Add first iteration (45k)

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/t5-v1_1-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "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 sha256:1e73df4acf596669fc8bbc5025e78d667d77045e11a809f1f2e7f6638f868a82
+size 990383053

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ebddd8d23b9d2745ef5ee1df068df17974bd5cfbdcfb208e5eeb559e7e4a61
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:863bc83c7e2bc3df963dc3b7cd76697e4379b39112e53c3aacbeab9768904dc4
+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": "google/t5-v1_1-base", "special_tokens_map_file": "/root/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08060226008737285,
+  "global_step": 45000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.955220966618126e-05,
+      "loss": 2.3776,
+      "step": 5000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.910441933236253e-05,
+      "loss": 0.2443,
+      "step": 10000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.865662899854379e-05,
+      "loss": 0.2738,
+      "step": 15000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8208838664725045e-05,
+      "loss": 0.1848,
+      "step": 20000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.776104833090631e-05,
+      "loss": 0.1507,
+      "step": 25000
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 0.11242648959159851,
+      "eval_runtime": 3430.1226,
+      "eval_samples_per_second": 18.085,
+      "eval_steps_per_second": 9.043,
+      "step": 25000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.7313257997087574e-05,
+      "loss": 0.1358,
+      "step": 30000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.6865467663268834e-05,
+      "loss": 0.1323,
+      "step": 35000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.64176773294501e-05,
+      "loss": 0.1193,
+      "step": 40000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.596988699563136e-05,
+      "loss": 0.1129,
+      "step": 45000
+    }
+  ],
+  "max_steps": 558297,
+  "num_train_epochs": 1,
+  "total_flos": 4.439552157522432e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d88579f56375596872ffe40e72d85e293c40c8fa8ed74b8701b8ecc7002ec505
+size 3119