bert-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 [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4492
-- Accuracy: 0.7921
+- Loss: 0.4570
+- Accuracy: 0.8194
 
 ## Model description
 
@@ -37,21 +37,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 6.383530088472568e-05
 - train_batch_size: 8
 - eval_batch_size: 8
-- seed: 42
+- seed: 38
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 358  | 0.6238          | 0.6806   |
-| 0.582         | 2.0   | 716  | 0.6726          | 0.6754   |
-| 0.3462        | 3.0   | 1074 | 0.8248          | 0.7089   |
+| No log        | 1.0   | 358  | 0.5821          | 0.6951   |
+| 0.5947        | 2.0   | 716  | 0.7254          | 0.6993   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a65cfd6c8c67ea81c8a9bd210904b5a3207c4cb59b697427c8624d4a158fbe3c
+oid sha256:98e54a5db3a597e7660c2c7923cb394161ba914ae470992f98b353c56dfb4bf3
 size 437958648

run-0/checkpoint-1432/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-1432/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466f56598d470d0d6e6863f102554af8793f8000017cf67dfb3c1b0b1c11a746
+size 437958648

run-0/checkpoint-1432/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efefa1cb2e43eca86388c140d986fc42044bf02eff95d330c750a7121ef14a8f
+size 876038394

run-0/checkpoint-1432/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b3cf3545a26ad3b5b8ac5e19b825521066c417f4612f09c6113c18275eb81d5
+size 14244

run-0/checkpoint-1432/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6109cba35272005a0b96a29d208d6cd5344a03fe5d1e2a18ceb80837835819b8
+size 1064

run-0/checkpoint-1432/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-1432/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-1432/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.6532331109046936,
+  "best_model_checkpoint": "./bert_irony/run-0/checkpoint-716",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1432,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "grad_norm": 9.312857627868652,
+      "learning_rate": 3.361475882040115e-05,
+      "loss": 0.6817,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5763888888888888,
+      "eval_loss": 0.6532331109046936,
+      "eval_runtime": 8.2239,
+      "eval_samples_per_second": 116.125,
+      "eval_steps_per_second": 14.592,
+      "step": 716
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.967634201049805,
+      "learning_rate": 2.3416106265667792e-05,
+      "loss": 0.6184,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6913194444444445,
+      "eval_loss": 0.7047404050827026,
+      "eval_runtime": 8.215,
+      "eval_samples_per_second": 116.251,
+      "eval_steps_per_second": 14.607,
+      "step": 1432
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2148,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1051917999329280.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.381341137513451e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 28
+  }
+}

run-0/checkpoint-1432/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df87ed98c5e9d32ba2cafd8467572084a9877072cecd8864828f54a98caa3b2
+size 4920

run-0/checkpoint-2148/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-2148/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e686d6b911a5f49bd7811a66846d5d24d20c9ce21327249f97c4bf27ef14288a
+size 437958648

run-0/checkpoint-2148/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b405a9ca98682f2d9068f8433b4101363794e1cab25342a8319ac34b3a634100
+size 876038394

run-0/checkpoint-2148/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbbb5a2b8bb0078c73cce7cb2b760d7ca2b09c02604af5fd96d543cfc512bade
+size 14244

run-0/checkpoint-2148/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5412dfe8e228c1fb5574c1b3afd8d4239c37f91fa5039b7ce89f468d2f0f52c
+size 1064

run-0/checkpoint-2148/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-2148/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-2148/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 0.6532331109046936,
+  "best_model_checkpoint": "./bert_irony/run-0/checkpoint-716",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2148,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "grad_norm": 9.312857627868652,
+      "learning_rate": 3.361475882040115e-05,
+      "loss": 0.6817,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5763888888888888,
+      "eval_loss": 0.6532331109046936,
+      "eval_runtime": 8.2239,
+      "eval_samples_per_second": 116.125,
+      "eval_steps_per_second": 14.592,
+      "step": 716
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 11.967634201049805,
+      "learning_rate": 2.3416106265667792e-05,
+      "loss": 0.6184,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6913194444444445,
+      "eval_loss": 0.7047404050827026,
+      "eval_runtime": 8.215,
+      "eval_samples_per_second": 116.251,
+      "eval_steps_per_second": 14.607,
+      "step": 1432
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 6.910437107086182,
+      "learning_rate": 1.3217453710934432e-05,
+      "loss": 0.5339,
+      "step": 1500
+    },
+    {
+      "epoch": 2.79,
+      "grad_norm": 0.3941420316696167,
+      "learning_rate": 3.018801156201074e-06,
+      "loss": 0.3536,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6774305555555554,
+      "eval_loss": 1.3720420598983765,
+      "eval_runtime": 8.2327,
+      "eval_samples_per_second": 116.001,
+      "eval_steps_per_second": 14.576,
+      "step": 2148
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2148,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2103835998658560.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.381341137513451e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 28
+  }
+}

