distilbert-irony-hyper

README.md

@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4854
-- Accuracy: 0.7753
+- Loss: 0.6232
+- Accuracy: 0.6467
 
 ## Model description
 
@@ -37,23 +37,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
+- learning_rate: 4.268152647097221e-05
+- train_batch_size: 16
 - eval_batch_size: 8
-- seed: 42
+- seed: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 358  | 0.5964          | 0.6817   |
-| 0.6001        | 2.0   | 716  | 0.6292          | 0.6984   |
-| 0.3988        | 3.0   | 1074 | 0.8125          | 0.6974   |
-| 0.3988        | 4.0   | 1432 | 1.2034          | 0.6817   |
-| 0.212         | 5.0   | 1790 | 1.3528          | 0.6817   |
+| No log        | 1.0   | 179  | 0.5912          | 0.6701   |
+| No log        | 2.0   | 358  | 0.6109          | 0.6837   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ac2f467fd7283bfeb608e7c07e7ea0e77f93dec67aba487a3cd7e9870a9958f
+oid sha256:2bad854d772225a8f4a680bf070c5ec15d0f90673bb70e0aaba14a3a13c06ba9
 size 267832560

run-0/checkpoint-179/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": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-179/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10a2004847a6b6354b1a06f4a0cd58fef02ebd4e051825be795eeee22e06a847
+size 267832560

run-0/checkpoint-179/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507e3f5d7b4c2344cb5aa3d3af579bfbb3078ce89ff19ac795e97c4977f8d347
+size 535727290

run-0/checkpoint-179/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e201bd0daf6272369d70630574d07eafab969fe9d03b4e0e99ffab32524c637
+size 14244

run-0/checkpoint-179/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b08c65ec3d5e754faa0b67ee7b015e4bc95d52e261f90c819caab5e1bb03e0fb
+size 1064

run-0/checkpoint-179/special_tokens_map.json

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

run-0/checkpoint-179/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-179/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6798288226127625,
+  "best_model_checkpoint": "./distilbert/run-0/checkpoint-179",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 179,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5784722222222222,
+      "eval_loss": 0.6798288226127625,
+      "eval_runtime": 5.3067,
+      "eval_samples_per_second": 179.961,
+      "eval_steps_per_second": 22.613,
+      "step": 179
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.556759622796195e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 39
+  }
+}

run-0/checkpoint-179/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dae4db71985e91853b8722bde64461a96b971ae12b46e7e00357834fba150e
+size 4920

run-0/checkpoint-358/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": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-358/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f2628b01ee8c5a63f0907f0066aa5a858d5ffda41b9331ec9eb7e5c1eb9376
+size 267832560

run-0/checkpoint-358/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbf9757fb29fd94c954c6dfb2e0b6c76a9999d48cb6048ff163945fc21763de
+size 535727290

run-0/checkpoint-358/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87ac28b3badfac499e3ffee0dd7887c238588f6165649814ca117cc4f8e3a5d9
+size 14244

run-0/checkpoint-358/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d2fc968400ea97a983310368344784aa6c869519c5b089599ac76a8e7bd97f
+size 1064

run-0/checkpoint-358/special_tokens_map.json

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

run-0/checkpoint-358/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-358/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.6606646180152893,
+  "best_model_checkpoint": "./distilbert/run-0/checkpoint-358",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 358,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5784722222222222,
+      "eval_loss": 0.6798288226127625,
+      "eval_runtime": 5.3067,
+      "eval_samples_per_second": 179.961,
+      "eval_steps_per_second": 22.613,
+      "step": 179
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6045138888888888,
+      "eval_loss": 0.6606646180152893,
+      "eval_runtime": 5.2957,
+      "eval_samples_per_second": 180.334,
+      "eval_steps_per_second": 22.66,
+      "step": 358
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.556759622796195e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 39
+  }
+}

run-0/checkpoint-358/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dae4db71985e91853b8722bde64461a96b971ae12b46e7e00357834fba150e
+size 4920

run-0/checkpoint-537/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": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-537/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6631ac5ef3ff4e8117b3002fec57d1932e4c8dab7f08082f265b2c5b7840b0
+size 267832560

run-0/checkpoint-537/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9851109701b43d5b6f1ac365e12e468ef7a64e5ad19d373d5b16c66b57098dab
+size 535727290

run-0/checkpoint-537/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a805abbcf4b6a5209860837981feeca04033d4aed37340309556341d95903f
+size 14244

run-0/checkpoint-537/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b452e356e00f9255efd03421390269ded208bc8e1b4e27a265078417b2a0fd2
+size 1064

