Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c4ecf0fb267ca0111315770c7aee028de79177925924f83b69d961b456b023
+oid sha256:c5ec88bd4ec96273bf642b6b72db0af8c561d85f769cca178090698130901441
 size 438007864

run-1/checkpoint-250/config.json

@@ -0,0 +1,65 @@
+{
+  "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,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-250/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ec88bd4ec96273bf642b6b72db0af8c561d85f769cca178090698130901441
+size 438007864

run-1/checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:092daa342bdee2d9e0d92122804e4d287e06f45d290fded300651afa4881120b
+size 876140043

run-1/checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:862604ce98dc7990f5a856b473c2bb4483e47e7f93f40f8447841cfa74a2f462
+size 14645

run-1/checkpoint-250/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6cb8b0e819e611a531273899ac1b31b14ada277e3a73ef9b068865317455864
+size 1383

run-1/checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d87cac0fd443f7f352b825e57f2b2b13f5a3bfa66bb0cd9a1a281edc5b25880c
+size 1465

run-1/checkpoint-250/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_global_step": 125,
+  "best_metric": 0.7222001215424422,
+  "best_model_checkpoint": "./results/run-1/checkpoint-125",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 12.130753517150879,
+      "learning_rate": 1.6523003188214528e-05,
+      "loss": 1623.5764,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_economic_inequality_accuracy": 0.7770780856423174,
+      "eval_economic_inequality_f1": 0.6795991195482776,
+      "eval_economic_policy_benefits_accuracy": 0.8215488215488216,
+      "eval_economic_policy_benefits_f1": 0.7410643713786043,
+      "eval_ethnic_boundaries_accuracy": 0.946078431372549,
+      "eval_ethnic_boundaries_f1": 0.9198646713093299,
+      "eval_language_policy_accuracy": 0.6764705882352942,
+      "eval_language_policy_f1": 0.545923632610939,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.6805555555555556,
+      "eval_overall_accuracy": 0.8064020197505432,
+      "eval_overall_f1": 0.7222001215424422,
+      "eval_religion_ethnic_identity_accuracy": 0.839458413926499,
+      "eval_religion_ethnic_identity_f1": 0.7661933788519465,
+      "eval_runtime": 4.4741,
+      "eval_samples_per_second": 894.041,
+      "eval_steps_per_second": 55.878,
+      "step": 125
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 7.246724605560303,
+      "learning_rate": 3.3212905398532236e-05,
+      "loss": 4406.7347,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_economic_inequality_accuracy": 0.7770780856423174,
+      "eval_economic_inequality_f1": 0.6795991195482776,
+      "eval_economic_policy_benefits_accuracy": 0.8215488215488216,
+      "eval_economic_policy_benefits_f1": 0.7410643713786043,
+      "eval_ethnic_boundaries_accuracy": 0.946078431372549,
+      "eval_ethnic_boundaries_f1": 0.9198646713093299,
+      "eval_language_policy_accuracy": 0.6764705882352942,
+      "eval_language_policy_f1": 0.545923632610939,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.6805555555555556,
+      "eval_overall_accuracy": 0.8064020197505432,
+      "eval_overall_f1": 0.7222001215424422,
+      "eval_religion_ethnic_identity_accuracy": 0.839458413926499,
+      "eval_religion_ethnic_identity_f1": 0.7661933788519465,
+      "eval_runtime": 4.4873,
+      "eval_samples_per_second": 891.403,
+      "eval_steps_per_second": 55.713,
+      "step": 250
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 1
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6736610643148800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 4.305994770261968e-05,
+    "num_train_epochs": 16,
+    "per_device_train_batch_size": 32,
+    "warmup_steps": 258,
+    "weight_decay": 0.09399341365652919
+  }
+}

run-1/checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4410e061e9e9063477d5b57f26eeda29d8b119aba156a0a7c510c00764b1fd9b
+size 5777