Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "float32",
+  "transformers_version": "4.21.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

gaudi_config.json

@@ -0,0 +1,31 @@
+{
+  "hmp_bf16_ops": [
+    "add",
+    "addmm",
+    "bmm",
+    "div",
+    "dropout",
+    "gelu",
+    "iadd",
+    "linear",
+    "layer_norm",
+    "matmul",
+    "mm",
+    "rsub",
+    "softmax",
+    "truediv"
+  ],
+  "hmp_fp32_ops": [
+    "embedding",
+    "nll_loss",
+    "log_softmax",
+    "cross_entropy"
+  ],
+  "hmp_is_verbose": false,
+  "hmp_opt_level": "O1",
+  "optimum_version": "1.3.0",
+  "transformers_version": "4.21.1",
+  "use_fused_adam": true,
+  "use_fused_clip_norm": true,
+  "use_habana_mixed_precision": true
+}

logs/1660806180.365825/events.out.tfevents.1660806180.ip-172-31-93-36.193.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e673e5211ff97be7f4f6c2a4ef521a405227d862c8bb59808190848bfbe65c8
+size 5716

logs/events.out.tfevents.1660806180.ip-172-31-93-36.193.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ed131be3e5d2c4bdbb568d69f91390ed8d0f17b57b04ea3fc20815ad9a9431
+size 11699

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a82b48af644a9f956ccfdce5fcb004c79ae1224f61fa5bca66243003eacbf3
+size 541104679

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "philschmid/bert-base-uncased-2022-habana",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d6c995e86e8a2ed578c79b3423e9637605493ae9acd7fbf3f5b148610e623b
+size 3503