Adding checkpoints

checkpoint-1464/config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "BertClickbaitClassifier"
+  ],
+  "dropout": 0.2,
+  "freeze_bert": false,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "inner_dim1": 256,
+  "inner_dim2": 32,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "load_pretrained": true,
+  "max_length": 25,
+  "pretrained_model": "sentence-transformers/all-mpnet-base-v2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.2"
+}

checkpoint-1464/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86af40c41b9c7bd860a34891976e7ccb5cb03e35f540bac3901e768a5e90947
+size 872925589

checkpoint-1464/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881e07cb4fc93116a9f5bee91fc6048ce366725537b34edf7fdf7f243d2ba240
+size 438838053

checkpoint-1464/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af047df93f2e21bc6b802f06e57d980fb915986b57e8908ad2e2e43065125260
+size 14503

checkpoint-1464/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c454d2b62b7deada05505a5f5f4607c60de6caa71a7d7b0a6c0c1821f97993c7
+size 623

checkpoint-1464/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

checkpoint-1464/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "[UNK]", "pad_token": "<pad>", "mask_token": "<mask>", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sentence-transformers/all-mpnet-base-v2", "tokenizer_class": "MPNetTokenizer"}

checkpoint-1464/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 1.0750963687896729,
+  "best_model_checkpoint": "drive/MyDrive/nlp_lss_data/mpnet_clickbait_classification_maxlen25/checkpoint-488",
+  "epoch": 6.0,
+  "global_step": 1464,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8498845265588915,
+      "eval_balanced_accuracy": 0.7757283651550713,
+      "eval_f1": 0.670793472144063,
+      "eval_loss": 1.1807881593704224,
+      "eval_precision": 0.7146282973621103,
+      "eval_recall": 0.6320254506892895,
+      "eval_runtime": 34.3115,
+      "eval_samples_per_second": 113.577,
+      "eval_steps_per_second": 113.577,
+      "step": 244
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8545034642032333,
+      "eval_balanced_accuracy": 0.7932135085090511,
+      "eval_f1": 0.6916802610114193,
+      "eval_loss": 1.0750963687896729,
+      "eval_precision": 0.7098214285714286,
+      "eval_recall": 0.6744432661717922,
+      "eval_runtime": 33.949,
+      "eval_samples_per_second": 114.79,
+      "eval_steps_per_second": 114.79,
+      "step": 488
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 3.533724340175953e-05,
+      "loss": 1.3113,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8601488324352066,
+      "eval_balanced_accuracy": 0.7835817278869854,
+      "eval_f1": 0.6873207114170969,
+      "eval_loss": 1.1083189249038696,
+      "eval_precision": 0.74875,
+      "eval_recall": 0.6352067868504772,
+      "eval_runtime": 33.7352,
+      "eval_samples_per_second": 115.517,
+      "eval_steps_per_second": 115.517,
+      "step": 732
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8534770336156018,
+      "eval_balanced_accuracy": 0.7993947132812708,
+      "eval_f1": 0.6964380648591175,
+      "eval_loss": 1.1579805612564087,
+      "eval_precision": 0.6982942430703625,
+      "eval_recall": 0.694591728525981,
+      "eval_runtime": 33.9178,
+      "eval_samples_per_second": 114.895,
+      "eval_steps_per_second": 114.895,
+      "step": 976
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 1.7008797653958943e-05,
+      "loss": 0.7869,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8552732871439569,
+      "eval_balanced_accuracy": 0.8009405080804215,
+      "eval_f1": 0.6993603411513859,
+      "eval_loss": 1.2740588188171387,
+      "eval_precision": 0.7031082529474812,
+      "eval_recall": 0.6956521739130435,
+      "eval_runtime": 34.1758,
+      "eval_samples_per_second": 114.028,
+      "eval_steps_per_second": 114.028,
+      "step": 1220
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8555298947908647,
+      "eval_balanced_accuracy": 0.793168635227608,
+      "eval_f1": 0.6925177498634627,
+      "eval_loss": 1.3905503749847412,
+      "eval_precision": 0.713963963963964,
+      "eval_recall": 0.672322375397667,
+      "eval_runtime": 33.4993,
+      "eval_samples_per_second": 116.331,
+      "eval_steps_per_second": 116.331,
+      "step": 1464
+    }
+  ],
+  "max_steps": 1464,
+  "num_train_epochs": 6,
+  "total_flos": 1204353585477900.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1464/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf148502136d195161841d56eda30be54006d58e628e1439c9393fb6404ef4a
+size 3311

