Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:671728f6a878097a1162c257e1aa353fdc9acdcc4c03611fb10c3b0d3c63851a
+oid sha256:14f5762c371f130636e8407289379fd8a59813f886ded6dda1395d6d31a7f12c
 size 267829484

run-2/checkpoint-108/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-2/checkpoint-108/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecdf1600d2c703207fc2445099fac21fd4fa874049cf275de35c72a6b81a8332
+size 267829484

run-2/checkpoint-108/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba1aa152298b5a89ccb2e20dcb2d6f6f3c32b4300a9fa9a542aa3c606c43748
+size 535721146

run-2/checkpoint-108/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66be31c432556d1e4cd63f47c4fe9e83556b6dc838f90ac4025e897e6ae62376
+size 14308

run-2/checkpoint-108/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e816737c323e3a2d45e5481e584f40808fa11f3d51c831a99b0dbbf80623d29
+size 1064

run-2/checkpoint-108/special_tokens_map.json

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

run-2/checkpoint-108/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-2/checkpoint-108/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8156384301074189,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-108",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4969136714935303,
+      "eval_pearson": 0.32223422122729983,
+      "eval_runtime": 0.9052,
+      "eval_samples_per_second": 1657.071,
+      "eval_spearmanr": 0.32647520010278785,
+      "eval_steps_per_second": 103.843,
+      "step": 36
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1902464628219604,
+      "eval_pearson": 0.774068032504475,
+      "eval_runtime": 0.9073,
+      "eval_samples_per_second": 1653.256,
+      "eval_spearmanr": 0.7685396079860547,
+      "eval_steps_per_second": 103.604,
+      "step": 72
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.845661461353302,
+      "eval_pearson": 0.8156384301074189,
+      "eval_runtime": 0.9602,
+      "eval_samples_per_second": 1562.214,
+      "eval_spearmanr": 0.8142363416044488,
+      "eval_steps_per_second": 97.899,
+      "step": 108
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5099285971844188e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 8
+  }
+}

run-2/checkpoint-108/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
+size 4920

run-2/checkpoint-144/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-2/checkpoint-144/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f6582acf44517f58c26e691eb63d014825714aededbd69adac4d339c081105
+size 267829484

run-2/checkpoint-144/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbf6367e389ba399c49e51c1ee81b1addeb8c1c51c7cda327cee13a75fdfe1b
+size 535721146

run-2/checkpoint-144/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c69057d9a8716b83a57fd1bf30575ccb392f8cc39a8f0e55a46c81c9b5b431
+size 14308

run-2/checkpoint-144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaa559c16a11b6cfd5298e6bf6f570bf1e2be2e1785629c53d3a81a22fefc34d
+size 1064

run-2/checkpoint-144/special_tokens_map.json

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

run-2/checkpoint-144/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-2/checkpoint-144/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.820309116112808,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-144",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4969136714935303,
+      "eval_pearson": 0.32223422122729983,
+      "eval_runtime": 0.9052,
+      "eval_samples_per_second": 1657.071,
+      "eval_spearmanr": 0.32647520010278785,
+      "eval_steps_per_second": 103.843,
+      "step": 36
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1902464628219604,
+      "eval_pearson": 0.774068032504475,
+      "eval_runtime": 0.9073,
+      "eval_samples_per_second": 1653.256,
+      "eval_spearmanr": 0.7685396079860547,
+      "eval_steps_per_second": 103.604,
+      "step": 72
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.845661461353302,
+      "eval_pearson": 0.8156384301074189,
+      "eval_runtime": 0.9602,
+      "eval_samples_per_second": 1562.214,
+      "eval_spearmanr": 0.8142363416044488,
+      "eval_steps_per_second": 97.899,
+      "step": 108
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7359773516654968,
+      "eval_pearson": 0.820309116112808,
+      "eval_runtime": 0.9488,
+      "eval_samples_per_second": 1580.967,
+      "eval_spearmanr": 0.8207010328870485,
+      "eval_steps_per_second": 99.074,
+      "step": 144
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5099285971844188e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 8
+  }
+}

run-2/checkpoint-144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
+size 4920

run-2/checkpoint-180/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-2/checkpoint-180/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b7f2025a8d01e16baaf0c56e91991bd3fd2226c1e323a2c5372b694df927ae
+size 267829484

