Training in progress, epoch 1

config.json

@@ -21,7 +21,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float16",
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.20.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

ipu_config.json

@@ -1,5 +1,4 @@
 {
-  "decompose_grad_sum": false,
   "device_iterations": 1,
   "embedding_serialization_factor": 0,
   "enable_half_first_order_momentum": true,
@@ -20,7 +19,7 @@
     0.25
   ],
   "optimizer_state_offchip": true,
-  "optimum_version": "1.2.3",
+  "optimum_version": "1.3.0",
   "output_mode": "final",
   "profile_dir": "",
   "recompute_checkpoint_every_layer": true,
@@ -28,6 +27,6 @@
   "replication_factor": 4,
   "seed": 42,
   "sharded_execution_for_inference": false,
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.20.1",
   "use_popdist": false
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38e6d096cee7ca80787c6bda757f58635dc0db22402a6cd132c8609ca4854b4
+oid sha256:26d54378251a3465df537ae13c3fd481495c9558195ea39c0c5054898d24d32c
 size 249363181

special_tokens_map.json

@@ -1 +1,15 @@
-{"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}}
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -1 +1,16 @@
-{"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"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e143b207b8875610042b522bbc1c80bd32e78e5cecfac0771aca220c342fd034
+oid sha256:48a7aa281d37510563421a00de498272c56eba165bc7e76129d540c79f417032
 size 2671