int8 model

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.24037130604619567,
+    "train_runtime": 163.9793,
+    "train_samples_per_second": 22.369,
+    "train_steps_per_second": 1.403
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "Intel/MiniLM-L12-H384-uncased-mrpc",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "mrpc",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "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",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "int8",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1cee473de0aec3a78353bdf8993b7aabfdd775b9204d4d71df557b604647ed2
+size 34724137

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home2/xinhe/.cache/huggingface/transformers/1e5909e4dfaa904617797ed35a6105a23daa56cbefca48fef329f772584699fb.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "Intel/MiniLM-L12-H384-uncased-mrpc", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.24037130604619567,
+    "train_runtime": 163.9793,
+    "train_samples_per_second": 22.369,
+    "train_steps_per_second": 1.403
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "step": 230,
+      "total_flos": 60405293512704.0,
+      "train_loss": 0.24037130604619567,
+      "train_runtime": 163.9793,
+      "train_samples_per_second": 22.369,
+      "train_steps_per_second": 1.403
+    }
+  ],
+  "max_steps": 230,
+  "num_train_epochs": 1,
+  "total_flos": 60405293512704.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f61cd4e826907277f5665c6430780ad58f3fc2bf96732e97ca49b5ac32e8fc
+size 3055