Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8d6559adcf9e224d38864a1b5e5a1403e35e26169912ed2c48d05a8c54ac1d
+oid sha256:9999cc7240ed8263bf787b2aa642ae768be07d5dc6cb57accbab53463abfb27a
 size 438100144

run-1/checkpoint-4798/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-1/checkpoint-4798/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9999cc7240ed8263bf787b2aa642ae768be07d5dc6cb57accbab53463abfb27a
+size 438100144

run-1/checkpoint-4798/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c4f87270ecdb46a4ed80e28fd75b22e5aa5dd4dea4d573451f99c493c1fa7e
+size 876321402

run-1/checkpoint-4798/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb0e97c1d172b9504c5f98cbb1b58f207f6c16ca972b5327c99a6e610606e7e8
+size 14244

run-1/checkpoint-4798/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b2ba52a3c9a07d0137e6b249732c5d0eacfa68b875f8de3eda87d473ed1f11
+size 988

run-1/checkpoint-4798/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558e9c8611ea933eb52ce7a249f738b2c0c8cd97c3d095551f22599e7829ad33
+size 1064

run-1/checkpoint-4798/trainer_state.json

@@ -0,0 +1,444 @@
+{
+  "best_global_step": 4798,
+  "best_metric": 0.9342598776015526,
+  "best_model_checkpoint": "./results/run-1/checkpoint-4798",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4798,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041684035014589414,
+      "grad_norm": 2.362386465072632,
+      "learning_rate": 9.900000000000002e-06,
+      "loss": 1.3944,
+      "step": 100
+    },
+    {
+      "epoch": 0.08336807002917883,
+      "grad_norm": 0.7483571767807007,
+      "learning_rate": 1.9900000000000003e-05,
+      "loss": 0.5576,
+      "step": 200
+    },
+    {
+      "epoch": 0.12505210504376824,
+      "grad_norm": 0.8563070297241211,
+      "learning_rate": 2.9900000000000002e-05,
+      "loss": 0.4502,
+      "step": 300
+    },
+    {
+      "epoch": 0.16673614005835766,
+      "grad_norm": 0.7200814485549927,
+      "learning_rate": 3.99e-05,
+      "loss": 0.388,
+      "step": 400
+    },
+    {
+      "epoch": 0.20842017507294705,
+      "grad_norm": 1.4553083181381226,
+      "learning_rate": 4.99e-05,
+      "loss": 0.3508,
+      "step": 500
+    },
+    {
+      "epoch": 0.25010421008753647,
+      "grad_norm": 0.9915399551391602,
+      "learning_rate": 4.978927203065135e-05,
+      "loss": 0.3186,
+      "step": 600
+    },
+    {
+      "epoch": 0.29178824510212586,
+      "grad_norm": 0.9978141188621521,
+      "learning_rate": 4.957641549595573e-05,
+      "loss": 0.3087,
+      "step": 700
+    },
+    {
+      "epoch": 0.3334722801167153,
+      "grad_norm": 1.3709461688995361,
+      "learning_rate": 4.936355896126011e-05,
+      "loss": 0.2976,
+      "step": 800
+    },
+    {
+      "epoch": 0.3751563151313047,
+      "grad_norm": 1.82745361328125,
+      "learning_rate": 4.91507024265645e-05,
+      "loss": 0.28,
+      "step": 900
+    },
+    {
+      "epoch": 0.4168403501458941,
+      "grad_norm": 1.2072925567626953,
+      "learning_rate": 4.893784589186888e-05,
+      "loss": 0.2751,
+      "step": 1000
+    },
+    {
+      "epoch": 0.45852438516048355,
+      "grad_norm": 1.0433937311172485,
+      "learning_rate": 4.872498935717327e-05,
+      "loss": 0.2712,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5002084201750729,
+      "grad_norm": 1.1097549200057983,
+      "learning_rate": 4.851213282247765e-05,
+      "loss": 0.2909,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5418924551896623,
+      "grad_norm": 1.2917771339416504,
+      "learning_rate": 4.8299276287782034e-05,
+      "loss": 0.2501,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5835764902042517,
+      "grad_norm": 0.9812286496162415,
+      "learning_rate": 4.808641975308642e-05,
+      "loss": 0.2621,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6252605252188412,
+      "grad_norm": 1.1786612272262573,
+      "learning_rate": 4.7873563218390804e-05,
+      "loss": 0.2435,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6669445602334306,
+      "grad_norm": 1.4759145975112915,
+      "learning_rate": 4.766070668369519e-05,
+      "loss": 0.2398,
+      "step": 1600
+    },
+    {
+      "epoch": 0.70862859524802,
+      "grad_norm": 1.5548242330551147,
+      "learning_rate": 4.744785014899958e-05,
+      "loss": 0.2432,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7503126302626094,
