Training in progress, epoch 1

logs/events.out.tfevents.1700291440.1d5d6d420ef6.278.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312505ee32099921ac0125cbd59fe2fe5cd3d8dd1eca64baaf0e0392f809df19
-size 5417
+oid sha256:3546c7f3efd3a7be16d1e7a22210179184e6d1bd623edb73fed19130d276749c
+size 6251

logs/events.out.tfevents.1700291506.1d5d6d420ef6.278.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a1890fddfc1f36ef494c0ee273f79f0e691a233b282e3766925c8d7701e1c3
+size 4938

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bfef2dfc1bcdaf28c9218b915404ea8823a8221597c2e158ef0d8d1effe42c2
+oid sha256:9e169d449f7621f64e7139c87c7d55e90ca341a3e4087cafed3bec145a11d870
 size 17558633

run-1/checkpoint-1581/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-1/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e07ef1c9ef9862c57e1b9f4c02b395259a7068f14c15bdb3df4f8cbdf96dc1d
+size 35123898

run-1/checkpoint-1581/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9cc89cea9c2fdcf61d2f397da913d6b0e81714a118581fe36aca4aa56b474c
+size 17558633

run-1/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a492aa2aa78833133789a0fc9f9a31c23df184695444fd90548b17b63b6e46
+size 14308

run-1/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44ab186eaae3543021594ff16a9515fc826d27e3dfff200399ac05e13f89f469
+size 1064

run-1/checkpoint-1581/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-1/checkpoint-1581/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-1/checkpoint-1581/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.7821100917431193,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_qat/run-1/checkpoint-1054",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0005360693320467115,
+      "loss": 0.0488,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7442660550458715,
+      "eval_loss": 0.9055079221725464,
+      "eval_runtime": 0.2627,
+      "eval_samples_per_second": 3320.001,
+      "eval_steps_per_second": 26.651,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00026803466602335577,
+      "loss": 0.067,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7821100917431193,
+      "eval_loss": 0.7046255469322205,
+      "eval_runtime": 0.1576,
+      "eval_samples_per_second": 5532.01,
+      "eval_steps_per_second": 44.408,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0476,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7775229357798165,
+      "eval_loss": 0.9072702527046204,
+      "eval_runtime": 0.159,
+      "eval_samples_per_second": 5484.099,
+      "eval_steps_per_second": 44.024,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1581,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 33080251712760.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.0008041039980700674,
+    "num_train_epochs": 3
+  }
+}

run-1/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0ef1139584a95744d24b8608f75b32a06bf2f0a630bf15110dab417ee23ecd
+size 4600

run-2/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-2/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0881fd643ca0b21288d05a59467cba138b6fb63795416fbd5a4524e12e359341
+size 35123898

run-2/checkpoint-527/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e169d449f7621f64e7139c87c7d55e90ca341a3e4087cafed3bec145a11d870
+size 17558633

run-2/checkpoint-527/rng_state.pth

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

run-2/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1900afb42438fc73084a4bd20dfd9b793aae7c37c56b556d96b9ba720000eb36
+size 1064

run-2/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-2/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-2/checkpoint-527/trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": 0.7717889908256881,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_qat/run-2/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": 1.6804188087684686e-05,
+      "loss": 0.0092,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7717889908256881,
+      "eval_loss": 1.2892308235168457,
+      "eval_runtime": 0.2668,
+      "eval_samples_per_second": 3268.2,
+      "eval_steps_per_second": 26.236,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 11027137672440.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8904711598645274e-05,
+    "num_train_epochs": 9
+  }
+}

run-2/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e88bee13fb6e1bebe56aae8ff7e82f5cab1eb5180b10cf9c35fececd41893a1
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce0ef1139584a95744d24b8608f75b32a06bf2f0a630bf15110dab417ee23ecd
+oid sha256:6e88bee13fb6e1bebe56aae8ff7e82f5cab1eb5180b10cf9c35fececd41893a1
 size 4600