End of training

ipu_config.json

@@ -7,7 +7,7 @@
   "execute_encoder_on_cpu_for_generation": false,
   "gradient_accumulation_steps": 64,
   "inference_device_iterations": 5,
-  "inference_replication_factor": 1,
+  "inference_replication_factor": 4,
   "ipus_per_replica": 4,
   "layers_per_ipu": [
     0,
@@ -20,8 +20,8 @@
   "optimum_version": "1.5.1",
   "output_mode": "final",
   "recompute_checkpoint_every_layer": true,
-  "replicated_tensor_sharding": false,
-  "replication_factor": 1,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
   "seed": 42,
   "sharded_execution_for_inference": false,
   "transformers_version": "4.20.1"

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31194c519403d7e2f1dbd8a958af8702b2ab98afd2c5ce5d95b0ff40d0ba453
+oid sha256:36926fb2303b63982636576ca63c762ce3da408281b084d2268d6b0bc233a959
 size 261514473

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b5734e7ae80416bdea951443d75ac2bd35834740fe774ca9e4df5ad07bf13f
+oid sha256:e6afbeb8ad0a80cd456bb8d79d3a616df3262e0d75ccb57c88ea6d6ce4e6ab23
 size 2671