Training in progress, step 500

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "bert-base-cased",
   "architectures": [
-    "PipelinedBertForMaskedLM"
+    "PoptorchPipelinedBertForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,

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": 4,
+  "inference_replication_factor": 1,
   "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": 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 sha256:0d19494fe316c8a48e054cada738b0e7e89497ce361b69da6376fcbcac02d302
+oid sha256:5156a1c9857df71ffd7d8250de16adf66ea2a73f5db844e2824b6ab486e8888b
 size 216750379

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e564c5deff8c739fa6d9877ca2c8d1cbdedc008228e1b61154607bb8d65daf2f
+oid sha256:df9764f28d3938e904d5273392ba93388ce968234094473260429de18f78441e
 size 2735