Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83289d49a1897a95376dc8056c492e781f94290e22bf6fb5825ca21e8da31d4c
+oid sha256:914577c533cdded27b6a9b9b391d2be1ff58397d904b2c7436992d7e73b71639
 size 437958648

run-0/checkpoint-4175/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-0/checkpoint-4175/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:914577c533cdded27b6a9b9b391d2be1ff58397d904b2c7436992d7e73b71639
+size 437958648

run-0/checkpoint-4175/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a480ddd0e298e4912b58fd1f6f710c3ba4a923a62529f8c4caab5d835edfb6
+size 876038394

run-0/checkpoint-4175/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798d1a598515b5f39e49e894202da3a9a32d4526f09d842c2f066fdabdef5495
+size 14308

run-0/checkpoint-4175/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fa67bb6249bbd17ddb876a8ac04190cbd262b992e8706450782238b133b4a6
+size 1064

run-0/checkpoint-4175/special_tokens_map.json

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

run-0/checkpoint-4175/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-0/checkpoint-4175/trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.9840023966446975,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-0/checkpoint-4175",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4175,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.6855844259262085,
+      "learning_rate": 7.660219401214295e-06,
+      "loss": 0.2399,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9690832834032355,
+      "eval_loss": 0.1404273957014084,
+      "eval_runtime": 321.4031,
+      "eval_samples_per_second": 51.929,
+      "eval_steps_per_second": 3.248,
+      "step": 835
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.28391602635383606,
+      "learning_rate": 6.618012679960649e-06,
+      "loss": 0.1015,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.011191217228770256,
+      "learning_rate": 5.575805958707004e-06,
+      "loss": 0.0775,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9820850808867585,
+      "eval_loss": 0.08610038459300995,
+      "eval_runtime": 318.1892,
+      "eval_samples_per_second": 52.453,
+      "eval_steps_per_second": 3.281,
+      "step": 1670
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.1603321135044098,
+      "learning_rate": 4.533599237453358e-06,
+      "loss": 0.0478,
+      "step": 2000
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.008322106674313545,
+      "learning_rate": 3.4913925161997123e-06,
+      "loss": 0.031,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9775314559616537,
+      "eval_loss": 0.12152887880802155,
+      "eval_runtime": 321.3639,
+      "eval_samples_per_second": 51.935,
+      "eval_steps_per_second": 3.249,
+      "step": 2505
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 0.0044579822570085526,
+      "learning_rate": 2.449185794946067e-06,
+      "loss": 0.0155,
+      "step": 3000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9748352306770521,
+      "eval_loss": 0.1382024884223938,
+      "eval_runtime": 323.2353,
+      "eval_samples_per_second": 51.634,
+      "eval_steps_per_second": 3.23,
+      "step": 3340
+    },
+    {
+      "epoch": 4.19,
+      "grad_norm": 0.004470017272979021,
+      "learning_rate": 1.4069790736924213e-06,
+      "loss": 0.0158,
+      "step": 3500
+    },
+    {
+      "epoch": 4.79,
+      "grad_norm": 0.004255039617419243,
+      "learning_rate": 3.647723524387759e-07,
+      "loss": 0.0105,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9840023966446975,
+      "eval_loss": 0.0952066108584404,
+      "eval_runtime": 321.933,
+      "eval_samples_per_second": 51.843,
+      "eval_steps_per_second": 3.243,
+      "step": 4175
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8074611066832800.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.70242612246794e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 20
+  }
+}

run-0/checkpoint-4175/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e099818249ddecf442df98b949821a6e1bc96f54b7f97f17dac7a7067b75e3b4
+size 4920

runs/Apr07_19-58-20_6f1fc297b560/events.out.tfevents.1712519919.6f1fc297b560.655.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6888b1cde650e82dbdbb7f70839b50ebe6a2ee41a5ca0ba07717d6e75885ae15
-size 7195
+oid sha256:d1a6322364271f1b6fdbea93924a00f2f166bd92f7b80f7b611abdb826e2cd4b
+size 8294