Upload folder using huggingface_hub

best/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "YituTech/conv-bert-base",
+  "architectures": [
+    "ConvBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "conv_kernel_size": 9,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "chatGPT",
+    "2": "cohere",
+    "3": "davinci",
+    "4": "bloomz",
+    "5": "dolly"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bloomz": 4,
+    "chatGPT": 1,
+    "cohere": 2,
+    "davinci": 3,
+    "dolly": 5,
+    "human": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 12,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

best/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735364986679ab1c52ea41611897a0ebed1ea1f2026f6e2e797cc2d7349c13de
+size 425138888

best/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

best/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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": "ConvBertTokenizer",
+  "unk_token": "[UNK]"
+}

best/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d251a585b021c6b5db1fde6c0dc615e9d997c4cb7296ba87d7628a4766ea4480
+size 4728

checkpoint-1776/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "YituTech/conv-bert-base",
+  "architectures": [
+    "ConvBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "conv_kernel_size": 9,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "chatGPT",
+    "2": "cohere",
+    "3": "davinci",
+    "4": "bloomz",
+    "5": "dolly"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bloomz": 4,
+    "chatGPT": 1,
+    "cohere": 2,
+    "davinci": 3,
+    "dolly": 5,
+    "human": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 12,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

checkpoint-1776/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735364986679ab1c52ea41611897a0ebed1ea1f2026f6e2e797cc2d7349c13de
+size 425138888

checkpoint-1776/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f05660feab3b0cffe0ca9cb402ba792951be3566af24327509864453e0ff6df6
+size 850443770

checkpoint-1776/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159d63499ae0b9cec1de1f1856693361a68b6e6290d39440e6d841bb4ae6168e
+size 14244

checkpoint-1776/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0c6be97e1b3a48df0541ca2d55e2bdae7a9b36cd25de0bd8b59e25ffcea3a4
+size 1064

checkpoint-1776/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-1776/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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": "ConvBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-1776/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.26428040862083435,
+  "best_model_checkpoint": "YituTech/conv-bert-base/subtaskB/42/checkpoint-1776",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1776,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.718468468468469e-05,
+      "loss": 0.6011,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.4369369369369375e-05,
+      "loss": 0.2811,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.1554054054054055e-05,
+      "loss": 0.2427,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9117274391102351,
+      "eval_loss": 0.26428040862083435,
+      "eval_runtime": 93.1627,
+      "eval_samples_per_second": 152.486,
+      "eval_steps_per_second": 4.766,
+      "step": 1776
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8880,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.4390254608500736e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1776/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d251a585b021c6b5db1fde6c0dc615e9d997c4cb7296ba87d7628a4766ea4480
+size 4728

checkpoint-3552/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "YituTech/conv-bert-base",
+  "architectures": [
+    "ConvBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "conv_kernel_size": 9,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "chatGPT",
+    "2": "cohere",
+    "3": "davinci",
+    "4": "bloomz",
+    "5": "dolly"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bloomz": 4,
+    "chatGPT": 1,
+    "cohere": 2,
+    "davinci": 3,
+    "dolly": 5,
+    "human": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 12,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

checkpoint-3552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60a93d61495c21d04792cb4051156dc7ad6d7d4b918448947c2166017eab4992
+size 425138888

checkpoint-3552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bee55d46714e1906040e61115450f1bf54a43170fc2a38b44158b8ad9f9f114
+size 850443770

checkpoint-3552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6527f72b37732bdcda16c2d0b6237381b39ed034d9bdc69ddc6c7c8b61f5b3b
+size 14244

checkpoint-3552/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46f4268104ef2b51a09bc192562c9a1b0a0e0a19899b24a2cc409c9bcfbc030
+size 1064

checkpoint-3552/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-3552/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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": "ConvBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-3552/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.26428040862083435,
+  "best_model_checkpoint": "YituTech/conv-bert-base/subtaskB/42/checkpoint-1776",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 3552,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.718468468468469e-05,
+      "loss": 0.6011,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.4369369369369375e-05,
+      "loss": 0.2811,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.1554054054054055e-05,
+      "loss": 0.2427,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9117274391102351,
+      "eval_loss": 0.26428040862083435,
+      "eval_runtime": 93.1627,
+      "eval_samples_per_second": 152.486,
+      "eval_steps_per_second": 4.766,
+      "step": 1776
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.873873873873874e-05,
+      "loss": 0.1753,
+      "step": 2000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.592342342342343e-05,
+      "loss": 0.1239,
+      "step": 2500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.310810810810811e-05,
+      "loss": 0.1203,
+      "step": 3000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.0292792792792797e-05,
+      "loss": 0.1015,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9108123328171195,
+      "eval_loss": 0.3175283372402191,
+      "eval_runtime": 93.2571,
+      "eval_samples_per_second": 152.332,
+      "eval_steps_per_second": 4.761,
+      "step": 3552
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8880,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.878050921700147e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3552/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d251a585b021c6b5db1fde6c0dc615e9d997c4cb7296ba87d7628a4766ea4480
+size 4728

checkpoint-5328/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "YituTech/conv-bert-base",
+  "architectures": [
+    "ConvBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "conv_kernel_size": 9,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "chatGPT",
+    "2": "cohere",
+    "3": "davinci",
+    "4": "bloomz",
+    "5": "dolly"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bloomz": 4,
+    "chatGPT": 1,
+    "cohere": 2,
+    "davinci": 3,
+    "dolly": 5,
+    "human": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 12,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

checkpoint-5328/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6ec531632c7ead362458d0657551c31758c5f131a347eca6c0e5900d5095c6b
+size 425138888

checkpoint-5328/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac3cd7dcaac0b95e847e851403b8aaf748c83e122df87d48e297d1894f1e6e5
+size 850443770

