add MT model

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 10.0,
+    "eval_bleu": 11.0618,
+    "eval_gen_len": 38.682,
+    "eval_loss": 1.9924222230911255,
+    "eval_runtime": 889.7608,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1.686,
+    "eval_steps_per_second": 0.169,
+    "predict_bleu": 14.088,
+    "predict_gen_len": 37.862,
+    "predict_loss": 1.8863457441329956,
+    "predict_runtime": 931.3591,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 1.611,
+    "predict_steps_per_second": 0.161,
+    "train_loss": 2.376877005440848,
+    "train_runtime": 2452.745,
+    "train_samples": 6998,
+    "train_samples_per_second": 28.531,
+    "train_steps_per_second": 2.854
+}

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": 11.0618,
+    "eval_gen_len": 38.682,
+    "eval_loss": 1.9924222230911255,
+    "eval_runtime": 889.7608,
+    "eval_samples": 1500,
+    "eval_samples_per_second": 1.686,
+    "eval_steps_per_second": 0.169
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 14.088,
+    "predict_gen_len": 37.862,
+    "predict_loss": 1.8863457441329956,
+    "predict_runtime": 931.3591,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 1.611,
+    "predict_steps_per_second": 0.161
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c74c657d6670a7386f7133b7f1addc1facfb670613ea8ad901ca19ae1e22f4
+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": 2.376877005440848,
+    "train_runtime": 2452.745,
+    "train_samples": 6998,
+    "train_samples_per_second": 28.531,
+    "train_steps_per_second": 2.854
+}

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": 5.9139,
+      "step": 500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 2.8028,
+      "step": 1000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 3.928571428571429e-05,
+      "loss": 2.5129,
+      "step": 1500
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 2.3447,
+      "step": 2000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 3.2142857142857144e-05,
+      "loss": 2.2255,
+      "step": 2500
+    },
+    {
+      "epoch": 4.29,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 2.1201,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 2.0644,
+      "step": 3500
+    },
+    {
+      "epoch": 5.71,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 1.9872,
+      "step": 4000
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 1.9635,
+      "step": 4500
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 1.9039,
+      "step": 5000
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 1.0714285714285714e-05,
+      "loss": 1.8859,
+      "step": 5500
+    },
+    {
+      "epoch": 8.57,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 1.8624,
+      "step": 6000
+    },
+    {
+      "epoch": 9.29,
+      "learning_rate": 3.5714285714285714e-06,
+      "loss": 1.8489,
+      "step": 6500
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 1.8401,
+      "step": 7000
+    },
+    {
+      "epoch": 10.0,
+      "step": 7000,
+      "total_flos": 2.852352859705344e+16,
+      "train_loss": 2.376877005440848,
+      "train_runtime": 2452.745,
+      "train_samples_per_second": 28.531,
+      "train_steps_per_second": 2.854
+    }
+  ],
+  "max_steps": 7000,
+  "num_train_epochs": 10,
+  "total_flos": 2.852352859705344e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c9eb4598701ed300f38f5287b66460bf0397fd79a0f043effbdf77ccec2be1
+size 2927