Add model files (2.43m) - finetuned from https://huggingface.co/EColi/sponsorblock-base-v1

added_tokens.json

@@ -0,0 +1 @@
+{"START_INTERACTION_TOKEN": 32116, "EXTRACT_SEGMENTS: ": 32100, "START_SELFPROMO_TOKEN": 32114, "PROFANITY_TOKEN": 32110, "END_SELFPROMO_TOKEN": 32115, "[Music]": 32107, "END_SPONSOR_TOKEN": 32113, "NUMBER_PERCENTAGE_TOKEN": 32103, "HYPHENATED_URL_TOKEN": 32102, "[Applause]": 32108, "[Laughter]": 32109, "END_INTERACTION_TOKEN": 32117, "BETWEEN_SEGMENTS_TOKEN": 32118, "LONG_WORD_TOKEN": 32106, "URL_TOKEN": 32101, "NUMBER_TOKEN": 32104, "SHORT_HYPHENATED_TOKEN": 32105, "START_SPONSOR_TOKEN": 32112, "NO_SEGMENT_TOKEN": 32111}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "EColi/sponsorblock-base-v1",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.15.0",
+  "use_cache": true,
+  "vocab_size": 32119
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73edbd433a522246e28e3335a1e66fb839f6f470632e4455c38ad39d2ffea58
+size 891703231

