Training in progress, step 500

config.json

@@ -2,7 +2,7 @@
   "_name_or_path": "gpt2",
   "activation_function": "gelu",
   "architectures": [
-    "PipelinedGPT2LMHeadModel"
+    "PoptorchPipelinedGPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,

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 sha256:098b3647c1fc1f6dfec838602e3c14650fbd27a60644c1c26daf1a7c42ab08fb
+oid sha256:e70c1ea321b105434650988294a0d038f373574156c0036a3a1b263fac473a51
 size 261514473

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dddd72216e055d0fad617b0f2383e163d10a21c8b1ff31203432e057541bd3f
+oid sha256:4869f5fe88dbf550509285ebaef436d3fe02346852a455707d5b9ba2730fc64d
 size 2735