Training in progress, step 500

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+base_model: pilotj/distilbert-base-uncased-fibe-full-finetuned
+tags:
+- generated_from_trainer
+model-index:
+- name: distil-bert-final-version
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# distil-bert-final-version
+
+This model is a fine-tuned version of [pilotj/distilbert-base-uncased-fibe-full-finetuned](https://huggingface.co/pilotj/distilbert-base-uncased-fibe-full-finetuned) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.4621
+- eval_runtime: 244.5245
+- eval_samples_per_second: 106.946
+- eval_steps_per_second: 0.838
+- epoch: 0.4331
+- step: 9000
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-05
+- train_batch_size: 32
+- eval_batch_size: 128
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.5
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "pilotj/distilbert-base-uncased-fibe-full-finetuned",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "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": "4.44.2",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15cbb923a4355813b46ea8954e05ab8effa2eda9f1b8f64d439a26f31842a1f7
+size 267906392

runs/Sep28_06-24-12_7b554403b730/events.out.tfevents.1727504661.7b554403b730.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72620e7ad90e348f7dc450323ec2eb23060f56769b550b73e150fe412abc4a2
+size 12292

runs/Sep28_09-12-42_7b554403b730/events.out.tfevents.1727514769.7b554403b730.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645843db27019cab03ff5f8e434da20bcef64b021f771b1e770026d3d8b2ff80
+size 6038

runs/Sep28_09-13-17_7b554403b730/events.out.tfevents.1727514803.7b554403b730.30.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9608403a6dd2a18d24b22c0356195bb684f417ce8afbfaccb8dad6fc71b1a2f2
+size 8116

runs/Sep28_10-37-54_7b554403b730/events.out.tfevents.1727519881.7b554403b730.30.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3321ed86dc4abe7dccfb1e458164a6c8da6c0ef2b2f7527905ea72c966dea364
+size 6050

runs/Sep28_10-39-30_7b554403b730/events.out.tfevents.1727519976.7b554403b730.30.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f686c34e403f92c6b82285d1ce73a7262573687d062d128a91af5340688effd
+size 6530

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2108f8a59b7a937ff2416112d40f2053ee3034987ade2881502fa804a2fd165f
+size 5240