Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c44f40241882d43d1192bd8ecbe6a18fcffc320508cf66af7ba9fc0765b7ddf
+oid sha256:f0b46a03117a30b4cb6728141993318afbd64fbddb7bf76632095e5a0f82136d
 size 267832560

run-2/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": "4.40.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c07206b09044882ac35d599ec205545326d6153e8a138b0e88c21aaebd13c5
+size 267832560

run-2/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0fbc04f6856c3a776b2e8e5b859d38bdff1c6a7478b50f7b07cc7341bb0d134
+size 535727290

run-2/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc326810e752fcc7182919d846ff872ae3415e13b24c953d1076202546217d82
+size 14244

run-2/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1ee5da7baca42314125aad673b347cde93af0f44ff3bae899ad57b3985627c
+size 1064

run-2/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-2/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-2/checkpoint-1070/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.415128776020243,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1070",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 5.135624885559082,
+      "learning_rate": 3.571015099578109e-06,
+      "loss": 0.5612,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5108451843261719,
+      "eval_matthews_correlation": 0.4068953869702192,
+      "eval_runtime": 0.3429,
+      "eval_samples_per_second": 3041.66,
+      "eval_steps_per_second": 192.473,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 11.39373779296875,
+      "learning_rate": 2.750092088180842e-06,
+      "loss": 0.4687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5220178365707397,
+      "eval_matthews_correlation": 0.415128776020243,
+      "eval_runtime": 0.3609,
+      "eval_samples_per_second": 2889.801,
+      "eval_steps_per_second": 182.864,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 85863970691724.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.391938110975375e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-2/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c0c99d5135598e41d9cfcd5d809cb4ad2ec062b4f8de30cf2751cb06fa39f8
+size 5048

run-2/checkpoint-1605/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": "4.40.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f304b87ede28d9f3a0aee8219195c3fedb9ca2c30e84fe46cb5300447053f7f
+size 267832560

run-2/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ca4f7b1cade4afddbb09fae636234ec0b09c1c5203e4cc41b8875b69bf672b7
+size 535727290

run-2/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0e39da31ecf8134a66b4a09eb1f46fa8b3760f432b43e79545b69a23a9d700
+size 14244

run-2/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cd67a39da768e3b3d557f0a8c9dbf4246a73e43b0b43526c40d0066c28a4f3f
+size 1064

run-2/checkpoint-1605/special_tokens_map.json

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

run-2/checkpoint-1605/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-2/checkpoint-1605/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.45042204436320565,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1605",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1605,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 5.135624885559082,
+      "learning_rate": 3.571015099578109e-06,
+      "loss": 0.5612,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5108451843261719,
+      "eval_matthews_correlation": 0.4068953869702192,
+      "eval_runtime": 0.3429,
+      "eval_samples_per_second": 3041.66,
+      "eval_steps_per_second": 192.473,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 11.39373779296875,
+      "learning_rate": 2.750092088180842e-06,
+      "loss": 0.4687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5220178365707397,
+      "eval_matthews_correlation": 0.415128776020243,
+      "eval_runtime": 0.3609,
+      "eval_samples_per_second": 2889.801,
+      "eval_steps_per_second": 182.864,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 14.82923412322998,
+      "learning_rate": 1.929169076783576e-06,
+      "loss": 0.4153,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5056647658348083,
+      "eval_matthews_correlation": 0.45042204436320565,
+      "eval_runtime": 0.396,
+      "eval_samples_per_second": 2633.94,
+      "eval_steps_per_second": 166.673,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 128780303151612.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.391938110975375e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-2/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c0c99d5135598e41d9cfcd5d809cb4ad2ec062b4f8de30cf2751cb06fa39f8
+size 5048

run-2/checkpoint-2140/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": "4.40.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d2a74fa5b51fcc187a81536b27d18625f65233c47eea13c2f2a89e7f7b3205
+size 267832560

run-2/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c305061c8f6afd15a4c67851af28e75f3ee2ff24ff9643d852e49bdfbabc11
+size 535727290

run-2/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46ebcf8c05df1438c7acf46f93b2c0db5a77f0c030da859acfe9915e55756d39
+size 14244

run-2/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a179f515f177b718ff19b8bfd53e6186ea8670fa69ee72ddcfb16e5f80cb851e
+size 1064

run-2/checkpoint-2140/special_tokens_map.json

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

run-2/checkpoint-2140/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-2/checkpoint-2140/trainer_state.json

