Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9a1ef6f0a633a3ef7aba179414e63d5eb2a3dbaa976ecf5d7b577bf84a3609
+oid sha256:3ccdc4bb498f954a3872115444406f355d43610eaabacd686d34bce8c8aa4a1a
 size 267832560

run-5/checkpoint-268/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": "4.39.1",
+  "vocab_size": 30522
+}

run-5/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccdc4bb498f954a3872115444406f355d43610eaabacd686d34bce8c8aa4a1a
+size 267832560

run-5/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ed55dd2f783ff7c930ce75144a213bb6390251caef73a898b9ad270daf1dd7
+size 535727290

run-5/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25de9062e39b437f33e259486d14e9d697997bfd1a94e2133406605b55f12ae1
+size 14244

run-5/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e01155cb6e39f89c48518f9bf1c646d3a4bf277caea56672e1d2ab72e6308b
+size 1064

run-5/checkpoint-268/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-268/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-268/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.4611631351812362,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-268",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.46541309356689453,
+      "eval_matthews_correlation": 0.4611631351812362,
+      "eval_runtime": 0.7349,
+      "eval_samples_per_second": 1419.226,
+      "eval_steps_per_second": 89.807,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1340,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.6144778537845165e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 32,
+    "seed": 3
+  }
+}

run-5/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb396c880ed21cbe5386566eb59cb1266f1baa96469ad33b08f5bdf8bfd36bd0
+size 5048

runs/Mar23_02-14-11_d179836e26c8/events.out.tfevents.1711161009.d179836e26c8.903.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc4dedafea88b4a2ece330afdb6957e47a89003088010d1f0ca1a964ee3d9a2
+size 5487

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a34705c4ced7c490cf6b38b7d55b846d0d088aa88737f5a5ca5f346ec25d2e
+oid sha256:bb396c880ed21cbe5386566eb59cb1266f1baa96469ad33b08f5bdf8bfd36bd0
 size 5048