add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 11.8792,
+    "predict_gen_len": 35.6226,
+    "predict_loss": 2.598799467086792,
+    "predict_runtime": 972.3337,
+    "predict_samples": 1558,
+    "predict_samples_per_second": 1.602,
+    "predict_steps_per_second": 0.16,
+    "train_loss": 2.876378885140096,
+    "train_runtime": 2243.2035,
+    "train_samples": 6644,
+    "train_samples_per_second": 29.618,
+    "train_steps_per_second": 2.965
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0",
+  "use_cache": true,
+  "vocab_size": 250100
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 11.8792,
+    "predict_gen_len": 35.6226,
+    "predict_loss": 2.598799467086792,
+    "predict_runtime": 972.3337,
+    "predict_samples": 1558,
+    "predict_samples_per_second": 1.602,
+    "predict_steps_per_second": 0.16
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd43f96ab88a533a9b79f010a055a3e08ea557a82db59946c69b584bd3a4fb0
+size 2329633625

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 2.876378885140096,
+    "train_runtime": 2243.2035,
+    "train_samples": 6644,
+    "train_samples_per_second": 29.618,
+    "train_steps_per_second": 2.965
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 6650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.62406015037594e-05,
+      "loss": 6.2225,
+      "step": 500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.24812030075188e-05,
+      "loss": 3.3431,
+      "step": 1000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.87218045112782e-05,
+      "loss": 3.0415,
+      "step": 1500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 3.49624060150376e-05,
+      "loss": 2.8598,
+      "step": 2000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 3.120300751879699e-05,
+      "loss": 2.7177,
+      "step": 2500
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 2.7443609022556393e-05,
+      "loss": 2.6127,
+      "step": 3000
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 2.5436,
+      "step": 3500
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 1.9924812030075188e-05,
+      "loss": 2.4844,
+      "step": 4000
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 1.6165413533834585e-05,
+      "loss": 2.4068,
+      "step": 4500
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 1.2406015037593984e-05,
+      "loss": 2.3725,
+      "step": 5000
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 8.646616541353383e-06,
+      "loss": 2.3542,
+      "step": 5500
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 4.887218045112782e-06,
+      "loss": 2.3098,
+      "step": 6000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 1.1278195488721805e-06,
+      "loss": 2.2902,
+      "step": 6500
+    },
+    {
+      "epoch": 10.0,
+      "step": 6650,
+      "total_flos": 3.38537295309312e+16,
+      "train_loss": 2.876378885140096,
+      "train_runtime": 2243.2035,
+      "train_samples_per_second": 29.618,
+      "train_steps_per_second": 2.965
+    }
+  ],
+  "max_steps": 6650,
+  "num_train_epochs": 10,
+  "total_flos": 3.38537295309312e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b0982d852e7d4be3591a213800231cbcc286a7f3cea56a2782c5126dafbb114
+size 2927