Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7146b3ca7e9468f45433de50933b7660a70608b7c97361130c3410e071d86a08
+oid sha256:1c6bc8a04cc435a7b40b65f3adf41b4d72a1cd6f3e3dfeb32dcfce8111aa0ea8
 size 267832560

run-6/checkpoint-2138/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-6/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6bc8a04cc435a7b40b65f3adf41b4d72a1cd6f3e3dfeb32dcfce8111aa0ea8
+size 267832560

run-6/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476dde5796ec692ecad7dc45322c392277a3230ef79176a3761bb1ecdaa05d26
+size 535727290

run-6/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6adef909c722787fec62e68e29d36d8bd96e201138f6d91b406f157aee940cf
+size 14308

run-6/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1707e5ae47bc1eb0399c327357c1a3a6280d4b0ca3fff4d30eaf83c1c665f3fd
+size 1064

run-6/checkpoint-2138/special_tokens_map.json

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

run-6/checkpoint-2138/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-6/checkpoint-2138/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 0.4279924761510222,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-2138",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.8198594968909895e-06,
+      "loss": 0.6022,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.583360012254533e-06,
+      "loss": 0.5521,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.346860527618076e-06,
+      "loss": 0.5166,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.110361042981619e-06,
+      "loss": 0.5388,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6151991486549377,
+      "eval_matthews_correlation": 0.4279924761510222,
+      "eval_runtime": 0.7154,
+      "eval_samples_per_second": 1457.835,
+      "eval_steps_per_second": 92.25,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10690,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 36863452007628.0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 5.056358981527446e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 13
+  }
+}

run-6/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50705ae525f9e6a06c3db42e472a08e563496b4d579b21777c60dadaa477aaad
+size 4664

runs/Nov17_02-59-16_faa202bf7ecf/events.out.tfevents.1700191873.faa202bf7ecf.336.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419c7db955be41198f125ebf985d2ac3e80970399fc9a131d09042a976d33213
+size 6162

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:692a73347812984741a703df47072293057562dff76f25cadbe1dfeff21891ed
+oid sha256:50705ae525f9e6a06c3db42e472a08e563496b4d579b21777c60dadaa477aaad
 size 4664