add MT model

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 4.6799,
+    "eval_gen_len": 90.7953,
+    "eval_loss": 2.772725820541382,
+    "eval_runtime": 1880.257,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 0.798,
+    "eval_steps_per_second": 0.08,
+    "predict_bleu": 3.9024,
+    "predict_gen_len": 92.5453,
+    "predict_loss": 2.8333799839019775,
+    "predict_runtime": 1900.5199,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 0.789,
+    "predict_steps_per_second": 0.079,
+    "train_loss": 3.576076851639093,
+    "train_runtime": 1207.6752,
+    "train_samples": 4075,
+    "train_samples_per_second": 33.743,
+    "train_steps_per_second": 3.378
+}

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
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 4.6799,
+    "eval_gen_len": 90.7953,
+    "eval_loss": 2.772725820541382,
+    "eval_runtime": 1880.257,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 0.798,
+    "eval_steps_per_second": 0.08
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 3.9024,
+    "predict_gen_len": 92.5453,
+    "predict_loss": 2.8333799839019775,
+    "predict_runtime": 1900.5199,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 0.789,
+    "predict_steps_per_second": 0.079
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dcb6ef98a6d91b1e469d590b0a63a1c491864a6d863e683e73d69c12269cc1c
+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": 3.576076851639093,
+    "train_runtime": 1207.6752,
+    "train_samples": 4075,
+    "train_samples_per_second": 33.743,
+    "train_steps_per_second": 3.378
+}

trainer_state.json

@@ -0,0 +1,73 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 4080,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.23,
+      "learning_rate": 4.387254901960784e-05,
+      "loss": 6.7397,
+      "step": 500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 3.774509803921569e-05,
+      "loss": 3.7513,
+      "step": 1000
+    },
+    {
+      "epoch": 3.68,
+      "learning_rate": 3.161764705882353e-05,
+      "loss": 3.3683,
+      "step": 1500
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 2.5490196078431373e-05,
+      "loss": 3.1707,
+      "step": 2000
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 1.936274509803922e-05,
+      "loss": 3.0248,
+      "step": 2500
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 1.323529411764706e-05,
+      "loss": 2.9444,
+      "step": 3000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 7.107843137254902e-06,
+      "loss": 2.8809,
+      "step": 3500
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 2.8489,
+      "step": 4000
+    },
+    {
+      "epoch": 10.0,
+      "step": 4080,
+      "total_flos": 1.29736772522496e+16,
+      "train_loss": 3.576076851639093,
+      "train_runtime": 1207.6752,
+      "train_samples_per_second": 33.743,
+      "train_steps_per_second": 3.378
+    }
+  ],
+  "max_steps": 4080,
+  "num_train_epochs": 10,
+  "total_flos": 1.29736772522496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0180e1d3b8c4d474f11a74cb25c5297bf53cbe05e70ada21cf68ff32d89cfe
+size 2927