Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "neg",
+    "1": "pos"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "neg": "0",
+    "pos": "1"
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "vocab_size": 30522
+}

gaudi_config.json

@@ -0,0 +1,30 @@
+{
+  "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"
+  ],
+  "hmp_is_verbose": false,
+  "hmp_opt_level": "O1",
+  "optimum_version": "1.3.0",
+  "transformers_version": "4.20.1",
+  "use_fused_adam": true,
+  "use_fused_clip_norm": true,
+  "use_habana_mixed_precision": true
+}

logs/1658737170.3634062/events.out.tfevents.1658737170.ip-172-31-83-241.145.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5735083ff12545adc283888419674cc2925b974cb3681d19f3f839480cf7cda2
+size 5624

logs/events.out.tfevents.1658737170.ip-172-31-83-241.145.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed58ddcae16bbbd1c716ec9bb79d25548d48ce359a98f9589bfb117d143ce506
+size 4262

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee244c381b38244fe66e8c0527085fed5d7bfbdd1946517cc2ddbc7bbb95e3e
+size 267852913

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": "distilbert-base-uncased",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e0bb6d3ab62d917d8285e2df100d5a50dafc79b13b37e5768bcba7fe1d3696
+size 3439