Next training iteration (2.5m)

added_tokens.json

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

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/small+140000/",
+  "_name_or_path": "Xenova/sponsorblock-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953853624a364416ef1c00d39cc455ef45fe4a965b17640ecd2e284e286ea198
+oid sha256:18e97e4150a29791d0e46726f7d6fbe917ec538fb08a92291d4b4145757adcda
 size 307892869

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a98b37c4fbbb2d3fe519fa6ad3f69d142d52742de56fcb0d1cd9eb549a0a04
+oid sha256:9f31c8b4ef533fcfa55bffb5ee21c80376ccc692cea8db19476044e2ceeba614
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7df15d137fce618f6fe590ee2b8930bb7a89e41510e95f6ea420bc96e1b47d
+oid sha256:8cd8ff39fb7a5439f74ce48e9cf4d6d59e1b56abf563ac9187eac4effabaeed0
 size 623

tokenizer_config.json

@@ -1 +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, "name_or_path": "models/small+140000/", "special_tokens_map_file": "C:\\Users\\joshu/.cache\\huggingface\\transformers\\3ad6f8335c1b1ef8966245899d47dcf735abd134d21fd7d26f621fe45ac01184.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "max_length": 512, "tokenizer_class": "T5Tokenizer"}
+{"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, "name_or_path": "Xenova/sponsorblock-small", "special_tokens_map_file": "C:\\Users\\joshu/.cache\\huggingface\\transformers\\3ad6f8335c1b1ef8966245899d47dcf735abd134d21fd7d26f621fe45ac01184.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "max_length": 512, "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6139607605790083,
-  "global_step": 160000,
+  "epoch": 3.328794068694205,
+  "global_step": 330000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,11 +296,177 @@
       "eval_samples_per_second": 80.549,
       "eval_steps_per_second": 20.139,
       "step": 160000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.142583345942402e-05,
+      "loss": 0.0416,
+      "step": 170000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.0921470721743075e-05,
+      "loss": 0.041,
+      "step": 180000
+    },
+    {
+      "epoch": 1.82,
+      "eval_loss": 0.04102006182074547,
+      "eval_runtime": 281.9283,
+      "eval_samples_per_second": 78.14,
+      "eval_steps_per_second": 19.537,
+      "step": 180000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 4.041710798406214e-05,
+      "loss": 0.0433,
+      "step": 190000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 3.99127452463812e-05,
+      "loss": 0.0429,
+      "step": 200000
+    },
+    {
+      "epoch": 2.02,
+      "eval_loss": 0.03989257290959358,
+      "eval_runtime": 280.0034,
+      "eval_samples_per_second": 78.678,
+      "eval_steps_per_second": 19.671,
+      "step": 200000
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 3.940838250870026e-05,
+      "loss": 0.0415,
+      "step": 210000
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.890401977101932e-05,
+      "loss": 0.0414,
+      "step": 220000
+    },
+    {
+      "epoch": 2.22,
+      "eval_loss": 0.04061907157301903,
+      "eval_runtime": 267.0149,
+      "eval_samples_per_second": 82.505,
+      "eval_steps_per_second": 20.628,
+      "step": 220000
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 3.8399657033338377e-05,
+      "loss": 0.0418,
+      "step": 230000
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 3.789529429565744e-05,
+      "loss": 0.0418,
+      "step": 240000
+    },
+    {
+      "epoch": 2.42,
+      "eval_loss": 0.03996673598885536,
+      "eval_runtime": 276.1955,
+      "eval_samples_per_second": 79.762,
+      "eval_steps_per_second": 19.942,
+      "step": 240000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 3.73909315579765e-05,
+      "loss": 0.0406,
+      "step": 250000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 3.688656882029556e-05,
+      "loss": 0.041,
+      "step": 260000
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 0.040077704936265945,
+      "eval_runtime": 288.7223,
+      "eval_samples_per_second": 76.302,
+      "eval_steps_per_second": 19.077,
+      "step": 260000
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 3.6382206082614615e-05,
+      "loss": 0.0413,
+      "step": 270000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.587784334493368e-05,
+      "loss": 0.0425,
+      "step": 280000
+    },
+    {
+      "epoch": 2.82,
+      "eval_loss": 0.03996116667985916,
+      "eval_runtime": 267.335,
+      "eval_samples_per_second": 82.406,
+      "eval_steps_per_second": 20.603,
+      "step": 280000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.537348060725274e-05,
+      "loss": 0.0401,
+      "step": 290000
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 3.48691178695718e-05,
+      "loss": 0.0396,
+      "step": 300000
+    },
+    {
+      "epoch": 3.03,
+      "eval_loss": 0.040498603135347366,
+      "eval_runtime": 265.1951,
+      "eval_samples_per_second": 83.071,
+      "eval_steps_per_second": 20.77,
+      "step": 300000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 3.436475513189086e-05,
+      "loss": 0.0409,
+      "step": 310000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.3860392394209916e-05,
+      "loss": 0.0409,
+      "step": 320000
+    },
+    {
+      "epoch": 3.23,
+      "eval_loss": 0.03931990638375282,
+      "eval_runtime": 283.7794,
+      "eval_samples_per_second": 77.631,
+      "eval_steps_per_second": 19.409,
+      "step": 320000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.335602965652897e-05,
+      "loss": 0.0406,
+      "step": 330000
     }
   ],
   "max_steps": 991350,
   "num_train_epochs": 10,
-  "total_flos": 1.169186500333609e+17,
+  "total_flos": 2.411321596919808e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:684e0b4330b8bb7c9b3e400b71095184c0853b5625598615f94e17fe26941f2b
+oid sha256:6f739aa08e0a2ae96132c28ae43db755ab627999cd9ee400c990d1f3e0e975ab
 size 3119