@@ -0,0 +1,90 @@
+{
+  "best_metric": 0.45042204436320565,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1605",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2140,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 5.135624885559082,
+      "learning_rate": 3.571015099578109e-06,
+      "loss": 0.5612,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5108451843261719,
+      "eval_matthews_correlation": 0.4068953869702192,
+      "eval_runtime": 0.3429,
+      "eval_samples_per_second": 3041.66,
+      "eval_steps_per_second": 192.473,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 11.39373779296875,
+      "learning_rate": 2.750092088180842e-06,
+      "loss": 0.4687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5220178365707397,
+      "eval_matthews_correlation": 0.415128776020243,
+      "eval_runtime": 0.3609,
+      "eval_samples_per_second": 2889.801,
+      "eval_steps_per_second": 182.864,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 14.82923412322998,
+      "learning_rate": 1.929169076783576e-06,
+      "loss": 0.4153,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5056647658348083,
+      "eval_matthews_correlation": 0.45042204436320565,
+      "eval_runtime": 0.396,
+      "eval_samples_per_second": 2633.94,
+      "eval_steps_per_second": 166.673,
+      "step": 1605
+    },
+    {
+      "epoch": 3.7383177570093458,
+      "grad_norm": 9.636689186096191,
+      "learning_rate": 1.1082460653863094e-06,
+      "loss": 0.3805,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5095609426498413,
+      "eval_matthews_correlation": 0.4504043574931814,
+      "eval_runtime": 0.3683,
+      "eval_samples_per_second": 2832.059,
+      "eval_steps_per_second": 179.21,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171771924699408.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.391938110975375e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-2/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c0c99d5135598e41d9cfcd5d809cb4ad2ec062b4f8de30cf2751cb06fa39f8
+size 5048

run-2/checkpoint-2675/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": "4.40.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-2675/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c55ab4cfed3acde1a877d524459181d66ce08c6f4a86d290ce08027d85140948
+size 267832560

run-2/checkpoint-2675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22996676b8c6bdfd68be316ca94489930472b69d7ae467b00be48b605c120754
+size 535727290

run-2/checkpoint-2675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4097c9f86c53f5a6be89f29d5f96a0305bfff2e0d6155daf48e2d74bba9654b
+size 14244

run-2/checkpoint-2675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4493e274e582287fad66a925802d7a03178d973697592554799a612d10a72fc
+size 1064

run-2/checkpoint-2675/special_tokens_map.json

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

run-2/checkpoint-2675/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-2/checkpoint-2675/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.45749443397572137,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2675",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2675,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 5.135624885559082,
+      "learning_rate": 3.571015099578109e-06,
+      "loss": 0.5612,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5108451843261719,
+      "eval_matthews_correlation": 0.4068953869702192,
+      "eval_runtime": 0.3429,
+      "eval_samples_per_second": 3041.66,
+      "eval_steps_per_second": 192.473,
+      "step": 535
+    },
+    {
+      "epoch": 1.8691588785046729,
+      "grad_norm": 11.39373779296875,
+      "learning_rate": 2.750092088180842e-06,
+      "loss": 0.4687,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5220178365707397,
+      "eval_matthews_correlation": 0.415128776020243,
+      "eval_runtime": 0.3609,
+      "eval_samples_per_second": 2889.801,
+      "eval_steps_per_second": 182.864,
+      "step": 1070
+    },
+    {
+      "epoch": 2.803738317757009,
+      "grad_norm": 14.82923412322998,
+      "learning_rate": 1.929169076783576e-06,
+      "loss": 0.4153,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5056647658348083,
+      "eval_matthews_correlation": 0.45042204436320565,
+      "eval_runtime": 0.396,
+      "eval_samples_per_second": 2633.94,
+      "eval_steps_per_second": 166.673,
+      "step": 1605
+    },
+    {
+      "epoch": 3.7383177570093458,
+      "grad_norm": 9.636689186096191,
+      "learning_rate": 1.1082460653863094e-06,
+      "loss": 0.3805,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5095609426498413,
+      "eval_matthews_correlation": 0.4504043574931814,
+      "eval_runtime": 0.3683,
+      "eval_samples_per_second": 2832.059,
+      "eval_steps_per_second": 179.21,
+      "step": 2140
+    },
+    {
+      "epoch": 4.672897196261682,
+      "grad_norm": 6.002148628234863,
+      "learning_rate": 2.8732305398904323e-07,
+      "loss": 0.358,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.525900661945343,
+      "eval_matthews_correlation": 0.45749443397572137,
+      "eval_runtime": 0.3551,
+      "eval_samples_per_second": 2936.996,
+      "eval_steps_per_second": 185.85,
+      "step": 2675
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 214443502942248.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.391938110975375e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-2/checkpoint-2675/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c0c99d5135598e41d9cfcd5d809cb4ad2ec062b4f8de30cf2751cb06fa39f8
+size 5048

run-3/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": "4.40.2",
+  "vocab_size": 30522
+}

run-3/checkpoint-134/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b46a03117a30b4cb6728141993318afbd64fbddb7bf76632095e5a0f82136d
+size 267832560

run-3/checkpoint-134/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1c1ddc0c3dcf1312fea205a65556108dffda368f41694298e91c761b99adcde
+size 535727290

run-3/checkpoint-134/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44f9684e45a24545175da7aaef6a3aa8a5e3e151bf2483fd7b2240c9e868bc16
+size 14244

run-3/checkpoint-134/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6793a24cdf1e1fa6569ad08ed5dbbc059c955a6d86bba8a29875727973f5ae4f
+size 1064