Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950b404fc8b9ba00d75eb9b54361601d892df46c5df20204e1b401f14e8ab925
+oid sha256:61b4f741e6da4a5f3ceb0090ea4bb6ff8bd986f5d0d25dba0202dc9e575ddc3b
 size 438100144

run-0/checkpoint-1800/config.json

@@ -0,0 +1,125 @@
+{
+  "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",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31",
+    "32": "LABEL_32",
+    "33": "LABEL_33",
+    "34": "LABEL_34",
+    "35": "LABEL_35",
+    "36": "LABEL_36",
+    "37": "LABEL_37",
+    "38": "LABEL_38",
+    "39": "LABEL_39",
+    "40": "LABEL_40",
+    "41": "LABEL_41",
+    "42": "LABEL_42",
+    "43": "LABEL_43",
+    "44": "LABEL_44",
+    "45": "LABEL_45",
+    "46": "LABEL_46",
+    "47": "LABEL_47"
+  },
+  "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_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_32": 32,
+    "LABEL_33": 33,
+    "LABEL_34": 34,
+    "LABEL_35": 35,
+    "LABEL_36": 36,
+    "LABEL_37": 37,
+    "LABEL_38": 38,
+    "LABEL_39": 39,
+    "LABEL_4": 4,
+    "LABEL_40": 40,
+    "LABEL_41": 41,
+    "LABEL_42": 42,
+    "LABEL_43": 43,
+    "LABEL_44": 44,
+    "LABEL_45": 45,
+    "LABEL_46": 46,
+    "LABEL_47": 47,
+    "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": "4.50.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1800/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b4f741e6da4a5f3ceb0090ea4bb6ff8bd986f5d0d25dba0202dc9e575ddc3b
+size 438100144

run-0/checkpoint-1800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a38c6c83cd5b2da7ce730f43be4c278d33033e51ee4dac8e270e62312b12d17
+size 876321402

run-0/checkpoint-1800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714a982d29c5cad10f1f61ff55536b945838337379aaedf05d2dafc18b602ef9
+size 14244

run-0/checkpoint-1800/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c82eba5f0b1f93e15ecc4950174958b6ab54879225c616d56316b6b87157e59
+size 988

run-0/checkpoint-1800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7845c736d1a82f7133cf9d090efb4f55804103981e69b939d12fd2af5fbbf90
+size 1064

