Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6bc46733237ac944dc44623c146016d3d1e41b375fc5646b4157890c4392eff
+oid sha256:01ec2eeccfb520f88890e9d95ef9501f1a9d913e9fe7495fe6322ab6060d93b9
 size 437958648

run-2/checkpoint-208/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-2/checkpoint-208/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ec2eeccfb520f88890e9d95ef9501f1a9d913e9fe7495fe6322ab6060d93b9
+size 437958648

run-2/checkpoint-208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5103b6949aa04faf275a06513a2b3e46cdbff344e20c07d0fb1fe5ffb4888c
+size 876038394

run-2/checkpoint-208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861f8365c117dce09f30482d0da85fa8995b7355c46508dc4730cbd7b984df62
+size 14244

run-2/checkpoint-208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f107aefc3d449cbb397820b46a57903ed8b11b5f049bb257a9f8cd31b02d313e
+size 1064

run-2/checkpoint-208/special_tokens_map.json

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

run-2/checkpoint-208/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-2/checkpoint-208/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.9808268424206111,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-105",
+  "epoch": 3.961904761904762,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.9720191731575794,
+      "eval_loss": 0.08049887418746948,
+      "eval_runtime": 129.4849,
+      "eval_samples_per_second": 128.895,
+      "eval_steps_per_second": 16.118,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9808268424206111,
+      "eval_loss": 0.0663532018661499,
+      "eval_runtime": 129.584,
+      "eval_samples_per_second": 128.797,
+      "eval_steps_per_second": 16.105,
+      "step": 105
+    },
+    {
+      "epoch": 2.99,
+      "eval_accuracy": 0.9679448771719592,
+      "eval_loss": 0.11977529525756836,
+      "eval_runtime": 129.6054,
+      "eval_samples_per_second": 128.776,
+      "eval_steps_per_second": 16.103,
+      "step": 157
+    },
+    {
+      "epoch": 3.96,
+      "eval_accuracy": 0.9803475134811265,
+      "eval_loss": 0.07485608756542206,
+      "eval_runtime": 129.6725,
+      "eval_samples_per_second": 128.709,
+      "eval_steps_per_second": 16.094,
+      "step": 208
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.848744961833747e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 40
+  }
+}

run-2/checkpoint-208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83691e4cee6baa5a8511f8f79336b31f5cd88f53b70ea13a4b286e00edbb6da
+size 4920

runs/Apr14_18-31-48_6ec9497f7a76/events.out.tfevents.1713120899.6ec9497f7a76.2144.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd2d5737dcff6f013493722c074dacb4d67708f6adae0f00e07ee311c7cdb89f
-size 5595
+oid sha256:31128da0fc3afbd7f115fef5263f91e711ef1c86217face52714193445e52c64
+size 6272