Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<hl>": 250100
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "checkpoints_ae/model_ndjknu/epoch_2",
+  "add_prefix": false,
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": 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_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 250101
+}

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.14958763003550635, "Bleu_2": 0.0776954384111485, "Bleu_3": 0.05541388979497489, "Bleu_4": 0.04431563624245334}, "test": {"Bleu_1": 0.1462125614072153, "Bleu_2": 0.07330449017259459, "Bleu_3": 0.050916003086275176, "Bleu_4": 0.04002292051787572}}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eaa849f46a0c448edbb5b570e857bd57f18ee67077f36fb07af5a83527666c7
+size 2329634869

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "additional_special_tokens": [
+    "<hl>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0d2a9b1e74c78117caaf355264121c1391aef3c28f883e132e87710411e3cf
+size 16315302

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "checkpoints_ae/model_ndjknu/epoch_2",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_config.json

@@ -0,0 +1 @@
+{"dataset_path": "NoaCA14/base_quac_es", "dataset_name": "default", "input_types": ["context"], "output_types": ["answer"], "prefix_types": "qg", "model": "lmqg/mt5-base-esquad-ae", "max_length": 512, "max_length_output": 32, "epoch": 9, "batch": 16, "lr": 0.0001, "fp16": false, "random_seed": 42, "gradient_accumulation_steps": 4, "label_smoothing": 0.15}