End of training

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: 0.8001
-- Matthews Correlation: 0.5452
+- Loss: 1.0949
+- Matthews Correlation: 0.5222
 
 ## Model description
 
@@ -37,23 +37,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
+- learning_rate: 9.640871494419937e-06
+- train_batch_size: 4
 - eval_batch_size: 16
-- seed: 42
+- seed: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
-|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5175        | 1.0   | 535  | 0.4595          | 0.4481               |
-| 0.3432        | 2.0   | 1070 | 0.4666          | 0.5169               |
-| 0.233         | 3.0   | 1605 | 0.6238          | 0.5073               |
-| 0.1765        | 4.0   | 2140 | 0.8001          | 0.5452               |
-| 0.1316        | 5.0   | 2675 | 0.8660          | 0.5173               |
+| Training Loss | Epoch | Step  | Validation Loss | Matthews Correlation |
+|:-------------:|:-----:|:-----:|:---------------:|:--------------------:|
+| 0.5382        | 1.0   | 2138  | 0.5065          | 0.4539               |
+| 0.5225        | 2.0   | 4276  | 0.7784          | 0.4731               |
+| 0.3999        | 3.0   | 6414  | 0.8716          | 0.5052               |
+| 0.2923        | 4.0   | 8552  | 1.0318          | 0.5363               |
+| 0.2003        | 5.0   | 10690 | 1.0949          | 0.5222               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21b6e6b9ffdabd565264aa5290a7393bd73aa202f71783da347f92b2ebb9432
+oid sha256:c03e763a5f5d97d3cab2a02b6ad9d819a53c16fbdc85279d23a4725342c5bbd4
 size 267832560

run-0/checkpoint-10690/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-10690/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aedbd383510592e138a099c2283675308d18616282b0698c27344b9e0d3a03d1
+size 267832560

run-0/checkpoint-10690/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30aac7e741934dae5ef0eacb3dabc1fcd825dc9680b5fc1b8ff1c727896ada2f
+size 535727290

run-0/checkpoint-10690/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1d0b508da8125724e75d4c8bc521664bf671c8e360759040a3797489720e4b
+size 14308

run-0/checkpoint-10690/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8085f191ce5f4025d1c25342f597c2ac8fb0915960595356c711828554faa70a
+size 1064

run-0/checkpoint-10690/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-10690/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-0/checkpoint-10690/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_metric": 0.536262647683346,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-8552",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 10690,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 31.300899505615234,
+      "learning_rate": 9.18994205127588e-06,
+      "loss": 0.5844,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 10.452669143676758,
+      "learning_rate": 8.739012608131823e-06,
+      "loss": 0.5545,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 42.02324676513672,
+      "learning_rate": 8.288083164987766e-06,
+      "loss": 0.547,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 38.979740142822266,
+      "learning_rate": 7.837153721843709e-06,
+      "loss": 0.5382,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5065158605575562,
+      "eval_matthews_correlation": 0.4539100120594166,
+      "eval_runtime": 0.7267,
+      "eval_samples_per_second": 1435.351,
+      "eval_steps_per_second": 90.828,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 42.54972839355469,
+      "learning_rate": 7.3862242786996525e-06,
+      "loss": 0.4498,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 38.12797927856445,
+      "learning_rate": 6.935294835555595e-06,
+      "loss": 0.4789,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 2.2431697845458984,
+      "learning_rate": 6.4843653924115385e-06,
+      "loss": 0.4803,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 0.8748724460601807,
+      "learning_rate": 6.033435949267481e-06,
+      "loss": 0.5225,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.778407871723175,
+      "eval_matthews_correlation": 0.4730676912894765,
+      "eval_runtime": 0.7349,
+      "eval_samples_per_second": 1419.24,
+      "eval_steps_per_second": 89.808,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 0.08216582238674164,
+      "learning_rate": 5.5825065061234246e-06,
+      "loss": 0.4451,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 34.81584167480469,
+      "learning_rate": 5.131577062979367e-06,
+      "loss": 0.3457,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 0.2907339334487915,
+      "learning_rate": 4.680647619835311e-06,
+      "loss": 0.3718,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 0.22318235039710999,
+      "learning_rate": 4.229718176691254e-06,
+      "loss": 0.3999,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8715924024581909,
+      "eval_matthews_correlation": 0.5051600900029769,
+      "eval_runtime": 0.7186,
+      "eval_samples_per_second": 1451.341,
+      "eval_steps_per_second": 91.839,
+      "step": 6414
+    },
+    {
+      "epoch": 3.0402245088868103,
+      "grad_norm": 0.47206905484199524,
+      "learning_rate": 3.7787887335471967e-06,
+      "loss": 0.3685,
+      "step": 6500
+    },
+    {
+      "epoch": 3.2740879326473338,
+      "grad_norm": 0.04389917850494385,
+      "learning_rate": 3.3278592904031397e-06,
+      "loss": 0.249,
+      "step": 7000
+    },
+    {
+      "epoch": 3.5079513564078577,
+      "grad_norm": 0.21924751996994019,
+      "learning_rate": 2.8769298472590827e-06,
+      "loss": 0.252,
+      "step": 7500
+    },
+    {
+      "epoch": 3.7418147801683816,
+      "grad_norm": 9.382844924926758,
+      "learning_rate": 2.4260004041150266e-06,
+      "loss": 0.2621,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9756782039289056,
+      "grad_norm": 134.2183074951172,
+      "learning_rate": 1.975070960970969e-06,
+      "loss": 0.2923,
+      "step": 8500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.0317972898483276,
+      "eval_matthews_correlation": 0.536262647683346,
+      "eval_runtime": 0.7324,
+      "eval_samples_per_second": 1424.048,
+      "eval_steps_per_second": 90.112,
+      "step": 8552
+    },
+    {
+      "epoch": 4.209541627689429,
+      "grad_norm": 0.09477799385786057,
+      "learning_rate": 1.5241415178269122e-06,
+      "loss": 0.22,
+      "step": 9000
+    },
+    {
+      "epoch": 4.443405051449953,
+      "grad_norm": 0.18212155997753143,
+      "learning_rate": 1.0732120746828554e-06,
+      "loss": 0.225,
+      "step": 9500
+    },
+    {
+      "epoch": 4.677268475210477,
+      "grad_norm": 0.04502077028155327,
+      "learning_rate": 6.222826315387986e-07,
+      "loss": 0.1876,
+      "step": 10000
+    },
+    {
+      "epoch": 4.911131898971001,
+      "grad_norm": 0.0519992969930172,
+      "learning_rate": 1.713531883947416e-07,
+      "loss": 0.2003,
+      "step": 10500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.094925880432129,
+      "eval_matthews_correlation": 0.522211073949747,
+      "eval_runtime": 0.8243,
+      "eval_samples_per_second": 1265.281,
+      "eval_steps_per_second": 80.066,
+      "step": 10690
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 171182806990932.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.640871494419937e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 8
+  }
+}

