Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:914577c533cdded27b6a9b9b391d2be1ff58397d904b2c7436992d7e73b71639
+oid sha256:71b9b02fcaadd08ecf41ab6d26a6ba3af18d5ce2ce39e6fd3be4e94354775b79
 size 437958648

run-1/checkpoint-1669/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-1669/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b9b02fcaadd08ecf41ab6d26a6ba3af18d5ce2ce39e6fd3be4e94354775b79
+size 437958648

run-1/checkpoint-1669/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60e898b214c573ad94f4d449cd3ea00ad2b45d69e3aed9bbcc7107df1494a95b
+size 876038394

run-1/checkpoint-1669/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fa511f66a6aff1106c40fd12edc88cd20c3b4cbe632d5bca291bb1778c32166
+size 14244

run-1/checkpoint-1669/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a5a7123f86992d5093150f8ff33d3d4c1404329a026a7aa91d280292eaa0688
+size 1064

run-1/checkpoint-1669/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-1669/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]"
+}

run-1/checkpoint-1669/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.9698621929298982,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-1669",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1669,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.8941549062728882,
+      "learning_rate": 2.7998077239858024e-06,
+      "loss": 0.3584,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.23405538499355316,
+      "learning_rate": 2.5731393525491277e-06,
+      "loss": 0.157,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.15349306166172028,
+      "learning_rate": 2.3464709811124533e-06,
+      "loss": 0.1768,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9698621929298982,
+      "eval_loss": 0.13613532483577728,
+      "eval_runtime": 318.6416,
+      "eval_samples_per_second": 52.379,
+      "eval_steps_per_second": 3.276,
+      "step": 1669
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6676,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1346627047993920.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.0264760954224767e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 6
+  }
+}

run-1/checkpoint-1669/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60379ae07aa3728c9424d4499cfa9907fccd032fa9110c665a9cee7da027e697
+size 4920

runs/Apr07_19-58-20_6f1fc297b560/events.out.tfevents.1712522594.6f1fc297b560.655.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:607996658fef0dc089c99e72c658ae243633e9aa61f68229904c0ba8deb19708
+size 5594

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e099818249ddecf442df98b949821a6e1bc96f54b7f97f17dac7a7067b75e3b4
+oid sha256:60379ae07aa3728c9424d4499cfa9907fccd032fa9110c665a9cee7da027e697
 size 4920