End of training

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 85.26963103122044,
+    "eval_f1": 91.74547836701485,
+    "eval_samples": 10790,
+    "train_loss": 1.2527947025022645,
+    "train_runtime": 134.5045,
+    "train_samples": 88568,
+    "train_samples_per_second": 1316.952,
+    "train_steps_per_second": 5.13
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "PoptorchPipelinedRobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float16",
+  "transformers_version": "4.18.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15b906a072d75ed2f41e09a5bac4004d5f448e1e2bfc65b3055522073e6079e5
+size 45648758

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 85.26963103122044,
+    "eval_f1": 91.74547836701485,
+    "eval_samples": 10790
+}

ipu_config.json

@@ -0,0 +1,29 @@
+{
+  "device_iterations": 1,
+  "embedding_serialization_factor": 0,
+  "enable_half_first_order_momentum": true,
+  "enable_half_partials": true,
+  "executable_cache_dir": "./exe_cache",
+  "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": "0.1.2",
+  "output_mode": "final",
+  "profile_dir": "",
+  "recompute_checkpoint_every_layer": true,
+  "replicated_tensor_sharding": true,
+  "replication_factor": 4,
+  "seed": 1984,
+  "use_popdist": false
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a725b2e8e7bcb6925174539798407f55f220d82b095dabfb3635a9538fa7c533
+size 248181489

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 1.2527947025022645,
+    "train_runtime": 134.5045,
+    "train_samples": 88568,
+    "train_samples_per_second": 1316.952,
+    "train_steps_per_second": 5.13
+}