Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "K024/mt5-zh-ja-en-trimmed",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "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": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 85292
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9a901afd2f51585dafadc0401f8147f80b99410e1930f1e116f8056fcc0e977
+size 1317042253

runs/Apr17_10-01-17_c40057eefc9b/1650189752.160124/events.out.tfevents.1650189752.c40057eefc9b.60.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a868e54dedb7e581e4af00cfd4e29f37859ad6170e5240f00f97423cc44d07b7
+size 5135

runs/Apr17_10-01-17_c40057eefc9b/events.out.tfevents.1650189739.c40057eefc9b.60.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13841a3aea07cf77e7fcb46c36d55e89ae862da52d0f765d33fc6f85f06e5c7d
+size 294

special_tokens_map.json

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

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8557a50825d59b58c004cb4dc566ff98926d864c51fd153fb32cf5c5f19643e
+size 1511055

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": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "K024/mt5-zh-ja-en-trimmed", "return_tensors": "tf", "tokenizer_class": "T5Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089e109a03940b3ef49f4322933ab0fb862a8cbc9669edb626bb549abd6b2187
+size 3247