Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad0b0b61955ac4a2652f205d6c90f184fedf219e1a2a38d68df99905c9a8263
+oid sha256:b3d873e808ceb4619e57f04fb8f420f4cefcdf9ef188f491fa2f6bf84653f588
 size 442505820

run-1/checkpoint-348/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-1/checkpoint-348/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d873e808ceb4619e57f04fb8f420f4cefcdf9ef188f491fa2f6bf84653f588
+size 442505820

run-1/checkpoint-348/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ef8ca320c8212b522b55232c9e3c747c6bb3e8344eaf364a4ab35102dee194
+size 885131514

run-1/checkpoint-348/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0deb9b0131077aedccb8f03318ccc1b752694b14c2beb8ef7d2612dbf56b6cc
+size 14244

run-1/checkpoint-348/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f008b51db4b1f716388cb3e20f0d0a408465733787331f92d4ba95f9e2e0b706
+size 1064

run-1/checkpoint-348/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-348/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-348/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.6372146146419233,
+  "best_model_checkpoint": "test-klue/ynat/run-1/checkpoint-348",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.6029877323344476,
+      "eval_loss": 0.8173701167106628,
+      "eval_runtime": 9.3445,
+      "eval_samples_per_second": 253.518,
+      "eval_steps_per_second": 2.033,
+      "step": 87
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.6209005601673058,
+      "eval_loss": 0.8260294795036316,
+      "eval_runtime": 9.4061,
+      "eval_samples_per_second": 251.859,
+      "eval_steps_per_second": 2.02,
+      "step": 174
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.634850468939329,
+      "eval_loss": 0.9556489586830139,
+      "eval_runtime": 9.4009,
+      "eval_samples_per_second": 251.998,
+      "eval_steps_per_second": 2.021,
+      "step": 261
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.6372146146419233,
+      "eval_loss": 1.1425336599349976,
+      "eval_runtime": 9.3999,
+      "eval_samples_per_second": 252.025,
+      "eval_steps_per_second": 2.021,
+      "step": 348
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 435,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.692156877095423e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 7
+  }
+}

run-1/checkpoint-348/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81d472e0d5577affb665ca4b6743bf94144aa0b6bb4c1544057b0143ff175d03
+size 4728