Training in progress, step 15

README.md

@@ -4,24 +4,25 @@ license: mit
 base_model: vidore/colqwen2-base
 tags:
 - ColPali
+- "\U0001F372 Tambouille"
 - "Tambouille \U0001F372"
 - generated_from_trainer
 model-index:
-- name: checkpoints
+- name: test_tambouille
   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. -->
 
-# checkpoints
+# test_tambouille
 
 This model is a fine-tuned version of [vidore/colqwen2-base](https://huggingface.co/vidore/colqwen2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - eval_loss: 1.0650
 - eval_model_preparation_time: 0.0048
-- eval_runtime: 25.2744
-- eval_samples_per_second: 2.374
+- eval_runtime: 25.2861
+- eval_samples_per_second: 2.373
 - eval_steps_per_second: 0.593
 - step: 0
 
@@ -46,8 +47,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53a96077e3a67ba71553f045d8a64d3b1a4819f70a21d9efb8274dfbf94c60b
+oid sha256:a9f4d525b7f5e34120992f48cd5806c01e5de2681404a8b1fa9a6401b79e53d7
 size 147877240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12fda042bdd74b15f7e466fcfd189a962b7750fc5188361fa22ee360042d4b97
+oid sha256:262e0494f3bd71c2684cb0b07e2481c3ee5467c49b795c02428f1acac10e6e0b
 size 5240