Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be399b98f7c8ae3edf98046e915680a0ccecc7fac003892c545ee8155074ef7e
+oid sha256:9ade93a8a60e92be51a24bbbd66ea0fc85737064cd64d34a5151809fadb2cd19
 size 267832560

run-1/checkpoint-1069/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": "4.36.2",
+  "vocab_size": 30522
+}

run-1/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ade93a8a60e92be51a24bbbd66ea0fc85737064cd64d34a5151809fadb2cd19
+size 267832560

run-1/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758a74fe0d4e1ce5944f7f19a989323a3cb08aa76049601dcfa3c54485cab57d
+size 535727290

run-1/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c5611e67a5ac13cbd4609a24db947366c3c5eda9baa3775b51533a395102f4
+size 14244

run-1/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6bf55b8146b83d6859915708ca68d48b6418f94f647ec18639b5bba58129c7b
+size 1064

run-1/checkpoint-1069/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-1069/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-1/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.44836079619347136,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.3307927897685286e-05,
+      "loss": 0.5442,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6137909049917133e-06,
+      "loss": 0.5034,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.48460718989372253,
+      "eval_matthews_correlation": 0.44836079619347136,
+      "eval_runtime": 0.7459,
+      "eval_samples_per_second": 1398.274,
+      "eval_steps_per_second": 88.481,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1069,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 37629020430720.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.5002064890378863e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 28
+  }
+}

run-1/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e8679c98015f19069f7fc93e8c223604fd65d8ced89ea27f5eada5445d7478
+size 4792

runs/Dec23_02-09-17_17d63b357dd6/events.out.tfevents.1703298189.17d63b357dd6.603.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21093b11b86a681977151d06c484ed2c7c2719cc3ffb86253d419ba7ccdb308f
+size 5349

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:275f1d68a8ef32b480ebf8aa4b71dc84bc91a96440c4262c169a2b08dba67dca
+oid sha256:29e8679c98015f19069f7fc93e8c223604fd65d8ced89ea27f5eada5445d7478
 size 4792