End of training

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.8970588235294118,
+    "eval_combined_score": 0.9114269382664727,
+    "eval_f1": 0.9257950530035336,
+    "eval_loss": 0.38710883259773254,
+    "eval_runtime": 10.2395,
+    "eval_samples": 408,
+    "eval_samples_per_second": 39.846,
+    "eval_steps_per_second": 2.539,
+    "train_loss": 0.13981886300810045,
+    "train_runtime": 2408.1272,
+    "train_samples": 3668,
+    "train_samples_per_second": 18.278,
+    "train_steps_per_second": 1.146
+}

eval_model_config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "vuiseng9/baseline-ft-mrpc-IRoberta-b-unquantized",
+  "architectures": [
+    "IBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "mrpc",
+  "force_dequant": "none",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "hweff_logexp_softmax_cfg": null,
+  "id2label": {
+    "0": 0,
+    "1": 1
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "ibert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "quant_mode": true,
+  "quant_mode_actfunc": true,
+  "tokenizer_class": "RobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 1,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 12.0,
+    "eval_accuracy": 0.8970588235294118,
+    "eval_combined_score": 0.9114269382664727,
+    "eval_f1": 0.9257950530035336,
+    "eval_loss": 0.38710883259773254,
+    "eval_runtime": 10.2395,
+    "eval_samples": 408,
+    "eval_samples_per_second": 39.846,
+    "eval_steps_per_second": 2.539
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 12.0,
+    "train_loss": 0.13981886300810045,
+    "train_runtime": 2408.1272,
+    "train_samples": 3668,
+    "train_samples_per_second": 18.278,
+    "train_steps_per_second": 1.146
+}