Training in progress, epoch 1

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "xlm-roberta-large",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "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": 1024,
+  "id2label": {
+    "0": "social",
+    "1": "transport",
+    "10": "audio",
+    "11": "lists",
+    "12": "qa",
+    "13": "cooking",
+    "14": "takeaway",
+    "15": "music",
+    "16": "alarm",
+    "17": "weather",
+    "2": "calendar",
+    "3": "play",
+    "4": "news",
+    "5": "datetime",
+    "6": "recommendation",
+    "7": "email",
+    "8": "iot",
+    "9": "general"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "alarm": "16",
+    "audio": "10",
+    "calendar": "2",
+    "cooking": "13",
+    "datetime": "5",
+    "email": "7",
+    "general": "9",
+    "iot": "8",
+    "lists": "11",
+    "music": "15",
+    "news": "4",
+    "play": "3",
+    "qa": "12",
+    "recommendation": "6",
+    "social": "0",
+    "takeaway": "14",
+    "transport": "1",
+    "weather": "17"
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

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": "1.2.3",
+  "transformers_version": "4.20.1",
+  "use_fused_adam": true,
+  "use_fused_clip_norm": true,
+  "use_habana_mixed_precision": true
+}

logs/1656073687.3282573/events.out.tfevents.1656073687.ip-172-31-86-34.3714.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d49e179e931d71e4f8d48af5eb18b5d316db2e9f27a0d55afdf9599d56def552
+size 5596

logs/1656073921.375385/events.out.tfevents.1656073921.ip-172-31-86-34.5992.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af434f0b979b33a98c39ce3f54499251e32f5091f7814c3ebc12e49894edc35
+size 5596

logs/events.out.tfevents.1656073687.ip-172-31-86-34.3714.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba896475e9019f64145c67a50caf6fd4a60e361c316edbaa6d3c64b938276b05
+size 4564

logs/events.out.tfevents.1656073921.ip-172-31-86-34.5992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f6aea471ab0b5f6805a643fd494dcd166ac779c6993a1ed85b7fa7d3ceaddc
+size 5088

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfb0bb9a1d98e24dbf465bc88c5355a74965599daea597b836051bb8f6c9c954
+size 2239767213

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
+size 17082660

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "xlm-roberta-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9c7a5780a53d3434a4cf25d5441aa791ecaf7927ae2359bac447a629b937e0
+size 3439