run-0/checkpoint-1800/trainer_state.json

@@ -0,0 +1,275 @@
+{
+  "best_global_step": 1800,
+  "best_metric": 0.9346706078324559,
+  "best_model_checkpoint": "./results/run-0/checkpoint-1800",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1800,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16673614005835766,
+      "grad_norm": 2.8743319511413574,
+      "learning_rate": 6e-06,
+      "loss": 1.4727,
+      "step": 100
+    },
+    {
+      "epoch": 0.3334722801167153,
+      "grad_norm": 0.8747783899307251,
+      "learning_rate": 1.2e-05,
+      "loss": 0.617,
+      "step": 200
+    },
+    {
+      "epoch": 0.5002084201750729,
+      "grad_norm": 0.7884620428085327,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4493,
+      "step": 300
+    },
+    {
+      "epoch": 0.6669445602334306,
+      "grad_norm": 0.8924545645713806,
+      "learning_rate": 2.4e-05,
+      "loss": 0.3876,
+      "step": 400
+    },
+    {
+      "epoch": 0.8336807002917882,
+      "grad_norm": 0.8031777739524841,
+      "learning_rate": 3e-05,
+      "loss": 0.3361,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5999459624290466,
+      "learning_rate": 2.9453551912568308e-05,
+      "loss": 0.3004,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_administration_accuracy": 0.9140087554721701,
+      "eval_administration_f1": 0.8740363354524873,
+      "eval_corruption_accuracy": 0.9370439858244737,
+      "eval_corruption_f1": 0.9192595640701061,
+      "eval_democracy_accuracy": 0.9347508859703981,
+      "eval_democracy_f1": 0.9095054688749907,
+      "eval_development_accuracy": 0.8763810715030227,
+      "eval_development_f1": 0.8253993969919758,
+      "eval_economy_accuracy": 0.9010840108401084,
+      "eval_economy_f1": 0.8737219947600353,
+      "eval_education_accuracy": 0.9571607254534084,
+      "eval_education_f1": 0.9485581438064299,
+      "eval_environment_accuracy": 0.9734208880550344,
+      "eval_environment_f1": 0.9693817386774968,
+      "eval_instability_accuracy": 0.9219303731498854,
+      "eval_instability_f1": 0.8878400653107733,
+      "eval_leadership_accuracy": 0.7652699603919116,
+      "eval_leadership_f1": 0.7080044131422123,
+      "eval_loss": 0.2839118242263794,
+      "eval_overall_accuracy": 0.9120109790841496,
+      "eval_overall_f1": 0.8849771384459072,
+      "eval_race_accuracy": 0.9283927454659162,
+      "eval_race_f1": 0.907176591968042,
+      "eval_religion_accuracy": 0.9369397540129247,
+      "eval_religion_f1": 0.9217332965382043,
+      "eval_runtime": 10.9229,
+      "eval_safety_accuracy": 0.8977485928705441,
+      "eval_safety_f1": 0.8751086517581315,
+      "eval_samples_per_second": 878.336,
+      "eval_steps_per_second": 54.93,
+      "step": 600
+    },
+    {
+      "epoch": 1.1667361400583576,
+      "grad_norm": 0.6991692781448364,
+      "learning_rate": 2.890710382513661e-05,
+      "loss": 0.2667,
+      "step": 700
+    },
+    {
+      "epoch": 1.3334722801167154,
+      "grad_norm": 0.6808522343635559,
+      "learning_rate": 2.836065573770492e-05,
+      "loss": 0.2573,
+      "step": 800
+    },
+    {
+      "epoch": 1.500208420175073,
+      "grad_norm": 0.8924445509910583,
+      "learning_rate": 2.7814207650273226e-05,
+      "loss": 0.2447,
+      "step": 900
+    },
+    {
+      "epoch": 1.6669445602334307,
+      "grad_norm": 0.9563364386558533,
+      "learning_rate": 2.7267759562841533e-05,
+      "loss": 0.2282,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8336807002917883,
+      "grad_norm": 0.8881794810295105,
+      "learning_rate": 2.6721311475409837e-05,
+      "loss": 0.2217,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.2946265935897827,
+      "learning_rate": 2.6174863387978144e-05,
+      "loss": 0.2197,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_administration_accuracy": 0.9364185949551803,
+      "eval_administration_f1": 0.9264664888238818,
+      "eval_corruption_accuracy": 0.9562226391494684,
+      "eval_corruption_f1": 0.9508457468931831,
+      "eval_democracy_accuracy": 0.947571398790911,
+      "eval_democracy_f1": 0.9355668234958175,
+      "eval_development_accuracy": 0.9049405878674172,
