Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f5762c371f130636e8407289379fd8a59813f886ded6dda1395d6d31a7f12c
+oid sha256:7415615791e29904ce088212da37b0c3848feffe108ed1ca7a498483bbfd324d
 size 267829484

run-3/checkpoint-18/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-18/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f670a7bc2e85b36d63192f0d128ca6f674d4cb95702f386cdd32b99e598fa2f9
+size 267829484

run-3/checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5163a1827246a3df71f6f6739c8028fe0195075ca2294f8781ae566c7f5eef5c
+size 535721146

run-3/checkpoint-18/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd3b20d13cc947d3fe8837480a28641637ef12d62750314c6901be85133cb70
+size 14180

run-3/checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e51ba4afa0d8569a56a97e7f179262890d3b642b3394523af8148fdb6fcb3d28
+size 1064

run-3/checkpoint-18/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-18/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-18/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.0470495796010619,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-18",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.199407577514648,
+      "eval_pearson": 0.024278120881494558,
+      "eval_runtime": 0.9268,
+      "eval_samples_per_second": 1618.438,
+      "eval_spearmanr": 0.025433044219399577,
+      "eval_steps_per_second": 101.422,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.31046724319458,
+      "eval_pearson": 0.0470495796010619,
+      "eval_runtime": 0.9557,
+      "eval_samples_per_second": 1569.521,
+      "eval_spearmanr": 0.048936574609921006,
+      "eval_steps_per_second": 98.357,
+      "step": 18
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.243560941114439e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
+size 4920

run-3/checkpoint-27/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e698e612426ff730d573fd75d791a225076371ff8a36ad1591451c3d75ed2fe
+size 267829484

run-3/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:139bc6f51504facdd9adc3719caa9e62ef93409add07d855913aa534889cb737
+size 535721146

run-3/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36808ed814219680d29bcb5adc567b3fc23a005176ca2885d7e2c70b3412de8
+size 14180

run-3/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58cda4dc8a86e6a77e408072203e5a513a344d6bb368dadbd0740d08209488c
+size 1064

run-3/checkpoint-27/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-27/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-27/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.05278675976955915,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-27",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.199407577514648,
+      "eval_pearson": 0.024278120881494558,
+      "eval_runtime": 0.9268,
+      "eval_samples_per_second": 1618.438,
+      "eval_spearmanr": 0.025433044219399577,
+      "eval_steps_per_second": 101.422,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.31046724319458,
+      "eval_pearson": 0.0470495796010619,
+      "eval_runtime": 0.9557,
+      "eval_samples_per_second": 1569.521,
+      "eval_spearmanr": 0.048936574609921006,
+      "eval_steps_per_second": 98.357,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.604863166809082,
+      "eval_pearson": 0.05278675976955915,
+      "eval_runtime": 0.9249,
+      "eval_samples_per_second": 1621.719,
+      "eval_spearmanr": 0.05579666652056003,
+      "eval_steps_per_second": 101.628,
+      "step": 27
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.243560941114439e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-27/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
+size 4920

run-3/checkpoint-36/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-36/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c629568e16dc74409d4dfa02a57321ba6ae6562c21d2fc48ffa505ded3a4e6
+size 267829484

run-3/checkpoint-36/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60f8e6feef4eb32f7ba3f7c0faf9f4c6ae8f291f6e1418fea38e79ce1dc3601
+size 535721146

run-3/checkpoint-36/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d83c4a58d2ee55cb30b32045e660936fc993b17a15c3e3f39a67e2c75fae7ec7
+size 14180

run-3/checkpoint-36/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:660ee25a0ddd4682dcd06e6ffe649e6382c31e6ac22a1275061d2ccb894eb7da
+size 1064

