Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac72c37e4bf87ca55daea5688a5d309981579ac35b83d6d9d2820a9961e67d02
+oid sha256:dd4d89ad8b9454f1d0b670fc7e447f6d0a2f1c8aa327f29fe93915db5e9510ab
 size 442518124

run-0/checkpoint-500/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

run-0/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e28d0877e39cf4981fe1853332f44375247091fb142a44eff49a7e4117e1d48a
+size 442518124

run-0/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941f2fb5277406b1cc7a2725ce82bd31a8351cf1ad1d03559e3b969408f5fa70
+size 885156090

run-0/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b848ecc9f77091b625c7ab6b26f39289f22d82f487cf00c08e735b3db79a1e9e
+size 14308

run-0/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf2b9dab5c75b593f3935828818ba859971cbc94a6e560697ae45bdd2de9400
+size 1064

run-0/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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-0/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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-0/checkpoint-500/trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 0.8294788131616876,
+  "best_model_checkpoint": "test-klue/ynat/run-0/checkpoint-500",
+  "epoch": 0.8756567425569177,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.501135446959971e-06,
+      "loss": 1.9347,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "eval_f1": 0.023996321521970284,
+      "eval_loss": 1.9860223531723022,
+      "eval_runtime": 12.5956,
+      "eval_samples_per_second": 723.029,
+      "eval_steps_per_second": 1.429,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.1002270893919942e-05,
+      "loss": 1.8117,
+      "step": 100
+    },
+    {
+      "epoch": 0.18,
+      "eval_f1": 0.4595604236792048,
+      "eval_loss": 1.628663420677185,
+      "eval_runtime": 13.2033,
+      "eval_samples_per_second": 689.752,
+      "eval_steps_per_second": 1.363,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6503406340879914e-05,
+      "loss": 1.0313,
+      "step": 150
+    },
+    {
+      "epoch": 0.26,
+      "eval_f1": 0.724489576070544,
+      "eval_loss": 0.9617213606834412,
+      "eval_runtime": 13.2461,
+      "eval_samples_per_second": 687.525,
+      "eval_steps_per_second": 1.359,
+      "step": 150
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 2.2004541787839884e-05,
+      "loss": 0.694,
+      "step": 200
+    },
+    {
+      "epoch": 0.35,
+      "eval_f1": 0.7120632351612463,
+      "eval_loss": 0.9053735136985779,
+      "eval_runtime": 12.8156,
+      "eval_samples_per_second": 710.619,
+      "eval_steps_per_second": 1.405,
+      "step": 200
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.9038970118319684e-05,
+      "loss": 0.6727,
+      "step": 250
+    },
+    {
+      "epoch": 0.44,
+      "eval_f1": 0.7875925728315641,
+      "eval_loss": 0.6879186630249023,
+      "eval_runtime": 12.6123,
+      "eval_samples_per_second": 722.073,
+      "eval_steps_per_second": 1.427,
+      "step": 250
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.6073398448799484e-05,
+      "loss": 0.5443,
+      "step": 300
+    },
+    {
+      "epoch": 0.53,
+      "eval_f1": 0.7917152333868122,
+      "eval_loss": 0.7034006118774414,
+      "eval_runtime": 12.5646,
+      "eval_samples_per_second": 724.812,
+      "eval_steps_per_second": 1.433,
+      "step": 300
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.3107826779279283e-05,
+      "loss": 0.4465,
+      "step": 350
+    },
+    {
+      "epoch": 0.61,
+      "eval_f1": 0.799694788275597,
+      "eval_loss": 0.6883692145347595,
+      "eval_runtime": 12.8573,
+      "eval_samples_per_second": 708.314,
+      "eval_steps_per_second": 1.4,
+      "step": 350
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0142255109759083e-05,
+      "loss": 0.4948,
+      "step": 400
+    },
+    {
+      "epoch": 0.7,
+      "eval_f1": 0.798769862417967,
+      "eval_loss": 0.7284345626831055,
+      "eval_runtime": 12.9495,
+      "eval_samples_per_second": 703.271,
+      "eval_steps_per_second": 1.39,
+      "step": 400
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.176683440238885e-06,
+      "loss": 0.4655,
+      "step": 450
+    },
+    {
+      "epoch": 0.79,
+      "eval_f1": 0.8126114042217406,
+      "eval_loss": 0.6704472303390503,
+      "eval_runtime": 12.9039,
+      "eval_samples_per_second": 705.754,
+      "eval_steps_per_second": 1.395,
+      "step": 450
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.211111770718684e-06,
+      "loss": 0.4316,
+      "step": 500
+    },
+    {
+      "epoch": 0.88,
+      "eval_f1": 0.8294788131616876,
+      "eval_loss": 0.5909184813499451,
+      "eval_runtime": 12.752,
+      "eval_samples_per_second": 714.164,
+      "eval_steps_per_second": 1.412,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 571,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 40886826786000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2004541787839884e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 8
+  }
+}