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa2f33287398fca8deeed195495504ad565fd9a6ff416b3b341afbf8facdeca6
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:764855c1fd49439e1ca3e8d2ff382456d8c6aa45ad71142cbff0d9ff375234e6
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "EColi/sponsorblock-base-v1", "max_length": 768, "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,362 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5748183573990618,
+  "global_step": 200000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.992814770532512e-05,
+      "loss": 0.0668,
+      "step": 5000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.985629541065024e-05,
+      "loss": 0.0693,
+      "step": 10000
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.0688803568482399,
+      "eval_runtime": 645.0212,
+      "eval_samples_per_second": 29.968,
+      "eval_steps_per_second": 29.968,
+      "step": 10000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.978444311597535e-05,
+      "loss": 0.0634,
+      "step": 15000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.971259082130047e-05,
+      "loss": 0.0637,
+      "step": 20000
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.05873561650514603,
+      "eval_runtime": 644.2466,
+      "eval_samples_per_second": 30.004,
+      "eval_steps_per_second": 30.004,
+      "step": 20000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.964073852662559e-05,
+      "loss": 0.0605,
+      "step": 25000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9568886231950703e-05,
+      "loss": 0.0633,
+      "step": 30000
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.05583559721708298,
+      "eval_runtime": 644.4128,
+      "eval_samples_per_second": 29.996,
+      "eval_steps_per_second": 29.996,
+      "step": 30000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.9497033937275825e-05,
+      "loss": 0.0635,
+      "step": 35000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.9425181642600946e-05,
+      "loss": 0.0584,
+      "step": 40000
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.06174061447381973,
+      "eval_runtime": 644.7843,
+      "eval_samples_per_second": 29.979,
+      "eval_steps_per_second": 29.979,
+      "step": 40000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.935332934792606e-05,
+      "loss": 0.0592,
+      "step": 45000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.9281477053251175e-05,
+      "loss": 0.061,
+      "step": 50000
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.05651352182030678,
+      "eval_runtime": 642.7605,
+      "eval_samples_per_second": 30.073,
+      "eval_steps_per_second": 30.073,
+      "step": 50000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.92096247585763e-05,
+      "loss": 0.0693,
+      "step": 55000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.913777246390141e-05,
+      "loss": 0.0652,
+      "step": 60000
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.055016856640577316,
+      "eval_runtime": 641.3853,
+      "eval_samples_per_second": 30.138,
+      "eval_steps_per_second": 30.138,
+      "step": 60000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9065920169226526e-05,
+      "loss": 0.0665,
+      "step": 65000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.899406787455164e-05,
+      "loss": 0.0646,
+      "step": 70000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.05567777901887894,
+      "eval_runtime": 642.5363,
+      "eval_samples_per_second": 30.084,
+      "eval_steps_per_second": 30.084,
+      "step": 70000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.892221557987676e-05,
+      "loss": 0.0617,
+      "step": 75000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.8850363285201876e-05,
+      "loss": 0.0648,
+      "step": 80000
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.05431482940912247,
+      "eval_runtime": 641.7629,
+      "eval_samples_per_second": 30.12,
+      "eval_steps_per_second": 30.12,
+      "step": 80000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.877851099052699e-05,
+      "loss": 0.0654,
+      "step": 85000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.870665869585211e-05,
+      "loss": 0.0664,
+      "step": 90000
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.05483051761984825,
+      "eval_runtime": 643.1769,
+      "eval_samples_per_second": 30.054,
+      "eval_steps_per_second": 30.054,
+      "step": 90000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.863480640117723e-05,
+      "loss": 0.0649,
+      "step": 95000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.856295410650235e-05,
+      "loss": 0.0615,
+      "step": 100000
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.061954181641340256,
+      "eval_runtime": 641.5389,
+      "eval_samples_per_second": 30.131,
+      "eval_steps_per_second": 30.131,
+      "step": 100000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.849110181182747e-05,
+      "loss": 0.0596,
+      "step": 105000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.8419249517152584e-05,
+      "loss": 0.0629,
+      "step": 110000
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.06062796711921692,
+      "eval_runtime": 642.0211,
+      "eval_samples_per_second": 30.108,
+      "eval_steps_per_second": 30.108,
+      "step": 110000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 4.83473972224777e-05,
+      "loss": 0.0613,
+      "step": 115000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.827554492780282e-05,
+      "loss": 0.0683,
+      "step": 120000
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.055720094591379166,
+      "eval_runtime": 642.5633,
+      "eval_samples_per_second": 30.083,
+      "eval_steps_per_second": 30.083,
+      "step": 120000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.8203692633127935e-05,
+      "loss": 0.0631,
+      "step": 125000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.813184033845305e-05,
+      "loss": 0.0649,
+      "step": 130000
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.06274710595607758,
+      "eval_runtime": 642.0067,
+      "eval_samples_per_second": 30.109,
+      "eval_steps_per_second": 30.109,
+      "step": 130000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.805998804377817e-05,
+      "loss": 0.0642,
+      "step": 135000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.7988135749103285e-05,
+      "loss": 0.064,
+      "step": 140000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.05436055734753609,
+      "eval_runtime": 642.9629,
+      "eval_samples_per_second": 30.064,
+      "eval_steps_per_second": 30.064,
+      "step": 140000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.79162834544284e-05,
+      "loss": 0.0592,
+      "step": 145000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.784443115975352e-05,
+      "loss": 0.0574,
+      "step": 150000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.059992264956235886,
+      "eval_runtime": 642.342,
+      "eval_samples_per_second": 30.093,
+      "eval_steps_per_second": 30.093,
+      "step": 150000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.7772578865078636e-05,
+      "loss": 0.0637,
+      "step": 155000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 4.770072657040375e-05,
+      "loss": 0.0599,
+      "step": 160000
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 0.05961042642593384,
+      "eval_runtime": 642.0137,
+      "eval_samples_per_second": 30.108,
+      "eval_steps_per_second": 30.108,
+      "step": 160000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.762887427572887e-05,
+      "loss": 0.0618,
+      "step": 165000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.748516968637911e-05,
+      "loss": 0.0619,
+      "step": 175000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.7125908213004694e-05,
+      "loss": 0.0558,
+      "step": 200000
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.061555784195661545,
+      "eval_runtime": 654.4106,
+      "eval_samples_per_second": 29.538,
+      "eval_steps_per_second": 29.538,
+      "step": 200000
+    }
+  ],
+  "max_steps": 3479360,
+  "num_train_epochs": 10,
+  "total_flos": 6.998757674752512e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff45ae7a4c7d70aca065fada9ae931b0ce50044f40c72cead39c54826e164fb2
+size 3119