End of training

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.8995098039215687,
+    "eval_combined_score": 0.9130822722648988,
+    "eval_f1": 0.9266547406082289,
+    "eval_loss": 0.5354248285293579,
+    "eval_runtime": 0.8363,
+    "eval_samples": 408,
+    "eval_samples_per_second": 487.863,
+    "eval_steps_per_second": 31.089,
+    "train_loss": 0.2699521788773532,
+    "train_runtime": 359.8356,
+    "train_samples": 3668,
+    "train_samples_per_second": 50.968,
+    "train_steps_per_second": 3.196
+}

eval_model_config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "kssteven/ibert-roberta-base",
+  "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": "not_equivalent",
+    "1": "equivalent"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "equivalent": 1,
+    "not_equivalent": 0
+  },
+  "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": false,
+  "quant_mode_actfunc": false,
+  "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": 5.0,
+    "eval_accuracy": 0.8995098039215687,
+    "eval_combined_score": 0.9130822722648988,
+    "eval_f1": 0.9266547406082289,
+    "eval_loss": 0.5354248285293579,
+    "eval_runtime": 0.8363,
+    "eval_samples": 408,
+    "eval_samples_per_second": 487.863,
+    "eval_steps_per_second": 31.089
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.2699521788773532,
+    "train_runtime": 359.8356,
+    "train_samples": 3668,
+    "train_samples_per_second": 50.968,
+    "train_steps_per_second": 3.196
+}