f9b23e8518406ca0cb42dd69ca6c4
+size 35123898

run-7/checkpoint-527/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e605cf555b04d8c06312fe6abcb93d5b1568d6847d42c543fba057287fbec91e
+size 17558633

run-7/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8bafa2724c49fac6846da9a209f9146b915741f49bf28687492d32d6f5533d
+size 14308

run-7/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2036e85278d34c44f830f21ed0192b766d6528642df1f2f383665d93a576b57a
+size 1064

run-7/checkpoint-527/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-7/checkpoint-527/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-7/checkpoint-527/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": 0.7775229357798165,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_qat/run-7/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.625873090345263e-05,
+      "loss": 0.0103,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 1.4271998405456543,
+      "eval_runtime": 0.1565,
+      "eval_samples_per_second": 5572.535,
+      "eval_steps_per_second": 44.734,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 11027137672440.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.00011000997817537444,
+    "num_train_epochs": 8
+  }
+}

run-7/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064b9cba85ab4b56eaf145188f9ce01dd79a584eea1b108dd1ad63e7d8e20c31
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3436304f4bd91f2949ec10fed41876aed94708b948956ff07d9c4996847c95
+oid sha256:064b9cba85ab4b56eaf145188f9ce01dd79a584eea1b108dd1ad63e7d8e20c31
 size 4600