checkpoint-5328/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40c5d3ed465e23aadcc4ab7f8ed9344b9abd8c85c626aecc35b2f7acc775612
+size 14244

checkpoint-5328/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc7aa4ccac4a13f9949dce2b78c8a5296626034b4b06f0f26c9be48b29ff05d
+size 1064

checkpoint-5328/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-5328/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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": "ConvBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-5328/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 0.26428040862083435,
+  "best_model_checkpoint": "YituTech/conv-bert-base/subtaskB/42/checkpoint-1776",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5328,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.718468468468469e-05,
+      "loss": 0.6011,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.4369369369369375e-05,
+      "loss": 0.2811,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.1554054054054055e-05,
+      "loss": 0.2427,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9117274391102351,
+      "eval_loss": 0.26428040862083435,
+      "eval_runtime": 93.1627,
+      "eval_samples_per_second": 152.486,
+      "eval_steps_per_second": 4.766,
+      "step": 1776
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.873873873873874e-05,
+      "loss": 0.1753,
+      "step": 2000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.592342342342343e-05,
+      "loss": 0.1239,
+      "step": 2500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.310810810810811e-05,
+      "loss": 0.1203,
+      "step": 3000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.0292792792792797e-05,
+      "loss": 0.1015,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9108123328171195,
+      "eval_loss": 0.3175283372402191,
+      "eval_runtime": 93.2571,
+      "eval_samples_per_second": 152.332,
+      "eval_steps_per_second": 4.761,
+      "step": 3552
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.7477477477477483e-05,
+      "loss": 0.0539,
+      "step": 4000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.4662162162162162e-05,
+      "loss": 0.0475,
+      "step": 4500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.1846846846846845e-05,
+      "loss": 0.052,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9283401379698719,
+      "eval_loss": 0.3505339026451111,
+      "eval_runtime": 93.5325,
+      "eval_samples_per_second": 151.883,
+      "eval_steps_per_second": 4.747,
+      "step": 5328
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8880,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 4.317076382550221e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5328/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d251a585b021c6b5db1fde6c0dc615e9d997c4cb7296ba87d7628a4766ea4480
+size 4728

checkpoint-7104/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "YituTech/conv-bert-base",
+  "architectures": [
+    "ConvBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "conv_kernel_size": 9,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "head_ratio": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "human",
+    "1": "chatGPT",
+    "2": "cohere",
+    "3": "davinci",
+    "4": "bloomz",
+    "5": "dolly"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "bloomz": 4,
+    "chatGPT": 1,
+    "cohere": 2,
+    "davinci": 3,
+    "dolly": 5,
+    "human": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "convbert",
+  "num_attention_heads": 12,
+  "num_groups": 1,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30522
+}

checkpoint-7104/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e01ab46d027f17108acbaf8b47a71e696b7932142add2dc4656c5ceff6a012e
+size 425138888

checkpoint-7104/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:feb8268eeb0cce3f74aa7d3adeb36e9f49f479fb488b33c17f7c7470da7eaf93
+size 850443770

checkpoint-7104/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8910514881863e4b777da6a45da7697ae76940c96bd3a37bbac45a9f86b1a6
+size 14244

checkpoint-7104/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4644143c012bf941219243ea6e65806053aae9c619200e42f4199f37bdc43761
+size 1064

checkpoint-7104/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

checkpoint-7104/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "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": "ConvBertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-7104/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.26428040862083435,
+  "best_model_checkpoint": "YituTech/conv-bert-base/subtaskB/42/checkpoint-1776",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 7104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.718468468468469e-05,
+      "loss": 0.6011,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.4369369369369375e-05,
+      "loss": 0.2811,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 4.1554054054054055e-05,
+      "loss": 0.2427,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.9117274391102351,
+      "eval_loss": 0.26428040862083435,
+      "eval_runtime": 93.1627,
+      "eval_samples_per_second": 152.486,
+      "eval_steps_per_second": 4.766,
+      "step": 1776
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.873873873873874e-05,
+      "loss": 0.1753,
+      "step": 2000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 3.592342342342343e-05,
+      "loss": 0.1239,
+      "step": 2500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.310810810810811e-05,
+      "loss": 0.1203,
+      "step": 3000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 3.0292792792792797e-05,
+      "loss": 0.1015,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.9108123328171195,
+      "eval_loss": 0.3175283372402191,
+      "eval_runtime": 93.2571,
+      "eval_samples_per_second": 152.332,
+      "eval_steps_per_second": 4.761,
+      "step": 3552
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.7477477477477483e-05,
+      "loss": 0.0539,
+      "step": 4000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 2.4662162162162162e-05,
+      "loss": 0.0475,
+      "step": 4500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.1846846846846845e-05,
+      "loss": 0.052,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.9283401379698719,
+      "eval_loss": 0.3505339026451111,
+      "eval_runtime": 93.5325,
+      "eval_samples_per_second": 151.883,
+      "eval_steps_per_second": 4.747,
+      "step": 5328
+    },
+    {
+      "epoch": 3.1,
+      "learning_rate": 1.9031531531531532e-05,
+      "loss": 0.0305,
+      "step": 5500
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 1.6216216216216218e-05,
+      "loss": 0.018,
+      "step": 6000
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 1.3400900900900901e-05,
+      "loss": 0.0187,
+      "step": 6500
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 1.0585585585585586e-05,
+      "loss": 0.0136,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.9349570603970153,
+      "eval_loss": 0.3897482752799988,
+      "eval_runtime": 93.39,
+      "eval_samples_per_second": 152.115,
+      "eval_steps_per_second": 4.754,
+      "step": 7104
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8880,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 5.756101843400294e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-7104/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d251a585b021c6b5db1fde6c0dc615e9d997c4cb7296ba87d7628a4766ea4480
+size 4728