OtisV1

{'loss': 0.2879, 'learning_rate': 4.75e-05, 'epoch': 0.5}
{'loss': 0.1868, 'learning_rate': 4.5e-05, 'epoch': 1.0}
{'eval_loss': 0.23244266211986542, 'eval_runtime': 4.2923, 'eval_samples_per_second': 465.951, 'eval_steps_per_second': 58.244, 'epoch': 1.0}
{'loss': 0.1462, 'learning_rate': 4.25e-05, 'epoch': 1.5}
{'loss': 0.1244, 'learning_rate': 4e-05, 'epoch': 2.0}
{'eval_loss': 0.19869782030582428, 'eval_runtime': 4.5759, 'eval_samples_per_second': 437.075, 'eval_steps_per_second': 54.634, 'epoch': 2.0}
{'loss': 0.0962, 'learning_rate': 3.7500000000000003e-05, 'epoch': 2.5}
{'loss': 0.07, 'learning_rate': 3.5e-05, 'epoch': 3.0}
{'eval_loss': 0.18761929869651794, 'eval_runtime': 4.1205, 'eval_samples_per_second': 485.372, 'eval_steps_per_second': 60.672, 'epoch': 3.0}
{'loss': 0.0553, 'learning_rate': 3.2500000000000004e-05, 'epoch': 3.5}
{'loss': 0.0721, 'learning_rate': 3e-05, 'epoch': 4.0}
{'eval_loss': 0.19852963089942932, 'eval_runtime': 3.992, 'eval_samples_per_second': 501.004, 'eval_steps_per_second': 62.625, 'epoch': 4.0}
{'loss': 0.0447, 'learning_rate': 2.7500000000000004e-05, 'epoch': 4.5}
{'loss': 0.0461, 'learning_rate': 2.5e-05, 'epoch': 5.0}
{'eval_loss': 0.20028768479824066, 'eval_runtime': 3.8479, 'eval_samples_per_second': 519.766, 'eval_steps_per_second': 64.971, 'epoch': 5.0}
{'loss': 0.0432, 'learning_rate': 2.25e-05, 'epoch': 5.5}
{'loss': 0.033, 'learning_rate': 2e-05, 'epoch': 6.0}
{'eval_loss': 0.20464178919792175, 'eval_runtime': 3.9167, 'eval_samples_per_second': 510.638, 'eval_steps_per_second': 63.83, 'epoch': 6.0}
{'loss': 0.0356, 'learning_rate': 1.75e-05, 'epoch': 6.5}
{'loss': 0.027, 'learning_rate': 1.5e-05, 'epoch': 7.0}
{'eval_loss': 0.20742492377758026, 'eval_runtime': 3.9716, 'eval_samples_per_second': 503.578, 'eval_steps_per_second': 62.947, 'epoch': 7.0}
{'loss': 0.0225, 'learning_rate': 1.25e-05, 'epoch': 7.5}
{'loss': 0.0329, 'learning_rate': 1e-05, 'epoch': 8.0}
{'eval_loss': 0.20604351162910461, 'eval_runtime': 4.0244, 'eval_samples_per_second': 496.964, 'eval_steps_per_second': 62.12, 'epoch': 8.0}
{'loss': 0.0221, 'learning_rate': 7.5e-06, 'epoch': 8.5}
{'loss': 0.0127, 'learning_rate': 5e-06, 'epoch': 9.0}
{'eval_loss': 0.21241146326065063, 'eval_runtime': 3.9242, 'eval_samples_per_second': 509.659, 'eval_steps_per_second': 63.707, 'epoch': 9.0}
{'loss': 0.0202, 'learning_rate': 2.5e-06, 'epoch': 9.5}
{'loss': 0.0229, 'learning_rate': 0.0, 'epoch': 10.0}
{'eval_loss': 0.2140526920557022, 'eval_runtime': 3.9546, 'eval_samples_per_second': 505.743, 'eval_steps_per_second': 63.218, 'epoch': 10.0}
{'train_runtime': 667.0781, 'train_samples_per_second': 119.926, 'train_steps_per_second': 14.991, 'train_loss': 0.07010261821746826, 'epoch': 10.0}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c8234056abe04b1c644355e6715acce036da9d5b764cdf7aca87b294ce9f771
+size 17596023

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce8ae0a81c132344aba2c070350716897494adbdd888d72bccded77a221eb1a
+size 17549312

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676273421f37aef41c5a7ccea4be7350f7de04f43a7f539c3f5993f324e67a48
+size 17560937

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 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}