Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93177cf8473e1cec983c023736935f949b697b6f5d109f28f1195f132b09408
+oid sha256:44e9666be0de51bf8e807601715c97bbec4bbdfd0054cac7689917841bd00c89
 size 267832560

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": "4.35.2",
+  "vocab_size": 30522
+}

run-0/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44e9666be0de51bf8e807601715c97bbec4bbdfd0054cac7689917841bd00c89
+size 267832560

run-0/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9c0fbd71b987fc6c04bd768be4e1a5295f220d1369855794f0058fdc74930d3
+size 535727290

run-0/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c323d9d6a01df98b437225cc5e80127bed5a9add9c9cb7c0b671e8498fda30fe
+size 14308

run-0/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d29b834bee56053865371e0536c1e41ff5a9bfff0a7747e9d1e8950a6f16194d
+size 1064

run-0/checkpoint-535/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-535/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-535/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.37671460599948314,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-535",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.808385185650082e-07,
+      "loss": 0.5484,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5239843130111694,
+      "eval_matthews_correlation": 0.37671460599948314,
+      "eval_runtime": 1.4494,
+      "eval_samples_per_second": 719.632,
+      "eval_steps_per_second": 45.538,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 42861482677632.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.87853164092227e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 16,
+    "seed": 26
+  }
+}

run-0/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eafd2d8e8afea4a85d296e4f8fd764e674ab73c6c139777832461c59f4f92792
+size 4664

runs/Jan08_03-19-08_fe6f5592002e/events.out.tfevents.1704685004.fe6f5592002e.4919.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3782ec8347c37628d05ee611c567f3934919709bdbc7dd741b062d89f6b2f36f
+size 5035

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aefe49ec61af411f1e44c1510d987b5168be8f60ba05258589eeb9de4d09cb6
+oid sha256:eafd2d8e8afea4a85d296e4f8fd764e674ab73c6c139777832461c59f4f92792
 size 4664