Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfc7b91c4dd349a9fbfee77e6969e0e0fdb2ceae36cd99336d54bb57a4ded58
+oid sha256:26d45660e79eae18a1d64284246777a584fb8ee16373738db06275d022d6d302
 size 438007864

run-0/checkpoint-6000/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-0/checkpoint-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d45660e79eae18a1d64284246777a584fb8ee16373738db06275d022d6d302
+size 438007864

run-0/checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c1f923ba57a48157f78126b95da5409a7dd604bfb0fc514716c3e876dbc2e7
+size 876140043

run-0/checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:853c64a36d920f68957f9512fc79a83588307b0ec23c83a30caebc328b0f31db
+size 14645

run-0/checkpoint-6000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77fdcd5b11c0aa6b0b8ab80a017a3385c1d0bd0d4c15102fbc89a2be040e5a69
+size 1383

run-0/checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfd4d542f49f82c6c7923b41668e8af5063d7ff6f25e67b417419e910f8af45
+size 1465

run-0/checkpoint-6000/trainer_state.json

@@ -0,0 +1,536 @@
+{
+  "best_global_step": 4000,
+  "best_metric": 0.7960173130694123,
+  "best_model_checkpoint": "./results/run-0/checkpoint-4000",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.039576768875122,
+      "learning_rate": 1.447537100215313e-06,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 4.460484504699707,
+      "learning_rate": 2.9096957873014878e-06,
+      "loss": 0.0821,
+      "step": 200
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 26.84711456298828,
+      "learning_rate": 4.371854474387663e-06,
+      "loss": 0.0519,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6646966934204102,
+      "learning_rate": 5.834013161473838e-06,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.8385223150253296,
+      "learning_rate": 7.296171848560012e-06,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.9234638810157776,
+      "learning_rate": 8.758330535646188e-06,
+      "loss": 0.0,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 38.24382400512695,
+      "learning_rate": 9.9933989317167e-06,
+      "loss": 0.0,
+      "step": 700
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 42.83884811401367,
+      "learning_rate": 9.94162234536513e-06,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.8020399808883667,
+      "learning_rate": 9.889845759013559e-06,
+      "loss": 0.0,
+      "step": 900
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.86091148853302,
+      "learning_rate": 9.838069172661988e-06,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.16439934074878693,
+      "learning_rate": 9.786292586310415e-06,
+      "loss": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.752115488052368,
+      "learning_rate": 9.734515999958846e-06,
+      "loss": 0.0,
+      "step": 1200
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.5777802467346191,
+      "learning_rate": 9.682739413607275e-06,
+      "loss": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.708035945892334,
+      "learning_rate": 9.630962827255703e-06,
+      "loss": 0.0598,
+      "step": 1400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3160113990306854,
+      "learning_rate": 9.579186240904132e-06,
+      "loss": 0.0441,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2273201942443848,
+      "learning_rate": 9.527409654552563e-06,
+      "loss": 0.0,
+      "step": 1600
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 29.215551376342773,
+      "learning_rate": 9.47563306820099e-06,
+      "loss": 0.0,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.18806450068950653,
+      "learning_rate": 9.42385648184942e-06,
+      "loss": 0.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.41723617911338806,
+      "learning_rate": 9.372079895497849e-06,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.9550623893737793,
+      "learning_rate": 9.32030330914628e-06,
+      "loss": 0.0,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_economic_inequality_accuracy": 0.8047858942065491,
+      "eval_economic_inequality_f1": 0.7536914695213144,
+      "eval_economic_policy_benefits_accuracy": 0.8282828282828283,
+      "eval_economic_policy_benefits_f1": 0.7567090529234769,
+      "eval_ethnic_boundaries_accuracy": 0.9526143790849673,
+      "eval_ethnic_boundaries_f1": 0.9344984933861545,
+      "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": 0.8392311075242039,
