Upload folder using huggingface_hub

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "checkpoints_qg_ae/model_msisjo/epoch_10",
+  "_name_or_path": "checkpoints_qg_ae/model_onvcyh/epoch_2",
   "add_prefix": true,
   "architectures": [
     "MT5ForConditionalGeneration"
   ],
-  "d_ff": 1024,
+  "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -17,9 +17,10 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "mt5",
-  "num_decoder_layers": 8,
-  "num_heads": 6,
-  "num_layers": 8,
+  "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,

eval/metric.first.answer.context.question.NoaCA14_base_quac_es.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.043064322604203585, "Bleu_2": 0.03208874001887557, "Bleu_3": 0.027278203301308576, "Bleu_4": 0.02371109598812169}, "test": {"Bleu_1": 0.04605895448849715, "Bleu_2": 0.03535081604640602, "Bleu_3": 0.030419185987962664, "Bleu_4": 0.02658593730190876}}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e8a6151ef6cbdf84423ce143514ac8731c1a348d4522a5802a442bd5752e56
-size 1200727429
+oid sha256:061e08c7b67c7416db99c3722f19747db565a5f3f6623686b2ea851a06ad8365
+size 2329634869

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0d2a9b1e74c78117caaf355264121c1391aef3c28f883e132e87710411e3cf
-size 16315302
+oid sha256:6e6f102e00fd7c0bc8dbaf509bd484bf6a31063f5b496740f90b989b9baa1d1b
+size 16315565

tokenizer_config.json

@@ -3,10 +3,10 @@
   "eos_token": "</s>",
   "extra_ids": 0,
   "model_max_length": 1000000000000000019884624838656,
-  "name_or_path": "checkpoints_qg_ae/model_msisjo/epoch_10",
+  "name_or_path": "checkpoints_qg_ae/model_onvcyh/epoch_2",
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
-  "special_tokens_map_file": "/home/asahi/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

trainer_config.json

@@ -1 +1 @@
-{"dataset_path": "NoaCA14/small_quac_es", "dataset_name": "default", "input_types": ["context", "context"], "output_types": ["question", "answer"], "prefix_types": ["qg", "ae"], "model": "lmqg/mt5-small-esquad-qg-ae", "max_length": 512, "max_length_output": 32, "epoch": 11, "batch": 64, "lr": 0.0001, "fp16": false, "random_seed": 42, "gradient_accumulation_steps": 4, "label_smoothing": 0.15}
+{"dataset_path": "NoaCA14/base_quac_es", "dataset_name": "default", "input_types": ["context", "context"], "output_types": ["question", "answer"], "prefix_types": ["qg", "ae"], "model": "lmqg/mt5-base-esquad-qg-ae", "max_length": 512, "max_length_output": 32, "epoch": 5, "batch": 24, "lr": 0.0001, "fp16": false, "random_seed": 42, "gradient_accumulation_steps": 4, "label_smoothing": 0.15}