Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6da3f78d55f317df91df9117983098596eeeff5a9ab5168ffbd4d740d4b53066
+oid sha256:a7c3eb9e3a3d55b639ba84794b72b17a7bd88ad4d98b09e4af35531ca3c5f046
 size 267832560

run-1/checkpoint-216/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": "4.37.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c3eb9e3a3d55b639ba84794b72b17a7bd88ad4d98b09e4af35531ca3c5f046
+size 267832560

run-1/checkpoint-216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d72450b324ec4807f57b7543628697dee6786ea1f8e50d5be5d19f3faae7c1b5
+size 535724410

run-1/checkpoint-216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f73e6fc59b3306d5d7841b7ebaacf21065007f35e86d24f7c5d9259aaab475c3
+size 13990

run-1/checkpoint-216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdc766fe5d663ab5cb83956e1dcc9adc941d3190d3e007429f0f0c273cfbb9ea
+size 1064

run-1/checkpoint-216/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-216/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-216/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.31087774676686925,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-216",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5931112766265869,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 30.6162,
+      "eval_samples_per_second": 34.067,
+      "eval_steps_per_second": 2.156,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.556400716304779,
+      "eval_matthews_correlation": 0.25285211471364255,
+      "eval_runtime": 30.8319,
+      "eval_samples_per_second": 33.829,
+      "eval_steps_per_second": 2.141,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.561941921710968,
+      "eval_matthews_correlation": 0.31016392231638445,
+      "eval_runtime": 30.9625,
+      "eval_samples_per_second": 33.686,
+      "eval_steps_per_second": 2.132,
+      "step": 162
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5864373445510864,
+      "eval_matthews_correlation": 0.31087774676686925,
+      "eval_runtime": 37.4586,
+      "eval_samples_per_second": 27.844,
+      "eval_steps_per_second": 1.762,
+      "step": 216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.7766946372870676e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 23
+  }
+}

run-1/checkpoint-216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02704f8f4bf0ed2b371cb83cfa9d1a20fd4bc70307b6bbf4e9b3f48403165e54
+size 4792

runs/Jan26_08-04-50_7ac5f092fd85/events.out.tfevents.1706283789.7ac5f092fd85.1710.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:583cffa4b7e731624dccc48323dd88a5d2bd4bfbfb0c6a78f41eb652b2368e39
-size 5325
+oid sha256:287870595d89eeb17c427f552fcb76bd025afc3f6517199bd70b49b2b4740dc6
+size 6014