versae commited on Nov 12, 2021

Commit

a5ffafd

•

1 Parent(s): 0dafe37

Training in progress, step 10000

Browse files

Files changed (17) hide show

.gitignore +1 -0
config.json +30 -0
last-checkpoint/config.json +30 -0
last-checkpoint/optimizer.pt +3 -0
last-checkpoint/pytorch_model.bin +3 -0
last-checkpoint/rng_state.pth +3 -0
last-checkpoint/scheduler.pt +3 -0
last-checkpoint/special_tokens_map.json +1 -0
last-checkpoint/tokenizer_config.json +1 -0
last-checkpoint/trainer_state.json +146 -0
last-checkpoint/training_args.bin +3 -0
pytorch_model.bin +3 -0
runs/Nov12_06-59-12_5003b978b404/1636700372.90083/events.out.tfevents.1636700372.5003b978b404.83.1 +3 -0
runs/Nov12_06-59-12_5003b978b404/events.out.tfevents.1636700372.5003b978b404.83.0 +3 -0
special_tokens_map.json +1 -0
tokenizer_config.json +1 -0
training_args.bin +3 -0

.gitignore ADDED Viewed

	@@ -0,0 +1 @@


1	+ checkpoint-*/

config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "google/byt5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3968,
+  "d_kv": 64,
+  "d_model": 1536,
+  "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": 6,
+  "num_heads": 12,
+  "num_layers": 18,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "use_cache": true,
+  "vocab_size": 384
+}

last-checkpoint/config.json ADDED Viewed

	@@ -0,0 +1,30 @@

+{
+  "_name_or_path": "google/byt5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3968,
+  "d_kv": 64,
+  "d_model": 1536,
+  "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": 6,
+  "num_heads": 12,
+  "num_layers": 18,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "use_cache": true,
+  "vocab_size": 384
+}

last-checkpoint/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f9755548d468cd2ef6bd285545d9da76255c88543c974b7b49565c3117c7a0c6
+size 4653374485

last-checkpoint/pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:04d1fdfcb987463f91233e4edf99810eb23b1e366f79cb16cb3e8e69c41a262a
+size 2326726857

last-checkpoint/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:04ee215f1802693b03e9883486a14cc58891d61adafa164f4c1dc85b24c13236
+size 14503

last-checkpoint/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ea4719bf4579360c2d2e9bd88999d25d3a9ef68a96f71f474e58bf3471a5127
+size 623

last-checkpoint/special_tokens_map.json ADDED Viewed

	@@ -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>"]}

last-checkpoint/tokenizer_config.json ADDED Viewed

	@@ -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/f22e687c418a9ed3e651ca340d6a5880bbb312bc24bbe893f5cd47288891b89d.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "tokenizer_file": null, "name_or_path": "google/byt5-base", "tokenizer_class": "ByT5Tokenizer"}

last-checkpoint/trainer_state.json ADDED Viewed

	@@ -0,0 +1,146 @@

+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.35454706612302783,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.940908822312829e-05,
+      "loss": 0.5489,
+      "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.881817644625659e-05,
+      "loss": 0.2319,
+      "step": 1000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.822726466938487e-05,
+      "loss": 0.2106,
+      "step": 1500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.763635289251316e-05,
+      "loss": 0.1957,
+      "step": 2000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.704544111564144e-05,
+      "loss": 0.1787,
+      "step": 2500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.645452933876972e-05,
+      "loss": 0.1735,
+      "step": 3000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.586361756189801e-05,
+      "loss": 0.1711,
+      "step": 3500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.52727057850263e-05,
+      "loss": 0.1714,
+      "step": 4000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.468179400815459e-05,
+      "loss": 0.166,
+      "step": 4500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.409088223128288e-05,
+      "loss": 0.1728,
+      "step": 5000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 9.349997045441116e-05,
+      "loss": 0.1572,
+      "step": 5500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.290905867753945e-05,
+      "loss": 0.1498,
+      "step": 6000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.231814690066773e-05,
+      "loss": 0.1613,
+      "step": 6500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.172723512379601e-05,
+      "loss": 0.1543,
+      "step": 7000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.113632334692431e-05,
+      "loss": 0.1553,
+      "step": 7500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.05454115700526e-05,
+      "loss": 0.1695,
+      "step": 8000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 8.995449979318088e-05,
+      "loss": 0.1461,
+      "step": 8500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.936358801630918e-05,
+      "loss": 0.1501,
+      "step": 9000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 8.877267623943746e-05,
+      "loss": 0.146,
+      "step": 9500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 8.818176446256575e-05,
+      "loss": 0.1474,
+      "step": 10000
+    },
+    {
+      "epoch": 0.35,
+      "eval_bleu": 42.8789,
+      "eval_gen_len": 18.4441,
+      "eval_loss": 0.13595277070999146,
+      "eval_runtime": 952.992,
+      "eval_samples_per_second": 14.798,
+      "eval_steps_per_second": 3.7,
+      "step": 10000
+    }
+  ],
+  "max_steps": 84615,
+  "num_train_epochs": 3,
+  "total_flos": 8756298127835136.0,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1b0ea10cc485d3fab3898639302461759fded8ef8a5dee95611b60690ef49e
+size 2991

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:04d1fdfcb987463f91233e4edf99810eb23b1e366f79cb16cb3e8e69c41a262a
+size 2326726857

runs/Nov12_06-59-12_5003b978b404/1636700372.90083/events.out.tfevents.1636700372.5003b978b404.83.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:17f1ccce90e67746d11e71896e57150797ea1bd965a8f663ce203bf7ebf6d9d8
+size 4805

runs/Nov12_06-59-12_5003b978b404/events.out.tfevents.1636700372.5003b978b404.83.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:84417c91a91e3948c6cc57890902a6c31bf07031ceaeb21c69b2a073a7a48754
+size 6914

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1 @@

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1 @@

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1b0ea10cc485d3fab3898639302461759fded8ef8a5dee95611b60690ef49e
+size 2991