ahmedabdo/video-classifier

README.md

@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.5115
+- eval_loss: 0.6511
 - eval_accuracy: 0.7953
-- eval_runtime: 374.4
-- eval_samples_per_second: 2.179
-- eval_steps_per_second: 0.272
-- epoch: 0.05
-- step: 70
+- eval_runtime: 400.3964
+- eval_samples_per_second: 2.038
+- eval_steps_per_second: 0.255
+- epoch: 2.03
+- step: 210
 
 ## Model description
 
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 1500
+- training_steps: 2200
 
 ### Framework versions
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4acd0f7c367e80c70ca34c2338abcfef28f09441b5c1f9c48a8541014478c1c
+oid sha256:32b496f3e8d9b26f1a814395ed4e70f39245148da947b065019d7b8b1eeec613
 size 344937368

runs/Feb27_01-24-29_8943b7457fd3/events.out.tfevents.1708997075.8943b7457fd3.1814.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e0eb819f908c0160c36ec6af8924ec296088b46ecdece7c1a52aace7425adc
+size 9935

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba598d5230f05915bc3e6e3c13a2e7d47ff67d8d58b44b6bd1c09cec90cdd4f0
+oid sha256:e8b72abdad81222d768743e9912e33d93e25fe71ba7eed12271811d1742dd189
 size 4792