Training in progress, epoch 1

ipu_config.json

@@ -7,7 +7,7 @@
   "execute_encoder_on_cpu_for_generation": false,
   "gradient_accumulation_steps": 32,
   "inference_device_iterations": 4,
-  "inference_replication_factor": 4,
+  "inference_replication_factor": 1,
   "ipus_per_replica": 4,
   "layers_per_ipu": [
     3,
@@ -22,8 +22,8 @@
   "optimum_version": "1.5.2",
   "output_mode": "final",
   "recompute_checkpoint_every_layer": true,
-  "replicated_tensor_sharding": true,
-  "replication_factor": 4,
+  "replicated_tensor_sharding": false,
+  "replication_factor": 1,
   "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 sha256:725a851a1d8703a502136f076721ce446c38b6459790a35d50d4c7e74001792f
+oid sha256:b15024af701da5ac1d88e29fc965d78a1ef279fa31e4f6b140caba7277d6349f
 size 171677805

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd38409ca0f12cf3b7b3710b5954ab48e787c3aa818e5d22685fa6d847cf0fc
+oid sha256:db1dfe143c2a7a46eaf41350c1ceb5115f84ba047ffab15e47c3532f497da0e5
 size 2811