Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ce053085dba606f02c99f5a26489e2408e8e7ef3bf4ee7d38f42add1c26ae45
+oid sha256:813e5a928ee1ceb25f3478f3c4fd0ebc977791c2168e028204f65db5dc1f94da
 size 267832560

run-7/checkpoint-1070/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb78622fa3ad648866fb3d24132841f869ad71a19810d859157beaa1d7a35f6d
+size 267832560

run-7/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5707848bd5503345fca11a9948ef0eecac169ad046dbffe0a32dec88094434b0
+size 535727290

run-7/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb299cabe77b031e81b9d378ae67a89d8761424f0cb3e95c52615f7b89e0f3ab
+size 14308

run-7/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff21b9fc22d881c2be9c20f519f17e3d5fcf087de2017c35d96e7e9e1f6304d
+size 1064

run-7/checkpoint-1070/special_tokens_map.json

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

run-7/checkpoint-1070/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-7/checkpoint-1070/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.3393769209893431,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-642",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5881524085998535,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5145,
+      "eval_samples_per_second": 2027.266,
+      "eval_steps_per_second": 128.283,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6095048785209656,
+      "eval_matthews_correlation": 0.2920277228925403,
+      "eval_runtime": 0.517,
+      "eval_samples_per_second": 2017.266,
+      "eval_steps_per_second": 127.651,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 7.986351013183594,
+      "learning_rate": 6.259012645042397e-06,
+      "loss": 0.5246,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8854954838752747,
+      "eval_matthews_correlation": 0.3393769209893431,
+      "eval_runtime": 0.5407,
+      "eval_samples_per_second": 1928.84,
+      "eval_steps_per_second": 122.055,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2050410509109497,
+      "eval_matthews_correlation": 0.2903129121495111,
+      "eval_runtime": 0.518,
+      "eval_samples_per_second": 2013.528,
+      "eval_steps_per_second": 127.414,
+      "step": 856
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 0.35196247696876526,
+      "learning_rate": 7.68650675706961e-07,
+      "loss": 0.1995,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.173661708831787,
+      "eval_matthews_correlation": 0.3306791468948119,
+      "eval_runtime": 0.5275,
+      "eval_samples_per_second": 1977.377,
+      "eval_steps_per_second": 125.126,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 26085728519712.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1749374614377834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-7/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fcb7249a5efa5afe771702791f5160b4a2945d2ff42557241bfc280f53e9e0
+size 4984

run-7/checkpoint-428/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ecdefa80f917ea569f0967595a130829d55c644d450070ad209a282aa744ba
+size 267832560

run-7/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a63584a039d849689fd63923843cf10efa9bafed1afa39085ca6c12d9745f9f
+size 535727290

run-7/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ce71c1db32d16c6a980eac9223dab51229b094e48c0cb557b3e000bb0070971
+size 14308

run-7/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5780399df3370635b3d241bce58a54b8e5e2b5e1c37f0b56ca5f2495fd3e0a3
+size 1064

run-7/checkpoint-428/special_tokens_map.json

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

run-7/checkpoint-428/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-7/checkpoint-428/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.2920277228925403,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5881524085998535,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5145,
+      "eval_samples_per_second": 2027.266,
+      "eval_steps_per_second": 128.283,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6095048785209656,
+      "eval_matthews_correlation": 0.2920277228925403,
+      "eval_runtime": 0.517,
+      "eval_samples_per_second": 2017.266,
+      "eval_steps_per_second": 127.651,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1749374614377834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-7/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fcb7249a5efa5afe771702791f5160b4a2945d2ff42557241bfc280f53e9e0
+size 4984

run-7/checkpoint-642/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-642/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eece3145b2389f904695e6b7da639c58e9cc22af598b92bd6b21cd37095b2e1
+size 267832560

run-7/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96cfca7bd62ee04d274222e0ec67d900d2d933c1ee29110200358f8a9a71f4c
+size 535727290

run-7/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3c6ddf0be1ebadfa7cea8e78f6a48be2ad22fe42af768f78ba810cf3a17c24
+size 14308

run-7/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:facc2082b7e122bdfb0357ad5f75c7a4b0cb3810c50bf86d86f452e5efc9a7fc
+size 1064

run-7/checkpoint-642/special_tokens_map.json

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

run-7/checkpoint-642/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-7/checkpoint-642/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.3393769209893431,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-642",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5881524085998535,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5145,
+      "eval_samples_per_second": 2027.266,
+      "eval_steps_per_second": 128.283,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6095048785209656,
+      "eval_matthews_correlation": 0.2920277228925403,
+      "eval_runtime": 0.517,
+      "eval_samples_per_second": 2017.266,
+      "eval_steps_per_second": 127.651,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 7.986351013183594,
+      "learning_rate": 6.259012645042397e-06,
+      "loss": 0.5246,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8854954838752747,
+      "eval_matthews_correlation": 0.3393769209893431,
+      "eval_runtime": 0.5407,
+      "eval_samples_per_second": 1928.84,
+      "eval_steps_per_second": 122.055,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 17799530518236.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1749374614377834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-7/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fcb7249a5efa5afe771702791f5160b4a2945d2ff42557241bfc280f53e9e0
+size 4984

run-7/checkpoint-856/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4ea1ef5cbae23d4af671eb3bc85f60e2e1972cac4b4657892c7b10034c8046
+size 267832560

run-7/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e8d028c1160c9183841ba9a626e6a32eab1d32f6ff04c66d76eaf7ff56900a
+size 535727290

run-7/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:424b29a8d7984d831b37c237918d52a7b797b383055f8f01206d835f24fd1109
+size 14308

run-7/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f7b619521f8362d9fd7cd9e113c7a381d8bb87559928cd43dae7fa8b97adc0
+size 1064

run-7/checkpoint-856/special_tokens_map.json

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

run-7/checkpoint-856/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-7/checkpoint-856/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.3393769209893431,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-642",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5881524085998535,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.5145,
+      "eval_samples_per_second": 2027.266,
+      "eval_steps_per_second": 128.283,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6095048785209656,
+      "eval_matthews_correlation": 0.2920277228925403,
+      "eval_runtime": 0.517,
+      "eval_samples_per_second": 2017.266,
+      "eval_steps_per_second": 127.651,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 7.986351013183594,
+      "learning_rate": 6.259012645042397e-06,
+      "loss": 0.5246,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8854954838752747,
+      "eval_matthews_correlation": 0.3393769209893431,
+      "eval_runtime": 0.5407,
+      "eval_samples_per_second": 1928.84,
+      "eval_steps_per_second": 122.055,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2050410509109497,
+      "eval_matthews_correlation": 0.2903129121495111,
+      "eval_runtime": 0.518,
+      "eval_samples_per_second": 2013.528,
+      "eval_steps_per_second": 127.414,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 17799530518236.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.1749374614377834e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-7/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fcb7249a5efa5afe771702791f5160b4a2945d2ff42557241bfc280f53e9e0
+size 4984

run-9/checkpoint-27/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "vocab_size": 30522
+}

run-9/checkpoint-27/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813e5a928ee1ceb25f3478f3c4fd0ebc977791c2168e028204f65db5dc1f94da
+size 267832560

run-9/checkpoint-27/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549ce50afe795416334fac5d660258464810bc7718e84c6e1752cee431025c31
+size 535727290

run-9/checkpoint-27/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcb5d493c752dab5e0f871b61bbf3a2081da99b6255e78690d7917f0783f79d
+size 14308

run-9/checkpoint-27/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c49d63029f0e79861581b9747a5fc3617830d857879487f434e7a574108208e
+size 1064