End of training

README.md

@@ -5,6 +5,8 @@ tags:
 - generated_from_trainer
 metrics:
 - accuracy
+- precision
+- recall
 model-index:
 - name: videomae-base-ssbd-trim-yolo
   results: []
@@ -17,8 +19,11 @@ 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:
-- Loss: 0.7293
-- Accuracy: 0.6410
+- Loss: 0.9877
+- Accuracy: 0.5849
+- Precision: 0.5950
+- Recall: 0.5176
+- F1 Score: 0.4976
 
 ## Model description
 
@@ -38,20 +43,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 84
+- training_steps: 21
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 1.1783        | 0.5119 | 43   | 0.9590          | 0.6111   |
-| 0.7626        | 1.4881 | 84   | 0.8350          | 0.6667   |
 
 
 ### Framework versions

all_results.json

@@ -1,8 +1,11 @@
 {
-    "epoch": 1.4880952380952381,
-    "eval_accuracy": 0.6410256410256411,
-    "eval_loss": 0.7293055653572083,
-    "eval_runtime": 18.2512,
-    "eval_samples_per_second": 2.137,
-    "eval_steps_per_second": 1.096
+    "epoch": 1.0,
+    "eval_accuracy": 0.5849056603773585,
+    "eval_f1_score": 0.497638326585695,
+    "eval_loss": 0.9877004623413086,
+    "eval_precision": 0.5949644225506294,
+    "eval_recall": 0.5176077119811135,
+    "eval_runtime": 60.375,
+    "eval_samples_per_second": 0.878,
+    "eval_steps_per_second": 0.232
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7da07c469abc4217173ab22ca42e4d074027104666763c0d7ed267cd1232c75
+oid sha256:361f0c2dfadcf9877d79fda1030ee84af4c71bceab43c14cfa2af46bdfc79a52
 size 344940444

runs/May07_19-11-43_2a9d0c1c9eb7/events.out.tfevents.1715109107.2a9d0c1c9eb7.228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8709bc2a73a2c13ff03289939a34ee04c0ae096e61ad777d47e2fbd06fa257
+size 6291

runs/May07_19-11-43_2a9d0c1c9eb7/events.out.tfevents.1715109360.2a9d0c1c9eb7.228.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1f6893628ff7f89e2b253afa55e50a2edcf61c8c166c377fb689422ec330391
+size 7286

runs/May07_19-11-43_2a9d0c1c9eb7/events.out.tfevents.1715109962.2a9d0c1c9eb7.228.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396275d61ba7c06a46d331ff12c23822f3ea141c765f2a4639b269cb0c600856
+size 1495

test_results.json

@@ -1,8 +1,11 @@
 {
-    "epoch": 1.4880952380952381,
-    "eval_accuracy": 0.6410256410256411,
-    "eval_loss": 0.7293055653572083,
-    "eval_runtime": 18.2512,
-    "eval_samples_per_second": 2.137,
-    "eval_steps_per_second": 1.096
+    "epoch": 1.0,
+    "eval_accuracy": 0.5849056603773585,
+    "eval_f1_score": 0.497638326585695,
+    "eval_loss": 0.9877004623413086,
+    "eval_precision": 0.5949644225506294,
+    "eval_recall": 0.5176077119811135,
+    "eval_runtime": 60.375,
+    "eval_samples_per_second": 0.878,
+    "eval_steps_per_second": 0.232
 }

