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": "4.35.2",
+  "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:d99d51ad1c108526467c19998614f2008818c36679d24617de54f9d3f066b529
+size 1346677820

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cae6b51173c94ede440512b24105faf95cba13c58ad157c04d314b3b796178
+size 2693490234

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad1da5758d2976dab48c4877bccf9ed80af2303868df90c4ec21096da80273e
+size 14308

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60d0d525133978ce1d905126709b02bcf3b00be31b7c97f654c9a9d67029a39
+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": 0.17135023989033585,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.993468091981985e-05,
+      "loss": 0.6403,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.973891330515646e-05,
+      "loss": 0.5248,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.941326548314407e-05,
+      "loss": 0.5079,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 8.895868283228029e-05,
+      "loss": 0.5916,
+      "step": 40
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.837648503792598e-05,
+      "loss": 0.5116,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 8.766836226116608e-05,
+      "loss": 0.5206,
+      "step": 60
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.683637023215313e-05,
+      "loss": 0.535,
+      "step": 70
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 8.588292428217834e-05,
+      "loss": 0.6067,
+      "step": 80
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 8.481079233179524e-05,
+      "loss": 0.6139,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 8.362308685535183e-05,
+      "loss": 0.5015,
+      "step": 100
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.0,
+      "eval_loss": 0.5284319519996643,
+      "eval_runtime": 27.5165,
+      "eval_samples_per_second": 141.406,
+      "eval_steps_per_second": 23.586,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 583,
+  "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 sha256:695e130918d61548f4c2cafeb09df62eb554ce76c30c528e836ec09a77ba1c54
+size 4664