Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bac9f553e5b07f6962c1b1f725ef608c678e5b177fc195724896c716462fe6e
+oid sha256:5c74ae6a3ea4365a9178834cd465401c5445444e4226ae06794c61a344510281
 size 437958648

run-3/checkpoint-627/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-3/checkpoint-627/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c74ae6a3ea4365a9178834cd465401c5445444e4226ae06794c61a344510281
+size 437958648

run-3/checkpoint-627/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef373923e96beae13fd0dfa5c156d94e80328ff4a01e4e5f0e4dbc54b6890230
+size 876038394

run-3/checkpoint-627/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f308ad6acf8c1651291a8b39d98d4325b4c252e92fe8dc605003116e14f2da
+size 14308

run-3/checkpoint-627/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6adb01e2346408048ef1e9cd25bebacbbb4626122c239d462c39546c6bf441
+size 1064

run-3/checkpoint-627/special_tokens_map.json

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

run-3/checkpoint-627/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-3/checkpoint-627/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.9040742959856202,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-3/checkpoint-627",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 627,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8203115638106651,
+      "eval_loss": 0.5042904615402222,
+      "eval_runtime": 129.4295,
+      "eval_samples_per_second": 128.95,
+      "eval_steps_per_second": 16.125,
+      "step": 209
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8947872977831036,
+      "eval_loss": 0.3739599585533142,
+      "eval_runtime": 129.4507,
+      "eval_samples_per_second": 128.929,
+      "eval_steps_per_second": 16.122,
+      "step": 418
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 6.7307233810424805,
+      "learning_rate": 2.3798610323153638e-07,
+      "loss": 0.5071,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9040742959856202,
+      "eval_loss": 0.34588372707366943,
+      "eval_runtime": 129.5008,
+      "eval_samples_per_second": 128.879,
+      "eval_steps_per_second": 16.116,
+      "step": 627
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 627,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2034221541187080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1749392655604196e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 31
+  }
+}

run-3/checkpoint-627/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303aeb956fd1d861930deca58dc128af481376b0dbebeaf44e09d4458832a264
+size 4920

runs/Apr14_18-31-48_6ec9497f7a76/events.out.tfevents.1713121839.6ec9497f7a76.2144.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b47f80800beba93e1cdf07b0f69aa45f42b579ba32564cfd6d07995a75abeee8
-size 5495
+oid sha256:4310ab948dd1289ddf27277183a7273fe03ec642745b351d4596d0b4243d2dc9
+size 6172