Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64243f51512150f74facd126faa7c16f1d3fcedb123488abb591f1e502843b95
+oid sha256:7146b3ca7e9468f45433de50933b7660a70608b7c97361130c3410e071d86a08
 size 267832560

run-5/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": "4.35.2",
+  "vocab_size": 30522
+}

run-5/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7146b3ca7e9468f45433de50933b7660a70608b7c97361130c3410e071d86a08
+size 267832560

run-5/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f591ec83c2348971f4bde2e836b668159c31c59540c8341354dfc75bae910141
+size 535727290

run-5/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf783246e80bcb5beeb8b9e6145cba98a417523250d656e55ab4fc147ef82975
+size 14244

run-5/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3b6c378bbc56886ff42767c6f66523c73d41186530b59dfcfd9efed220f3b9
+size 1064

run-5/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-5/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-5/checkpoint-2138/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.3489786582473965,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/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": 0.23,
+      "learning_rate": 2.0303810286193334e-06,
+      "loss": 0.6094,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.9043017297731252e-06,
+      "loss": 0.5899,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7782224309269175e-06,
+      "loss": 0.5665,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6521431320807095e-06,
+      "loss": 0.5457,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5572062730789185,
+      "eval_matthews_correlation": 0.3489786582473965,
+      "eval_runtime": 0.7167,
+      "eval_samples_per_second": 1455.295,
+      "eval_steps_per_second": 92.09,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 8552,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 32728761582000.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.1564603274655414e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 27
+  }
+}

run-5/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:692a73347812984741a703df47072293057562dff76f25cadbe1dfeff21891ed
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700191623.faa202bf7ecf.336.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ea87d4b52ab453e767b7a778abf4d2762da012a30d3e83a0b8e3dbad81326b2
+size 6163

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8458a62b10627cfe6604828b9f4db4980645fe9d09ff42d0c948ff346137eaa
+oid sha256:692a73347812984741a703df47072293057562dff76f25cadbe1dfeff21891ed
 size 4664