Training in progress, step 684

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "byt5-base-squad",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3968,
+  "d_kv": 64,
+  "d_model": 1536,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 6,
+  "num_heads": 12,
+  "num_layers": 18,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "ByT5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 384
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa83fd40db5c66907cef4140d858a2f65e25d24aefcc827ab50ea277f2ca121
+size 2326728585

runs/Apr10_09-00-34_stwl6pctr1649515016669-j28st/1649552467.354788/events.out.tfevents.1649552467.stwl6pctr1649515016669-j28st.2996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3d3bff487b5c5cce7c4a4d8211b87fb1748c58e85f293fa4d671ed4154f444d
+size 4770

runs/Apr10_09-00-34_stwl6pctr1649515016669-j28st/events.out.tfevents.1649552467.stwl6pctr1649515016669-j28st.2996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6dec2e6fd6691b01a6403719cee1367cfb004b4a32e932c6590126fba52f9e
+size 3368

runs/Apr10_09-22-09_stwl6pctr1649515016669-j28st/1649553756.4964561/events.out.tfevents.1649553756.stwl6pctr1649515016669-j28st.3231.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c37c20f508fa5fa755f1409e312f331088811f6d7165a8c895532a2662b46e
+size 4770

runs/Apr10_09-22-09_stwl6pctr1649515016669-j28st/events.out.tfevents.1649553756.stwl6pctr1649515016669-j28st.3231.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440b34105e42ae4cc90726fc745a77583dfe8cdd88a8bcfc1435ac1879b427d9
+size 3552

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438bd1f950e23af702c55250b53129e4b21920af50dc570f25c5eae1f04c620b
+size 3055