add MT model

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 16.0317,
+    "eval_gen_len": 81.014,
+    "eval_loss": 0.6556891798973083,
+    "eval_runtime": 667.421,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2.247,
+    "eval_steps_per_second": 0.225,
+    "predict_bleu": 20.775,
+    "predict_gen_len": 78.1973,
+    "predict_loss": 0.5993978381156921,
+    "predict_runtime": 656.3965,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 2.285,
+    "predict_steps_per_second": 0.229,
+    "train_loss": 0.6619879237583706,
+    "train_runtime": 5416.7606,
+    "train_samples": 6998,
+    "train_samples_per_second": 12.919,
+    "train_steps_per_second": 1.292
+}

config.json

@@ -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": "4.12.0",
+  "use_cache": true,
+  "vocab_size": 384
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 16.0317,
+    "eval_gen_len": 81.014,
+    "eval_loss": 0.6556891798973083,
+    "eval_runtime": 667.421,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 2.247,
+    "eval_steps_per_second": 0.225
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 20.775,
+    "predict_gen_len": 78.1973,
+    "predict_loss": 0.5993978381156921,
+    "predict_runtime": 656.3965,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 2.285,
+    "predict_steps_per_second": 0.229
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79de92673af77e59ee1478f7347d755965d1a2f1a16f53ccda16cdd6616f7307
+size 2326733259

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": "/nethome/didelani/.cache/huggingface/transformers/f22e687c418a9ed3e651ca340d6a5880bbb312bc24bbe893f5cd47288891b89d.063895353d5ef9e19a25220cb616c43abc5e84a2f11b1ffb71c29e097572a109", "tokenizer_file": null, "name_or_path": "google/byt5-base", "tokenizer_class": "ByT5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.6619879237583706,
+    "train_runtime": 5416.7606,
+    "train_samples": 6998,
+    "train_samples_per_second": 12.919,
+    "train_steps_per_second": 1.292
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.642857142857143e-05,
+      "loss": 1.1411,
+      "step": 500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 0.8444,
+      "step": 1000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 0.7621,
+      "step": 1500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 0.7039,
+      "step": 2000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 0.6671,
+      "step": 2500
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 0.6399,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.6155,
+      "step": 3500
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.5895,
+      "step": 4000
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 0.5783,
+      "step": 4500
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 0.561,
+      "step": 5000
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 0.5527,
+      "step": 5500
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.5425,
+      "step": 6000
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 0.5391,
+      "step": 6500
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 0.5306,
+      "step": 7000
+    },
+    {
+      "epoch": 10.0,
+      "step": 7000,
+      "total_flos": 9.528930633616589e+16,
+      "train_loss": 0.6619879237583706,
+      "train_runtime": 5416.7606,
+      "train_samples_per_second": 12.919,
+      "train_steps_per_second": 1.292
+    }
+  ],
+  "max_steps": 7000,
+  "num_train_epochs": 10,
+  "total_flos": 9.528930633616589e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0c03714a2a9fbcad8ece2d6ad74017375edd44dea3750ff23e8eadfccc5644
+size 2927