run-0/checkpoint-10690/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431eff645e4e364ffdd1287885c479902fbed1f7a06e676424f5979c1bdd5d35
+size 5240

run-0/checkpoint-2138/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc39a60b12b84bee581f63dd692b654123fdf8769d083accd5c6755f60912c8d
+size 267832560

run-0/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4cf35325c7cc361d74d6e81b83573f573044b70eccc2e41fe12b9c04e21cae7
+size 535727290

run-0/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932e2bfd991d06cded0f1f6718a4e2bafd9b85b66f9fe6c3477c435ae6d9b082
+size 14308

run-0/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69801f8069ed99895ca426d3534219f51b3a02ad191486e7d0131daff69d3a12
+size 1064

run-0/checkpoint-2138/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-2138/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-0/checkpoint-2138/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": 0.4539100120594166,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 31.300899505615234,
+      "learning_rate": 9.18994205127588e-06,
+      "loss": 0.5844,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 10.452669143676758,
+      "learning_rate": 8.739012608131823e-06,
+      "loss": 0.5545,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 42.02324676513672,
+      "learning_rate": 8.288083164987766e-06,
+      "loss": 0.547,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 38.979740142822266,
+      "learning_rate": 7.837153721843709e-06,
+      "loss": 0.5382,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5065158605575562,
+      "eval_matthews_correlation": 0.4539100120594166,
+      "eval_runtime": 0.7267,
+      "eval_samples_per_second": 1435.351,
+      "eval_steps_per_second": 90.828,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 32576631053856.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.640871494419937e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 8
+  }
+}

run-0/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431eff645e4e364ffdd1287885c479902fbed1f7a06e676424f5979c1bdd5d35
+size 5240

run-0/checkpoint-4276/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-4276/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3386103f829027662377c23e8518c80e8480dac432bed9f21dd2f1576b56af
+size 267832560

run-0/checkpoint-4276/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9053a2c9de00751e72e31b360b1782a88797e76c6bb1f519382f4cc106045818
+size 535727290

run-0/checkpoint-4276/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8f4f5ad0a942f2c44c012377ecf9d8504ef968c06751edb7eea2c2f14d862a
+size 14308

run-0/checkpoint-4276/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b3883abab0337b87a1094924c94048c730d494f5fddf733071e7a9a542af0b5
+size 1064

run-0/checkpoint-4276/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-4276/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-0/checkpoint-4276/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_metric": 0.4730676912894765,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-4276",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 4276,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 31.300899505615234,
+      "learning_rate": 9.18994205127588e-06,
+      "loss": 0.5844,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 10.452669143676758,
+      "learning_rate": 8.739012608131823e-06,
+      "loss": 0.5545,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 42.02324676513672,
+      "learning_rate": 8.288083164987766e-06,
+      "loss": 0.547,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 38.979740142822266,
+      "learning_rate": 7.837153721843709e-06,
+      "loss": 0.5382,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5065158605575562,
+      "eval_matthews_correlation": 0.4539100120594166,
+      "eval_runtime": 0.7267,
+      "eval_samples_per_second": 1435.351,
+      "eval_steps_per_second": 90.828,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 42.54972839355469,
+      "learning_rate": 7.3862242786996525e-06,
+      "loss": 0.4498,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 38.12797927856445,
+      "learning_rate": 6.935294835555595e-06,
+      "loss": 0.4789,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 2.2431697845458984,
+      "learning_rate": 6.4843653924115385e-06,
+      "loss": 0.4803,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 0.8748724460601807,
+      "learning_rate": 6.033435949267481e-06,
+      "loss": 0.5225,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.778407871723175,
+      "eval_matthews_correlation": 0.4730676912894765,
+      "eval_runtime": 0.7349,
+      "eval_samples_per_second": 1419.24,
+      "eval_steps_per_second": 89.808,
+      "step": 4276
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 65193364542852.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.640871494419937e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 8
+  }
+}

