Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa6b75b1799435c9ff320f86b7706760f79a872ff30f52205c7a23884a45b65f
+oid sha256:9bfa9e12772a197f214fe66ea3535735b293c4ee2ec9ca4ea13008ff722502db
 size 267832560

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

run-0/checkpoint-1605/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfa9e12772a197f214fe66ea3535735b293c4ee2ec9ca4ea13008ff722502db
+size 267832560

run-0/checkpoint-1605/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d748c85dc1fd5c39f7fb21df1249549157f79be24600580b01b60f23da0381a5
+size 535724410

run-0/checkpoint-1605/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552baf1bf6349ce490fb36dbcf46df475a62fd77ea1a79a4cdf7966aa97e95c5
+size 14054

run-0/checkpoint-1605/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8918d81e637920d4a19e81554557ad55a031080f7409bd008c73a99d536dcea9
+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 +1,69 @@
+{
+  "best_metric": 0.12300105566407585,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-1605",
+  "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": 9.212400120037402e-07,
+      "loss": 0.6099,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.594454824924469,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 36.4602,
+      "eval_samples_per_second": 28.607,
+      "eval_steps_per_second": 1.81,
+      "step": 535
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 5.043893278391519e-07,
+      "loss": 0.5647,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5665746927261353,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 36.791,
+      "eval_samples_per_second": 28.349,
+      "eval_steps_per_second": 1.794,
+      "step": 1070
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 8.753864367456354e-08,
+      "loss": 0.5402,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.557535707950592,
+      "eval_matthews_correlation": 0.12300105566407585,
+      "eval_runtime": 38.1419,
+      "eval_samples_per_second": 27.345,
+      "eval_steps_per_second": 1.73,
+      "step": 1605
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1605,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 139575619965912.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3380906961683286e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-0/checkpoint-1605/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:423290cba7635e78e720e265a2f901ed8603d916cf30d17897498298f0982346
+size 4664

runs/Dec27_12-01-37_e619de3c5f04/events.out.tfevents.1703678719.e619de3c5f04.301.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1cf06c7d5e2c0f53c353cc8fd46afe51eddad705028e178e650e2ee70328858
-size 37988
+oid sha256:c25732ad6b633ecb4e5dd74de9bede7435842b7c13055dc3db25afb51ad98aae
+size 38834