run-0/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f597826c9a1bfa4e37bed4cf4e45d548bccbec0ebdaa31bc6739facb51a0fa
+size 4728

run-1/checkpoint-500/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "klue/roberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

run-1/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4d89ad8b9454f1d0b670fc7e447f6d0a2f1c8aa327f29fe93915db5e9510ab
+size 442518124

run-1/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bfeb4cd61b7f89aef6c894a76e5cf6da2fa925d17a0256c9941bb027f4e1b22
+size 885156090

run-1/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8676fbd04f9752ca208326869aadf87a8e201d4c9c4328ccab03b20bbb933463
+size 14308

run-1/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b084160dc6107c5c64602fdf374da79d74a6e7e085133c00104fa7a15de63149
+size 1064

run-1/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "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-500/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "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-1/checkpoint-500/trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_metric": 0.8162388724528657,
+  "best_model_checkpoint": "test-klue/ynat/run-1/checkpoint-500",
+  "epoch": 0.43782837127845886,
+  "eval_steps": 50,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.707876059953676e-06,
+      "loss": 1.9595,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "eval_f1": 0.01705140497086806,
+      "eval_loss": 1.9648141860961914,
+      "eval_runtime": 13.2976,
+      "eval_samples_per_second": 684.86,
+      "eval_steps_per_second": 1.354,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.415752119907352e-06,
+      "loss": 1.9099,
+      "step": 100
+    },
+    {
+      "epoch": 0.09,
+      "eval_f1": 0.07360850081330118,
+      "eval_loss": 2.032604217529297,
+      "eval_runtime": 13.3151,
+      "eval_samples_per_second": 683.961,
+      "eval_steps_per_second": 1.352,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.4123628179861027e-05,
+      "loss": 1.6735,
+      "step": 150
+    },
+    {
+      "epoch": 0.13,
+      "eval_f1": 0.38393105234961034,
+      "eval_loss": 1.5790455341339111,
+      "eval_runtime": 12.7623,
+      "eval_samples_per_second": 713.584,
+      "eval_steps_per_second": 1.41,
+      "step": 150
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8831504239814704e-05,
+      "loss": 0.9703,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "eval_f1": 0.7721326246350599,
+      "eval_loss": 0.9168348908424377,
+      "eval_runtime": 12.5558,
+      "eval_samples_per_second": 725.324,
+      "eval_steps_per_second": 1.434,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.866061944634996e-05,
+      "loss": 0.7516,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "eval_f1": 0.7687755468039507,
+      "eval_loss": 0.7031986713409424,
+      "eval_runtime": 12.6864,
+      "eval_samples_per_second": 717.854,
+      "eval_steps_per_second": 1.419,
+      "step": 250
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8489734652885216e-05,
+      "loss": 0.6465,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "eval_f1": 0.8144320202800481,
+      "eval_loss": 0.6549465656280518,
+      "eval_runtime": 12.8685,
+      "eval_samples_per_second": 707.697,
+      "eval_steps_per_second": 1.399,
+      "step": 300
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8318849859420474e-05,
+      "loss": 0.6678,
+      "step": 350
+    },
+    {
+      "epoch": 0.31,
+      "eval_f1": 0.793206481293857,
+      "eval_loss": 0.7163683176040649,
+      "eval_runtime": 12.9464,
+      "eval_samples_per_second": 703.437,
+      "eval_steps_per_second": 1.39,
+      "step": 350
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8147965065955732e-05,
+      "loss": 0.7099,
+      "step": 400
+    },
+    {
+      "epoch": 0.35,
+      "eval_f1": 0.8066754005498158,
+      "eval_loss": 0.7112386226654053,
+      "eval_runtime": 12.8448,
+      "eval_samples_per_second": 709.006,
+      "eval_steps_per_second": 1.401,
+      "step": 400
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.7977080272490987e-05,
+      "loss": 0.5154,
+      "step": 450
+    },
+    {
+      "epoch": 0.39,
+      "eval_f1": 0.8128681854085146,
+      "eval_loss": 0.6707363724708557,
+      "eval_runtime": 12.7035,
+      "eval_samples_per_second": 716.892,
+      "eval_steps_per_second": 1.417,
+      "step": 450
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7806195479026245e-05,
+      "loss": 0.6595,
+      "step": 500
+    },
+    {
+      "epoch": 0.44,
+      "eval_f1": 0.8162388724528657,
+      "eval_loss": 0.6982755064964294,
+      "eval_runtime": 12.7345,
+      "eval_samples_per_second": 715.146,
+      "eval_steps_per_second": 1.413,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5710,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 19068185282400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8831504239814704e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 32
+  }
+}

run-1/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aff63987d55bdb29a46347243764a71254aa8765001a1e61e633d8ed4d1fb8a
+size 4728

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bb32898c4be99d8d400e0e32f0f539e55cb3e467c4da6d08278d9e2ba82513
+oid sha256:0aff63987d55bdb29a46347243764a71254aa8765001a1e61e633d8ed4d1fb8a
 size 4728