Training in progress, step 2500, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,26 @@
+{
+  "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": "4.50.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe00ab37bd8ffbfbbd47c01757176185a0197aec8e8da71163201afa36c9852
+size 437958648

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e601937745c2174e864504dff955aa7212cc0cc0eccef309c7b968ef79e4c80a
+size 876032762

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bf1c033ed8ff8a1ebda7c735dbabedb61a89cc74e57667ee9abff75e0a9f8c
+size 13990

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1705a7c11aa908addc84d5fd7ef2c7e81922a331e53011688220f858f888dc32
+size 1064

checkpoint-2500/special_tokens_map.json

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

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "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]"
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": 2500,
+  "best_metric": 0.9573901464713716,
+  "best_model_checkpoint": "C:\\Users\\Daniel\\Desktop\\GitHub\\NLPinitiative\\models\\dlsmallw\\NLPinitiative-Binary-Classification\\checkpoint-2500",
+  "epoch": 2.7203482045701852,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.544069640914037,
+      "grad_norm": 17.53396987915039,
+      "learning_rate": 1.637286906057309e-05,
+      "loss": 0.2811,
+      "step": 500
+    },
+    {
+      "epoch": 0.544069640914037,
+      "eval_accuracy": 0.949238578680203,
+      "eval_auprc": 0.2945266340168414,
+      "eval_auroc": 0.015546624960699109,
+      "eval_f1": 0.946914399469144,
+      "eval_loss": 0.19298532605171204,
+      "eval_precision": 0.9564343163538874,
+      "eval_recall": 0.9375821287779238,
+      "eval_runtime": 102.1508,
+      "eval_samples_per_second": 30.856,
+      "eval_steps_per_second": 3.857,
+      "step": 500
+    },
+    {
+      "epoch": 1.088139281828074,
+      "grad_norm": 1.0602138042449951,
+      "learning_rate": 1.2745738121146174e-05,
+      "loss": 0.1844,
+      "step": 1000
+    },
+    {
+      "epoch": 1.088139281828074,
+      "eval_accuracy": 0.9530456852791879,
+      "eval_auprc": 0.29439297154104793,
+      "eval_auroc": 0.013553767645090812,
+      "eval_f1": 0.9514435695538058,
+      "eval_loss": 0.19708991050720215,
+      "eval_precision": 0.9501965923984272,
+      "eval_recall": 0.9526938239159002,
+      "eval_runtime": 104.1259,
+      "eval_samples_per_second": 30.271,
+      "eval_steps_per_second": 3.784,
+      "step": 1000
+    },
+    {
+      "epoch": 1.632208922742111,
+      "grad_norm": 0.019807865843176842,
+      "learning_rate": 9.11860718171926e-06,
+      "loss": 0.0806,
+      "step": 1500
+    },
+    {
+      "epoch": 1.632208922742111,
+      "eval_accuracy": 0.9568527918781726,
+      "eval_auprc": 0.29427235149466713,
+      "eval_auroc": 0.011200752964697724,
+      "eval_f1": 0.9545758183032732,
+      "eval_loss": 0.23076476156711578,
+      "eval_precision": 0.9707880434782609,
+      "eval_recall": 0.9388961892247043,
+      "eval_runtime": 103.9447,
+      "eval_samples_per_second": 30.324,
+      "eval_steps_per_second": 3.79,
+      "step": 1500
+    },
+    {
+      "epoch": 2.176278563656148,
+      "grad_norm": 0.047856587916612625,
+      "learning_rate": 5.491476242292347e-06,
+      "loss": 0.0743,
+      "step": 2000
+    },
+    {
+      "epoch": 2.176278563656148,
+      "eval_accuracy": 0.9517766497461929,
+      "eval_auprc": 0.2942364000520487,
+      "eval_auroc": 0.010148496892206732,
+      "eval_f1": 0.9500984898227183,
+      "eval_loss": 0.2236114740371704,
+      "eval_precision": 0.949475065616798,
+      "eval_recall": 0.9507227332457293,
+      "eval_runtime": 100.9487,
+      "eval_samples_per_second": 31.224,
+      "eval_steps_per_second": 3.903,
+      "step": 2000
+    },
+    {
+      "epoch": 2.7203482045701852,
+      "grad_norm": 0.010896860621869564,
+      "learning_rate": 1.8643453028654336e-06,
+      "loss": 0.0256,
+      "step": 2500
+    },
+    {
+      "epoch": 2.7203482045701852,
+      "eval_accuracy": 0.9593908629441624,
+      "eval_auprc": 0.29418955133811675,
+      "eval_auroc": 0.009661165886023393,
+      "eval_f1": 0.9573901464713716,
+      "eval_loss": 0.21993429958820343,
+      "eval_precision": 0.970310391363023,
+      "eval_recall": 0.9448094612352168,
+      "eval_runtime": 100.9275,
+      "eval_samples_per_second": 31.23,
+      "eval_steps_per_second": 3.904,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2757,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1315555276800000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1c0cd83c87672929cbce8fc2ed371343bdb0fb899364dfc5bb23635f9b95ef
+size 5496