Initial commit

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "google/byt5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3584,
+  "d_kv": 64,
+  "d_model": 1472,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 4,
+  "num_heads": 6,
+  "num_layers": 12,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "use_cache": true,
+  "vocab_size": 384
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6441062b402882ccf653f62d19a51da7fd429e2725e8fa76768d0b04fa773b06
+size 1198608045

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c367c4e27d4b5ab81258c499bfceffee4b73e0e0a98bbef45134f805273c6f5
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add80cc6f6ce2beee63291761d515aaf1d129a2f5eebc131dd26448d741ee929
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "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>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "extra_ids": 125, "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>", "<extra_id_100>", "<extra_id_101>", "<extra_id_102>", "<extra_id_103>", "<extra_id_104>", "<extra_id_105>", "<extra_id_106>", "<extra_id_107>", "<extra_id_108>", "<extra_id_109>", "<extra_id_110>", "<extra_id_111>", "<extra_id_112>", "<extra_id_113>", "<extra_id_114>", "<extra_id_115>", "<extra_id_116>", "<extra_id_117>", "<extra_id_118>", "<extra_id_119>", "<extra_id_120>", "<extra_id_121>", "<extra_id_122>", "<extra_id_123>", "<extra_id_124>"], "special_tokens_map_file": "/root/.cache/huggingface/transformers/3715c3de7f5eda8f5c9274c55ea8e8632fe6e4cdfdf8e9066ae173b956cd9b80.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "name_or_path": "google/byt5-small", "tokenizer_class": "ByT5Tokenizer"}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.362265145153057,
+  "global_step": 22000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.958833506232608e-05,
+      "loss": 0.3018,
+      "step": 500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9176670124652144e-05,
+      "loss": 0.1198,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.876500518697822e-05,
+      "loss": 0.1041,
+      "step": 1500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.835334024930429e-05,
+      "loss": 0.0934,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.794167531163036e-05,
+      "loss": 0.0893,
+      "step": 2500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.753001037395643e-05,
+      "loss": 0.0827,
+      "step": 3000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.71183454362825e-05,
+      "loss": 0.0794,
+      "step": 3500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.670668049860858e-05,
+      "loss": 0.0773,
+      "step": 4000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6295015560934644e-05,
+      "loss": 0.0761,
+      "step": 4500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.588335062326072e-05,
+      "loss": 0.0719,
+      "step": 5000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.547168568558679e-05,
+      "loss": 0.0702,
+      "step": 5500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.506002074791286e-05,
+      "loss": 0.0681,
+      "step": 6000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.4648355810238935e-05,
+      "loss": 0.0684,
+      "step": 6500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.423669087256501e-05,
+      "loss": 0.0651,
+      "step": 7000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.382502593489107e-05,
+      "loss": 0.0642,
+      "step": 7500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.3413360997217144e-05,
+      "loss": 0.0651,
+      "step": 8000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.300169605954322e-05,
+      "loss": 0.064,
+      "step": 8500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.2590031121869286e-05,
+      "loss": 0.061,
+      "step": 9000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.217836618419536e-05,
+      "loss": 0.0623,
+      "step": 9500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.1766701246521435e-05,
+      "loss": 0.0589,
+      "step": 10000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.13550363088475e-05,
+      "loss": 0.058,
+      "step": 10500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.094337137117358e-05,
+      "loss": 0.0581,
+      "step": 11000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.053170643349965e-05,
+      "loss": 0.0574,
+      "step": 11500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.012004149582572e-05,
+      "loss": 0.0582,
+      "step": 12000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.9708376558151786e-05,
+      "loss": 0.0561,
+      "step": 12500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.929671162047786e-05,
+      "loss": 0.0557,
+      "step": 13000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.8885046682803935e-05,
+      "loss": 0.0549,
+      "step": 13500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.847338174513e-05,
+      "loss": 0.0556,
+      "step": 14000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.806171680745608e-05,
+      "loss": 0.0535,
+      "step": 14500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.765005186978215e-05,
+      "loss": 0.0539,
+      "step": 15000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.723838693210822e-05,
+      "loss": 0.0544,
+      "step": 15500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.682672199443429e-05,
+      "loss": 0.0532,
+      "step": 16000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.641505705676037e-05,
+      "loss": 0.0541,
+      "step": 16500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.6003392119086435e-05,
+      "loss": 0.0523,
+      "step": 17000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.55917271814125e-05,
+      "loss": 0.0518,
+      "step": 17500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.518006224373858e-05,
+      "loss": 0.0518,
+      "step": 18000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.476839730606465e-05,
+      "loss": 0.0508,
+      "step": 18500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.435673236839072e-05,
+      "loss": 0.0522,
+      "step": 19000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.3945067430716793e-05,
+      "loss": 0.0518,
+      "step": 19500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.353340249304287e-05,
+      "loss": 0.0506,
+      "step": 20000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.3121737555368935e-05,
+      "loss": 0.0503,
+      "step": 20500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.271007261769501e-05,
+      "loss": 0.0502,
+      "step": 21000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.2298407680021084e-05,
+      "loss": 0.0497,
+      "step": 21500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.1886742742347145e-05,
+      "loss": 0.051,
+      "step": 22000
+    }
+  ],
+  "max_steps": 60729,
+  "num_train_epochs": 1,
+  "total_flos": 8.854507190040883e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8dc7723ae38f891836e2f95ea12cab48f86df73a5295410769aebd18371dc6
+size 3183