Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "PoptorchPipelinedBertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

ipu_config.json

@@ -0,0 +1,31 @@
+{
+  "decompose_grad_sum": false,
+  "device_iterations": 1,
+  "embedding_serialization_factor": 0,
+  "enable_half_first_order_momentum": true,
+  "enable_half_partials": true,
+  "executable_cache_dir": "./exe_cache",
+  "execute_encoder_on_cpu_for_generation": false,
+  "gradient_accumulation_steps": 16,
+  "inference_device_iterations": 5,
+  "inference_replication_factor": 4,
+  "ipus_per_replica": 4,
+  "layers_per_ipu": [
+    0,
+    4,
+    4,
+    4
+  ],
+  "matmul_proportion": 0.25,
+  "optimizer_state_offchip": false,
+  "optimum_version": "1.3.0",
+  "output_mode": "final",
+  "profile_dir": "",
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
+  "seed": 42,
+  "sharded_execution_for_inference": false,
+  "transformers_version": "4.20.0",
+  "use_popdist": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80713a2e3d3a3e630c1db52a4d4d40bca95c9d3abbb457d091c14ed5be579e0a
+size 217864753

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec385bea5d0d9dc3b60909025d8eddb07f1ee00f4cd9aa8f5a499208f10b532f
+size 2671