Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google/long-t5-local-base",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "local",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "local_radius": 127,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

logs/1684414365.7296805/events.out.tfevents.1684414365.be219b0c48b0.31.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5e4d600bf6088541c544f3b422def3a3c39912b1118e7db5549c40b47406b96
+size 6117

logs/events.out.tfevents.1684414365.be219b0c48b0.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b24bfaa9cce57feb77c152c6145e8881ee81b3f759f5b1f09ef90842dd61965d
+size 4872

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef7eed8fd948162f31f97240ce4df8f01f2613577f0c7eff39774d993b7cdedf
+size 990409141

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef72b5641c4385e9b1ec7811d49f96105dc32d16a70973db879c34c3314c3f7
+size 3771