First stigma model

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c82fcc45490ded6f9b7db15e39541f26579e1ccb85d9ebd3ceef9446d20148
+size 657020933

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073f6035a2e1fd67e1389e9d081614431d1c6f739c7ffc13a9f5c4491223a36f
+size 328519925

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117a95bd0514634aa2e66194a1b64fb0f2c38ea2af7c2410bfd584c58dd20964
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b0e38e86e2b0ae8fcc43efeaae364ad84828772c63c0375ed9e8635129b7f2
+size 627

trainer_state.json

@@ -0,0 +1,184 @@
+{
+  "best_metric": 0.6666666666666667,
+  "best_model_checkpoint": "NLP/trained_models/256_5e-06_90/checkpoint-140",
+  "epoch": 70.0,
+  "global_step": 140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5647058823529412,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6881718635559082,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 2.0353,
+      "eval_samples_per_second": 41.763,
+      "eval_steps_per_second": 0.491,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5647058823529412,
+      "eval_f1": 0.0,
+      "eval_loss": 0.6862292885780334,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 3.3692,
+      "eval_samples_per_second": 25.229,
+      "eval_steps_per_second": 0.297,
+      "step": 20
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.5764705882352941,
+      "eval_f1": 0.1,
+      "eval_loss": 0.6834429502487183,
+      "eval_precision": 0.6666666666666666,
+      "eval_recall": 0.05405405405405406,
+      "eval_runtime": 1.8134,
+      "eval_samples_per_second": 46.873,
+      "eval_steps_per_second": 0.551,
+      "step": 30
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.6235294117647059,
+      "eval_f1": 0.3846153846153846,
+      "eval_loss": 0.6755977272987366,
+      "eval_precision": 0.6666666666666666,
+      "eval_recall": 0.2702702702702703,
+      "eval_runtime": 2.1098,
+      "eval_samples_per_second": 40.288,
+      "eval_steps_per_second": 0.474,
+      "step": 40
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.611764705882353,
+      "eval_f1": 0.47619047619047616,
+      "eval_loss": 0.6568019390106201,
+      "eval_precision": 0.5769230769230769,
+      "eval_recall": 0.40540540540540543,
+      "eval_runtime": 2.4655,
+      "eval_samples_per_second": 34.475,
+      "eval_steps_per_second": 0.406,
+      "step": 50
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.6588235294117647,
+      "eval_f1": 0.5797101449275363,
+      "eval_loss": 0.6438259482383728,
+      "eval_precision": 0.625,
+      "eval_recall": 0.5405405405405406,
+      "eval_runtime": 1.8313,
+      "eval_samples_per_second": 46.416,
+      "eval_steps_per_second": 0.546,
+      "step": 60
+    },
+    {
+      "epoch": 35.0,
+      "eval_accuracy": 0.6588235294117647,
+      "eval_f1": 0.6133333333333333,
+      "eval_loss": 0.6628918647766113,
+      "eval_precision": 0.6052631578947368,
+      "eval_recall": 0.6216216216216216,
+      "eval_runtime": 1.8199,
+      "eval_samples_per_second": 46.706,
+      "eval_steps_per_second": 0.549,
+      "step": 70
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.6588235294117647,
+      "eval_f1": 0.6133333333333333,
+      "eval_loss": 0.6717644333839417,
+      "eval_precision": 0.6052631578947368,
+      "eval_recall": 0.6216216216216216,
+      "eval_runtime": 6.0426,
+      "eval_samples_per_second": 14.067,
+      "eval_steps_per_second": 0.165,
+      "step": 80
+    },
+    {
+      "epoch": 45.0,
+      "eval_accuracy": 0.6823529411764706,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 0.7056936025619507,
+      "eval_precision": 0.6136363636363636,
+      "eval_recall": 0.7297297297297297,
+      "eval_runtime": 4.3129,
+      "eval_samples_per_second": 19.708,
+      "eval_steps_per_second": 0.232,
+      "step": 90
+    },
+    {
+      "epoch": 50.0,
+      "eval_accuracy": 0.6705882352941176,
+      "eval_f1": 0.6410256410256411,
+      "eval_loss": 0.7082163095474243,
+      "eval_precision": 0.6097560975609756,
+      "eval_recall": 0.6756756756756757,
+      "eval_runtime": 2.7778,
+      "eval_samples_per_second": 30.6,
+      "eval_steps_per_second": 0.36,
+      "step": 100
+    },
+    {
+      "epoch": 55.0,
+      "eval_accuracy": 0.6705882352941176,
+      "eval_f1": 0.6499999999999999,
+      "eval_loss": 0.7371630668640137,
+      "eval_precision": 0.6046511627906976,
+      "eval_recall": 0.7027027027027027,
+      "eval_runtime": 2.1835,
+      "eval_samples_per_second": 38.928,
+      "eval_steps_per_second": 0.458,
+      "step": 110
+    },
+    {
+      "epoch": 60.0,
+      "eval_accuracy": 0.6823529411764706,
+      "eval_f1": 0.6582278481012659,
+      "eval_loss": 0.7530251145362854,
+      "eval_precision": 0.6190476190476191,
+      "eval_recall": 0.7027027027027027,
+      "eval_runtime": 2.1705,
+      "eval_samples_per_second": 39.161,
+      "eval_steps_per_second": 0.461,
+      "step": 120
+    },
+    {
+      "epoch": 65.0,
+      "eval_accuracy": 0.6823529411764706,
+      "eval_f1": 0.6582278481012659,
+      "eval_loss": 0.7745981812477112,
+      "eval_precision": 0.6190476190476191,
+      "eval_recall": 0.7027027027027027,
+      "eval_runtime": 2.8635,
+      "eval_samples_per_second": 29.684,
+      "eval_steps_per_second": 0.349,
+      "step": 130
+    },
+    {
+      "epoch": 70.0,
+      "eval_accuracy": 0.6941176470588235,
+      "eval_f1": 0.6666666666666667,
+      "eval_loss": 0.7838086485862732,
+      "eval_precision": 0.6341463414634146,
+      "eval_recall": 0.7027027027027027,
+      "eval_runtime": 1.9223,
+      "eval_samples_per_second": 44.219,
+      "eval_steps_per_second": 0.52,
+      "step": 140
+    }
+  ],
+  "max_steps": 180,
+  "num_train_epochs": 90,
+  "total_flos": 116488518693120.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3123bb444fcb1096aa3a773774c3c9eee8cb9d6331b894f1ec8953f09692681
+size 3579