Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebee92d6a69c7413a679f3e1727c53f3adcd14df873d43dabca10b00b33066a
+oid sha256:07cb66408e84749abcb73a31aed63d6592983c68fcaf326ff9fa389496230d2e
 size 442505820

run-3/checkpoint-2073/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-3/checkpoint-2073/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07cb66408e84749abcb73a31aed63d6592983c68fcaf326ff9fa389496230d2e
+size 442505820

run-3/checkpoint-2073/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:658560ace86c934e3327d9de0b15777a34e2dd49ab0887b422fa4421bac854a1
+size 885131514

run-3/checkpoint-2073/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4106cfc304201318c2dbd7c073855b2693135a3ee729f1f642923557a9811c3
+size 14244

run-3/checkpoint-2073/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d244ac977b2a954d18e31b16180dedbdb4433224340982e63aabb489e1460170
+size 1064

run-3/checkpoint-2073/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-3/checkpoint-2073/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-3/checkpoint-2073/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": 0.634705330626114,
+  "best_model_checkpoint": "test-klue/ynat/run-3/checkpoint-2073",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2073,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.7061206107369956e-05,
+      "loss": 0.8931,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.6198716753557617,
+      "eval_loss": 0.7939329743385315,
+      "eval_runtime": 9.5969,
+      "eval_samples_per_second": 246.85,
+      "eval_steps_per_second": 1.98,
+      "step": 691
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.1638063670189422e-05,
+      "loss": 0.7034,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6312509900868551,
+      "eval_loss": 0.8182857632637024,
+      "eval_runtime": 9.614,
+      "eval_samples_per_second": 246.412,
+      "eval_steps_per_second": 1.976,
+      "step": 1382
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 6.214921233008891e-06,
+      "loss": 0.5792,
+      "step": 1500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 7.917787958283578e-07,
+      "loss": 0.4078,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.634705330626114,
+      "eval_loss": 1.034997582435608,
+      "eval_runtime": 9.5469,
+      "eval_samples_per_second": 248.143,
+      "eval_steps_per_second": 1.99,
+      "step": 2073
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2073,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 672285615898680.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.237588569580688e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 39
+  }
+}

run-3/checkpoint-2073/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca42cd1860a77f1891a7e2e57b0da97d27de86e1595fa73d5b8296b68537abb3
+size 4728