run-0/checkpoint-537/special_tokens_map.json

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

run-0/checkpoint-537/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-537/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.654659628868103,
+  "best_model_checkpoint": "./distilbert/run-0/checkpoint-537",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 537,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5784722222222222,
+      "eval_loss": 0.6798288226127625,
+      "eval_runtime": 5.3067,
+      "eval_samples_per_second": 179.961,
+      "eval_steps_per_second": 22.613,
+      "step": 179
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6045138888888888,
+      "eval_loss": 0.6606646180152893,
+      "eval_runtime": 5.2957,
+      "eval_samples_per_second": 180.334,
+      "eval_steps_per_second": 22.66,
+      "step": 358
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 4.923989295959473,
+      "learning_rate": 7.713129588323717e-07,
+      "loss": 0.667,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6024305555555555,
+      "eval_loss": 0.654659628868103,
+      "eval_runtime": 5.3201,
+      "eval_samples_per_second": 179.508,
+      "eval_steps_per_second": 22.556,
+      "step": 537
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1059209319653376.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.556759622796195e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 39
+  }
+}

run-0/checkpoint-537/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dae4db71985e91853b8722bde64461a96b971ae12b46e7e00357834fba150e
+size 4920

run-0/checkpoint-716/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": "4.38.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-716/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0650a5d51adc1727cef49f80f66e948d5df0a95aad8b1ec67bbb4d21bb0e7ea2
+size 267832560

run-0/checkpoint-716/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cd2bfadb191606a369ec6d833b904198e9c0ff1c3de190ff1ce93cc55c429e
+size 535727290

run-0/checkpoint-716/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26eb957e2bcfe5954f2ec6c90be1c7eef516fda2aa73b93f6d661cfb78c75563
+size 14244

run-0/checkpoint-716/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeca1a4f2a06ab1891aa6b6444347289f182f5957e9f8f2786048ae776a97834
+size 1064

run-0/checkpoint-716/special_tokens_map.json

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

run-0/checkpoint-716/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-716/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.6529272794723511,
+  "best_model_checkpoint": "./distilbert/run-0/checkpoint-716",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 716,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5784722222222222,
+      "eval_loss": 0.6798288226127625,
+      "eval_runtime": 5.3067,
+      "eval_samples_per_second": 179.961,
+      "eval_steps_per_second": 22.613,
+      "step": 179
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6045138888888888,
+      "eval_loss": 0.6606646180152893,
+      "eval_runtime": 5.2957,
+      "eval_samples_per_second": 180.334,
+      "eval_steps_per_second": 22.66,
+      "step": 358
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 4.923989295959473,
+      "learning_rate": 7.713129588323717e-07,
+      "loss": 0.667,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6024305555555555,
+      "eval_loss": 0.654659628868103,
+      "eval_runtime": 5.3201,
+      "eval_samples_per_second": 179.508,
+      "eval_steps_per_second": 22.556,
+      "step": 537
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6086805555555554,
+      "eval_loss": 0.6529272794723511,
+      "eval_runtime": 5.2992,
+      "eval_samples_per_second": 180.217,
+      "eval_steps_per_second": 22.645,
+      "step": 716
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1059209319653376.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.556759622796195e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 39
+  }
+}

run-0/checkpoint-716/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25dae4db71985e91853b8722bde64461a96b971ae12b46e7e00357834fba150e
+size 4920

run-1/checkpoint-179/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": "4.38.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-179/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53f24a98ce6e4fae7bc61fc39fab17064b8422faa0308f312d4c74b967b779f
+size 267832560

run-1/checkpoint-179/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69e43d95efa991f6f69ec34022c047ecef3c033f8607986f5494d11040f77b97
+size 535727290

run-1/checkpoint-179/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d121aae83ebd33c8582e79b4c34690e63e12f82c5ceb578d16918b4d7299803
+size 14244

run-1/checkpoint-179/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c30b67065f71fd1090bd7ab2a2ffb5fffc7df49e96ccc642db6ebb8a503a3f4
+size 1064

run-1/checkpoint-179/special_tokens_map.json

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

run-1/checkpoint-179/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-179/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.6864913702011108,
+  "best_model_checkpoint": "./distilbert/run-1/checkpoint-179",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 179,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5673611111111112,
+      "eval_loss": 0.6864913702011108,
+      "eval_runtime": 5.327,
+      "eval_samples_per_second": 179.277,
+      "eval_steps_per_second": 22.527,
+      "step": 179
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.5004317532564466e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 36
+  }
+}