Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62af02836c115a9e9d1b2ce917b882f3f2045f3a08b66535a7c1f7182b734531
+oid sha256:a8b0b555ee94ce7552bb12e90c534d458d6a204253d570019df85b4a63c8da88
 size 437958648

run-2/checkpoint-313/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-313/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8b0b555ee94ce7552bb12e90c534d458d6a204253d570019df85b4a63c8da88
+size 437958648

run-2/checkpoint-313/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c104ecb660519258b9b5d088a9518537f31aac7701bed4722cc6302dd4091019
+size 876038394

run-2/checkpoint-313/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2daeb412228cb70175c940d0cffa357a5a08ac3d871600a2bfcff543c220630
+size 14308

run-2/checkpoint-313/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd0ad71de5eef60b8fc9eb2e65b10f01272a5d4b4ca1b729c5f183587ba2d358
+size 1064

run-2/checkpoint-313/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-313/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-313/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.9783702816057519,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-2/checkpoint-313",
+  "epoch": 2.9952153110047846,
+  "eval_steps": 500,
+  "global_step": 313,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9642300778909527,
+      "eval_loss": 0.10540720075368881,
+      "eval_runtime": 511.327,
+      "eval_samples_per_second": 32.641,
+      "eval_steps_per_second": 4.082,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9622528460155781,
+      "eval_loss": 0.13376426696777344,
+      "eval_runtime": 511.478,
+      "eval_samples_per_second": 32.631,
+      "eval_steps_per_second": 4.08,
+      "step": 209
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9783702816057519,
+      "eval_loss": 0.10255199670791626,
+      "eval_runtime": 506.6183,
+      "eval_samples_per_second": 32.944,
+      "eval_steps_per_second": 4.119,
+      "step": 313
+    }
+  ],
+  "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": 6.170280629869221e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 13
+  }
+}

run-2/checkpoint-313/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4aa6fee3a9832c933a46b915398cbe7360cab8548f2d3253bf9a80801fa0a7
+size 4920

runs/Apr08_02-37-12_c6651826e9bb/events.out.tfevents.1712547752.c6651826e9bb.838.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46bd283fddcffeca09c7aae2f9b764cb87d5b7c6a788d40e48e9be1dc5e255dd
-size 5278
+oid sha256:53b22bf1f7a1486c7f324f3b442df9e22d375477f2263ea6d46c755f16206fc3
+size 5601