add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 2.5067,
+    "predict_gen_len": 78.8958,
+    "predict_loss": 2.534496784210205,
+    "predict_runtime": 2061.8326,
+    "predict_samples": 1574,
+    "predict_samples_per_second": 0.763,
+    "predict_steps_per_second": 0.077,
+    "train_loss": 2.8751321984170306,
+    "train_runtime": 969.1613,
+    "train_samples": 2287,
+    "train_samples_per_second": 23.598,
+    "train_steps_per_second": 2.363
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "afriT5_1",
+  "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": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 250100
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 2.5067,
+    "predict_gen_len": 78.8958,
+    "predict_loss": 2.534496784210205,
+    "predict_runtime": 2061.8326,
+    "predict_samples": 1574,
+    "predict_samples_per_second": 0.763,
+    "predict_steps_per_second": 0.077
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3b5eab5d3b20e47fa4d4cd20941d98ec0f2b8777259cb04bd87b431d26d00b
+size 2329626573

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": "afriT5_1", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 2.8751321984170306,
+    "train_runtime": 969.1613,
+    "train_samples": 2287,
+    "train_samples_per_second": 23.598,
+    "train_steps_per_second": 2.363
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 2290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.9082969432314415e-05,
+      "loss": 3.452,
+      "step": 500
+    },
+    {
+      "epoch": 4.37,
+      "learning_rate": 2.816593886462882e-05,
+      "loss": 2.8827,
+      "step": 1000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 1.7248908296943234e-05,
+      "loss": 2.7159,
+      "step": 1500
+    },
+    {
+      "epoch": 8.73,
+      "learning_rate": 6.3318777292576415e-06,
+      "loss": 2.6167,
+      "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "step": 2290,
+      "total_flos": 1.366948696467456e+16,
+      "train_loss": 2.8751321984170306,
+      "train_runtime": 969.1613,
+      "train_samples_per_second": 23.598,
+      "train_steps_per_second": 2.363
+    }
+  ],
+  "max_steps": 2290,
+  "num_train_epochs": 10,
+  "total_flos": 1.366948696467456e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd067096c0b28d5bbd134b62364a667173bcbfcc3926fffe8172dbe42eb2d19
+size 2799