Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5470233f6984fea28080c0c0263e193fe18e95092a14e3cf45a7eb0bf3d72415
+oid sha256:cf15e2794e157a871904f9c595afcc0fcb3f6d5969641c646116e509d6b165bc
 size 442505820

run-0/checkpoint-2764/config.json

@@ -0,0 +1,40 @@
+{
+  "_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"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "4.37.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

run-0/checkpoint-2764/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf15e2794e157a871904f9c595afcc0fcb3f6d5969641c646116e509d6b165bc
+size 442505820

run-0/checkpoint-2764/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db37f2f46bb280f76d2cb17b9f838e9c450e742f51b1daebd5cb53740c05b33
+size 885131514

run-0/checkpoint-2764/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579640e3f9eab142dad32be3e40cf5119759b67ccf3e400860d398d86dd2580b
+size 14244

run-0/checkpoint-2764/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13a41b1169c206173bc782464e18fcc27f8dafdd2f82013d7e1db88920940cf
+size 1064

run-0/checkpoint-2764/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-2764/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-2764/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.5966597659617285,
+  "best_model_checkpoint": "test-klue/ynat/run-0/checkpoint-2764",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2764,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.549617863520091e-06,
+      "loss": 1.0402,
+      "step": 500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.2073877699865019e-06,
+      "loss": 0.8825,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.5922490852804443,
+      "eval_loss": 0.8286302089691162,
+      "eval_runtime": 9.5242,
+      "eval_samples_per_second": 248.734,
+      "eval_steps_per_second": 1.995,
+      "step": 1382
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 8.65157676452913e-07,
+      "loss": 0.8276,
+      "step": 1500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.22927582919324e-07,
+      "loss": 0.7615,
+      "step": 2000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.8069748938573499e-07,
+      "loss": 0.7606,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.5966597659617285,
+      "eval_loss": 0.8385059237480164,
+      "eval_runtime": 9.5681,
+      "eval_samples_per_second": 247.594,
+      "eval_steps_per_second": 1.986,
+      "step": 2764
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2764,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 417767579078724.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.8850033551830082e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 4,
+    "seed": 19
+  }
+}

run-0/checkpoint-2764/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af98c47737861dbadd5484fe0d159b1b72fb3dd72eb572c61de392f3b326bfaf
+size 4728