Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c264122d89160fe9154fd3bf882718ac262be9624845584d192b191c6c54068
+oid sha256:1cc62f265dbdd4dce4a4b6b25bb32be8f2ecef46b94f865d0870bcd119f670ef
 size 267832560

run-0/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e588d4660f90e51fdbd3b5178050fd5d681cca09424e31ffcce8c232d87fffc9
+size 267832560

run-0/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13dafcfe753dc858bd9df9dc59e6b40ff7892f3e67a9b4e88ae50232c93ca2b
+size 535727290

run-0/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8f6718c0b0c58f833e26408edaa90f1651508e8d07672d72d303d1bd9b3bbb
+size 14244

run-0/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:194b5e63a8b1c0dbafa55c45c6039153fa9aeed3c8ab7505e7eb6a039b676ae0
+size 1064

run-0/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-0/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-0/checkpoint-1070/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.49799539554804517,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "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": 0.93,
+      "learning_rate": 1.85192391864203e-05,
+      "loss": 0.5264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.46143588423728943,
+      "eval_matthews_correlation": 0.49799539554804517,
+      "eval_runtime": 1.0072,
+      "eval_samples_per_second": 1035.567,
+      "eval_steps_per_second": 65.53,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4261942821725978e-05,
+      "loss": 0.3406,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5079557299613953,
+      "eval_matthews_correlation": 0.48003141444537994,
+      "eval_runtime": 0.8361,
+      "eval_samples_per_second": 1247.424,
+      "eval_steps_per_second": 78.936,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 85812225614124.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.277653555111462e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-0/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cdafb2f3028d92aeb215c4f9ee1fa4b2ece61c011af271e09c318dcf8f36fa
+size 4792

run-0/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31a03f9a73dc34f0ca0a3349adb92c24fe4a434ece6653ba47e952efca18d513
+size 267832560

run-0/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0bc4147533f2426c2924dd7b85244a1912882b7a4ec370f89ed0acf85ad004c
+size 535727290

run-0/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c3c0efccb212640297e1686338de57674899895cfb2304a92046b0feca32e9
+size 14244

run-0/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08a17364a5365ee7a2afe91ab2cd564d92803b19f75943e68899b7fde6136aa
+size 1064

run-0/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-0/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-0/checkpoint-1605/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.49799539554804517,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "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": 0.93,
+      "learning_rate": 1.85192391864203e-05,
+      "loss": 0.5264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.46143588423728943,
+      "eval_matthews_correlation": 0.49799539554804517,
+      "eval_runtime": 1.0072,
+      "eval_samples_per_second": 1035.567,
+      "eval_steps_per_second": 65.53,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4261942821725978e-05,
+      "loss": 0.3406,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5079557299613953,
+      "eval_matthews_correlation": 0.48003141444537994,
+      "eval_runtime": 0.8361,
+      "eval_samples_per_second": 1247.424,
+      "eval_steps_per_second": 78.936,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.0004646457031656e-05,
+      "loss": 0.2246,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6419426202774048,
+      "eval_matthews_correlation": 0.49626557567073315,
+      "eval_runtime": 0.7375,
+      "eval_samples_per_second": 1414.219,
+      "eval_steps_per_second": 89.49,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 128728040623236.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.277653555111462e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-0/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cdafb2f3028d92aeb215c4f9ee1fa4b2ece61c011af271e09c318dcf8f36fa
+size 4792

run-0/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2140/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d48015502fd707666613619773d3141491fa5193213715fc0605ac6cf1408ac7
+size 267832560

run-0/checkpoint-2140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2def37ecee8ecea57a36b9a2a89d36733c63f2e9fe5b33450ae23c9c01640693
+size 535727290

run-0/checkpoint-2140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad6ceacfe91bd2dce0f4512c0dd7bea2de33d2de9ffb69f1114febefddd150e
+size 14244

run-0/checkpoint-2140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc792ce8a14b99adff674554ae7b8fa2393ea81b59547e6dc04de7730bc3085
+size 1064