+      "eval_overall_f1": 0.782435168791527,
+      "eval_religion_ethnic_identity_accuracy": 0.8549323017408124,
+      "eval_religion_ethnic_identity_f1": 0.8055321027383222,
+      "eval_runtime": 4.4874,
+      "eval_samples_per_second": 891.378,
+      "eval_steps_per_second": 55.711,
+      "step": 2000
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 2.762986183166504,
+      "learning_rate": 9.268526722794707e-06,
+      "loss": 0.0,
+      "step": 2100
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.5487369298934937,
+      "learning_rate": 9.216750136443136e-06,
+      "loss": 0.0,
+      "step": 2200
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 4.76751184463501,
+      "learning_rate": 9.164973550091565e-06,
+      "loss": 0.0102,
+      "step": 2300
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 2.681756019592285,
+      "learning_rate": 9.113196963739995e-06,
+      "loss": 0.0,
+      "step": 2400
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.24124185740947723,
+      "learning_rate": 9.061420377388424e-06,
+      "loss": 0.0,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.943154215812683,
+      "learning_rate": 9.009643791036853e-06,
+      "loss": 0.0,
+      "step": 2600
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 0.28053101897239685,
+      "learning_rate": 8.957867204685282e-06,
+      "loss": 0.0347,
+      "step": 2700
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.7952568531036377,
+      "learning_rate": 8.906090618333711e-06,
+      "loss": 0.4436,
+      "step": 2800
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 3.859933614730835,
+      "learning_rate": 8.85431403198214e-06,
+      "loss": 0.0,
+      "step": 2900
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.094464898109436,
+      "learning_rate": 8.80253744563057e-06,
+      "loss": 0.0,
+      "step": 3000
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.5670285820960999,
+      "learning_rate": 8.750760859278999e-06,
+      "loss": 0.0,
+      "step": 3100
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.8412418365478516,
+      "learning_rate": 8.698984272927428e-06,
+      "loss": 0.0,
+      "step": 3200
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 65.82475280761719,
+      "learning_rate": 8.647207686575855e-06,
+      "loss": 0.0,
+      "step": 3300
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 8.976615905761719,
+      "learning_rate": 8.595431100224286e-06,
+      "loss": 0.0048,
+      "step": 3400
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 126.71548461914062,
+      "learning_rate": 8.543654513872716e-06,
+      "loss": 0.0,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.595015823841095,
+      "learning_rate": 8.491877927521143e-06,
+      "loss": 0.0033,
+      "step": 3600
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 3.98215651512146,
+      "learning_rate": 8.440101341169572e-06,
+      "loss": 0.1482,
+      "step": 3700
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 3.0417540073394775,
+      "learning_rate": 8.388324754818003e-06,
+      "loss": 0.0031,
+      "step": 3800
+    },
+    {
+      "epoch": 1.95,
+      "grad_norm": 27.85649299621582,
+      "learning_rate": 8.33654816846643e-06,
+      "loss": 0.0589,
+      "step": 3900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.3094232082366943,
+      "learning_rate": 8.28477158211486e-06,
+      "loss": 0.0,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_economic_inequality_accuracy": 0.8236775818639799,
+      "eval_economic_inequality_f1": 0.8161521311449569,
+      "eval_economic_policy_benefits_accuracy": 0.835016835016835,
+      "eval_economic_policy_benefits_f1": 0.81117677081242,
+      "eval_ethnic_boundaries_accuracy": 0.9477124183006536,
+      "eval_ethnic_boundaries_f1": 0.9421262334088456,
+      "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": 0.8277126438976526,
+      "eval_overall_f1": 0.7960173130694123,
+      "eval_religion_ethnic_identity_accuracy": 0.8762088974854932,
+      "eval_religion_ethnic_identity_f1": 0.8587651451666537,
+      "eval_runtime": 4.4654,
+      "eval_samples_per_second": 895.775,
+      "eval_steps_per_second": 55.986,
+      "step": 4000
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 8.547677040100098,
+      "learning_rate": 8.232994995763289e-06,
+      "loss": 0.0,