checkpoint-150/config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "google/pegasus-xsum",
+  "activation_dropout": 0.1,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "PegasusForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 16,
+  "decoder_start_token_id": 0,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 16,
+  "eos_token_id": 1,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 1,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 0.6,
+  "max_length": 64,
+  "max_position_embeddings": 512,
+  "model_type": "pegasus",
+  "normalize_before": true,
+  "normalize_embedding": false,
+  "num_beams": 8,
+  "num_hidden_layers": 16,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 96103
+}

checkpoint-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31a813daf8949431f72c9672f50293c37c937f8239655269de86409df0a04ad
+size 5839694

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61da4aab34859d84193f6d36e1ca6db2cab8dd2449b8ba79a7f1af61aa8c44a5
+size 14503

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e43ff59eb3184ee5df5457b7f99569ad47a950434bbef23184de1d9025687c8e
+size 623

checkpoint-150/special_tokens_map.json

@@ -0,0 +1,110 @@
+{
+  "additional_special_tokens": [
+    "<mask_1>",
+    "<unk_2>",
+    "<unk_3>",
+    "<unk_4>",
+    "<unk_5>",
+    "<unk_6>",
+    "<unk_7>",
+    "<unk_8>",
+    "<unk_9>",
+    "<unk_10>",
+    "<unk_11>",
+    "<unk_12>",
+    "<unk_13>",
+    "<unk_14>",
+    "<unk_15>",
+    "<unk_16>",
+    "<unk_17>",
+    "<unk_18>",
+    "<unk_19>",
+    "<unk_20>",
+    "<unk_21>",
+    "<unk_22>",
+    "<unk_23>",
+    "<unk_24>",
+    "<unk_25>",
+    "<unk_26>",
+    "<unk_27>",
+    "<unk_28>",
+    "<unk_29>",
+    "<unk_30>",
+    "<unk_31>",
+    "<unk_32>",
+    "<unk_33>",
+    "<unk_34>",
+    "<unk_35>",
+    "<unk_36>",
+    "<unk_37>",
+    "<unk_38>",
+    "<unk_39>",
+    "<unk_40>",
+    "<unk_41>",
+    "<unk_42>",
+    "<unk_43>",
+    "<unk_44>",
+    "<unk_45>",
+    "<unk_46>",
+    "<unk_47>",
+    "<unk_48>",
+    "<unk_49>",
+    "<unk_50>",
+    "<unk_51>",
+    "<unk_52>",
+    "<unk_53>",
+    "<unk_54>",
+    "<unk_55>",
+    "<unk_56>",
+    "<unk_57>",
+    "<unk_58>",
+    "<unk_59>",
+    "<unk_60>",
+    "<unk_61>",
+    "<unk_62>",
+    "<unk_63>",
+    "<unk_64>",
+    "<unk_65>",
+    "<unk_66>",
+    "<unk_67>",
+    "<unk_68>",
+    "<unk_69>",
+    "<unk_70>",
+    "<unk_71>",
+    "<unk_72>",
+    "<unk_73>",
+    "<unk_74>",
+    "<unk_75>",
+    "<unk_76>",
+    "<unk_77>",
+    "<unk_78>",
+    "<unk_79>",
+    "<unk_80>",
+    "<unk_81>",
+    "<unk_82>",
+    "<unk_83>",
+    "<unk_84>",
+    "<unk_85>",
+    "<unk_86>",
+    "<unk_87>",
+    "<unk_88>",
+    "<unk_89>",
+    "<unk_90>",
+    "<unk_91>",
+    "<unk_92>",
+    "<unk_93>",
+    "<unk_94>",
+    "<unk_95>",
+    "<unk_96>",
+    "<unk_97>",
+    "<unk_98>",
+    "<unk_99>",
+    "<unk_100>",
+    "<unk_101>",
+    "<unk_102>"
+  ],
+  "eos_token": "</s>",
+  "mask_token": "<mask_2>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

checkpoint-150/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
+size 1912529

