Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "medardif/long-t5-local-base_complete_dataset_V_1.0.10",
+  "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": "4.26.0",
+  "use_cache": false,
+  "vocab_size": 32128
+}

logs/1684877696.0275674/events.out.tfevents.1684877696.134d7a02a642.395.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:313ded8836da17dbb9b0359c519ca888c3d19541c9b0b731560f923641c1c8e1
+size 5993

logs/events.out.tfevents.1684877695.134d7a02a642.395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3a6f146b17f7f35d4a96b910a2c8cd68c5e1a51610cc4045d23333882e270b
+size 4818

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0b875e8d43956667f733b899d0e2427afa52632965255b0b2d5e16999e00f2
+size 990405045

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79d6923ffff1acc2b14fbdd66694248136c52bd6d7a3fefb856e405c455d60b
+size 4795