Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "PoptorchPipelinedT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float16",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

ipu_config.json

@@ -0,0 +1,33 @@
+{
+  "auto_loss_scaling": false,
+  "device_iterations": 1,
+  "embedding_serialization_factor": 2,
+  "enable_half_partials": true,
+  "executable_cache_dir": "/tmp/exe_cache",
+  "execute_encoder_on_cpu_for_generation": false,
+  "gradient_accumulation_steps": 16,
+  "inference_device_iterations": 5,
+  "inference_replication_factor": 1,
+  "ipus_per_replica": 4,
+  "layers_per_ipu": [
+    0,
+    3,
+    4,
+    5
+  ],
+  "matmul_proportion": [
+    0.25,
+    0.25,
+    0.25,
+    0.25
+  ],
+  "optimizer_state_offchip": true,
+  "optimum_version": "1.5.0",
+  "output_mode": "final",
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": false,
+  "replication_factor": 1,
+  "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 sha256:8e8eac098140367a0fba1d56738c96b0c4c1a7187074a8a6d7d5bfaed35afd88
+size 121055163

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57704b9905598f6b73258e5a82d54ea3a07ea4cff27632dac6bbfe2321e66552
+size 2863