Training in progress, step 100, checkpoint

checkpoint-100/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "klue/roberta-large",
+  "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": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 2,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a8e20d6dbf0fcb9f528b9d741026773d61e5949e0946bf2a03d67452a05765
+size 1346677820

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:793960638083211709d547d2e9d8d0ba2f02634498dc14db41e627703b20c60c
+size 2693490234

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ae8df3c502f58dd8e85bd65313ad4a078201c4264b01fa6f5f62fbefe29786
+size 14308

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c841fb02172bb27ae70a1e45eae364586e59bd3e03cbcd7042d9d1f9860020ce
+size 1064

checkpoint-100/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-100/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]"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12572685840012573,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.996486892091073e-06,
+      "loss": 0.6543,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.985953053665263e-06,
+      "loss": 0.469,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8.968414932060827e-06,
+      "loss": 0.2958,
+      "step": 30
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.94389991097275e-06,
+      "loss": 0.2424,
+      "step": 40
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8.912446267696357e-06,
+      "loss": 0.2481,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 8.874103113361848e-06,
+      "loss": 0.251,
+      "step": 60
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.828930316253112e-06,
+      "loss": 0.1803,
+      "step": 70
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.7769984083305e-06,
+      "loss": 0.2148,
+      "step": 80
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 8.718388475103545e-06,
+      "loss": 0.1926,
+      "step": 90
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 8.653192029025561e-06,
+      "loss": 0.2202,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.0,
+      "eval_loss": 0.07498380541801453,
+      "eval_runtime": 28.9719,
+      "eval_samples_per_second": 97.612,
+      "eval_steps_per_second": 24.403,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 795,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97515eaa596c1259df8da372577f8444c126856d2334b3f90d539244c52eb51c
+size 4664