trainer_state.json

@@ -1,122 +1,92 @@
 {
-  "best_metric": 0.6666666666666666,
-  "best_model_checkpoint": "videomae-base-ssbd-trim-yolo/checkpoint-84",
-  "epoch": 1.4880952380952381,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 84,
+  "global_step": 21,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.11904761904761904,
-      "grad_norm": 28.264497756958008,
-      "learning_rate": 4.933333333333334e-05,
-      "loss": 1.1398,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 8.043018341064453,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 1.1213,
       "step": 10
     },
     {
-      "epoch": 0.23809523809523808,
-      "grad_norm": 10.53657341003418,
-      "learning_rate": 4.266666666666667e-05,
-      "loss": 1.1844,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 12.485899925231934,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.9914,
       "step": 20
     },
     {
-      "epoch": 0.35714285714285715,
-      "grad_norm": 12.06249713897705,
-      "learning_rate": 3.6e-05,
-      "loss": 1.0073,
-      "step": 30
-    },
-    {
-      "epoch": 0.47619047619047616,
-      "grad_norm": 13.21811580657959,
-      "learning_rate": 2.9333333333333336e-05,
-      "loss": 1.1783,
-      "step": 40
-    },
-    {
-      "epoch": 0.5119047619047619,
-      "eval_accuracy": 0.6111111111111112,
-      "eval_loss": 0.9590351581573486,
-      "eval_runtime": 14.8834,
-      "eval_samples_per_second": 2.419,
-      "eval_steps_per_second": 1.209,
-      "step": 43
-    },
-    {
-      "epoch": 1.0833333333333333,
-      "grad_norm": 11.67470932006836,
-      "learning_rate": 2.2666666666666668e-05,
-      "loss": 1.0231,
-      "step": 50
-    },
-    {
-      "epoch": 1.2023809523809523,
-      "grad_norm": 12.88428020477295,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.8124,
-      "step": 60
-    },
-    {
-      "epoch": 1.3214285714285714,
-      "grad_norm": 8.641340255737305,
-      "learning_rate": 9.333333333333334e-06,
-      "loss": 0.7514,
-      "step": 70
-    },
-    {
-      "epoch": 1.4404761904761905,
-      "grad_norm": 14.43031120300293,
-      "learning_rate": 2.666666666666667e-06,
-      "loss": 0.7626,
-      "step": 80
+      "epoch": 1.0,
+      "step": 21,
+      "train_accuracy": 0.611764705882353,
+      "train_f1_score": 0.5340022296544036,
+      "train_loss": 0.9291688203811646,
+      "train_precision": 0.6305555555555555,
+      "train_recall": 0.5425353925353925,
+      "train_runtime": 85.8442,
+      "train_samples_per_second": 0.99,
+      "train_steps_per_second": 0.256
     },
     {
-      "epoch": 1.4880952380952381,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_loss": 0.834980845451355,
-      "eval_runtime": 14.5774,
-      "eval_samples_per_second": 2.47,
-      "eval_steps_per_second": 1.235,
-      "step": 84
+      "epoch": 1.0,
+      "step": 21,
+      "total_flos": 1.0467035897226854e+17,
+      "train_loss": 1.0484393806684584,
+      "train_runtime": 199.3107,
+      "train_samples_per_second": 0.421,
+      "train_steps_per_second": 0.105
     },
     {
-      "epoch": 1.4880952380952381,
-      "step": 84,
-      "total_flos": 2.0809464224248627e+17,
-      "train_loss": 0.959182776155926,
-      "train_runtime": 146.0318,
-      "train_samples_per_second": 1.15,
-      "train_steps_per_second": 0.575
+      "epoch": 1.0,
+      "eval_accuracy": 0.5849056603773585,
+      "eval_f1_score": 0.497638326585695,
+      "eval_loss": 0.987700343132019,
+      "eval_precision": 0.5949644225506294,
+      "eval_recall": 0.5176077119811135,
+      "eval_runtime": 42.1824,
+      "eval_samples_per_second": 1.256,
+      "eval_steps_per_second": 0.332,
+      "step": 21
     },
     {
-      "epoch": 1.4880952380952381,
-      "eval_accuracy": 0.6410256410256411,
-      "eval_loss": 0.7293055653572083,
-      "eval_runtime": 18.831,
-      "eval_samples_per_second": 2.071,
-      "eval_steps_per_second": 1.062,
-      "step": 84
+      "epoch": 1.0,
+      "eval_accuracy": 0.5849056603773585,
+      "eval_f1_score": 0.497638326585695,
+      "eval_loss": 0.987700343132019,
+      "eval_precision": 0.5949644225506294,
+      "eval_recall": 0.5176077119811135,
+      "eval_runtime": 60.1628,
+      "eval_samples_per_second": 0.881,
+      "eval_steps_per_second": 0.233,
+      "step": 21
     },
     {
-      "epoch": 1.4880952380952381,
-      "eval_accuracy": 0.6410256410256411,
-      "eval_loss": 0.7293055653572083,
-      "eval_runtime": 18.2512,
-      "eval_samples_per_second": 2.137,
-      "eval_steps_per_second": 1.096,
-      "step": 84
+      "epoch": 1.0,
+      "eval_accuracy": 0.5849056603773585,
+      "eval_f1_score": 0.497638326585695,
+      "eval_loss": 0.9877004623413086,
+      "eval_precision": 0.5949644225506294,
+      "eval_recall": 0.5176077119811135,
+      "eval_runtime": 60.375,
+      "eval_samples_per_second": 0.878,
+      "eval_steps_per_second": 0.232,
+      "step": 21
     }
   ],
   "logging_steps": 10,
-  "max_steps": 84,
+  "max_steps": 21,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
   "save_steps": 500,
-  "total_flos": 2.0809464224248627e+17,
-  "train_batch_size": 2,
+  "total_flos": 1.0467035897226854e+17,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a22c0054c395b91ed1c4dfa6bdf8f4a07b46e0460d6ab9dee3f6fd094b644311
+oid sha256:c9f7772dc4148a4c99bd2db9cb196759615d95ea0bf074a49952e8277f1e42c9
 size 5048