Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97687f5fed50ebc5579f2887c4a528f3caa14d8822166df6c145698780fc26c1
+oid sha256:93a55419d375b6f555dcce0afc4f5d7ccb7609f57b3ef5ca045ca3aa20627b19
 size 438100144

run-4/checkpoint-1200/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-4/checkpoint-1200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a55419d375b6f555dcce0afc4f5d7ccb7609f57b3ef5ca045ca3aa20627b19
+size 438100144

run-4/checkpoint-1200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0aa85f20545a4130eb9b81544cf037e4906948993b9b138830e7893fe9561a1
+size 876321402

run-4/checkpoint-1200/rng_state.pth

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

run-4/checkpoint-1200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942cfd7aded7d16363d1ae1a2911c01ef4e25f3c70ed059c88f1845d9b6c24dc
+size 988

run-4/checkpoint-1200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb55480e111ec4cb2dfeeb267f1e8d6764a7a1688d3a8485c58779a12209d4b
+size 1064

run-4/checkpoint-1200/trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_global_step": 1200,
+  "best_metric": 0.9285199435647921,
+  "best_model_checkpoint": "./results/run-4/checkpoint-1200",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16673614005835766,
+      "grad_norm": 1.7758623361587524,
+      "learning_rate": 1e-05,
+      "loss": 1.3361,
+      "step": 100
+    },
+    {
+      "epoch": 0.3334722801167153,
+      "grad_norm": 0.6607375144958496,
+      "learning_rate": 2e-05,
+      "loss": 0.5099,
+      "step": 200
+    },
+    {
+      "epoch": 0.5002084201750729,
+      "grad_norm": 0.5690075159072876,
+      "learning_rate": 3e-05,
+      "loss": 0.4223,
+      "step": 300
+    },
+    {
+      "epoch": 0.6669445602334306,
+      "grad_norm": 0.848582923412323,
+      "learning_rate": 4e-05,
+      "loss": 0.3466,
+      "step": 400
+    },
+    {
+      "epoch": 0.8336807002917882,
+      "grad_norm": 0.7310414910316467,
+      "learning_rate": 5e-05,
+      "loss": 0.3032,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5762994289398193,
+      "learning_rate": 4.7995991983967934e-05,
+      "loss": 0.2757,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_administration_accuracy": 0.9163018553262455,
+      "eval_administration_f1": 0.8799341161157713,
+      "eval_corruption_accuracy": 0.9427767354596623,
+      "eval_corruption_f1": 0.9297320702956003,
+      "eval_democracy_accuracy": 0.9418386491557224,
+      "eval_democracy_f1": 0.9228010908644549,
+      "eval_development_accuracy": 0.8867000208463623,
+      "eval_development_f1": 0.8490864044420574,
+      "eval_economy_accuracy": 0.9122368146758391,
+      "eval_economy_f1": 0.8967581427500766,
+      "eval_education_accuracy": 0.9583072753804461,
+      "eval_education_f1": 0.9515050567699045,
+      "eval_environment_accuracy": 0.9754012924744632,
+      "eval_environment_f1": 0.971384333060466,
+      "eval_instability_accuracy": 0.924119241192412,
+      "eval_instability_f1": 0.8935408759758452,
+      "eval_leadership_accuracy": 0.7805920366895976,
+      "eval_leadership_f1": 0.7320671383079426,
+      "eval_loss": 0.26127132773399353,
+      "eval_overall_accuracy": 0.9182127718713086,
+      "eval_overall_f1": 0.8968188861118868,
+      "eval_race_accuracy": 0.9360016677089847,
+      "eval_race_f1": 0.9209694401775296,
+      "eval_religion_accuracy": 0.9441317490097978,
+      "eval_religion_f1": 0.9328887566718251,
+      "eval_runtime": 10.8983,
+      "eval_safety_accuracy": 0.9001459245361685,
+      "eval_safety_f1": 0.8811592079111662,
+      "eval_samples_per_second": 880.318,
+      "eval_steps_per_second": 55.054,
+      "step": 600
+    },
+    {
+      "epoch": 1.1667361400583576,
+      "grad_norm": 0.6828027367591858,
+      "learning_rate": 4.599198396793588e-05,
+      "loss": 0.2396,
+      "step": 700
+    },
+    {
+      "epoch": 1.3334722801167154,
+      "grad_norm": 0.67964106798172,
+      "learning_rate": 4.398797595190381e-05,
+      "loss": 0.2312,
+      "step": 800
+    },
+    {
+      "epoch": 1.500208420175073,
+      "grad_norm": 0.7818251252174377,
+      "learning_rate": 4.198396793587174e-05,
+      "loss": 0.2237,
+      "step": 900
+    },
+    {
+      "epoch": 1.6669445602334307,
+      "grad_norm": 0.8807923197746277,
+      "learning_rate": 3.997995991983968e-05,
+      "loss": 0.2085,
+      "step": 1000
+    },
+    {
+      "epoch": 1.8336807002917883,
+      "grad_norm": 0.8586667776107788,
+      "learning_rate": 3.797595190380762e-05,
+      "loss": 0.2007,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9014652371406555,
+      "learning_rate": 3.5971943887775555e-05,
+      "loss": 0.2,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_administration_accuracy": 0.9375651448822181,
+      "eval_administration_f1": 0.9290316070134363,
+      "eval_corruption_accuracy": 0.9589326662497394,
+      "eval_corruption_f1": 0.9550373529738804,
+      "eval_democracy_accuracy": 0.9521575984990619,
+      "eval_democracy_f1": 0.9433460958983528,
+      "eval_development_accuracy": 0.9138002918490723,
+      "eval_development_f1": 0.8974478772752896,
+      "eval_economy_accuracy": 0.9307900771315405,
+      "eval_economy_f1": 0.9241148503263762,
+      "eval_education_accuracy": 0.9664373566812591,
+      "eval_education_f1": 0.9649731388208568,
+      "eval_environment_accuracy": 0.9822805920366896,
+      "eval_environment_f1": 0.9806789699363689,
+      "eval_instability_accuracy": 0.9471544715447154,
+      "eval_instability_f1": 0.9400721946847931,
+      "eval_leadership_accuracy": 0.8124869710235564,
+      "eval_leadership_f1": 0.7871605097392734,
+      "eval_loss": 0.20422659814357758,
+      "eval_overall_accuracy": 0.9359582377875061,
+      "eval_overall_f1": 0.9285199435647921,
+      "eval_race_accuracy": 0.9536168438607463,
+      "eval_race_f1": 0.950384319474048,
+      "eval_religion_accuracy": 0.9576818845111528,
+      "eval_religion_f1": 0.956169902275164,
+      "eval_runtime": 11.0011,
+      "eval_safety_accuracy": 0.9185949551803211,
+      "eval_safety_f1": 0.913822504359663,
+      "eval_samples_per_second": 872.094,
+      "eval_steps_per_second": 54.54,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2995,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 2.020053452075827e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 5e-05,
+    "num_train_epochs": 5
+  }
+}

run-4/checkpoint-1200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23c4b505069b659bf843cf83d2a0a253f99487d90fb9c81ceef3ac1152d69eb
+size 5368