Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d9f241fe83935d68f18735b6668d5492714595cc5df686be3ec3dc4b4a974f
+oid sha256:bd0aa211059f3aa3ce713ed51bc533d9a3ebd922ccc6608d6e82c53194639c1a
 size 267835644

run-3/checkpoint-40/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "CAROLL",
+    "1": "DICKENS",
+    "2": "DOYLE"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "CAROLL": 0,
+    "DICKENS": 1,
+    "DOYLE": 2
+  },
+  "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-3/checkpoint-40/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0aa211059f3aa3ce713ed51bc533d9a3ebd922ccc6608d6e82c53194639c1a
+size 267835644

run-3/checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f620fefc7fca0439f9b9ec4df4b332f06da6aa50b36aa187e0d4e95a71b5d185
+size 535733434

run-3/checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:446b0e0c6f58d1c28be154fd545c6c620f6f0c261ac0aed3b80def33b053dc79
+size 14308

run-3/checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:245d5f6fbdc2c04027c6a8436dc6eb92eeba87f57c3270b2073f62f6a47234d7
+size 1064

run-3/checkpoint-40/special_tokens_map.json

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

run-3/checkpoint-40/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-3/checkpoint-40/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 1.0376627445220947,
+  "best_model_checkpoint": "DistilBERT-PD_Books/run-3/checkpoint-40",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5856423173803527,
+      "eval_loss": 1.0376627445220947,
+      "eval_macro-f1": 0.27681595821974625,
+      "eval_macro-precision": 0.36284722222222215,
+      "eval_macro-recall": 0.3442988594220138,
+      "eval_micro-f1": 0.5856423173803527,
+      "eval_micro-precision": 0.5856423173803527,
+      "eval_micro-recall": 0.5856423173803527,
+      "eval_runtime": 15.2973,
+      "eval_samples_per_second": 51.904,
+      "eval_steps_per_second": 3.269,
+      "step": 40
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 40,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.634044552097651e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 8,
+    "seed": 33
+  }
+}

run-3/checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d4baf92915164af6d1b3880340ae2b4aa9721c3e4f88ec1a86b19bfb4da56d6
+size 4600

runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220759.37a4be0f03a9.346.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b2c03522f6567575f17892402f3bbfec05e25d4ff03b90c7256290974812dda
+size 5258

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00b6b22867f93d7846ca52745a5338d90652270692f2e223ce0a5c07a5f28bdb
+oid sha256:4d4baf92915164af6d1b3880340ae2b4aa9721c3e4f88ec1a86b19bfb4da56d6
 size 4600