run-0/checkpoint-2148/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df87ed98c5e9d32ba2cafd8467572084a9877072cecd8864828f54a98caa3b2
+size 4920

run-0/checkpoint-716/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-716/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f9c4b20e1a7e18015be933993dc5eb7848a6b910e16c5a842b9333f8f145722
+size 437958648

run-0/checkpoint-716/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a478d1c361999a29ff1ccf0bca2692b0603e1ae5f6157433716ad6973c0c9e
+size 876038394

run-0/checkpoint-716/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836ec545da560e0ef9dcd573d79329688b0b8f346bd3375c9a14b53dac27b72c
+size 14244

run-0/checkpoint-716/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddda7cd7e7d09d8f3ffd501f009210617180a252f88afa9a65d1aa461d2d82f1
+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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-0/checkpoint-716/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.6532331109046936,
+  "best_model_checkpoint": "./bert_irony/run-0/checkpoint-716",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 716,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "grad_norm": 9.312857627868652,
+      "learning_rate": 3.361475882040115e-05,
+      "loss": 0.6817,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5763888888888888,
+      "eval_loss": 0.6532331109046936,
+      "eval_runtime": 8.2239,
+      "eval_samples_per_second": 116.125,
+      "eval_steps_per_second": 14.592,
+      "step": 716
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2148,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 526222110720000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.381341137513451e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 28
+  }
+}

run-0/checkpoint-716/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df87ed98c5e9d32ba2cafd8467572084a9877072cecd8864828f54a98caa3b2
+size 4920

run-1/checkpoint-358/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-358/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e54a5db3a597e7660c2c7923cb394161ba914ae470992f98b353c56dfb4bf3
+size 437958648

run-1/checkpoint-358/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfcca6f4886422080a93b76a2bc0bc082b1e1d94a508f236f10333c44c91f9b
+size 876038394

run-1/checkpoint-358/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00c61b49be04244217ed78dccdf50df27b9864769abbee9d4e91bbb27eaab18
+size 14244

run-1/checkpoint-358/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:119adbe001b0638d9f3aa55ae6a19cb918923192d98b9be2d18a518ddf3ba9d5
+size 1064

run-1/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-1/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-358/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.5820930004119873,
+  "best_model_checkpoint": "./bert_irony/run-1/checkpoint-358",
+  "epoch": 1.0,
+  "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": 0.6951388888888889,
+      "eval_loss": 0.5820930004119873,
+      "eval_runtime": 8.2633,
+      "eval_samples_per_second": 115.572,
+      "eval_steps_per_second": 14.522,
+      "step": 358
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.383530088472568e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}

run-1/checkpoint-358/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a17cf45345a048e3bb423ce94e685f9c5474594feffe769b012354aba56eb10c
+size 4920

run-1/checkpoint-716/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-716/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1429753d738639c4fa1ab93473dc77af872e36bd1cf6387f98de1d5b5057779a
+size 437958648

run-1/checkpoint-716/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:502fda613d1c6414c797d2840125a54cd9ebb77887ba96d77b8ae721932c2095
+size 876038394

run-1/checkpoint-716/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0003f77cca47ec17d738631773d261bb7add0e4531087f0c7cd4c62127b3c13e
+size 14244

run-1/checkpoint-716/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f187bacd792cd20f7e19f2cae507203958d1bc673201186808eb1d01b79e1bba
+size 1064

run-1/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-1/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-716/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.5820930004119873,
+  "best_model_checkpoint": "./bert_irony/run-1/checkpoint-358",
+  "epoch": 2.0,
+  "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": 0.6951388888888889,
+      "eval_loss": 0.5820930004119873,
+      "eval_runtime": 8.2633,
+      "eval_samples_per_second": 115.572,
+      "eval_steps_per_second": 14.522,
+      "step": 358
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 7.699513912200928,
+      "learning_rate": 1.9257576803213335e-05,
+      "loss": 0.5947,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6993055555555555,
+      "eval_loss": 0.7253889441490173,
+      "eval_runtime": 8.266,
+      "eval_samples_per_second": 115.533,
+      "eval_steps_per_second": 14.517,
+      "step": 716
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 716,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1051917999329280.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.383530088472568e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 38
+  }
+}