Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c2cea454034f3db7cb35b2972483c724dcf125e416f1516e4531343cad5a43
+oid sha256:70a5b54d3a4c3e347067d556c03039c86bdd4c26a269820cbb61f4070d7c464a
 size 437958648

run-1/checkpoint-416/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-416/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a5b54d3a4c3e347067d556c03039c86bdd4c26a269820cbb61f4070d7c464a
+size 437958648

run-1/checkpoint-416/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e71d18a10ac192119328a5a3a626b0de77b3a5f16dae3ecf545fd0fcfc8e04e
+size 876038394

run-1/checkpoint-416/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c690fa67a0ceb6c4695472a312dafbfeb413d5c06e12d40e9597a7c5b52c4a2
+size 14244

run-1/checkpoint-416/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f68652183e32efef3b3da15b6778d033ddb2a871b87f23d3c1e3e0c51356089d
+size 1064

run-1/checkpoint-416/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-416/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-416/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.9801677651288196,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/checkpoint-416",
+  "epoch": 3.9808612440191387,
+  "eval_steps": 500,
+  "global_step": 416,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9651887357699221,
+      "eval_loss": 0.1194479838013649,
+      "eval_runtime": 512.5403,
+      "eval_samples_per_second": 32.563,
+      "eval_steps_per_second": 4.072,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9775314559616537,
+      "eval_loss": 0.07069126516580582,
+      "eval_runtime": 511.5618,
+      "eval_samples_per_second": 32.626,
+      "eval_steps_per_second": 4.08,
+      "step": 209
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9791491911324146,
+      "eval_loss": 0.08672985434532166,
+      "eval_runtime": 540.0361,
+      "eval_samples_per_second": 30.905,
+      "eval_steps_per_second": 3.865,
+      "step": 313
+    },
+    {
+      "epoch": 3.98,
+      "eval_accuracy": 0.9801677651288196,
+      "eval_loss": 0.08871355652809143,
+      "eval_runtime": 507.4158,
+      "eval_samples_per_second": 32.892,
+      "eval_steps_per_second": 4.113,
+      "step": 416
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 416,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.7633342814387334e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-1/checkpoint-416/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e70c6e682ff4679414666a12647b55c4e70bdccf653d9bd96a7a5f7ed2f6901
+size 4920

runs/Apr08_02-37-12_c6651826e9bb/events.out.tfevents.1712545178.c6651826e9bb.838.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be88cb915ff8937a41446bb7c2adf18ff7b0762d90293a00daa21d036a253e5
-size 5602
+oid sha256:9b505c758aca5830fd3e6da743ea9cf95b2e32f383a43fb9a8736adcf4fceb4d
+size 6279