Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20c8f88e8d41543d8c729c178b45d847dbc04c7cf96d3177c90444061f869df
+oid sha256:e416576047034dae9e19f403c1a908081e857294f2e87d70e1d9d58fc2426b5d
 size 267835644

run-1/checkpoint-10/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-1/checkpoint-10/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e416576047034dae9e19f403c1a908081e857294f2e87d70e1d9d58fc2426b5d
+size 267835644

run-1/checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e771b10c7a9de3288ef2809ae64a5e7c8aa128b0911d407d1885cd0095110c
+size 535733434

run-1/checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dd15d654dd420ca1f85e4372e8f72a68520e1b89ddd545b5402c8a436e46174
+size 14308

run-1/checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb5f79d04b91f0d968c11ac323d35a02b13c58cc50453005fd2877d4544468b
+size 1064

run-1/checkpoint-10/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-10/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-10/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 1.0437079668045044,
+  "best_model_checkpoint": "DistilBERT-PD_Books/run-1/checkpoint-10",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6246851385390428,
+      "eval_loss": 1.0437079668045044,
+      "eval_macro-f1": 0.4250961051798347,
+      "eval_macro-precision": 0.4049519842647229,
+      "eval_macro-recall": 0.44806754834044743,
+      "eval_micro-f1": 0.6246851385390428,
+      "eval_micro-precision": 0.6246851385390428,
+      "eval_micro-recall": 0.6246851385390428,
+      "eval_runtime": 15.1824,
+      "eval_samples_per_second": 52.297,
+      "eval_steps_per_second": 3.293,
+      "step": 10
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 40,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.056719275757213e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 32,
+    "seed": 37
+  }
+}

run-1/checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6979160f04a8c400b011acf29c779deb101dc33edcd8024742710578175447af
+size 4600

runs/Nov29_01-02-41_37a4be0f03a9/events.out.tfevents.1701220519.37a4be0f03a9.346.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6d201e6990fde0b8536039d3d291eaa4919b729d59f2eb259cca120cfa8bd8
+size 4911

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2dc1986db770be354e8a8d2f540ffd5dae2b6492c3e0296072f43b11a1be16d
+oid sha256:6979160f04a8c400b011acf29c779deb101dc33edcd8024742710578175447af
 size 4600