Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5affcb78955f2047915ab0b3fb976eb563782fb706089691c2dfe18311c14ed
+oid sha256:244c32ef5c6373ef12161581b12f3c30ace5bf6c6e7a386d865a53ade913778d
 size 438007864

run-3/checkpoint-1500/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-3/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:244c32ef5c6373ef12161581b12f3c30ace5bf6c6e7a386d865a53ade913778d
+size 438007864

run-3/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6bd8e9aa7af2d50ff7a24fe7c9dfd22b1cd4c647812cd873e2e683f6b49baa
+size 876140043

run-3/checkpoint-1500/rng_state.pth

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

run-3/checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75757084f18ff187622eb1e42b0c6cdf1c89410ace1d2020230f8b8e51f77845
+size 1383

run-3/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:165f1dc311a18c6a15d2bcd1699ec421194889f2fe4640991aead581e8361342
+size 1465

run-3/checkpoint-1500/trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_global_step": 1500,
+  "best_metric": 0.7817611579593701,
+  "best_model_checkpoint": "./results/run-3/checkpoint-1500",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3840266466140747,
+      "learning_rate": 5.623773985869002e-05,
+      "loss": 0.4015,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 36.44963455200195,
+      "learning_rate": 6.805455705058522e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6683640480041504,
+      "learning_rate": 6.718217457333122e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7861915230751038,
+      "learning_rate": 6.630979209607721e-05,
+      "loss": 0.1644,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.053349256515503,
+      "learning_rate": 6.54374096188232e-05,
+      "loss": 0.0025,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_economic_inequality_accuracy": 0.7770780856423174,
+      "eval_economic_inequality_f1": 0.6795991195482776,
+      "eval_economic_policy_benefits_accuracy": 0.8215488215488216,
+      "eval_economic_policy_benefits_f1": 0.7410643713786043,
+      "eval_ethnic_boundaries_accuracy": 0.946078431372549,
+      "eval_ethnic_boundaries_f1": 0.9198646713093299,
+      "eval_language_policy_accuracy": 0.6764705882352942,
+      "eval_language_policy_f1": 0.545923632610939,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.6805555555555556,
+      "eval_overall_accuracy": 0.8064020197505432,
+      "eval_overall_f1": 0.7222001215424422,
+      "eval_religion_ethnic_identity_accuracy": 0.839458413926499,
+      "eval_religion_ethnic_identity_f1": 0.7661933788519465,
+      "eval_runtime": 4.4769,
+      "eval_samples_per_second": 893.468,
+      "eval_steps_per_second": 55.842,
+      "step": 500
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 4.278098106384277,
+      "learning_rate": 6.456502714156919e-05,
+      "loss": 0.003,
+      "step": 600
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 2.1036500930786133,
+      "learning_rate": 6.369264466431519e-05,
+      "loss": 0.0604,
+      "step": 700
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.2531561851501465,
+      "learning_rate": 6.282026218706118e-05,
+      "loss": 0.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.4897408485412598,
+      "learning_rate": 6.194787970980717e-05,
+      "loss": 0.0114,
+      "step": 900
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.9127349853515625,
+      "learning_rate": 6.107549723255315e-05,
+      "loss": 25991.0925,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_economic_inequality_accuracy": 0.8224181360201511,
+      "eval_economic_inequality_f1": 0.7973444391161673,
+      "eval_economic_policy_benefits_accuracy": 0.8215488215488216,
+      "eval_economic_policy_benefits_f1": 0.7410643713786043,
+      "eval_ethnic_boundaries_accuracy": 0.9330065359477124,
+      "eval_ethnic_boundaries_f1": 0.9306378882302275,
+      "eval_language_policy_accuracy": 0.6764705882352942,
+      "eval_language_policy_f1": 0.545923632610939,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.6805555555555556,
+      "eval_overall_accuracy": 0.8117800455760427,
+      "eval_overall_f1": 0.7478535187845178,
+      "eval_religion_ethnic_identity_accuracy": 0.839458413926499,
+      "eval_religion_ethnic_identity_f1": 0.7915952258156131,
+      "eval_runtime": 4.4757,
+      "eval_samples_per_second": 893.725,
+      "eval_steps_per_second": 55.858,
+      "step": 1000
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.9552398324012756,
+      "learning_rate": 6.020311475529915e-05,
+      "loss": 0.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.114319920539856,
+      "learning_rate": 5.9330732278045136e-05,
+      "loss": 0.0009,
+      "step": 1200
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.16842737793922424,
+      "learning_rate": 5.845834980079113e-05,
+      "loss": 0.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 1.0355138778686523,
+      "learning_rate": 5.758596732353712e-05,
+      "loss": 0.0638,
+      "step": 1400
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5731643438339233,
+      "learning_rate": 5.6713584846283115e-05,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_economic_inequality_accuracy": 0.8224181360201511,
+      "eval_economic_inequality_f1": 0.7938100421450593,
+      "eval_economic_policy_benefits_accuracy": 0.8383838383838383,
+      "eval_economic_policy_benefits_f1": 0.8108014554114583,
+      "eval_ethnic_boundaries_accuracy": 0.9395424836601307,
+      "eval_ethnic_boundaries_f1": 0.9340440546398507,
+      "eval_language_policy_accuracy": 0.6764705882352942,
+      "eval_language_policy_f1": 0.6109373423468875,
+      "eval_loss": NaN,
+      "eval_mother_tongue_education_accuracy": 0.7777777777777778,
+      "eval_mother_tongue_education_f1": 0.7407407407407408,
+      "eval_overall_accuracy": 0.8150304610083521,
+      "eval_overall_f1": 0.7817611579593701,
+      "eval_religion_ethnic_identity_accuracy": 0.8355899419729207,
+      "eval_religion_ethnic_identity_f1": 0.8002333124722241,
+      "eval_runtime": 4.4858,
+      "eval_samples_per_second": 891.71,
+      "eval_steps_per_second": 55.732,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 8000,
+  "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": 1.2631144955904e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 6.873501538284335e-05,
+    "num_train_epochs": 16,
+    "per_device_train_batch_size": 8,
+    "warmup_steps": 121,
+    "weight_decay": 0.08748775333302956
+  }
+}

run-3/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f25b0890fc1a55f215dd25d4ee6812fa588a4d653eedd59fd60c8d3a14cbe61a
+size 5777