Training in progress, epoch 1

config.json

@@ -21,7 +21,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float16",
-  "transformers_version": "4.20.0",
+  "transformers_version": "4.20.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

ipu_config.json

@@ -7,7 +7,7 @@
   "execute_encoder_on_cpu_for_generation": false,
   "gradient_accumulation_steps": 16,
   "inference_device_iterations": 5,
-  "inference_replication_factor": 1,
+  "inference_replication_factor": 4,
   "ipus_per_replica": 4,
   "layers_per_ipu": [
     0,
@@ -22,9 +22,9 @@
   "optimum_version": "1.5.0",
   "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": "4.20.0"
+  "transformers_version": "4.20.1"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f69ccfa34198cdf462cd9288ef91db57007861212aceb2432396d26a65dade1f
+oid sha256:db3d92af8c2e0e8a3428d4c1f9e887aebcae17673fd6cd1c03b7c3be35c8c0ca
 size 249363181

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4255b6f255bd98ed9f26868c03ebd15736c93c51b6f50970e8dfc4b4a0ffa1ae
-size 2735
+oid sha256:fbc32f87586394e75656532cc4bfa1864ec7359bb4bbc1c6baa5cd74df887219
+size 2799