distilbert-emotion-hyper

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.944
+      value: 0.921
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ 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 the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1774
-- Accuracy: 0.944
+- Loss: 0.2046
+- Accuracy: 0.921
 
 ## Model description
 
@@ -52,21 +52,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
+- learning_rate: 3.507837996446784e-06
+- train_batch_size: 16
 - eval_batch_size: 8
-- seed: 42
+- seed: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.2605        | 1.0   | 2000 | 0.2376          | 0.93     |
-| 0.1559        | 2.0   | 4000 | 0.1909          | 0.936    |
-| 0.1022        | 3.0   | 6000 | 0.1774          | 0.944    |
+| 0.8349        | 1.0   | 1000 | 0.6184          | 0.7905   |
+| 0.384         | 2.0   | 2000 | 0.3057          | 0.909    |
+| 0.2544        | 3.0   | 3000 | 0.2316          | 0.926    |
+| 0.2027        | 4.0   | 4000 | 0.2088          | 0.928    |
+| 0.1757        | 5.0   | 5000 | 0.2030          | 0.9295   |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ae041864a7bce41a596cfef38707c5d3c31f362722cdd30190b65b86e33842
+oid sha256:f5d704cc9862ddf1d8d932f63fd2a04f445025136eada995440f6c63cbfceb69
 size 267844872

run-0/checkpoint-1000/config.json

@@ -36,6 +36,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.1",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-0/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f714d0b136162061a284a20cfdda6222efc2bf27857f5630f85ab7599d93f8
+oid sha256:747beece75f8af284340a68dea598af6266f80094e18a38e1f3f96cba906ffa3
 size 267844872

run-0/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f32cfc0ad23d420d6d61f12b69ec49a371cc1e10726edbfdce43d3f6831f54
+oid sha256:a3d9524173dfc250a400cf3b08492b825804443aec9b18a05a31588844131d30
 size 535751866

run-0/checkpoint-1000/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8148aef41ba09d2856c03fa103eb3ba16dcc1ed9b2086510cb930a647a48c4ba
-size 14308
+oid sha256:af50b4fd0da5321ee737e722708435e6858a8884fd52e3e2ba2c6e8ee695d8ea
+size 14244

run-0/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4f8103da0f4bfa98cebe625453e24cafb981ea2e82d0ea5928d01c6a1e0a51f
+oid sha256:9a7cd9a1052aaeb3908d09e7d68dd345ad3d9621cae3dcbe46c5a456a8e29f89
 size 1064

run-0/checkpoint-1000/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.1864173263311386,
+  "best_metric": 0.6183840036392212,
   "best_model_checkpoint": "./results/run-0/checkpoint-1000",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,40 +10,40 @@
   "log_history": [
     {
       "epoch": 0.5,
-      "grad_norm": 2.885716676712036,
-      "learning_rate": 3.732667213318159e-05,
-      "loss": 0.5811,
+      "grad_norm": 4.100419521331787,
+      "learning_rate": 3.1570541968021056e-06,
+      "loss": 1.3549,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "grad_norm": 45.26211166381836,
-      "learning_rate": 2.986133770654527e-05,
-      "loss": 0.2295,
+      "grad_norm": 11.960673332214355,
+      "learning_rate": 2.8062703971574272e-06,
+      "loss": 0.8349,
       "step": 1000
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.9345,
-      "eval_loss": 0.1864173263311386,
-      "eval_runtime": 33.637,
-      "eval_samples_per_second": 59.458,
-      "eval_steps_per_second": 3.716,
+      "eval_accuracy": 0.7905,
+      "eval_loss": 0.6183840036392212,
+      "eval_runtime": 9.0459,
+      "eval_samples_per_second": 221.096,
+      "eval_steps_per_second": 27.637,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 3000,
+  "max_steps": 5000,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 2119629570048000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.479200655981791e-05,
-    "num_train_epochs": 3,
+    "learning_rate": 3.507837996446784e-06,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 16,
-    "seed": 13
+    "seed": 16
   }
 }

run-0/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf14954d29b1ae5aea2c382af10f5eb08277fe38bdff48b601d514f3dd3c259
+oid sha256:91f8f40dfcf0b2c79af71df18fa68d8aea743148ae225d30899abc38be627e74
 size 4920

run-0/checkpoint-2000/config.json

@@ -0,0 +1,41 @@
+{
+  "_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",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53a7d9aa3ca94fe6dd893ffdf9f7717e7304e06d21be4def3d022e9633d5409b
+size 267844872

run-0/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4dd58e88842ee66f117e257dd68bfa45836e260640fe05797b79f28b5420073
+size 535751866

run-0/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fb9afe5983bb41189c2d9b014c7655c37f0b479811b0d4d8c2502121dbbd3d5
+size 14244