+      "step": 4100
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 117.06266784667969,
+      "learning_rate": 8.181218409411718e-06,
+      "loss": 0.0,
+      "step": 4200
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.19274334609508514,
+      "learning_rate": 8.129441823060147e-06,
+      "loss": 0.0,
+      "step": 4300
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 1.0360257625579834,
+      "learning_rate": 8.077665236708576e-06,
+      "loss": 0.0,
+      "step": 4400
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.08476172387599945,
+      "learning_rate": 8.025888650357006e-06,
+      "loss": 0.0,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.08015169203281403,
+      "learning_rate": 7.974112064005435e-06,
+      "loss": 0.0,
+      "step": 4600
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 0.22844159603118896,
+      "learning_rate": 7.922335477653864e-06,
+      "loss": 0.0006,
+      "step": 4700
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.08015509694814682,
+      "learning_rate": 7.870558891302293e-06,
+      "loss": 0.0006,
+      "step": 4800
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 5.426948547363281,
+      "learning_rate": 7.818782304950722e-06,
+      "loss": 0.0,
+      "step": 4900
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.022730231285095215,
+      "learning_rate": 7.767005718599151e-06,
+      "loss": 0.0,
+      "step": 5000
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 5.662137508392334,
+      "learning_rate": 7.71522913224758e-06,
+      "loss": 0.0,
+      "step": 5100
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.05326724052429199,
+      "learning_rate": 7.66345254589601e-06,
+      "loss": 0.0,
+      "step": 5200
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 2.7219042778015137,
+      "learning_rate": 7.611675959544438e-06,
+      "loss": 0.0003,
+      "step": 5300
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 4.045983791351318,
+      "learning_rate": 7.559899373192868e-06,
+      "loss": 0.0,
+      "step": 5400
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.17610976099967957,
+      "learning_rate": 7.5081227868412964e-06,
+      "loss": 0.0,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.03921931982040405,
+      "learning_rate": 7.456346200489726e-06,
+      "loss": 0.0,
+      "step": 5600
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 3.3493025302886963,
+      "learning_rate": 7.404569614138155e-06,
+      "loss": 0.0,
+      "step": 5700
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.17839455604553223,
+      "learning_rate": 7.352793027786584e-06,
+      "loss": 0.0,
+      "step": 5800
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.01533100288361311,
+      "learning_rate": 7.301016441435013e-06,
+      "loss": 0.0,
+      "step": 5900
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.6168579459190369,
+      "learning_rate": 7.249239855083442e-06,
+      "loss": 0.0,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_economic_inequality_accuracy": 0.818639798488665,
+      "eval_economic_inequality_f1": 0.8128041981528128,
+      "eval_economic_policy_benefits_accuracy": 0.8686868686868687,
+      "eval_economic_policy_benefits_f1": 0.849679269639744,
+      "eval_ethnic_boundaries_accuracy": 0.9379084967320261,
+      "eval_ethnic_boundaries_f1": 0.9377319200237987,
+      "eval_language_policy_accuracy": 0.6470588235294118,
+      "eval_language_policy_f1": 0.5673202614379085,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.7407407407407408,
+      "eval_overall_accuracy": 0.8181454231515234,
+      "eval_overall_f1": 0.794560338168735,
+      "eval_religion_ethnic_identity_accuracy": 0.8588007736943907,
+      "eval_religion_ethnic_identity_f1": 0.8590856390174055,
+      "eval_runtime": 4.4722,
+      "eval_samples_per_second": 894.406,
+      "eval_steps_per_second": 55.9,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 20000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 1.2631144955904e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 1.0001165419669436e-05,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 8,
+    "warmup_steps": 684,
+    "weight_decay": 0.07522641729243515
+  }
+}

run-0/checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f9f98f39dc377d902877813dc8cf2a83bc674db97d85b5237e673a48a7375f
+size 5777