Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa62f4be7c81a75f9c028eacf1f7834c77930a095880542913186f34025b77f9
+oid sha256:d512d69737e4dd75ec635374e87e270786e7416f9a3ec71a00cf9aa4302ef623
 size 267832560

run-5/checkpoint-1072/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": "4.39.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-1072/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8a0395482996ee67e70a4a4ee998debc988418869081c8814f35b6ecec4801
+size 267832560

run-5/checkpoint-1072/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789398afd211d4499b333248de42f617220eeb5338ea98fce8eb0a863785a8d1
+size 535727290

run-5/checkpoint-1072/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2832be438043cede83e9bf53c7e3d2813a62058621d0c91f863900b90be46a00
+size 14244

run-5/checkpoint-1072/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:153d627dec725ee6b7713e3fcb7a47024e8d5185f6a97b2c12fa32ff17b3488e
+size 1064

run-5/checkpoint-1072/special_tokens_map.json

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

run-5/checkpoint-1072/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-5/checkpoint-1072/trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.5259674254268325,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-804",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 1072,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5089643001556396,
+      "eval_matthews_correlation": 0.42440981210667367,
+      "eval_runtime": 0.7825,
+      "eval_samples_per_second": 1332.954,
+      "eval_steps_per_second": 84.348,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 6.73560905456543,
+      "learning_rate": 1.8445818150231764e-05,
+      "loss": 0.431,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46689021587371826,
+      "eval_matthews_correlation": 0.5179258445384731,
+      "eval_runtime": 1.2385,
+      "eval_samples_per_second": 842.124,
+      "eval_steps_per_second": 53.289,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5552349090576172,
+      "eval_matthews_correlation": 0.5259674254268325,
+      "eval_runtime": 0.8397,
+      "eval_samples_per_second": 1242.121,
+      "eval_steps_per_second": 78.6,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 17.49067497253418,
+      "learning_rate": 7.4661644893795224e-06,
+      "loss": 0.1892,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7417210936546326,
+      "eval_matthews_correlation": 0.5157664784865402,
+      "eval_runtime": 0.8139,
+      "eval_samples_per_second": 1281.442,
+      "eval_steps_per_second": 81.088,
+      "step": 1072
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 190818770313192.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9425471811084e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 22
+  }
+}

run-5/checkpoint-1072/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d389a261c4ad79c8031d213d930b79b34def1ca6a13f6f38b7b0de9654f7854
+size 4984

run-5/checkpoint-1340/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": "4.39.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-1340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed2f32cc1e0ef2d9bb4f738f63c712c8bf64bb67d28c0d6771d8dc6999f40bc
+size 267832560

run-5/checkpoint-1340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acea47bff8193e40528fae679d12deb9f03b204e74fbdc31e81662a6967bf0a
+size 535727290

run-5/checkpoint-1340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d9b5af2591f9a60a1bef5220522e5fea70fe5d21efe572f897334e85cd04ed
+size 14244

run-5/checkpoint-1340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa0817b6fd92bf5c252476256b59c10ec324a5edf5d097fd0e3aa84b90edbe6
+size 1064

run-5/checkpoint-1340/special_tokens_map.json

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

run-5/checkpoint-1340/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-5/checkpoint-1340/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.5382179635494023,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1340",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1340,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5089643001556396,
+      "eval_matthews_correlation": 0.42440981210667367,
+      "eval_runtime": 0.7825,
+      "eval_samples_per_second": 1332.954,
+      "eval_steps_per_second": 84.348,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 6.73560905456543,
+      "learning_rate": 1.8445818150231764e-05,
+      "loss": 0.431,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46689021587371826,
+      "eval_matthews_correlation": 0.5179258445384731,
+      "eval_runtime": 1.2385,
+      "eval_samples_per_second": 842.124,
+      "eval_steps_per_second": 53.289,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5552349090576172,
+      "eval_matthews_correlation": 0.5259674254268325,
+      "eval_runtime": 0.8397,
+      "eval_samples_per_second": 1242.121,
+      "eval_steps_per_second": 78.6,
+      "step": 804
+    },
+    {
+      "epoch": 3.73,
+      "grad_norm": 17.49067497253418,
+      "learning_rate": 7.4661644893795224e-06,
+      "loss": 0.1892,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.7417210936546326,
+      "eval_matthews_correlation": 0.5157664784865402,
+      "eval_runtime": 0.8139,
+      "eval_samples_per_second": 1281.442,
+      "eval_steps_per_second": 81.088,
+      "step": 1072
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7818797826766968,
+      "eval_matthews_correlation": 0.5382179635494023,
+      "eval_runtime": 0.8061,
+      "eval_samples_per_second": 1293.934,
+      "eval_steps_per_second": 81.879,
+      "step": 1340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 190818770313192.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9425471811084e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 22
+  }
+}