run-0/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dce918e9a0d2e7e7af8db106a5648e11b498998cb964aafb1d95603b9176eb7
+size 1064

run-0/checkpoint-2000/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-2000/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-2000/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.30574527382850647,
+  "best_model_checkpoint": "./results/run-0/checkpoint-2000",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.100419521331787,
+      "learning_rate": 3.1570541968021056e-06,
+      "loss": 1.3549,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.960673332214355,
+      "learning_rate": 2.8062703971574272e-06,
+      "loss": 0.8349,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7905,
+      "eval_loss": 0.6183840036392212,
+      "eval_runtime": 9.0459,
+      "eval_samples_per_second": 221.096,
+      "eval_steps_per_second": 27.637,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.748434543609619,
+      "learning_rate": 2.4554865975127484e-06,
+      "loss": 0.5184,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 22.25712776184082,
+      "learning_rate": 2.10470279786807e-06,
+      "loss": 0.384,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.909,
+      "eval_loss": 0.30574527382850647,
+      "eval_runtime": 9.0588,
+      "eval_samples_per_second": 220.779,
+      "eval_steps_per_second": 27.597,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 4239259140096000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.507837996446784e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 16
+  }
+}

run-0/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f8f40dfcf0b2c79af71df18fa68d8aea743148ae225d30899abc38be627e74
+size 4920

run-0/checkpoint-3000/config.json

@@ -0,0 +1,41 @@
+{
+  "_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",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b15a33652cc1fae58dd5ee8cd21a9e9d21c610dd089b9aac5885025b66c670
+size 267844872

run-0/checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd844e763d33d7d4713949e397c3f28ace287c699e05264ec2b04a093300a488
+size 535751866

run-0/checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48587ce948f135b2307e71cc2ebb47fcf96a8b09e28fac4a40913827a1941c7
+size 14244

run-0/checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1eb477b2218e2219e9c3c790828b11022ce9659f22be28dbfbf8680de93d2aa
+size 1064

run-0/checkpoint-3000/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-3000/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-3000/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 0.23158574104309082,
+  "best_model_checkpoint": "./results/run-0/checkpoint-3000",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.100419521331787,
+      "learning_rate": 3.1570541968021056e-06,
+      "loss": 1.3549,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.960673332214355,
+      "learning_rate": 2.8062703971574272e-06,
+      "loss": 0.8349,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7905,
+      "eval_loss": 0.6183840036392212,
+      "eval_runtime": 9.0459,
+      "eval_samples_per_second": 221.096,
+      "eval_steps_per_second": 27.637,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.748434543609619,
+      "learning_rate": 2.4554865975127484e-06,
+      "loss": 0.5184,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 22.25712776184082,
+      "learning_rate": 2.10470279786807e-06,
+      "loss": 0.384,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.909,
+      "eval_loss": 0.30574527382850647,
+      "eval_runtime": 9.0588,
+      "eval_samples_per_second": 220.779,
+      "eval_steps_per_second": 27.597,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 5.657580852508545,
+      "learning_rate": 1.753918998223392e-06,
+      "loss": 0.2753,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.047184944152832,
+      "learning_rate": 1.4031351985787136e-06,
+      "loss": 0.2544,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.926,
+      "eval_loss": 0.23158574104309082,
+      "eval_runtime": 9.085,
+      "eval_samples_per_second": 220.144,
+      "eval_steps_per_second": 27.518,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 6358888710144000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.507837996446784e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 16
+  }
+}

run-0/checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f8f40dfcf0b2c79af71df18fa68d8aea743148ae225d30899abc38be627e74
+size 4920

run-0/checkpoint-4000/config.json

@@ -0,0 +1,41 @@
+{
+  "_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",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b521f6a9f4286c6b3d96b51d9404fb66778d34e231a0e2bc965c1d423e834bb
+size 267844872

run-0/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b096cb1b39e534de82f466c7a34c699c36212691c0232fa002e4f7539b25ef0b
+size 535751866

run-0/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0771581525ea94df74fc1ffc6d9a9a7e1f11965bb3edc1e62727de238162859
+size 14244

run-0/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b8d19b6744e771b4a9530f4add0974eda3dd465a7159708dd098be29e2ce042
+size 1064

