Training in progress, step 500

config.json

@@ -9,7 +9,7 @@
   "dropout_rate": 0.1,
   "eos_token_id": 1,
   "feed_forward_proj": "relu",
-  "hidden_size1": 256,
+  "hidden_size1": 128,
   "hidden_size2": 512,
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
@@ -19,7 +19,7 @@
   "num_heads": 8,
   "num_layer": 1,
   "num_layers": 6,
-  "output_size": 1024,
+  "output_size": 3072,
   "pad_token_id": 0,
   "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b932cf0382af5d85645ab52dc7789880e03edea9d5c70a170fd45fbfa67d23c7
-size 1558469677
+oid sha256:d42ea58d2aaa72cc1b6a6a4b2ae095a2eaf51841a92724ece46ce167d3da76dd
+size 2095086637

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 256
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f365416f6c66c0cf4c879b7628b57e76d7521df628414300dc6c1c4ebb180adf
-size 3119
+oid sha256:e0fd59d4b8042176f6fab6c163595f7944413fbed5d2378adc5cf25250a910d1
+size 3183