Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73bba3a098e02e126e642717687552e4c6f7bf0d957d79133225130fcb509a96
+oid sha256:9b0270b07bfbec4109b4ddda5753849594e831c4e505a19dd158e923aaf46b8f
 size 267832560

run-7/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": "4.37.2",
+  "vocab_size": 30522
+}

run-7/checkpoint-268/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23592ee5ecf8bd6bdf6a54b8cc1a56d0d891decf222b16a55074568bb1e07ecd
+size 267832560

run-7/checkpoint-268/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363e9a577afb3ced24abcc38c2a369a6d45b76d336fc88fc2af8d69311a5cc3a
+size 535727290

run-7/checkpoint-268/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d491401165d9beed7f8004e0712ff7d6f655b59fd09e6cb3850edc26514525fe
+size 14244

run-7/checkpoint-268/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca732731c7d1b11d4fb8a7851934921079b9c48638d31170136dce23fc3c4308
+size 1064

run-7/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-7/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-7/checkpoint-268/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.47817459022785963,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-268",
+  "epoch": 2.0,
+  "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": 0.46854841709136963,
+      "eval_matthews_correlation": 0.45077485078453133,
+      "eval_runtime": 0.7206,
+      "eval_samples_per_second": 1447.384,
+      "eval_steps_per_second": 91.589,
+      "step": 134
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5160251259803772,
+      "eval_matthews_correlation": 0.47817459022785963,
+      "eval_runtime": 0.761,
+      "eval_samples_per_second": 1370.633,
+      "eval_steps_per_second": 86.732,
+      "step": 268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.341573056233602e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 64,
+    "seed": 36
+  }
+}

run-7/checkpoint-268/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866c2f092974cb4d9da91ebf9b4c7d9a78acf83b95f3e7eb9241f2b2b86c04f1
+size 4792

runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707294026.5815a830ed1c.392.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563d79b214259498de59a61e46ab53791b2364d18adc93eeca4d605b04c1f368
+size 4687

runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707294046.5815a830ed1c.392.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:258fa7afba4147ccf111f6185cb1aef0dd255b893b0fbb7d11c136a066eb18f5
+size 4690

runs/Feb07_07-45-57_5815a830ed1c/events.out.tfevents.1707294149.5815a830ed1c.392.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c763e99a56c181954b17b69698093bb468707335f04b1ec9d2ccc0e6a85ef242
+size 5714

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866c2f092974cb4d9da91ebf9b4c7d9a78acf83b95f3e7eb9241f2b2b86c04f1
+oid sha256:42dc4a2db4fcbdc1296d623b336dd924ed0f0ce59aefb8c702da40300715a020
 size 4792