Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3734c7e63a57b13a78e1364c08a9ab44eafddc37ce274e8c1aa83d4a6e44092
+oid sha256:db2a60dc6bbb07338c4d0dfff0424ac1bfa4a30608dbd8bd9055ff57493d0093
 size 437958648

run-0/checkpoint-1670/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-1670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2a60dc6bbb07338c4d0dfff0424ac1bfa4a30608dbd8bd9055ff57493d0093
+size 437958648

run-0/checkpoint-1670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44763a5e2c5d3f7b655029eda2376b76307b1122b86d80084664b5b86917899f
+size 876038394

run-0/checkpoint-1670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627ea2f7cd2aedb5e1b4e507ea04b02dd0820e238075ddd9d5b5edf37464fe6d
+size 14308

run-0/checkpoint-1670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:366cda4d6512ba28553df7753df51ae469825d7fb82c5003880659bdb93dbc77
+size 1064

run-0/checkpoint-1670/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-1670/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-1670/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.9820850808867585,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-0/checkpoint-1670",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1670,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4175,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3026276636534160.0,
+  "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-1670/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 sha256:3fd9590160a0a2e20982e2233002405d82221566e2898179da9a51fe941fc680
-size 5171
+oid sha256:edb09292b0d419baf4aad18a81d557e61680e2e94e41f12543ed29d3323820a3
+size 5916