New model

added_tokens.json

@@ -0,0 +1 @@
+{"<sep>": 30000, "<hl>": 30001}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "muchad/idt5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.4.2",
+  "use_cache": true,
+  "vocab_size": 30002
+}

eval_results.txt

@@ -0,0 +1,8 @@
+epoch = 10.0
+eval_loss = 1.2842957973480225
+eval_mem_cpu_alloc_delta = 79820
+eval_mem_cpu_peaked_delta = 362963
+eval_mem_gpu_alloc_delta = 0
+eval_mem_gpu_peaked_delta = 1826335232
+eval_runtime = 95.4142
+eval_samples_per_second = 166.443

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer", "special_tokens_map_file": "/root/.cache/huggingface/transformers/d406518605bcf18fb54c18414fbd0c6ff59829690fa5429a50bf6e3854258ce9.294ebaa4cd17bb284635004c92d2c4d522ec488c828dcce0c2471b6f28e3fe82", "tokenizer_file": null, "name_or_path": "t5_qg_tokenizer"}