Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e2bb73208753a0f235c7105cf62b6e803fd9c3d7ee7e955b8aa4c19b6dcc26
+size 1202183429

runs/Aug14_07-15-39_d949d3bf39bd/events.out.tfevents.1691998767.d949d3bf39bd.1211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84856d5d02244858adbd27e4c9c04b9507a10f680739bdcd125acef5cd0425a9
+size 88

runs/Aug14_07-43-06_d949d3bf39bd/events.out.tfevents.1692000066.d949d3bf39bd.8750.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6f5e55af4cf59df3de37143d0777ffb226e22b6409b19fe709e97741d4ac32f
+size 7729

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1925eebee5c3c92bd72fb3b1eb033a6e633167e2eac716d365ce1185618159b3
+size 3963