Training in progress, epoch 1

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google-bert/bert-base-uncased
+tags:
+- generated_from_trainer
+metrics:
+- f1
+model-index:
+- name: modernbert-llm-router
+  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. -->
+
+# modernbert-llm-router
+
+This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2843
+- F1: 0.9313
+
+## 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: 16
+- seed: 42
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.5725        | 1.0   | 313  | 1.1465          | 0.7833 |
+| 0.5195        | 2.0   | 626  | 0.4696          | 0.9098 |
+| 0.2414        | 3.0   | 939  | 0.3351          | 0.9232 |
+| 0.131         | 4.0   | 1252 | 0.2948          | 0.9282 |
+| 0.0689        | 5.0   | 1565 | 0.2843          | 0.9313 |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "google-bert/bert-base-uncased",
+  "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": "small_llm",
+    "1": "large_llm"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "large_llm": "1",
+    "small_llm": "0"
+  },
+  "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": "4.48.0.dev0",
+  "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:b0c8f402ddccdfe19fc5735bf7fa1f9825e58720776be6850e9582e4b00d4f3b
+size 437958648

runs/Jan19_14-42-04_r-romainjeff-training-routerllm-modernbert-jj7xpnfy-2a560-x1a2w/events.out.tfevents.1737294125.r-romainjeff-training-routerllm-modernbert-jj7xpnfy-2a560-x1a2w.115.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a8f7c42fad3aace0766b4f912afc6efc69dff61ea9ff3bdd5d8bbd5aa9ffb6
+size 10439

runs/Jan19_14-43-33_r-romainjeff-training-routerllm-modernbert-jj7xpnfy-2a560-x1a2w/events.out.tfevents.1737294214.r-romainjeff-training-routerllm-modernbert-jj7xpnfy-2a560-x1a2w.435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e206659aea01032ba4a1c9a3e63bcff8042e50c8917cca99070b4ee9ad7287
+size 10439

runs/Jan19_14-47-49_r-romainjeff-training-routerllm-modernbert-kgy2xktk-f07f2-6uak1/events.out.tfevents.1737294470.r-romainjeff-training-routerllm-modernbert-kgy2xktk-f07f2-6uak1.114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27a2613ae7f9f416bb12aff85b521bafe61dec97bedc60ac46ead6e6f5af637
+size 15536

runs/Jan19_15-15-11_r-romainjeff-training-routerllm-modernbert-kgy2xktk-f07f2-6uak1/events.out.tfevents.1737296112.r-romainjeff-training-routerllm-modernbert-kgy2xktk-f07f2-6uak1.492.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8969e671232d4b7703b556bd832afa4b69dd6daa298cd5e2d1fe38227ff7da1b
+size 6401

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "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": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0f94bb0610572ef1e6b6d22178ebba1b2c7f81c0df5cddddf1a1589d5be00f
+size 5432