Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/flan-t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.27.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5dbd7982c423e3c62057b7e58e0e938fe8a42689c188fcef0a595cafdeea57
+size 1566493509

runs/Oct17_11-33-31_0a73535b96e1/1697542439.7851315/events.out.tfevents.1697542439.0a73535b96e1.608.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6603a6f16a5f26051fd8c1dc1d9427cd90eb8580bd1b6695f3dfee2a58ef267
+size 5820

runs/Oct17_11-33-31_0a73535b96e1/events.out.tfevents.1697542439.0a73535b96e1.608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345a5c2034fffa2c2276f3da371daa36bc148a42d7001552c0cc211eb100c066
+size 82232

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046d28fa2f61c705e401e6de59d50e9e345bb228f49b5643e8158d961fc478d8
+size 3579