Training in progress, step 500

.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": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:605f5f96ef8e77bafddfb6d3489d4897d55b28c13babb833965f52109d7d490e
+size 2329702453

runs/Apr30_08-44-37_b55a7cad6239/1682844330.9406428/events.out.tfevents.1682844330.b55a7cad6239.5156.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23e48bf7d716befbbcc7d095b05afb6bc4a349b5e5edb23fbfb060d86565ead8
+size 6328

runs/Apr30_08-44-37_b55a7cad6239/events.out.tfevents.1682844330.b55a7cad6239.5156.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56961620a2e20b4c742bd934cba48384215541e42e29973c9959b1229d6c60c9
+size 4554

runs/Apr30_08-48-44_b55a7cad6239/1682844708.8155892/events.out.tfevents.1682844708.b55a7cad6239.5156.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7317a977ddc76fda1aad981f0899e12d6e9e9c3e675fc49f314131050ee1ab39
+size 6328

runs/Apr30_08-48-44_b55a7cad6239/events.out.tfevents.1682844708.b55a7cad6239.5156.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e099f6c69416eed1a7d3e0475016e24b5d04281e818f3d7023b57ae65086dc
+size 4184

runs/Apr30_08-54-54_b55a7cad6239/1682845172.1819208/events.out.tfevents.1682845172.b55a7cad6239.11803.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c91f6754b3e9d715a653a10f48c6bf868a241ada72fd30d472cea7951f5b94
+size 6328

runs/Apr30_08-54-54_b55a7cad6239/events.out.tfevents.1682845172.b55a7cad6239.11803.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d5ff7f8fa99e81b7ae82268aded3ef0b490061f411ca42538502fcb005bb0a
+size 4554

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_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 900,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a705543d5a4e1dc768d2de9d09fe46797ca1d9a7e95b3a9f68421e5e39670aca
+size 3835