Training in progress, step 20000

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1536,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_input_size": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.2,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "min_length": 1024,
+  "model_type": "t5",
+  "num_decoder_layers": 10,
+  "num_heads": 12,
+  "num_layers": 10,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 1024
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f5a3db8b9d4d68e7c207d88d4549e289e05036015c0debad44a4cb46b54e93
+size 475241897

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5c27846b17bf0edd60977e0796de118903abaadf8d79f83ad546f2f0500235
+size 3451