+      "grad_norm": 1.9005539417266846,
+      "learning_rate": 4.723499361430396e-05,
+      "loss": 0.2351,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7919966652771988,
+      "grad_norm": 1.5831588506698608,
+      "learning_rate": 4.702213707960835e-05,
+      "loss": 0.2378,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8336807002917882,
+      "grad_norm": 1.5482088327407837,
+      "learning_rate": 4.680928054491273e-05,
+      "loss": 0.2271,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8753647353063777,
+      "grad_norm": 1.1437913179397583,
+      "learning_rate": 4.6596424010217114e-05,
+      "loss": 0.231,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9170487703209671,
+      "grad_norm": 0.7985406517982483,
+      "learning_rate": 4.63835674755215e-05,
+      "loss": 0.228,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9587328053355565,
+      "grad_norm": 1.9323142766952515,
+      "learning_rate": 4.6170710940825884e-05,
+      "loss": 0.2198,
+      "step": 2300
+    },
+    {
+      "epoch": 1.0,
+      "eval_administration_accuracy": 0.9322493224932249,
+      "eval_administration_f1": 0.9122911143651031,
+      "eval_corruption_accuracy": 0.9560141755263707,
+      "eval_corruption_f1": 0.9517304794081561,
+      "eval_democracy_accuracy": 0.9505941213258287,
+      "eval_democracy_f1": 0.9401838742047087,
+      "eval_development_accuracy": 0.9118198874296435,
+      "eval_development_f1": 0.9003553411809495,
+      "eval_economy_accuracy": 0.9264123410464874,
+      "eval_economy_f1": 0.9202465382357672,
+      "eval_education_accuracy": 0.9643527204502814,
+      "eval_education_f1": 0.9615509617901187,
+      "eval_environment_accuracy": 0.9799874921826142,
+      "eval_environment_f1": 0.9786142985651582,
+      "eval_instability_accuracy": 0.9417344173441734,
+      "eval_instability_f1": 0.9340921018628459,
+      "eval_leadership_accuracy": 0.8085261621846987,
+      "eval_leadership_f1": 0.7858417402549625,
+      "eval_loss": 0.21971678733825684,
+      "eval_overall_accuracy": 0.9324317281634354,
+      "eval_overall_f1": 0.9244250028140656,
+      "eval_race_accuracy": 0.9508025849489264,
+      "eval_race_f1": 0.9481714649378918,
+      "eval_religion_accuracy": 0.9530956848030019,
+      "eval_religion_f1": 0.9518106778632144,
+      "eval_runtime": 10.9084,
+      "eval_safety_accuracy": 0.9135918282259746,
+      "eval_safety_f1": 0.9082114410999095,
+      "eval_samples_per_second": 879.505,
+      "eval_steps_per_second": 55.003,
+      "step": 2399
+    },
+    {
+      "epoch": 1.0004168403501459,
+      "grad_norm": 1.2817295789718628,
+      "learning_rate": 4.5957854406130265e-05,
+      "loss": 0.2397,
+      "step": 2400
+    },
+    {
+      "epoch": 1.0421008753647354,
+      "grad_norm": 1.3623204231262207,
+      "learning_rate": 4.5744997871434654e-05,
+      "loss": 0.1885,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0837849103793247,
+      "grad_norm": 1.2534806728363037,
+      "learning_rate": 4.553214133673904e-05,
+      "loss": 0.1843,
+      "step": 2600
+    },
+    {
+      "epoch": 1.1254689453939142,
+      "grad_norm": 1.2860488891601562,
+      "learning_rate": 4.5319284802043424e-05,
+      "loss": 0.1817,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1671529804085035,
+      "grad_norm": 1.2887414693832397,
+      "learning_rate": 4.510642826734781e-05,
+      "loss": 0.1798,
+      "step": 2800
+    },
+    {
+      "epoch": 1.208837015423093,
+      "grad_norm": 1.973421335220337,
+      "learning_rate": 4.4893571732652194e-05,
+      "loss": 0.1878,
+      "step": 2900
+    },
+    {
+      "epoch": 1.2505210504376825,
+      "grad_norm": 0.7910940051078796,
+      "learning_rate": 4.468071519795658e-05,
+      "loss": 0.182,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2922050854522718,
+      "grad_norm": 1.7422680854797363,
+      "learning_rate": 4.4467858663260964e-05,
+      "loss": 0.1833,
+      "step": 3100
+    },
+    {
+      "epoch": 1.3338891204668613,
+      "grad_norm": 1.1493451595306396,
+      "learning_rate": 4.4255002128565345e-05,
+      "loss": 0.1766,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3755731554814505,
+      "grad_norm": 2.179731845855713,
+      "learning_rate": 4.4042145593869734e-05,
+      "loss": 0.1785,
+      "step": 3300
+    },
+    {
+      "epoch": 1.41725719049604,
