Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bb5d903a3edc725ae7efdf03dec1e15aa82c262f93e7f13ed66da62695c521
+oid sha256:82c2cea454034f3db7cb35b2972483c724dcf125e416f1516e4531343cad5a43
 size 437958648

run-1/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-1/checkpoint-313/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c2cea454034f3db7cb35b2972483c724dcf125e416f1516e4531343cad5a43
+size 437958648

run-1/checkpoint-313/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1532cb3bd17e1cebdc44e9abadb8894ab964001b7650fd25260d7aa09c5b09dd
+size 876038394

run-1/checkpoint-313/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34584916da72307ef84ba066880ce24fcf2d07355ad914ca9bbc02f120e6f779
+size 14244

run-1/checkpoint-313/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fafcd024df334613d9a6627c6e03d79b60f00c23d34f9be7901d8e4667d444fe
+size 1064

run-1/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-1/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-1/checkpoint-313/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.9791491911324146,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-1/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": 0.9651887357699221,
+      "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
+    }
+  ],
+  "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-313/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:e70c1f405b580399d20cc999948a622bccb5965ee5cded82bf82df9b9240354a
-size 5279
+oid sha256:2be88cb915ff8937a41446bb7c2adf18ff7b0762d90293a00daa21d036a253e5
+size 5602