+      "eval_development_f1": 0.8818640965909518,
+      "eval_economy_accuracy": 0.924119241192412,
+      "eval_economy_f1": 0.9144295841480942,
+      "eval_education_accuracy": 0.9669585157390036,
+      "eval_education_f1": 0.9649722301773493,
+      "eval_environment_accuracy": 0.981029810298103,
+      "eval_environment_f1": 0.9786767163906938,
+      "eval_instability_accuracy": 0.9422555764019178,
+      "eval_instability_f1": 0.9320449284299851,
+      "eval_leadership_accuracy": 0.8006045445069835,
+      "eval_leadership_f1": 0.7682063698028097,
+      "eval_loss": 0.21895167231559753,
+      "eval_overall_accuracy": 0.9317629073726635,
+      "eval_overall_f1": 0.9213111296186804,
+      "eval_race_accuracy": 0.9516364394413175,
+      "eval_race_f1": 0.9462871699636376,
+      "eval_religion_accuracy": 0.9586199708150928,
+      "eval_religion_f1": 0.9568464833874664,
+      "eval_runtime": 10.9295,
+      "eval_safety_accuracy": 0.9107775693141547,
+      "eval_safety_f1": 0.8995269173202963,
+      "eval_samples_per_second": 877.809,
+      "eval_steps_per_second": 54.897,
+      "step": 1200
+    },
+    {
+      "epoch": 2.1667361400583576,
+      "grad_norm": 0.8773576021194458,
+      "learning_rate": 2.5628415300546447e-05,
+      "loss": 0.1841,
+      "step": 1300
+    },
+    {
+      "epoch": 2.333472280116715,
+      "grad_norm": 0.7541666030883789,
+      "learning_rate": 2.5081967213114754e-05,
+      "loss": 0.1757,
+      "step": 1400
+    },
+    {
+      "epoch": 2.500208420175073,
+      "grad_norm": 0.9500707983970642,
+      "learning_rate": 2.453551912568306e-05,
+      "loss": 0.1776,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6669445602334307,
+      "grad_norm": 0.8599845170974731,
+      "learning_rate": 2.398907103825137e-05,
+      "loss": 0.1757,
+      "step": 1600
+    },
+    {
+      "epoch": 2.8336807002917883,
+      "grad_norm": 1.0130952596664429,
+      "learning_rate": 2.3442622950819672e-05,
+      "loss": 0.1675,
+      "step": 1700
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.4208967685699463,
+      "learning_rate": 2.289617486338798e-05,
+      "loss": 0.1664,
+      "step": 1800
+    },
+    {
+      "epoch": 3.0,
+      "eval_administration_accuracy": 0.940379403794038,
+      "eval_administration_f1": 0.9332522249114288,
+      "eval_corruption_accuracy": 0.9609130706691682,
+      "eval_corruption_f1": 0.9591571276198037,
+      "eval_democracy_accuracy": 0.9572649572649573,
+      "eval_democracy_f1": 0.951957009924363,
+      "eval_development_accuracy": 0.9184907233687721,
+      "eval_development_f1": 0.909063933465515,
+      "eval_economy_accuracy": 0.9327704815509693,
+      "eval_economy_f1": 0.9291641275521808,
+      "eval_education_accuracy": 0.967479674796748,
+      "eval_education_f1": 0.965512166473417,
+      "eval_environment_accuracy": 0.9835313737752762,
+      "eval_environment_f1": 0.9820983135141137,
+      "eval_instability_accuracy": 0.9481967896602043,
+      "eval_instability_f1": 0.9444250756726008,
+      "eval_leadership_accuracy": 0.8285386700020846,
+      "eval_leadership_f1": 0.8147910628849035,
+      "eval_loss": 0.19577622413635254,
+      "eval_overall_accuracy": 0.9393283996942533,
+      "eval_overall_f1": 0.9346706078324559,
+      "eval_race_accuracy": 0.9551803210339795,
+      "eval_race_f1": 0.9521792365558912,
+      "eval_religion_accuracy": 0.9598707525536794,
+      "eval_religion_f1": 0.9582958411796174,
+      "eval_runtime": 10.979,
+      "eval_safety_accuracy": 0.9193245778611632,
+      "eval_safety_f1": 0.9161511742356354,
+      "eval_samples_per_second": 873.853,
+      "eval_steps_per_second": 54.65,
+      "step": 1800
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5990,
+  "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": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.030080178113741e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 3e-05,
+    "num_train_epochs": 10
+  }
+}

run-0/checkpoint-1800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c268ed019d067f52ee3b6ec06e4f32fa79f82839c235ad890040984c5ac1cf
+size 5368