Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd486bfd7622038cbd592238455b5d463d45137e992a80b50bf559b27f281735
+oid sha256:d4b1b3788ae12f4c14826af0b01aca85c0cd39b9a4ccd024764676e17f9ace7c
 size 267835644

run-0/checkpoint-20/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-0/checkpoint-20/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4b1b3788ae12f4c14826af0b01aca85c0cd39b9a4ccd024764676e17f9ace7c
+size 267835644

run-0/checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:670e3fb57d6fd681b392f69674a12483ab7c5142dc8e2a84386dd8a945e25250
+size 535733434

run-0/checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46d08a234798f94734a092e98cad21aef9ead50a4f94ea875501eed970e58ec2
+size 14308

run-0/checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:150b7bb8ae709eeb8546425d64c501bb3eb37003bcacdf0a5a43c863e1ccb867
+size 1064

run-0/checkpoint-20/special_tokens_map.json

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

run-0/checkpoint-20/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-0/checkpoint-20/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.3749234080314636,
+  "best_model_checkpoint": "DistilBERT-PD_Books/run-0/checkpoint-20",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.906801007556675,
+      "eval_loss": 0.3749234080314636,
+      "eval_macro-f1": 0.8847089186696392,
+      "eval_macro-precision": 0.9199166655307006,
+      "eval_macro-recall": 0.8622656234182399,
+      "eval_micro-f1": 0.9068010075566751,
+      "eval_micro-precision": 0.906801007556675,
+      "eval_micro-recall": 0.906801007556675,
+      "eval_runtime": 15.3099,
+      "eval_samples_per_second": 25.931,
+      "eval_steps_per_second": 1.633,
+      "step": 20
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 80,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.124779204652346e-05,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "seed": 14
+  }
+}

run-0/checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d98096565acfbeb2383cc5c301d4fa6e8027ef5d91472ec0cfd1301b6f17497
+size 4600

runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701224448.37a4be0f03a9.346.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0179a4f11ed2a3a58dc6defc52cb2df872ac6b5bf611bc035e101dc975d438
+size 4911

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d31d747f15e0b4fbd4283ee52a2f599e96d6683ddd39b8fa6c9a61f4c5aea4
+oid sha256:9d98096565acfbeb2383cc5c301d4fa6e8027ef5d91472ec0cfd1301b6f17497
 size 4600