add MT model

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": "4.10.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c3af0175948db001de55f9ffbf25a07cb81d9ffb6efada266427459a9ed3f2a
+size 3866395883

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"}

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": 0.5605388283729553,
+  "best_model_checkpoint": "../results/africanlp/mt5base/checkpoint-30000",
+  "epoch": 1.1952131689210177,
+  "global_step": 30000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.6535710692405701,
+      "eval_runtime": 453.8571,
+      "eval_samples_per_second": 418.634,
+      "eval_steps_per_second": 13.083,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.5883721113204956,
+      "eval_runtime": 452.6987,
+      "eval_samples_per_second": 419.705,
+      "eval_steps_per_second": 13.117,
+      "step": 20000
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 0.5605388283729553,
+      "eval_runtime": 448.8636,
+      "eval_samples_per_second": 423.291,
+      "eval_steps_per_second": 13.229,
+      "step": 30000
+    }
+  ],
+  "max_steps": 75300,
+  "num_train_epochs": 3,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1806ca07dd165357e3474dd28ed3009cf6297752f17879105dfd4a6d11655e98
+size 2799