Training in progress, step 1500, checkpoint

checkpoint-1500/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-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:716a82fb01b51ad7b5dab410fa2f97e40d6bbd4cb7dee758320fae07f2de6d08
+size 437958648

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a16e5a100b9566c3a9324a69049f70c1950c19c1ac354ab4277d2b99a4b900c1
+size 876032762

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bafea81a99b84e00a894fc2a884b25ecf4a9405f0f81241e541ed90a2bd4ddf
+size 13990

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc9681c832b6123db950ec2a895755a34aa3a463cdb80c51df0837ed86372af
+size 1064

checkpoint-1500/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.9476439790575916,
+  "best_model_checkpoint": "C:\\Users\\Daniel\\Desktop\\GitHub\\NLPinitiative\\models\\dlsmallw\\NLPinitiative-Binary-Classification\\checkpoint-1500",
+  "epoch": 1.632208922742111,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.544069640914037,
+      "grad_norm": 0.14858652651309967,
+      "learning_rate": 1.637286906057309e-05,
+      "loss": 0.2817,
+      "step": 500
+    },
+    {
+      "epoch": 0.544069640914037,
+      "eval_accuracy": 0.9330583756345178,
+      "eval_auprc": 0.2921851625500245,
+      "eval_auroc": 0.01756043735337567,
+      "eval_f1": 0.9321761491481839,
+      "eval_loss": 0.250454306602478,
+      "eval_precision": 0.90625,
+      "eval_recall": 0.9596293845135672,
+      "eval_runtime": 102.5806,
+      "eval_samples_per_second": 30.727,
+      "eval_steps_per_second": 3.841,
+      "step": 500
+    },
+    {
+      "epoch": 1.088139281828074,
+      "grad_norm": 1.7654657363891602,
+      "learning_rate": 1.2745738121146174e-05,
+      "loss": 0.1722,
+      "step": 1000
+    },
+    {
+      "epoch": 1.088139281828074,
+      "eval_accuracy": 0.9479695431472082,
+      "eval_auprc": 0.29180260985958417,
+      "eval_auroc": 0.013246753142000309,
+      "eval_f1": 0.9453333333333334,
+      "eval_loss": 0.2592768967151642,
+      "eval_precision": 0.9523169912693082,
+      "eval_recall": 0.9384513567174056,
+      "eval_runtime": 102.9732,
+      "eval_samples_per_second": 30.61,
+      "eval_steps_per_second": 3.826,
+      "step": 1000
+    },
+    {
+      "epoch": 1.632208922742111,
+      "grad_norm": 0.4014647901058197,
+      "learning_rate": 9.11860718171926e-06,
+      "loss": 0.0946,
+      "step": 1500
+    },
+    {
+      "epoch": 1.632208922742111,
+      "eval_accuracy": 0.949238578680203,
+      "eval_auprc": 0.29179891736469293,
+      "eval_auroc": 0.010873339568333138,
+      "eval_f1": 0.9476439790575916,
+      "eval_loss": 0.25160646438598633,
+      "eval_precision": 0.9372168284789644,
+      "eval_recall": 0.9583057577763071,
+      "eval_runtime": 103.2978,
+      "eval_samples_per_second": 30.514,
+      "eval_steps_per_second": 3.814,
+      "step": 1500
+    }
+  ],
+  "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": 789333166080000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29909eb692988507c7e2fe9dbaafabc7dfb2f1505ddb732d33ccf795d5cf3f37
+size 5496