+      "grad_norm": 1.5773117542266846,
+      "learning_rate": 4.3829289059174115e-05,
+      "loss": 0.1901,
+      "step": 3400
+    },
+    {
+      "epoch": 1.4589412255106295,
+      "grad_norm": 2.4681854248046875,
+      "learning_rate": 4.3616432524478504e-05,
+      "loss": 0.1833,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5006252605252188,
+      "grad_norm": 2.391803503036499,
+      "learning_rate": 4.340357598978289e-05,
+      "loss": 0.1677,
+      "step": 3600
+    },
+    {
+      "epoch": 1.5423092955398081,
+      "grad_norm": 0.8182645440101624,
+      "learning_rate": 4.3190719455087274e-05,
+      "loss": 0.1666,
+      "step": 3700
+    },
+    {
+      "epoch": 1.5839933305543976,
+      "grad_norm": 1.2136952877044678,
+      "learning_rate": 4.297786292039166e-05,
+      "loss": 0.1787,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6256773655689871,
+      "grad_norm": 2.435816764831543,
+      "learning_rate": 4.2765006385696044e-05,
+      "loss": 0.1678,
+      "step": 3900
+    },
+    {
+      "epoch": 1.6673614005835766,
+      "grad_norm": 1.5172932147979736,
+      "learning_rate": 4.2552149851000425e-05,
+      "loss": 0.1779,
+      "step": 4000
+    },
+    {
+      "epoch": 1.709045435598166,
+      "grad_norm": 1.4677119255065918,
+      "learning_rate": 4.2339293316304814e-05,
+      "loss": 0.1824,
+      "step": 4100
+    },
+    {
+      "epoch": 1.7507294706127552,
+      "grad_norm": 1.8327163457870483,
+      "learning_rate": 4.2126436781609195e-05,
+      "loss": 0.1719,
+      "step": 4200
+    },
+    {
+      "epoch": 1.7924135056273447,
+      "grad_norm": 1.2324726581573486,
+      "learning_rate": 4.1913580246913584e-05,
+      "loss": 0.1592,
+      "step": 4300
+    },
+    {
+      "epoch": 1.8340975406419342,
+      "grad_norm": 3.6276469230651855,
+      "learning_rate": 4.1700723712217965e-05,
+      "loss": 0.1636,
+      "step": 4400
+    },
+    {
+      "epoch": 1.8757815756565237,
+      "grad_norm": 0.940485417842865,
+      "learning_rate": 4.148786717752235e-05,
+      "loss": 0.1639,
+      "step": 4500
+    },
+    {
+      "epoch": 1.917465610671113,
+      "grad_norm": 2.002577781677246,
+      "learning_rate": 4.127501064282674e-05,
+      "loss": 0.1756,
+      "step": 4600
+    },
+    {
+      "epoch": 1.9591496456857023,
+      "grad_norm": 2.6062567234039307,
+      "learning_rate": 4.1062154108131124e-05,
+      "loss": 0.1729,
+      "step": 4700
+    },
+    {
+      "epoch": 2.0,
+      "eval_administration_accuracy": 0.9374609130706691,
+      "eval_administration_f1": 0.9302102302828306,
+      "eval_corruption_accuracy": 0.9603919116114238,
+      "eval_corruption_f1": 0.9585025895331236,
+      "eval_democracy_accuracy": 0.9562226391494684,
+      "eval_democracy_f1": 0.9505005443286667,
+      "eval_development_accuracy": 0.9199499687304565,
+      "eval_development_f1": 0.9145013995891959,
+      "eval_economy_accuracy": 0.9319366270585783,
+      "eval_economy_f1": 0.9302256375627648,
+      "eval_education_accuracy": 0.9651865749426725,
+      "eval_education_f1": 0.9641689686262792,
+      "eval_environment_accuracy": 0.9806128830519074,
+      "eval_environment_f1": 0.9798389855050841,
+      "eval_instability_accuracy": 0.9244319366270586,
+      "eval_instability_f1": 0.9301250908302109,
+      "eval_leadership_accuracy": 0.8395872420262664,
+      "eval_leadership_f1": 0.830858580138579,
+      "eval_loss": 0.20445191860198975,
+      "eval_overall_accuracy": 0.9366791744840525,
+      "eval_overall_f1": 0.9342598776015526,
+      "eval_race_accuracy": 0.9545549301646863,
+      "eval_race_f1": 0.9531323667533257,
+      "eval_religion_accuracy": 0.9575776526996039,
+      "eval_religion_f1": 0.9560680494194458,
+      "eval_runtime": 10.9745,
+      "eval_safety_accuracy": 0.9122368146758391,
+      "eval_safety_f1": 0.9129860886491253,
+      "eval_samples_per_second": 874.208,
+      "eval_steps_per_second": 54.672,
+      "step": 4798
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 23990,
+  "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": 1.9790964629766144e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 5e-05,
+    "num_train_epochs": 10
+  }
+}

run-1/checkpoint-4798/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4312a997194e916559618a59f3bbf4e1f98c127e89ae3b7fb5162b782863b12c
+size 5368