End of training

.gitignore

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

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9230769230769231,
+    "eval_f1": 0.9189189189189189,
+    "eval_loss": 0.5037449598312378,
+    "eval_precision": 0.85,
+    "eval_recall": 1.0,
+    "eval_roc_auc": 0.9318181818181819,
+    "eval_runtime": 0.062,
+    "eval_samples": 39,
+    "eval_samples_per_second": 629.027,
+    "eval_steps_per_second": 48.387,
+    "train_loss": 0.1377350079192018,
+    "train_runtime": 17.676,
+    "train_samples": 343,
+    "train_samples_per_second": 194.048,
+    "train_steps_per_second": 12.446
+}

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "neuralsentry/distilbert-git-commits-mlm",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "vocab_size": 30522
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.9230769230769231,
+    "eval_f1": 0.9189189189189189,
+    "eval_loss": 0.5037449598312378,
+    "eval_precision": 0.85,
+    "eval_recall": 1.0,
+    "eval_roc_auc": 0.9318181818181819,
+    "eval_runtime": 0.062,
+    "eval_samples": 39,
+    "eval_samples_per_second": 629.027,
+    "eval_steps_per_second": 48.387
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86eb57ae585fbb2496727a9431388d96b5f6fec8df377860193163404db0adac
+size 267855533

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 +1,13 @@
+{
+  "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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.1377350079192018,
+    "train_runtime": 17.676,
+    "train_samples": 343,
+    "train_samples_per_second": 194.048,
+    "train_steps_per_second": 12.446
+}

trainer_state.json

@@ -0,0 +1,215 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.6837,
+      "step": 22
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5897435897435898,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.6039571166038513,
+      "eval_precision": 0.5161290322580645,
+      "eval_recall": 0.9411764705882353,
+      "eval_roc_auc": 0.6296791443850267,
+      "eval_runtime": 0.069,
+      "eval_samples_per_second": 565.227,
+      "eval_steps_per_second": 43.479,
+      "step": 22
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8.090909090909092e-05,
+      "loss": 0.3852,
+      "step": 44
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9189189189189189,
+      "eval_loss": 0.28810474276542664,
+      "eval_precision": 0.85,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9318181818181819,
+      "eval_runtime": 0.064,
+      "eval_samples_per_second": 609.374,
+      "eval_steps_per_second": 46.875,
+      "step": 44
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.090909090909092e-05,
+      "loss": 0.2148,
+      "step": 66
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9189189189189189,
+      "eval_loss": 0.38069406151771545,
+      "eval_precision": 0.85,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9318181818181819,
+      "eval_runtime": 0.065,
+      "eval_samples_per_second": 600.004,
+      "eval_steps_per_second": 46.154,
+      "step": 66
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.090909090909091e-05,
+      "loss": 0.0701,
+      "step": 88
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8717948717948718,
+      "eval_f1": 0.8717948717948718,
+      "eval_loss": 0.4933823347091675,
+      "eval_precision": 0.7727272727272727,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.8863636363636364,
+      "eval_runtime": 0.071,
+      "eval_samples_per_second": 549.297,
+      "eval_steps_per_second": 42.254,
+      "step": 88
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5.090909090909091e-05,
+      "loss": 0.0164,
+      "step": 110
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8974358974358975,
+      "eval_f1": 0.8947368421052632,
+      "eval_loss": 0.4892081320285797,
+      "eval_precision": 0.8095238095238095,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9090909090909091,
+      "eval_runtime": 0.064,
+      "eval_samples_per_second": 609.381,
+      "eval_steps_per_second": 46.875,
+      "step": 110
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.0909090909090915e-05,
+      "loss": 0.0039,
+      "step": 132
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8974358974358975,
+      "eval_f1": 0.8947368421052632,
+      "eval_loss": 0.49288177490234375,
+      "eval_precision": 0.8095238095238095,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9090909090909091,
+      "eval_runtime": 0.058,
+      "eval_samples_per_second": 672.418,
+      "eval_steps_per_second": 51.724,
+      "step": 132
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 3.090909090909091e-05,
+      "loss": 0.0012,
+      "step": 154
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9189189189189189,
+      "eval_loss": 0.4065372943878174,
+      "eval_precision": 0.85,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9318181818181819,
+      "eval_runtime": 0.063,
+      "eval_samples_per_second": 619.043,
+      "eval_steps_per_second": 47.619,
+      "step": 154
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 2.090909090909091e-05,
+      "loss": 0.0008,
+      "step": 176
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9189189189189189,
+      "eval_loss": 0.48369330167770386,
+      "eval_precision": 0.85,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9318181818181819,
+      "eval_runtime": 0.059,
+      "eval_samples_per_second": 661.03,
+      "eval_steps_per_second": 50.848,
+      "step": 176
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 1.0909090909090909e-05,
+      "loss": 0.0007,
+      "step": 198
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9189189189189189,
+      "eval_loss": 0.4999829828739166,
+      "eval_precision": 0.85,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9318181818181819,
+      "eval_runtime": 0.061,
+      "eval_samples_per_second": 639.321,
+      "eval_steps_per_second": 49.179,
+      "step": 198
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 9.09090909090909e-07,
+      "loss": 0.0006,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9230769230769231,
+      "eval_f1": 0.9189189189189189,
+      "eval_loss": 0.5037449598312378,
+      "eval_precision": 0.85,
+      "eval_recall": 1.0,
+      "eval_roc_auc": 0.9318181818181819,
+      "eval_runtime": 0.058,
+      "eval_samples_per_second": 672.418,
+      "eval_steps_per_second": 51.724,
+      "step": 220
+    },
+    {
+      "epoch": 10.0,
+      "step": 220,
+      "total_flos": 197738122089864.0,
+      "train_loss": 0.1377350079192018,
+      "train_runtime": 17.676,
+      "train_samples_per_second": 194.048,
+      "train_steps_per_second": 12.446
+    }
+  ],
+  "max_steps": 220,
+  "num_train_epochs": 10,
+  "total_flos": 197738122089864.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa15730fd91492ce3dbce622dd0d77268b21b86f56f2301bed4c78fb9e37cdf
+size 4091