run-3/checkpoint-36/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-36/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-36/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.06186573722446415,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-36",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.199407577514648,
+      "eval_pearson": 0.024278120881494558,
+      "eval_runtime": 0.9268,
+      "eval_samples_per_second": 1618.438,
+      "eval_spearmanr": 0.025433044219399577,
+      "eval_steps_per_second": 101.422,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.31046724319458,
+      "eval_pearson": 0.0470495796010619,
+      "eval_runtime": 0.9557,
+      "eval_samples_per_second": 1569.521,
+      "eval_spearmanr": 0.048936574609921006,
+      "eval_steps_per_second": 98.357,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.604863166809082,
+      "eval_pearson": 0.05278675976955915,
+      "eval_runtime": 0.9249,
+      "eval_samples_per_second": 1621.719,
+      "eval_spearmanr": 0.05579666652056003,
+      "eval_steps_per_second": 101.628,
+      "step": 27
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.163288593292236,
+      "eval_pearson": 0.06186573722446415,
+      "eval_runtime": 0.9496,
+      "eval_samples_per_second": 1579.549,
+      "eval_spearmanr": 0.06678878974516303,
+      "eval_steps_per_second": 98.985,
+      "step": 36
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.243560941114439e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-36/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
+size 4920

run-3/checkpoint-45/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-45/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d0c83a7bd7c921e1bcc37c1fda02d35c4caaf3fe5fb2bdcfdd912e0193d273
+size 267829484

run-3/checkpoint-45/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:152420f0357b982a437d54e165de9582b42e491cf214643b8a1a7f1e077876b4
+size 535721146

run-3/checkpoint-45/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbcadd327627ae50e7f089d46c5c091d80109e82be93e683b481080fb575a398
+size 14180

run-3/checkpoint-45/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae0be6c677ba4f8be1649bfda912af77981545adc6b777962a94b21590d0eec
+size 1064

run-3/checkpoint-45/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-45/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-45/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.06585301202568708,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-45",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 7.199407577514648,
+      "eval_pearson": 0.024278120881494558,
+      "eval_runtime": 0.9268,
+      "eval_samples_per_second": 1618.438,
+      "eval_spearmanr": 0.025433044219399577,
+      "eval_steps_per_second": 101.422,
+      "step": 9
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 6.31046724319458,
+      "eval_pearson": 0.0470495796010619,
+      "eval_runtime": 0.9557,
+      "eval_samples_per_second": 1569.521,
+      "eval_spearmanr": 0.048936574609921006,
+      "eval_steps_per_second": 98.357,
+      "step": 18
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 5.604863166809082,
+      "eval_pearson": 0.05278675976955915,
+      "eval_runtime": 0.9249,
+      "eval_samples_per_second": 1621.719,
+      "eval_spearmanr": 0.05579666652056003,
+      "eval_steps_per_second": 101.628,
+      "step": 27
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 5.163288593292236,
+      "eval_pearson": 0.06186573722446415,
+      "eval_runtime": 0.9496,
+      "eval_samples_per_second": 1579.549,
+      "eval_spearmanr": 0.06678878974516303,
+      "eval_steps_per_second": 98.985,
+      "step": 36
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 5.004383087158203,
+      "eval_pearson": 0.06585301202568708,
+      "eval_runtime": 0.9372,
+      "eval_samples_per_second": 1600.561,
+      "eval_spearmanr": 0.0703178793629636,
+      "eval_steps_per_second": 100.302,
+      "step": 45
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 45,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.243560941114439e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 10
+  }
+}

run-3/checkpoint-45/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43dea477fd3be8f6b457027410de4c6f7cf07a2710d25756956ebe9bfbdf4e31
+size 4920

run-4/checkpoint-36/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "regression",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-4/checkpoint-36/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7415615791e29904ce088212da37b0c3848feffe108ed1ca7a498483bbfd324d
+size 267829484

run-4/checkpoint-36/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e6c030837ee5d91a25afb3b90af6b4da7c853e6408b3730749bf425f6118a70
+size 535721146

run-4/checkpoint-36/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c909ba14abaaa8e7d3fd7f122fa501d6634b5a3b0ecd373bceaece83b57fe976
+size 14244

run-4/checkpoint-36/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66eed04a6c940ae505a3f5b371ec603313b051552fce9bbd465bcf3623cfb59e
+size 1064