run-0/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-0/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-0/checkpoint-2140/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.49799539554804517,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "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": 0.93,
+      "learning_rate": 1.85192391864203e-05,
+      "loss": 0.5264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.46143588423728943,
+      "eval_matthews_correlation": 0.49799539554804517,
+      "eval_runtime": 1.0072,
+      "eval_samples_per_second": 1035.567,
+      "eval_steps_per_second": 65.53,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4261942821725978e-05,
+      "loss": 0.3406,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5079557299613953,
+      "eval_matthews_correlation": 0.48003141444537994,
+      "eval_runtime": 0.8361,
+      "eval_samples_per_second": 1247.424,
+      "eval_steps_per_second": 78.936,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.0004646457031656e-05,
+      "loss": 0.2246,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6419426202774048,
+      "eval_matthews_correlation": 0.49626557567073315,
+      "eval_runtime": 0.7375,
+      "eval_samples_per_second": 1414.219,
+      "eval_steps_per_second": 89.49,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 5.7473500923373334e-06,
+      "loss": 0.1536,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8284639120101929,
+      "eval_matthews_correlation": 0.49254572565243004,
+      "eval_runtime": 1.6173,
+      "eval_samples_per_second": 644.915,
+      "eval_steps_per_second": 40.81,
+      "step": 2140
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 171463524036912.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.277653555111462e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-0/checkpoint-2140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cdafb2f3028d92aeb215c4f9ee1fa4b2ece61c011af271e09c318dcf8f36fa
+size 4792

run-0/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-2675/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cc62f265dbdd4dce4a4b6b25bb32be8f2ecef46b94f865d0870bcd119f670ef
+size 267832560

run-0/checkpoint-2675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4730e1ecc31f87e2e619acaa94b1533795b5f7b0b5aecee40113eb94b160d4
+size 535727290

run-0/checkpoint-2675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:432cec1c012ebf181ce7eb2341564cf746903d1005a62dcb8687a92b36f02c58
+size 14244

run-0/checkpoint-2675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05977ba1eac860071a12afa7a29dbaac1b293894cb88a935efc171f6165faa3
+size 1064

run-0/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-0/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-0/checkpoint-2675/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": 0.5317477654019562,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 0.93,
+      "learning_rate": 1.85192391864203e-05,
+      "loss": 0.5264,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.46143588423728943,
+      "eval_matthews_correlation": 0.49799539554804517,
+      "eval_runtime": 1.0072,
+      "eval_samples_per_second": 1035.567,
+      "eval_steps_per_second": 65.53,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.4261942821725978e-05,
+      "loss": 0.3406,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5079557299613953,
+      "eval_matthews_correlation": 0.48003141444537994,
+      "eval_runtime": 0.8361,
+      "eval_samples_per_second": 1247.424,
+      "eval_steps_per_second": 78.936,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.0004646457031656e-05,
+      "loss": 0.2246,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6419426202774048,
+      "eval_matthews_correlation": 0.49626557567073315,
+      "eval_runtime": 0.7375,
+      "eval_samples_per_second": 1414.219,
+      "eval_steps_per_second": 89.49,
+      "step": 1605
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 5.7473500923373334e-06,
+      "loss": 0.1536,
+      "step": 2000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8284639120101929,
+      "eval_matthews_correlation": 0.49254572565243004,
+      "eval_runtime": 1.6173,
+      "eval_samples_per_second": 644.915,
+      "eval_steps_per_second": 40.81,
+      "step": 2140
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 1.4900537276430125e-06,
+      "loss": 0.1123,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.9036486744880676,
+      "eval_matthews_correlation": 0.5317477654019562,
+      "eval_runtime": 0.7572,
+      "eval_samples_per_second": 1377.525,
+      "eval_steps_per_second": 87.168,
+      "step": 2675
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2675,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 214134067378200.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.277653555111462e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "seed": 38
+  }
+}

run-0/checkpoint-2675/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04cdafb2f3028d92aeb215c4f9ee1fa4b2ece61c011af271e09c318dcf8f36fa
+size 4792

run-0/checkpoint-535/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": "4.36.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9a7b74fd415de190b203000b32b9de9c47d703e7e6dfdca89b9c282fdcb20e
+size 267832560

run-0/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8bb1e67ab8502f9d0b397088edcd08eed133f92b82fa57f0184645fda80fd5
+size 535727290

run-0/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ec59925869aa667ca1305c5c318e032a3c0366ac1d448205d80a4623c3b4a3
+size 14244

run-0/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f23ddc752385ed380ba34ac7299700abbba701853f6f4448cba832e285609ab3
+size 1064