Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6751c47dcf7a248da893e7d752e058890f3cd7a4f1745cd530f4bc647188a05
+oid sha256:74dd7f6679bfcd26b218580b1921650f761b4b405ce2da0f62c0fcd429028318
 size 438007864

run-2/checkpoint-2000/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-2/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74dd7f6679bfcd26b218580b1921650f761b4b405ce2da0f62c0fcd429028318
+size 438007864

run-2/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6be48e899dabca2e11ada70ac756b2fff8adeee13f05aa8041754b5ef28079a
+size 876140043

run-2/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80211a900043c2aa59a00645f8979497aa988a0f7335800baf8daa8a3aa47adc
+size 14645

run-2/checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e32bac074b2e5dc8265a886fa46c66d17b3d0e219061829b92f5d16b718324
+size 1383

run-2/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05693c9e2cbfa5ac5dbaf1eeba155d0344ffbdce834e134e850482a6325ebb44
+size 1465

run-2/checkpoint-2000/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 0.7884819842273197,
+  "best_model_checkpoint": "./results/run-2/checkpoint-2000",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.6001648902893066,
+      "learning_rate": 3.1887409174919234e-06,
+      "loss": 0.0412,
+      "step": 100
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6239789128303528,
+      "learning_rate": 6.409691339200936e-06,
+      "loss": 0.1091,
+      "step": 200
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.6479267477989197,
+      "learning_rate": 9.63064176090995e-06,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 20.527082443237305,
+      "learning_rate": 1.054959200884952e-05,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8853731751441956,
+      "learning_rate": 1.0481970753745042e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.839735507965088,
+      "learning_rate": 1.0414349498640566e-05,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 2.7137391567230225,
+      "learning_rate": 1.0346728243536088e-05,
+      "loss": 0.0284,
+      "step": 700
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6026535630226135,
+      "learning_rate": 1.027910698843161e-05,
+      "loss": 0.1612,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.5444966554641724,
+      "learning_rate": 1.0211485733327134e-05,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2413469552993774,
+      "learning_rate": 1.0143864478222655e-05,
+      "loss": 0.0986,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_economic_inequality_accuracy": 0.8047858942065491,
+      "eval_economic_inequality_f1": 0.7538941327354425,
+      "eval_economic_policy_benefits_accuracy": 0.8282828282828283,
+      "eval_economic_policy_benefits_f1": 0.764129475069552,
+      "eval_ethnic_boundaries_accuracy": 0.9493464052287581,
+      "eval_ethnic_boundaries_f1": 0.9281293325410972,
+      "eval_language_policy_accuracy": 0.7058823529411765,
+      "eval_language_policy_f1": 0.6071428571428571,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.8888888888888888,
+      "eval_mother_tongue_education_f1": 0.837037037037037,
+      "eval_overall_accuracy": 0.8390088178776338,
+      "eval_overall_f1": 0.7839408748610676,
+      "eval_religion_ethnic_identity_accuracy": 0.8568665377176016,
+      "eval_religion_ethnic_identity_f1": 0.8133124146404199,
+      "eval_runtime": 4.4593,
+      "eval_samples_per_second": 897.004,
+      "eval_steps_per_second": 56.063,
+      "step": 1000
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.5792437195777893,
+      "learning_rate": 1.0076243223118178e-05,
+      "loss": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 8.802961349487305,
+      "learning_rate": 1.0008621968013701e-05,
+      "loss": 0.0297,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 3.981771469116211,
+      "learning_rate": 9.941000712909224e-06,
+      "loss": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.9215607047080994,
+      "learning_rate": 9.873379457804745e-06,
+      "loss": 0.263,
+      "step": 1400
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.5474179983139038,
+      "learning_rate": 9.805758202700268e-06,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.1813520193099976,
+      "learning_rate": 9.738136947595791e-06,
+      "loss": 0.0,
+      "step": 1600
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 5.511495113372803,
+      "learning_rate": 9.670515692491313e-06,
+      "loss": 0.0037,
+      "step": 1700
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 3.1629152297973633,
+      "learning_rate": 9.602894437386836e-06,
+      "loss": 0.0027,
+      "step": 1800
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.6996293663978577,
+      "learning_rate": 9.535273182282359e-06,
+      "loss": 19.1531,
+      "step": 1900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3346213102340698,
+      "learning_rate": 9.467651927177882e-06,
+      "loss": 2.9418,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_economic_inequality_accuracy": 0.7896725440806045,
+      "eval_economic_inequality_f1": 0.7951291586358689,
+      "eval_economic_policy_benefits_accuracy": 0.8148148148148148,
+      "eval_economic_policy_benefits_f1": 0.8131577832835695,
+      "eval_ethnic_boundaries_accuracy": 0.9264705882352942,
+      "eval_ethnic_boundaries_f1": 0.9324831159457648,
+      "eval_language_policy_accuracy": 0.7058823529411765,
+      "eval_language_policy_f1": 0.6071428571428571,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.7407407407407408,
+      "eval_overall_accuracy": 0.8103022392805538,
+      "eval_overall_f1": 0.7884819842273197,
+      "eval_religion_ethnic_identity_accuracy": 0.8471953578336557,
+      "eval_religion_ethnic_identity_f1": 0.8422382496151178,
+      "eval_runtime": 4.499,
+      "eval_samples_per_second": 889.087,
+      "eval_steps_per_second": 55.568,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 16000,
+  "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": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8420763303936000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 2,
+    "learning_rate": 1.0596926887422654e-05,
+    "num_train_epochs": 16,
+    "per_device_train_batch_size": 8,
+    "warmup_steps": 329,
+    "weight_decay": 0.059185379025811405
+  }
+}

run-2/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822a4a47339dd0b384da8628d960a86b7107ee8196c01d2a9c3866ddc7aa4cd5
+size 5777