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,117 @@
+{
+  "additional_special_tokens": [
+    "<mask_1>",
+    "<unk_2>",
+    "<unk_3>",
+    "<unk_4>",
+    "<unk_5>",
+    "<unk_6>",
+    "<unk_7>",
+    "<unk_8>",
+    "<unk_9>",
+    "<unk_10>",
+    "<unk_11>",
+    "<unk_12>",
+    "<unk_13>",
+    "<unk_14>",
+    "<unk_15>",
+    "<unk_16>",
+    "<unk_17>",
+    "<unk_18>",
+    "<unk_19>",
+    "<unk_20>",
+    "<unk_21>",
+    "<unk_22>",
+    "<unk_23>",
+    "<unk_24>",
+    "<unk_25>",
+    "<unk_26>",
+    "<unk_27>",
+    "<unk_28>",
+    "<unk_29>",
+    "<unk_30>",
+    "<unk_31>",
+    "<unk_32>",
+    "<unk_33>",
+    "<unk_34>",
+    "<unk_35>",
+    "<unk_36>",
+    "<unk_37>",
+    "<unk_38>",
+    "<unk_39>",
+    "<unk_40>",
+    "<unk_41>",
+    "<unk_42>",
+    "<unk_43>",
+    "<unk_44>",
+    "<unk_45>",
+    "<unk_46>",
+    "<unk_47>",
+    "<unk_48>",
+    "<unk_49>",
+    "<unk_50>",
+    "<unk_51>",
+    "<unk_52>",
+    "<unk_53>",
+    "<unk_54>",
+    "<unk_55>",
+    "<unk_56>",
+    "<unk_57>",
+    "<unk_58>",
+    "<unk_59>",
+    "<unk_60>",
+    "<unk_61>",
+    "<unk_62>",
+    "<unk_63>",
+    "<unk_64>",
+    "<unk_65>",
+    "<unk_66>",
+    "<unk_67>",
+    "<unk_68>",
+    "<unk_69>",
+    "<unk_70>",
+    "<unk_71>",
+    "<unk_72>",
+    "<unk_73>",
+    "<unk_74>",
+    "<unk_75>",
+    "<unk_76>",
+    "<unk_77>",
+    "<unk_78>",
+    "<unk_79>",
+    "<unk_80>",
+    "<unk_81>",
+    "<unk_82>",
+    "<unk_83>",
+    "<unk_84>",
+    "<unk_85>",
+    "<unk_86>",
+    "<unk_87>",
+    "<unk_88>",
+    "<unk_89>",
+    "<unk_90>",
+    "<unk_91>",
+    "<unk_92>",
+    "<unk_93>",
+    "<unk_94>",
+    "<unk_95>",
+    "<unk_96>",
+    "<unk_97>",
+    "<unk_98>",
+    "<unk_99>",
+    "<unk_100>",
+    "<unk_101>",
+    "<unk_102>"
+  ],
+  "eos_token": "</s>",
+  "full_tokenizer_file": null,
+  "mask_token": "<mask_2>",
+  "mask_token_sent": "<mask_1>",
+  "model_max_length": 512,
+  "name_or_path": "google/pegasus-xsum",
+  "offset": 103,
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "PegasusTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.982725527831094,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.98,
+      "eval_loss": 2.3803367614746094,
+      "eval_runtime": 213.2043,
+      "eval_samples_per_second": 18.33,
+      "eval_steps_per_second": 18.33,
+      "step": 30
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 2.2591161727905273,
+      "eval_runtime": 212.2667,
+      "eval_samples_per_second": 18.411,
+      "eval_steps_per_second": 18.411,
+      "step": 60
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 2.203186511993408,
+      "eval_runtime": 212.608,
+      "eval_samples_per_second": 18.381,
+      "eval_steps_per_second": 18.381,
+      "step": 90
+    },
+    {
+      "epoch": 3.98,
+      "eval_loss": 2.1706554889678955,
+      "eval_runtime": 212.4689,
+      "eval_samples_per_second": 18.393,
+      "eval_steps_per_second": 18.393,
+      "step": 120
+    },
+    {
+      "epoch": 4.98,
+      "eval_loss": 2.1453042030334473,
+      "eval_runtime": 213.096,
+      "eval_samples_per_second": 18.339,
+      "eval_steps_per_second": 18.339,
+      "step": 150
+    }
+  ],
+  "max_steps": 900,
+  "num_train_epochs": 30,
+  "total_flos": 1.076296204604375e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f1c331773948f1aafffbec50322b3f07edf4e08988fbdb44798e3e9b3db9fd
+size 3375