run-5/checkpoint-1340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d389a261c4ad79c8031d213d930b79b34def1ca6a13f6f38b7b0de9654f7854
+size 4984

run-5/checkpoint-536/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": "4.39.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-536/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00fa33ec5f76f5a061706a43afb8666567cc6178535bcea901faa6a85b49f62
+size 267832560

run-5/checkpoint-536/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42339a45944e0a6a8409aa499ba9c42d906d6ce04e6f4e01296416b5ac94caa1
+size 535727290

run-5/checkpoint-536/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb1efdc56f058e7a83c03c88dcdbd01b35b8148bad0ddd0584931854e62f1b3e
+size 14244

run-5/checkpoint-536/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9662833f5d6198852ca54aac2d3af3b54a1f53c6068978e022249b3406a752f0
+size 1064

run-5/checkpoint-536/special_tokens_map.json

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

run-5/checkpoint-536/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-5/checkpoint-536/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.5179258445384731,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-536",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5089643001556396,
+      "eval_matthews_correlation": 0.42440981210667367,
+      "eval_runtime": 0.7825,
+      "eval_samples_per_second": 1332.954,
+      "eval_steps_per_second": 84.348,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 6.73560905456543,
+      "learning_rate": 1.8445818150231764e-05,
+      "loss": 0.431,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46689021587371826,
+      "eval_matthews_correlation": 0.5179258445384731,
+      "eval_runtime": 1.2385,
+      "eval_samples_per_second": 842.124,
+      "eval_steps_per_second": 53.289,
+      "step": 536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95238108949740.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9425471811084e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 22
+  }
+}

run-5/checkpoint-536/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d389a261c4ad79c8031d213d930b79b34def1ca6a13f6f38b7b0de9654f7854
+size 4984

run-5/checkpoint-804/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": "4.39.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-804/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f98026e2f800f871e545fd9e1e144a40385704ba6bd2cf8d938b454d2fa8ef
+size 267832560

run-5/checkpoint-804/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2178109dc458e848d6d9bcaae61920d87a7f2abcac31bb656c3423be610f3e06
+size 535727290

run-5/checkpoint-804/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2c5be4d5ff5d99648470dc1e74095ee71eb9ddb1fe55bc8b553e8ab5c18ac3
+size 14244

run-5/checkpoint-804/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6329719373ebd19c3261434dc6743b2ad7257d8574f530215ee6e2b04e9dd536
+size 1064

run-5/checkpoint-804/special_tokens_map.json

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

run-5/checkpoint-804/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-5/checkpoint-804/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.5259674254268325,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-804",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 804,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5089643001556396,
+      "eval_matthews_correlation": 0.42440981210667367,
+      "eval_runtime": 0.7825,
+      "eval_samples_per_second": 1332.954,
+      "eval_steps_per_second": 84.348,
+      "step": 268
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 6.73560905456543,
+      "learning_rate": 1.8445818150231764e-05,
+      "loss": 0.431,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.46689021587371826,
+      "eval_matthews_correlation": 0.5179258445384731,
+      "eval_runtime": 1.2385,
+      "eval_samples_per_second": 842.124,
+      "eval_steps_per_second": 53.289,
+      "step": 536
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5552349090576172,
+      "eval_matthews_correlation": 0.5259674254268325,
+      "eval_runtime": 0.8397,
+      "eval_samples_per_second": 1242.121,
+      "eval_steps_per_second": 78.6,
+      "step": 804
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 95238108949740.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.9425471811084e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 22
+  }
+}

run-5/checkpoint-804/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d389a261c4ad79c8031d213d930b79b34def1ca6a13f6f38b7b0de9654f7854
+size 4984

run-6/checkpoint-134/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": "4.39.1",
+  "vocab_size": 30522
+}

run-6/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d512d69737e4dd75ec635374e87e270786e7416f9a3ec71a00cf9aa4302ef623
+size 267832560

run-6/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16abcc98944f4a08311444ad210c728fb4b02f6ff84d9aaa9d01c78f3f836df6
+size 535727290

run-6/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54004cbc6d9678ea40ad40223ca87b0f59f09bf57b5e845d0cf202ea314a346
+size 14308

run-6/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42533eac26789a5ede26e5255984843f752b52fa2f67926b32a21c31ffd886f
+size 1064