Add model info

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "models/small-120k/",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "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 sha256:58dcad2aa7c597dff5c6336e9906d9fb661f2ee5f52140381e429cbb2542da8b
+size 307892869

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23610cb1c788ca04723649d68925f34a3919771785f230f19b613fa86ae6502b
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b455b205a94d87558a731f71787ead81369846ddc1c53f4dd48da39686c1d9f0
+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, "name_or_path": "models/small-120k/", "special_tokens_map_file": "C:\\Users\\joshu/.cache\\huggingface\\transformers\\3ad6f8335c1b1ef8966245899d47dcf735abd134d21fd7d26f621fe45ac01184.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,436 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5045728266982867,
+  "global_step": 420000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8208841872978234e-05,
+      "loss": 0.0755,
+      "step": 10000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6417683745956466e-05,
+      "loss": 0.0721,
+      "step": 20000
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 0.06494459509849548,
+      "eval_runtime": 754.7473,
+      "eval_samples_per_second": 82.19,
+      "eval_steps_per_second": 20.549,
+      "step": 20000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.462652561893469e-05,
+      "loss": 0.0704,
+      "step": 30000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.2835367491912923e-05,
+      "loss": 0.0701,
+      "step": 40000
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 0.06424280256032944,
+      "eval_runtime": 676.9024,
+      "eval_samples_per_second": 91.642,
+      "eval_steps_per_second": 22.912,
+      "step": 40000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.104420936489115e-05,
+      "loss": 0.0713,
+      "step": 50000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.925305123786938e-05,
+      "loss": 0.0712,
+      "step": 60000
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.0624563954770565,
+      "eval_runtime": 678.8069,
+      "eval_samples_per_second": 91.385,
+      "eval_steps_per_second": 22.847,
+      "step": 60000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.746189311084761e-05,
+      "loss": 0.0698,
+      "step": 70000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.5670734983825844e-05,
+      "loss": 0.0667,
+      "step": 80000
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.06348983943462372,
+      "eval_runtime": 675.6836,
+      "eval_samples_per_second": 91.808,
+      "eval_steps_per_second": 22.953,
+      "step": 80000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.3879576856804076e-05,
+      "loss": 0.0657,
+      "step": 90000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.20884187297823e-05,
+      "loss": 0.0665,
+      "step": 100000
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.06186612322926521,
+      "eval_runtime": 676.1915,
+      "eval_samples_per_second": 91.739,
+      "eval_steps_per_second": 22.936,
+      "step": 100000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.0297260602760537e-05,
+      "loss": 0.0657,
+      "step": 110000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.8506102475738766e-05,
+      "loss": 0.0653,
+      "step": 120000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.061661478132009506,
+      "eval_runtime": 677.4648,
+      "eval_samples_per_second": 91.566,
+      "eval_steps_per_second": 22.893,
+      "step": 120000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.6714944348716997e-05,
+      "loss": 0.0658,
+      "step": 130000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.4923786221695226e-05,
+      "loss": 0.0656,
+      "step": 140000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.06098250672221184,
+      "eval_runtime": 677.3485,
+      "eval_samples_per_second": 91.582,
+      "eval_steps_per_second": 22.897,
+      "step": 140000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3132628094673455e-05,
+      "loss": 0.0649,
+      "step": 150000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1341469967651687e-05,
+      "loss": 0.0648,
+      "step": 160000
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 0.06077565252780914,
+      "eval_runtime": 677.1708,
+      "eval_samples_per_second": 91.606,
+      "eval_steps_per_second": 22.903,
+      "step": 160000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9550311840629915e-05,
+      "loss": 0.0642,
+      "step": 170000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7759153713608147e-05,
+      "loss": 0.0649,
+      "step": 180000
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 0.05941811203956604,
+      "eval_runtime": 677.9109,
+      "eval_samples_per_second": 91.506,
+      "eval_steps_per_second": 22.878,
+      "step": 180000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.5967995586586376e-05,
+      "loss": 0.0652,
+      "step": 190000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.4176837459564608e-05,
+      "loss": 0.0638,
+      "step": 200000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.06042506918311119,
+      "eval_runtime": 678.1922,
