Upload folder using huggingface_hub

checkpoint-500/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": "4.33.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7c4f3b6f6851ab4e989463fe19499fa61dc1e158aa905998167c47b37e24c9
+size 885131013

checkpoint-500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdec6e1d3764c8dcf3d4aea911ab279f2f41e745defa30cc4f931e4aee7504f
+size 442550641

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe738f0728067f737229030b774cec7e7d508778304f54ee2f38fd8f2fcf7f91
+size 14575

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47df1ebabfa77474c0b54122f36e4ab25e1baa66ed20377b424b61d5046ae0e5
+size 627

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "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]"
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.1020408163265305,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7943333333333333,
+      "eval_f1": 0.7930526774486847,
+      "eval_loss": 0.5377587080001831,
+      "eval_runtime": 3.0956,
+      "eval_samples_per_second": 969.112,
+      "eval_steps_per_second": 3.876,
+      "step": 98
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.838,
+      "eval_f1": 0.8378349608143602,
+      "eval_loss": 0.47621798515319824,
+      "eval_runtime": 3.0912,
+      "eval_samples_per_second": 970.483,
+      "eval_steps_per_second": 3.882,
+      "step": 196
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.851,
+      "eval_f1": 0.8511510805118198,
+      "eval_loss": 0.4523032605648041,
+      "eval_runtime": 3.1117,
+      "eval_samples_per_second": 964.094,
+      "eval_steps_per_second": 3.856,
+      "step": 294
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 3.344671201814059e-05,
+      "loss": 0.3853,
+      "step": 390
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8576666666666667,
+      "eval_f1": 0.8573781508901815,
+      "eval_loss": 0.4846896529197693,
+      "eval_runtime": 3.0975,
+      "eval_samples_per_second": 968.515,
+      "eval_steps_per_second": 3.874,
+      "step": 392
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8583333333333333,
+      "eval_f1": 0.8581937288721457,
+      "eval_loss": 0.5415525436401367,
+      "eval_runtime": 3.0931,
+      "eval_samples_per_second": 969.891,
+      "eval_steps_per_second": 3.88,
+      "step": 490
+    }
+  ],
+  "logging_steps": 390,
+  "max_steps": 980,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6554710240470000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ec9edc6e0f8865e25ee21ad84ad98845d86f96eaf887b9b0628887c7e3f642
+size 4027

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": "4.33.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20490e0faab9b65b9c5ebd7bcf2a03f1198cbbc853afe6503d75b35de5bc95d2
+size 442550641

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "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]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ec9edc6e0f8865e25ee21ad84ad98845d86f96eaf887b9b0628887c7e3f642
+size 4027