Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3880bdfe716acbfb56b4209bb6dcff9d33d1f160b06e84fa045a39235a630ed5
+oid sha256:0d02c86d9940a826ff1730795f4670f285175788a8d8f406c97878c487418a2d
 size 437958648

run-4/checkpoint-156/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-4/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d02c86d9940a826ff1730795f4670f285175788a8d8f406c97878c487418a2d
+size 437958648

run-4/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d62a4ba141d0c4be0063f2292e81239b8eda0a94c3cf06412fb9f1fe74257a
+size 876038394

run-4/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e518516ee60ddb5bfad20dbf48f6b6c7626ea5f19ead91f1f67481adeec81725
+size 14244

run-4/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5ba24b2006d6bcc98b0e7ec6d7bc07f9a5596574f6b5c4b73cf313e39d5fb2
+size 1064

run-4/checkpoint-156/special_tokens_map.json

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

run-4/checkpoint-156/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-4/checkpoint-156/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.9659676452965847,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-4/checkpoint-156",
+  "epoch": 2.9714285714285715,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.9539245056920311,
+      "eval_loss": 0.16542811691761017,
+      "eval_runtime": 129.3001,
+      "eval_samples_per_second": 129.08,
+      "eval_steps_per_second": 16.141,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9653085680047933,
+      "eval_loss": 0.1037997454404831,
+      "eval_runtime": 129.5128,
+      "eval_samples_per_second": 128.868,
+      "eval_steps_per_second": 16.114,
+      "step": 105
+    },
+    {
+      "epoch": 2.97,
+      "eval_accuracy": 0.9659676452965847,
+      "eval_loss": 0.10011225193738937,
+      "eval_runtime": 129.542,
+      "eval_samples_per_second": 128.838,
+      "eval_steps_per_second": 16.111,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 156,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.206795367564972e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 32,
+    "seed": 40
+  }
+}

run-4/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2194772225453dced683322f182f6b26593c24e9eb0509fd277a97b09331510
+size 4920

runs/Apr14_18-31-48_6ec9497f7a76/events.out.tfevents.1713122567.6ec9497f7a76.2144.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcfad39edeb989d6c29507fc8485d2f173444e2490a4c50c1594d54348d5ff43
-size 5272
+oid sha256:928f8af35d1ffac2ccd6af964c7276cfdf1391d8629845c793d391b98a74c0b4
+size 5949