+      "eval_samples_per_second": 91.468,
+      "eval_steps_per_second": 22.868,
+      "step": 200000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.2385679332542836e-05,
+      "loss": 0.0621,
+      "step": 210000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0594521205521066e-05,
+      "loss": 0.0643,
+      "step": 220000
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 0.059569716453552246,
+      "eval_runtime": 688.4187,
+      "eval_samples_per_second": 90.109,
+      "eval_steps_per_second": 22.528,
+      "step": 220000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.803363078499297e-06,
+      "loss": 0.0623,
+      "step": 230000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.012204951477527e-06,
+      "loss": 0.0646,
+      "step": 240000
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.059120796620845795,
+      "eval_runtime": 715.8659,
+      "eval_samples_per_second": 86.654,
+      "eval_steps_per_second": 21.665,
+      "step": 240000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.5522104682445576e-05,
+      "loss": 0.0634,
+      "step": 250000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.53429888697434e-05,
+      "loss": 0.0648,
+      "step": 260000
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 0.06051425263285637,
+      "eval_runtime": 694.96,
+      "eval_samples_per_second": 89.261,
+      "eval_steps_per_second": 22.316,
+      "step": 260000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.516387305704122e-05,
+      "loss": 0.0644,
+      "step": 270000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.4984757244339046e-05,
+      "loss": 0.0655,
+      "step": 280000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.06069951504468918,
+      "eval_runtime": 679.0968,
+      "eval_samples_per_second": 91.346,
+      "eval_steps_per_second": 22.838,
+      "step": 280000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 4.4805641431636866e-05,
+      "loss": 0.0652,
+      "step": 290000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.462652561893469e-05,
+      "loss": 0.0631,
+      "step": 300000
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 0.06102127209305763,
+      "eval_runtime": 705.9715,
+      "eval_samples_per_second": 87.869,
+      "eval_steps_per_second": 21.968,
+      "step": 300000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.444740980623252e-05,
+      "loss": 0.064,
+      "step": 310000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.426829399353034e-05,
+      "loss": 0.0643,
+      "step": 320000
+    },
+    {
+      "epoch": 1.15,
+      "eval_loss": 0.05971848592162132,
+      "eval_runtime": 698.4495,
+      "eval_samples_per_second": 88.815,
+      "eval_steps_per_second": 22.205,
+      "step": 320000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 4.408917818082816e-05,
+      "loss": 0.0638,
+      "step": 330000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 4.391006236812599e-05,
+      "loss": 0.064,
+      "step": 340000
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 0.05945688858628273,
+      "eval_runtime": 700.9514,
+      "eval_samples_per_second": 88.498,
+      "eval_steps_per_second": 22.126,
+      "step": 340000
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 4.373094655542381e-05,
+      "loss": 0.0613,
+      "step": 350000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 4.355183074272163e-05,
+      "loss": 0.0635,
+      "step": 360000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.06002034246921539,
+      "eval_runtime": 697.4531,
+      "eval_samples_per_second": 88.942,
+      "eval_steps_per_second": 22.237,
+      "step": 360000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.337271493001945e-05,
+      "loss": 0.0635,
+      "step": 370000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.319359911731728e-05,
+      "loss": 0.0627,
+      "step": 380000
+    },
+    {
+      "epoch": 1.36,
+      "eval_loss": 0.0593414306640625,
+      "eval_runtime": 720.1404,
+      "eval_samples_per_second": 86.14,
+      "eval_steps_per_second": 21.536,
+      "step": 380000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.30144833046151e-05,
+      "loss": 0.0629,
+      "step": 390000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.2835367491912923e-05,
+      "loss": 0.0642,
+      "step": 400000
+    },
+    {
+      "epoch": 1.43,
+      "eval_loss": 0.059706129133701324,
+      "eval_runtime": 706.6838,
+      "eval_samples_per_second": 87.78,
+      "eval_steps_per_second": 21.946,
+      "step": 400000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 4.265625167921074e-05,
+      "loss": 0.062,
+      "step": 410000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.247713586650857e-05,
+      "loss": 0.0616,
+      "step": 420000
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.058674536645412445,
+      "eval_runtime": 740.0142,
+      "eval_samples_per_second": 83.827,
+      "eval_steps_per_second": 20.958,
+      "step": 420000
+    }
+  ],
+  "max_steps": 2791490,
+  "num_train_epochs": 10,
+  "total_flos": 2.8075475590415155e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7a08ef5865769c06a81b1e3f66c88152210c1094a1f2e349653a6264646b2f
+size 3119