Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "facebook/bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "PoptorchPipelinedBartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 50265
+}

ipu_config.json

@@ -0,0 +1,33 @@
+{
+  "auto_loss_scaling": false,
+  "device_iterations": 1,
+  "embedding_serialization_factor": 5,
+  "enable_half_partials": true,
+  "executable_cache_dir": "/tmp/exe_cache//summarization",
+  "execute_encoder_on_cpu_for_generation": false,
+  "gradient_accumulation_steps": 16,
+  "inference_device_iterations": 6,
+  "inference_replication_factor": 4,
+  "ipus_per_replica": 4,
+  "layers_per_ipu": [
+    0,
+    6,
+    3,
+    3
+  ],
+  "matmul_proportion": [
+    0.25,
+    0.25,
+    0.25,
+    0.25
+  ],
+  "optimizer_state_offchip": true,
+  "optimum_version": "1.6.2.dev0",
+  "output_mode": "final",
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
+  "seed": 42,
+  "sharded_execution_for_inference": false,
+  "transformers_version": "4.20.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffdc0879c62753815d9da145619f031e0abcac471ee82c5fe3d559a24d3c63a
+size 279026141

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4925b2494a8874f689f9d9fc9564a17f0fee3a6c513c352c87366e8901f0e4
+size 2875