add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 3.0539,
+    "predict_gen_len": 115.8823,
+    "predict_loss": 3.0736546516418457,
+    "predict_runtime": 2037.5706,
+    "predict_samples": 1563,
+    "predict_samples_per_second": 0.767,
+    "predict_steps_per_second": 0.077,
+    "train_loss": 3.6552913421480526,
+    "train_runtime": 590.5954,
+    "train_samples": 2026,
+    "train_samples_per_second": 34.304,
+    "train_steps_per_second": 3.437
+}

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": 3.0539,
+    "predict_gen_len": 115.8823,
+    "predict_loss": 3.0736546516418457,
+    "predict_runtime": 2037.5706,
+    "predict_samples": 1563,
+    "predict_samples_per_second": 0.767,
+    "predict_steps_per_second": 0.077
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2ce3d2a4fbf8d763e2f97fb8bf80951d8cd9b8dbe0c50b6d79c02a7e477b30
+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": 3.6552913421480526,
+    "train_runtime": 590.5954,
+    "train_samples": 2026,
+    "train_samples_per_second": 34.304,
+    "train_steps_per_second": 3.437
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 2030,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.46,
+      "learning_rate": 3.768472906403941e-05,
+      "loss": 4.5139,
+      "step": 500
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 2.5369458128078822e-05,
+      "loss": 3.5618,
+      "step": 1000
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 1.3054187192118228e-05,
+      "loss": 3.3347,
+      "step": 1500
+    },
+    {
+      "epoch": 9.85,
+      "learning_rate": 7.389162561576355e-07,
+      "loss": 3.2368,
+      "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "step": 2030,
+      "total_flos": 6865519834275840.0,
+      "train_loss": 3.6552913421480526,
+      "train_runtime": 590.5954,
+      "train_samples_per_second": 34.304,
+      "train_steps_per_second": 3.437
+    }
+  ],
+  "max_steps": 2030,
+  "num_train_epochs": 10,
+  "total_flos": 6865519834275840.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86392a7b499401f70032e3e5650d458b01e60c157e51e6efe089bbf00ca61682
+size 2799