run-0/checkpoint-4000/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-4000/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-4000/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_metric": 0.20877034962177277,
+  "best_model_checkpoint": "./results/run-0/checkpoint-4000",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.100419521331787,
+      "learning_rate": 3.1570541968021056e-06,
+      "loss": 1.3549,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.960673332214355,
+      "learning_rate": 2.8062703971574272e-06,
+      "loss": 0.8349,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7905,
+      "eval_loss": 0.6183840036392212,
+      "eval_runtime": 9.0459,
+      "eval_samples_per_second": 221.096,
+      "eval_steps_per_second": 27.637,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.748434543609619,
+      "learning_rate": 2.4554865975127484e-06,
+      "loss": 0.5184,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 22.25712776184082,
+      "learning_rate": 2.10470279786807e-06,
+      "loss": 0.384,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.909,
+      "eval_loss": 0.30574527382850647,
+      "eval_runtime": 9.0588,
+      "eval_samples_per_second": 220.779,
+      "eval_steps_per_second": 27.597,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 5.657580852508545,
+      "learning_rate": 1.753918998223392e-06,
+      "loss": 0.2753,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.047184944152832,
+      "learning_rate": 1.4031351985787136e-06,
+      "loss": 0.2544,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.926,
+      "eval_loss": 0.23158574104309082,
+      "eval_runtime": 9.085,
+      "eval_samples_per_second": 220.144,
+      "eval_steps_per_second": 27.518,
+      "step": 3000
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 8.62791919708252,
+      "learning_rate": 1.052351398934035e-06,
+      "loss": 0.2115,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.2406601905822754,
+      "learning_rate": 7.015675992893568e-07,
+      "loss": 0.2027,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.928,
+      "eval_loss": 0.20877034962177277,
+      "eval_runtime": 9.0519,
+      "eval_samples_per_second": 220.949,
+      "eval_steps_per_second": 27.619,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 8478518280192000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.507837996446784e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 16
+  }
+}

run-0/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f8f40dfcf0b2c79af71df18fa68d8aea743148ae225d30899abc38be627e74
+size 4920

run-0/checkpoint-5000/config.json

@@ -0,0 +1,41 @@
+{
+  "_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",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d704cc9862ddf1d8d932f63fd2a04f445025136eada995440f6c63cbfceb69
+size 267844872

run-0/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784b996526526a5cd8fc3a55c22a62714f8a0d67fff050c0fda322b798aedf39
+size 535751866

run-0/checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ece59d05ca6ae22d9a98b2fa3a8a580231dea90e91aa2ae7692f6d0d637a0f
+size 14244

run-0/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d0139089d40e481dc003ac329dab0c85f60dcb6590bff943ed1972b51e69c4
+size 1064

run-0/checkpoint-5000/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-5000/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-5000/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.20295538008213043,
+  "best_model_checkpoint": "./results/run-0/checkpoint-5000",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "grad_norm": 4.100419521331787,
+      "learning_rate": 3.1570541968021056e-06,
+      "loss": 1.3549,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.960673332214355,
+      "learning_rate": 2.8062703971574272e-06,
+      "loss": 0.8349,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7905,
+      "eval_loss": 0.6183840036392212,
+      "eval_runtime": 9.0459,
+      "eval_samples_per_second": 221.096,
+      "eval_steps_per_second": 27.637,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 5.748434543609619,
+      "learning_rate": 2.4554865975127484e-06,
+      "loss": 0.5184,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 22.25712776184082,
+      "learning_rate": 2.10470279786807e-06,
+      "loss": 0.384,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.909,
+      "eval_loss": 0.30574527382850647,
+      "eval_runtime": 9.0588,
+      "eval_samples_per_second": 220.779,
+      "eval_steps_per_second": 27.597,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 5.657580852508545,
+      "learning_rate": 1.753918998223392e-06,
+      "loss": 0.2753,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.047184944152832,
+      "learning_rate": 1.4031351985787136e-06,
+      "loss": 0.2544,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.926,
+      "eval_loss": 0.23158574104309082,
+      "eval_runtime": 9.085,
+      "eval_samples_per_second": 220.144,
+      "eval_steps_per_second": 27.518,
+      "step": 3000
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 8.62791919708252,
+      "learning_rate": 1.052351398934035e-06,
+      "loss": 0.2115,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.2406601905822754,
+      "learning_rate": 7.015675992893568e-07,
+      "loss": 0.2027,
+      "step": 4000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.928,
+      "eval_loss": 0.20877034962177277,
+      "eval_runtime": 9.0519,
+      "eval_samples_per_second": 220.949,
+      "eval_steps_per_second": 27.619,
+      "step": 4000
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 2.1353747844696045,
+      "learning_rate": 3.507837996446784e-07,
+      "loss": 0.1858,
+      "step": 4500
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 15.034784317016602,
+      "learning_rate": 0.0,
+      "loss": 0.1757,
+      "step": 5000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9295,
+      "eval_loss": 0.20295538008213043,
+      "eval_runtime": 9.0539,
+      "eval_samples_per_second": 220.9,
+      "eval_steps_per_second": 27.612,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1.059814785024e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.507837996446784e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 16
+  }
+}

run-0/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f8f40dfcf0b2c79af71df18fa68d8aea743148ae225d30899abc38be627e74
+size 4920

run-1/checkpoint-1000/config.json

@@ -0,0 +1,41 @@
+{
+  "_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",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "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
+}