Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f7667f7c1ad16cdef3264c88fb5f1338b4584047676a1c15ebe4619ade199c2
+oid sha256:299a3a1778d979da450436f982d9a07300714da5b0bec5bfa4de2499e232bb89
 size 267832560

run-8/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-8/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:299a3a1778d979da450436f982d9a07300714da5b0bec5bfa4de2499e232bb89
+size 267832560

run-8/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:267943710e52e31bc8be1fd16eceff42949cf123258512291004596869572928
+size 535727290

run-8/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0559252c669e30e932c5f9838e7e4093c78bd1b93862edbe7e0544db8e869b58
+size 14308

run-8/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8505bf2827e5275979d138fca6de10f98f657a711f7b52553b5d0bb304f2b8
+size 1064

run-8/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-8/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-8/checkpoint-1069/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.43591443951045983,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/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": 7.540690617488091e-06,
+      "loss": 0.558,
+      "step": 500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 6.542188152248672e-06,
+      "loss": 0.5143,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49273109436035156,
+      "eval_matthews_correlation": 0.43591443951045983,
+      "eval_runtime": 0.7692,
+      "eval_samples_per_second": 1355.973,
+      "eval_steps_per_second": 85.805,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 37856698772160.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 8.53919308272751e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 8,
+    "seed": 13
+  }
+}

run-8/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03af6426126617078e5cb8b57bf2b46d6a95fbaa7edb84b6fba2f994f10481f9
+size 4792

runs/Dec23_01-44-29_cab255cafe95/events.out.tfevents.1703297055.cab255cafe95.13310.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32dd318ffd7cddf79a7c814d2e9357d7e0c14cf5faac95511658842a695aa10f
+size 5797

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d64e83635a4da4783e4c55867a30677ea946d7ffee6806d5df9c9caef4e2a1
+oid sha256:03af6426126617078e5cb8b57bf2b46d6a95fbaa7edb84b6fba2f994f10481f9
 size 4792