Training in progress, step 10000

.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

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "csebuetnlp/mT5_multilingual_XLSum",
+  "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,
+  "length_penalty": 0.6,
+  "max_length": 84,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 4,
+  "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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7bf4b7713f44d5ba68358df844f56962677e671eeed4056d1af6b3a220e479
+size 2329702453

runs/Jul07_18-04-27_64b4b5eb6458/events.out.tfevents.1688753083.64b4b5eb6458.28.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563f624e87f3d5c31a9e9d90f3ae849b3b45468e743b097632d01881cfaacf2f
+size 4387

runs/Jul07_18-05-01_64b4b5eb6458/events.out.tfevents.1688753109.64b4b5eb6458.28.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11045d7c0baeaf6e47d882af1744baeac82d9bb0af7c7aadfb4a59224f91b3f
+size 5778

runs/Jul07_18-12-54_64b4b5eb6458/events.out.tfevents.1688753591.64b4b5eb6458.249.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2244576c2a7ae82ec7037394776dd52de63252786ea49e8ef1aa8b7557d1d36a
+size 8280

runs/Jul07_18-15-06_64b4b5eb6458/events.out.tfevents.1688753715.64b4b5eb6458.417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fbd18597dbfc828eacbf612f560db6e434fb243ff43e58794aa1f7c3ab6eafd
+size 4184

runs/Jul07_18-16-38_64b4b5eb6458/events.out.tfevents.1688753804.64b4b5eb6458.417.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c06133ab1b62ba901a2b048ea0f391dfe41f30b4ecd86454267fd660c1da4efb
+size 4184

runs/Jul07_18-17-36_64b4b5eb6458/events.out.tfevents.1688753862.64b4b5eb6458.604.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4c3711a9a69fbe35a16407a699f6e1171711e2bf5265114628fc73f9719473
+size 4184

runs/Jul07_18-19-43_64b4b5eb6458/events.out.tfevents.1688753990.64b4b5eb6458.749.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18e1d3887c1cfbf57f02a89906ad940f1ca8fb5e880ac4a8a9d2e61e0625e50
+size 8001

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "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 sha256:6adcc635a67d3fab478a5d1dc33ec9687e09dc48aecfc16ebecbf3f9ebf6eaa4
+size 16330467

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8222836cec06c28a59dc38d3883d14d7bb1cf58562aee925fd235252ef55d16
+size 4091