Training in progress, step 500

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+base_model: biggy-smiley/bert-base-uncased-fibe-v2
+tags:
+- generated_from_trainer
+model-index:
+- name: bert-base-uncased-fibe-v3
+  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. -->
+
+# bert-base-uncased-fibe-v3
+
+This model is a fine-tuned version of [biggy-smiley/bert-base-uncased-fibe-v2](https://huggingface.co/biggy-smiley/bert-base-uncased-fibe-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.4755
+- eval_runtime: 40.9898
+- eval_samples_per_second: 253.722
+- eval_steps_per_second: 3.977
+- epoch: 1.0311
+- step: 15500
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.20.0

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "pilotj/bert-base-uncased-fibe-v3",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "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,
+  "intermediate_size": 3072,
+  "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
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d175b500f401cb55873c9daadce61e3256a282db70bafee0f2fe5e73293e01c
+size 438032472

runs/Sep29_10-38-36_ip-10-192-11-169/events.out.tfevents.1727606325.ip-10-192-11-169.1872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c82e13b7de2f98b5e34256f19a1f8527896af329c6dc77060a90cbc84d4dee94
+size 5795

runs/Sep29_10-39-20_ip-10-192-11-169/events.out.tfevents.1727606367.ip-10-192-11-169.1872.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48c8f55268eb56bfe07ac8dd42ea30b4a71b5e04d90964d8e8653a531f43e594
+size 5795

runs/Sep29_10-45-33_ip-10-192-11-51/events.out.tfevents.1727606749.ip-10-192-11-51.1643.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a678fb359834b1f96cf783c602f07b1593bf9f2738d705d73a5d3d972fc93c6
+size 21346

runs/Sep29_13-07-20_ip-10-192-11-181/events.out.tfevents.1727615262.ip-10-192-11-181.1121.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:277014894c7b90bb1d1fcac06cdf74f856569049015db724a4440970720943b8
+size 6613

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b29ef92b8ef1216e9b05dc70a7095ad0ceceb74c4ee837738ed797722e524334
+size 5240