Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898c5e96d647648a7ef654501f82166a08f86b55c447364076d9a7be18c30d21
+oid sha256:64243f51512150f74facd126faa7c16f1d3fcedb123488abb591f1e502843b95
 size 267832560

run-3/checkpoint-1072/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee579c3be6b18ed34570132d6ad056455e817eeedf6ced105e25062f6ae5047f
+size 267832560

run-3/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f7992342d7b81dc15de53643b07c34946d895515eaeec499acedade0f400d3
+size 535727290

run-3/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd95d45320fdedf8e0de7c806b02c281d31f144a09218901cc607319b0f6fcb
+size 14244

run-3/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4375662d28cd8438e736d3356f442bfed7c3486944f6d48e83cd864b995dd770
+size 1064

run-3/checkpoint-1072/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1072/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1072/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.47624343628277643,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1072",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5160695314407349,
+      "eval_matthews_correlation": 0.3884569188624487,
+      "eval_runtime": 0.688,
+      "eval_samples_per_second": 1516.05,
+      "eval_steps_per_second": 95.934,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.7623518427226e-06,
+      "loss": 0.5077,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4879527986049652,
+      "eval_matthews_correlation": 0.4537159672261629,
+      "eval_runtime": 1.8327,
+      "eval_samples_per_second": 569.098,
+      "eval_steps_per_second": 36.012,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49178388714790344,
+      "eval_matthews_correlation": 0.4752024043308134,
+      "eval_runtime": 0.7459,
+      "eval_samples_per_second": 1398.283,
+      "eval_steps_per_second": 88.482,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.9276186030067667e-06,
+      "loss": 0.3683,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5047063231468201,
+      "eval_matthews_correlation": 0.47624343628277643,
+      "eval_runtime": 1.64,
+      "eval_samples_per_second": 635.968,
+      "eval_steps_per_second": 40.243,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 190971935742888.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.597085082438434e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 25
+  }
+}

run-3/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
+size 4664

run-3/checkpoint-1340/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d9d008e3526dad8db02fa80f7c8cb222696d34a8e13be95bd33a3247e90e7f
+size 267832560

run-3/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128ab087568746952d97651c45c873c8ae6f388003c4268e7eb45fd4d698d00a
+size 535727290

run-3/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d1c02feea1b8b859a137fac929e9599c3778a96670405041c0f99e9b063171d
+size 14244

run-3/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:097411c16fc2093a8f6f3012817a5a3fb74a8c0dd0d8fe570a0547d5fcc3e3a5
+size 1064

run-3/checkpoint-1340/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1340/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1340/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.47624343628277643,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1072",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5160695314407349,
+      "eval_matthews_correlation": 0.3884569188624487,
+      "eval_runtime": 0.688,
+      "eval_samples_per_second": 1516.05,
+      "eval_steps_per_second": 95.934,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.7623518427226e-06,
+      "loss": 0.5077,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4879527986049652,
+      "eval_matthews_correlation": 0.4537159672261629,
+      "eval_runtime": 1.8327,
+      "eval_samples_per_second": 569.098,
+      "eval_steps_per_second": 36.012,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49178388714790344,
+      "eval_matthews_correlation": 0.4752024043308134,
+      "eval_runtime": 0.7459,
+      "eval_samples_per_second": 1398.283,
+      "eval_steps_per_second": 88.482,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.9276186030067667e-06,
+      "loss": 0.3683,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5047063231468201,
+      "eval_matthews_correlation": 0.47624343628277643,
+      "eval_runtime": 1.64,
+      "eval_samples_per_second": 635.968,
+      "eval_steps_per_second": 40.243,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5170151591300964,
+      "eval_matthews_correlation": 0.4618671668713098,
+      "eval_runtime": 1.1213,
+      "eval_samples_per_second": 930.176,
+      "eval_steps_per_second": 58.861,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 190971935742888.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.597085082438434e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 25
+  }
+}

run-3/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
+size 4664

run-3/checkpoint-536/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5779f0273bb08a058a48125e9e488fb0f2f9ca9e3696a52defbd501ab02cee15
+size 267832560

run-3/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071b172af341c87c659d703ee6759edbf433e301ad03a0097de6352776c3dc56
+size 535727290

run-3/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35212cf28600f61e0bb32d2d39fd85e8c2e286d360d22cdac903fef6d853406
+size 14244

run-3/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc51fa1b9f070025f1240231503e5be4016d4dae909dbb8cd226337c2beca79
+size 1064

run-3/checkpoint-536/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-536/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-536/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": 0.4537159672261629,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5160695314407349,
+      "eval_matthews_correlation": 0.3884569188624487,
+      "eval_runtime": 0.688,
+      "eval_samples_per_second": 1516.05,
+      "eval_steps_per_second": 95.934,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.7623518427226e-06,
+      "loss": 0.5077,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4879527986049652,
+      "eval_matthews_correlation": 0.4537159672261629,
+      "eval_runtime": 1.8327,
+      "eval_samples_per_second": 569.098,
+      "eval_steps_per_second": 36.012,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95345738711148.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.597085082438434e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 25
+  }
+}

run-3/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
+size 4664

run-3/checkpoint-804/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10b586cd2fada1821efbde7366d43aca9a8e0354c19584534ac04061b863ddd7
+size 267832560

run-3/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d396a9a111fd80f4c564ffc9893e796cb4e8b0f8eb861590cea26a82ccd4dbd6
+size 535727290

run-3/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5189150a42bef0eebfe62d93189587b49003ad9fbbe6956c14a2621f9948c2fd
+size 14244

run-3/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb69f74de7cbb6772f3c1b3c2e7152b2a8ea9b76acdd4055f3ca1a4411695f4
+size 1064

run-3/checkpoint-804/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-804/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-804/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.4752024043308134,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-804",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5160695314407349,
+      "eval_matthews_correlation": 0.3884569188624487,
+      "eval_runtime": 0.688,
+      "eval_samples_per_second": 1516.05,
+      "eval_steps_per_second": 95.934,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.7623518427226e-06,
+      "loss": 0.5077,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.4879527986049652,
+      "eval_matthews_correlation": 0.4537159672261629,
+      "eval_runtime": 1.8327,
+      "eval_samples_per_second": 569.098,
+      "eval_steps_per_second": 36.012,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.49178388714790344,
+      "eval_matthews_correlation": 0.4752024043308134,
+      "eval_runtime": 0.7459,
+      "eval_samples_per_second": 1398.283,
+      "eval_steps_per_second": 88.482,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95345738711148.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.597085082438434e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 25
+  }
+}

run-3/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e146b53417e0b814d9ba13d0cee3eaa639091f08d7b686dbe13e8a915dd71743
+size 4664

run-4/checkpoint-535/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64243f51512150f74facd126faa7c16f1d3fcedb123488abb591f1e502843b95
+size 267832560

run-4/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:030c099d6e487a296ab946bb7274394454590a2165c574f08203a6a2b3e2841f
+size 535727290

run-4/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00913233eb507d55793e89701c76adacfda2ed542654ed972db83dfea364c35
+size 14244

run-4/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138d6dd279f411ec8a8dbda20677c68f0083c4c529fdbe0c42294b7f92ee93bd
+size 1064