run-0/checkpoint-4276/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431eff645e4e364ffdd1287885c479902fbed1f7a06e676424f5979c1bdd5d35
+size 5240

run-0/checkpoint-6414/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-6414/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eecd09b54923e56deb153cd9e52b4e5525c1b2f8a6bbd86da17c2a7ec25ea38
+size 267832560

run-0/checkpoint-6414/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81cee999fd8ca9d6e66cd6f02c464b5133c334adde4160e668e12747e12868e3
+size 535727290

run-0/checkpoint-6414/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f62961781d6c3796067895388d40a6023741a315aa007a313792368a8ce34480
+size 14308

run-0/checkpoint-6414/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eaf64f825311a27841935e43177f06712995c9c45b01dfab7203c6dab0af19a
+size 1064

run-0/checkpoint-6414/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-6414/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-0/checkpoint-6414/trainer_state.json

@@ -0,0 +1,149 @@
+{
+  "best_metric": 0.5051600900029769,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-6414",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6414,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23386342376052385,
+      "grad_norm": 31.300899505615234,
+      "learning_rate": 9.18994205127588e-06,
+      "loss": 0.5844,
+      "step": 500
+    },
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 10.452669143676758,
+      "learning_rate": 8.739012608131823e-06,
+      "loss": 0.5545,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7015902712815716,
+      "grad_norm": 42.02324676513672,
+      "learning_rate": 8.288083164987766e-06,
+      "loss": 0.547,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 38.979740142822266,
+      "learning_rate": 7.837153721843709e-06,
+      "loss": 0.5382,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5065158605575562,
+      "eval_matthews_correlation": 0.4539100120594166,
+      "eval_runtime": 0.7267,
+      "eval_samples_per_second": 1435.351,
+      "eval_steps_per_second": 90.828,
+      "step": 2138
+    },
+    {
+      "epoch": 1.1693171188026192,
+      "grad_norm": 42.54972839355469,
+      "learning_rate": 7.3862242786996525e-06,
+      "loss": 0.4498,
+      "step": 2500
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 38.12797927856445,
+      "learning_rate": 6.935294835555595e-06,
+      "loss": 0.4789,
+      "step": 3000
+    },
+    {
+      "epoch": 1.637043966323667,
+      "grad_norm": 2.2431697845458984,
+      "learning_rate": 6.4843653924115385e-06,
+      "loss": 0.4803,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 0.8748724460601807,
+      "learning_rate": 6.033435949267481e-06,
+      "loss": 0.5225,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.778407871723175,
+      "eval_matthews_correlation": 0.4730676912894765,
+      "eval_runtime": 0.7349,
+      "eval_samples_per_second": 1419.24,
+      "eval_steps_per_second": 89.808,
+      "step": 4276
+    },
+    {
+      "epoch": 2.1047708138447145,
+      "grad_norm": 0.08216582238674164,
+      "learning_rate": 5.5825065061234246e-06,
+      "loss": 0.4451,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3386342376052385,
+      "grad_norm": 34.81584167480469,
+      "learning_rate": 5.131577062979367e-06,
+      "loss": 0.3457,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5724976613657624,
+      "grad_norm": 0.2907339334487915,
+      "learning_rate": 4.680647619835311e-06,
+      "loss": 0.3718,
+      "step": 5500
+    },
+    {
+      "epoch": 2.8063610851262863,
+      "grad_norm": 0.22318235039710999,
+      "learning_rate": 4.229718176691254e-06,
+      "loss": 0.3999,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8715924024581909,
+      "eval_matthews_correlation": 0.5051600900029769,
+      "eval_runtime": 0.7186,
+      "eval_samples_per_second": 1451.341,
+      "eval_steps_per_second": 91.839,
+      "step": 6414
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 97840886353020.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.640871494419937e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 8
+  }
+}

run-0/checkpoint-6414/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431eff645e4e364ffdd1287885c479902fbed1f7a06e676424f5979c1bdd5d35
+size 5240

run-0/checkpoint-8552/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": "4.44.0",
+  "vocab_size": 30522
+}

run-0/checkpoint-8552/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03e763a5f5d97d3cab2a02b6ad9d819a53c16fbdc85279d23a4725342c5bbd4
+size 267832560

run-0/checkpoint-8552/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00cb29926ed7f48632af5a2d53aade5920474939acb251cb1c8104e1330dd07c
+size 535727290

run-0/checkpoint-8552/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2aacab570f18a9a62ba3ce6db0a73d6f28b7efabaefa0ea28e71b91dc92b3c
+size 14308