run-2/checkpoint-180/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02621271fc9fcebe1cf4b01b6f890c052ca90fd951b20507f9c3a120ca2bd142
+size 535721146

run-2/checkpoint-180/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b985c4d07829b462d67d43e81a1329a8f2890d9c00496cf43889b6d5a40cd8d5
+size 14308

run-2/checkpoint-180/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e8f8c803d1f4cbb6bbf08444fe39507f528857226dd87c6b8ed525e8765cf5
+size 1064

run-2/checkpoint-180/special_tokens_map.json

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

run-2/checkpoint-180/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-2/checkpoint-180/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.8215994541006149,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-180",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4969136714935303,
+      "eval_pearson": 0.32223422122729983,
+      "eval_runtime": 0.9052,
+      "eval_samples_per_second": 1657.071,
+      "eval_spearmanr": 0.32647520010278785,
+      "eval_steps_per_second": 103.843,
+      "step": 36
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1902464628219604,
+      "eval_pearson": 0.774068032504475,
+      "eval_runtime": 0.9073,
+      "eval_samples_per_second": 1653.256,
+      "eval_spearmanr": 0.7685396079860547,
+      "eval_steps_per_second": 103.604,
+      "step": 72
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.845661461353302,
+      "eval_pearson": 0.8156384301074189,
+      "eval_runtime": 0.9602,
+      "eval_samples_per_second": 1562.214,
+      "eval_spearmanr": 0.8142363416044488,
+      "eval_steps_per_second": 97.899,
+      "step": 108
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7359773516654968,
+      "eval_pearson": 0.820309116112808,
+      "eval_runtime": 0.9488,
+      "eval_samples_per_second": 1580.967,
+      "eval_spearmanr": 0.8207010328870485,
+      "eval_steps_per_second": 99.074,
+      "step": 144
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7456313371658325,
+      "eval_pearson": 0.8215994541006149,
+      "eval_runtime": 0.9399,
+      "eval_samples_per_second": 1595.857,
+      "eval_spearmanr": 0.8210025491088271,
+      "eval_steps_per_second": 100.007,
+      "step": 180
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5099285971844188e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 8
+  }
+}

run-2/checkpoint-180/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
+size 4920

run-2/checkpoint-72/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-2/checkpoint-72/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:249941c828507120d54adf6c5c3e3fcb54092c15aabd84dbcf3cb5310dc37911
+size 267829484

run-2/checkpoint-72/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77633fbec22f842c94d0497b7fc329bd24ed1768be551c33e31789f8f18c0dc3
+size 535721146

run-2/checkpoint-72/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47b999f373d02779993f31b8f70bc6d254ebaa78c7cb6aceff9aa39b2c0fd53
+size 14308

run-2/checkpoint-72/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deab0b4d6a1efc5852cfd2b718d2f3d57a531cfe61c04096b0c43021400997ea
+size 1064

run-2/checkpoint-72/special_tokens_map.json

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

run-2/checkpoint-72/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-2/checkpoint-72/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.774068032504475,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-72",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 72,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.4969136714935303,
+      "eval_pearson": 0.32223422122729983,
+      "eval_runtime": 0.9052,
+      "eval_samples_per_second": 1657.071,
+      "eval_spearmanr": 0.32647520010278785,
+      "eval_steps_per_second": 103.843,
+      "step": 36
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.1902464628219604,
+      "eval_pearson": 0.774068032504475,
+      "eval_runtime": 0.9073,
+      "eval_samples_per_second": 1653.256,
+      "eval_spearmanr": 0.7685396079860547,
+      "eval_steps_per_second": 103.604,
+      "step": 72
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5099285971844188e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 8
+  }
+}

run-2/checkpoint-72/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
+size 4920

run-3/checkpoint-9/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-9/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14f5762c371f130636e8407289379fd8a59813f886ded6dda1395d6d31a7f12c
+size 267829484

run-3/checkpoint-9/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcd68c867bc7e66d09d00cd6972fb094c4307e4caf066972f81431f276b6868
+size 535721146

run-3/checkpoint-9/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b127592b1841e69ad559ad38563940b6d1bfd53a4fd2f85e1c970834cc7ebe
+size 14180

run-3/checkpoint-9/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44fdc4e9dd06a3de129eb66445c8274e22814d846d188dbc2e8fbe7cbbc70b19
+size 1064